---
_id: '11965'
abstract:
- lang: eng
  text: 'We present an unsupervised training approach for a neural network-based mask
    estimator in an acoustic beamforming application. The network is trained to maximize
    a likelihood criterion derived from a spatial mixture model of the observations.
    It is trained from scratch without requiring any parallel data consisting of degraded
    input and clean training targets. Thus, training can be carried out on real recordings
    of noisy speech rather than simulated ones. In contrast to previous work on unsupervised
    training of neural mask estimators, our approach avoids the need for a possibly
    pre-trained teacher model entirely. We demonstrate the effectiveness of our approach
    by speech recognition experiments on two different datasets: one mainly deteriorated
    by noise (CHiME 4) and one by reverberation (REVERB). The results show that the
    performance of the proposed system is on par with a supervised system using oracle
    target masks for training and with a system trained using a model-based teacher.'
author:
- first_name: Lukas
  full_name: Drude, Lukas
  id: '11213'
  last_name: Drude
- first_name: Jahn
  full_name: Heymann, Jahn
  id: '9168'
  last_name: Heymann
- first_name: Reinhold
  full_name: Haeb-Umbach, Reinhold
  id: '242'
  last_name: Haeb-Umbach
citation:
  ama: 'Drude L, Heymann J, Haeb-Umbach R. Unsupervised training of neural mask-based
    beamforming. In: <i>INTERSPEECH 2019, Graz, Austria</i>. ; 2019.'
  apa: Drude, L., Heymann, J., &#38; Haeb-Umbach, R. (2019). Unsupervised training
    of neural mask-based beamforming. In <i>INTERSPEECH 2019, Graz, Austria</i>.
  bibtex: '@inproceedings{Drude_Heymann_Haeb-Umbach_2019, title={Unsupervised training
    of neural mask-based beamforming}, booktitle={INTERSPEECH 2019, Graz, Austria},
    author={Drude, Lukas and Heymann, Jahn and Haeb-Umbach, Reinhold}, year={2019}
    }'
  chicago: Drude, Lukas, Jahn Heymann, and Reinhold Haeb-Umbach. “Unsupervised Training
    of Neural Mask-Based Beamforming.” In <i>INTERSPEECH 2019, Graz, Austria</i>,
    2019.
  ieee: L. Drude, J. Heymann, and R. Haeb-Umbach, “Unsupervised training of neural
    mask-based beamforming,” in <i>INTERSPEECH 2019, Graz, Austria</i>, 2019.
  mla: Drude, Lukas, et al. “Unsupervised Training of Neural Mask-Based Beamforming.”
    <i>INTERSPEECH 2019, Graz, Austria</i>, 2019.
  short: 'L. Drude, J. Heymann, R. Haeb-Umbach, in: INTERSPEECH 2019, Graz, Austria,
    2019.'
date_created: 2019-07-18T09:11:39Z
date_updated: 2022-01-06T06:51:14Z
ddc:
- '000'
department:
- _id: '54'
file:
- access_level: open_access
  content_type: application/pdf
  creator: huesera
  date_created: 2019-08-13T06:36:44Z
  date_updated: 2019-08-13T06:41:35Z
  file_id: '12914'
  file_name: INTERSPEECH_2019_Drude_Paper.pdf
  file_size: 223413
  relation: main_file
file_date_updated: 2019-08-13T06:41:35Z
has_accepted_license: '1'
language:
- iso: eng
license: https://creativecommons.org/publicdomain/zero/1.0/
oa: '1'
project:
- _id: '52'
  name: Computing Resources Provided by the Paderborn Center for Parallel Computing
publication: INTERSPEECH 2019, Graz, Austria
status: public
title: Unsupervised training of neural mask-based beamforming
type: conference
user_id: '59789'
year: '2019'
...
---
_id: '12874'
abstract:
- lang: eng
  text: We propose a training scheme to train neural network-based source separation
    algorithms from scratch when parallel clean data is unavailable. In particular,
    we demonstrate that an unsupervised spatial clustering algorithm is sufficient
    to guide the training of a deep clustering system. We argue that previous work
    on deep clustering requires strong supervision and elaborate on why this is a
    limitation. We demonstrate that (a) the single-channel deep clustering system
    trained according to the proposed scheme alone is able to achieve a similar performance
    as the multi-channel teacher in terms of word error rates and (b) initializing
    the spatial clustering approach with the deep clustering result yields a relative
    word error rate reduction of 26% over the unsupervised teacher.
author:
- first_name: Lukas
  full_name: Drude, Lukas
  id: '11213'
  last_name: Drude
- first_name: Daniel
  full_name: Hasenklever, Daniel
  last_name: Hasenklever
- first_name: Reinhold
  full_name: Haeb-Umbach, Reinhold
  id: '242'
  last_name: Haeb-Umbach
citation:
  ama: 'Drude L, Hasenklever D, Haeb-Umbach R. Unsupervised Training of a Deep Clustering
    Model for Multichannel Blind Source Separation. In: <i>ICASSP 2019, Brighton,
    UK</i>. ; 2019.'
  apa: Drude, L., Hasenklever, D., &#38; Haeb-Umbach, R. (2019). Unsupervised Training
    of a Deep Clustering Model for Multichannel Blind Source Separation. In <i>ICASSP
    2019, Brighton, UK</i>.
  bibtex: '@inproceedings{Drude_Hasenklever_Haeb-Umbach_2019, title={Unsupervised
    Training of a Deep Clustering Model for Multichannel Blind Source Separation},
    booktitle={ICASSP 2019, Brighton, UK}, author={Drude, Lukas and Hasenklever, Daniel
    and Haeb-Umbach, Reinhold}, year={2019} }'
  chicago: Drude, Lukas, Daniel Hasenklever, and Reinhold Haeb-Umbach. “Unsupervised
    Training of a Deep Clustering Model for Multichannel Blind Source Separation.”
    In <i>ICASSP 2019, Brighton, UK</i>, 2019.
  ieee: L. Drude, D. Hasenklever, and R. Haeb-Umbach, “Unsupervised Training of a
    Deep Clustering Model for Multichannel Blind Source Separation,” in <i>ICASSP
    2019, Brighton, UK</i>, 2019.
  mla: Drude, Lukas, et al. “Unsupervised Training of a Deep Clustering Model for
    Multichannel Blind Source Separation.” <i>ICASSP 2019, Brighton, UK</i>, 2019.
  short: 'L. Drude, D. Hasenklever, R. Haeb-Umbach, in: ICASSP 2019, Brighton, UK,
    2019.'
date_created: 2019-07-23T07:37:54Z
date_updated: 2022-01-06T06:51:21Z
ddc:
- '000'
department:
- _id: '54'
file:
- access_level: open_access
  content_type: application/pdf
  creator: huesera
  date_created: 2019-08-14T07:19:13Z
  date_updated: 2019-08-14T07:19:13Z
  file_id: '12925'
  file_name: ICASSP_2019_Drude_Paper.pdf
  file_size: 368225
  relation: main_file
file_date_updated: 2019-08-14T07:19:13Z
has_accepted_license: '1'
language:
- iso: eng
oa: '1'
project:
- _id: '52'
  name: Computing Resources Provided by the Paderborn Center for Parallel Computing
publication: ICASSP 2019, Brighton, UK
status: public
title: Unsupervised Training of a Deep Clustering Model for Multichannel Blind Source
  Separation
type: conference
user_id: '59789'
year: '2019'
...
---
_id: '12875'
abstract:
- lang: eng
  text: Signal dereverberation using the Weighted Prediction Error (WPE) method has
    been proven to be an effective means to raise the accuracy of far-field speech
    recognition. First proposed as an iterative algorithm, follow-up works have reformulated
    it as a recursive least squares algorithm and therefore enabled its use in online
    applications. For this algorithm, the estimation of the power spectral density
    (PSD) of the anechoic signal plays an important role and strongly influences its
    performance. Recently, we showed that using a neural network PSD estimator leads
    to improved performance for online automatic speech recognition. This, however,
    comes at a price. To train the network, we require parallel data, i.e., utterances
    simultaneously available in clean and reverberated form. Here we propose to overcome
    this limitation by training the network jointly with the acoustic model of the
    speech recognizer. To be specific, the gradients computed from the cross-entropy
    loss between the target senone sequence and the acoustic model network output
    is backpropagated through the complex-valued dereverberation filter estimation
    to the neural network for PSD estimation. Evaluation on two databases demonstrates
    improved performance for on-line processing scenarios while imposing fewer requirements
    on the available training data and thus widening the range of applications.
author:
- first_name: Jahn
  full_name: Heymann, Jahn
  id: '9168'
  last_name: Heymann
- first_name: Lukas
  full_name: Drude, Lukas
  id: '11213'
  last_name: Drude
- first_name: Reinhold
  full_name: Haeb-Umbach, Reinhold
  id: '242'
  last_name: Haeb-Umbach
- first_name: Keisuke
  full_name: Kinoshita, Keisuke
  last_name: Kinoshita
- first_name: Tomohiro
  full_name: Nakatani, Tomohiro
  last_name: Nakatani
citation:
  ama: 'Heymann J, Drude L, Haeb-Umbach R, Kinoshita K, Nakatani T. Joint Optimization
    of Neural Network-based WPE Dereverberation and Acoustic Model for Robust Online
    ASR. In: <i>ICASSP 2019, Brighton, UK</i>. ; 2019.'
  apa: Heymann, J., Drude, L., Haeb-Umbach, R., Kinoshita, K., &#38; Nakatani, T.
    (2019). Joint Optimization of Neural Network-based WPE Dereverberation and Acoustic
    Model for Robust Online ASR. In <i>ICASSP 2019, Brighton, UK</i>.
  bibtex: '@inproceedings{Heymann_Drude_Haeb-Umbach_Kinoshita_Nakatani_2019, title={Joint
    Optimization of Neural Network-based WPE Dereverberation and Acoustic Model for
    Robust Online ASR}, booktitle={ICASSP 2019, Brighton, UK}, author={Heymann, Jahn
    and Drude, Lukas and Haeb-Umbach, Reinhold and Kinoshita, Keisuke and Nakatani,
    Tomohiro}, year={2019} }'
  chicago: Heymann, Jahn, Lukas Drude, Reinhold Haeb-Umbach, Keisuke Kinoshita, and
    Tomohiro Nakatani. “Joint Optimization of Neural Network-Based WPE Dereverberation
    and Acoustic Model for Robust Online ASR.” In <i>ICASSP 2019, Brighton, UK</i>,
    2019.
  ieee: J. Heymann, L. Drude, R. Haeb-Umbach, K. Kinoshita, and T. Nakatani, “Joint
    Optimization of Neural Network-based WPE Dereverberation and Acoustic Model for
    Robust Online ASR,” in <i>ICASSP 2019, Brighton, UK</i>, 2019.
  mla: Heymann, Jahn, et al. “Joint Optimization of Neural Network-Based WPE Dereverberation
    and Acoustic Model for Robust Online ASR.” <i>ICASSP 2019, Brighton, UK</i>, 2019.
  short: 'J. Heymann, L. Drude, R. Haeb-Umbach, K. Kinoshita, T. Nakatani, in: ICASSP
    2019, Brighton, UK, 2019.'
date_created: 2019-07-23T07:42:26Z
date_updated: 2022-01-06T06:51:22Z
ddc:
- '000'
department:
- _id: '54'
file:
- access_level: open_access
  content_type: application/pdf
  creator: huesera
  date_created: 2019-12-17T07:28:06Z
  date_updated: 2019-12-17T07:28:06Z
  file_id: '15334'
  file_name: ICASSP_2019_Heymann_Paper.pdf
  file_size: 199109
  relation: main_file
file_date_updated: 2019-12-17T07:28:06Z
has_accepted_license: '1'
language:
- iso: eng
oa: '1'
project:
- _id: '52'
  name: Computing Resources Provided by the Paderborn Center for Parallel Computing
publication: ICASSP 2019, Brighton, UK
status: public
title: Joint Optimization of Neural Network-based WPE Dereverberation and Acoustic
  Model for Robust Online ASR
type: conference
user_id: '59789'
year: '2019'
...
---
_id: '12876'
abstract:
- lang: eng
  text: In this paper, we present libDirectional, a MATLAB library for directional
    statistics and directional estimation. It supports a variety of commonly used
    distributions on the unit circle, such as the von Mises, wrapped normal, and wrapped
    Cauchy distributions. Furthermore, various distributions on higher-dimensional
    manifolds such as the unit hypersphere and the hypertorus are available. Based
    on these distributions, several recursive filtering algorithms in libDirectional
    allow estimation on these manifolds. The functionality is implemented in a clear,
    well-documented, and object-oriented structure that is both easy to use and easy
    to extend.
author:
- first_name: Gerhard
  full_name: Kurz, Gerhard
  last_name: Kurz
- first_name: Igor
  full_name: Gilitschenski, Igor
  last_name: Gilitschenski
- first_name: Florian
  full_name: Pfaff, Florian
  last_name: Pfaff
- first_name: Lukas
  full_name: Drude, Lukas
  id: '11213'
  last_name: Drude
- first_name: Uwe D.
  full_name: Hanebeck, Uwe D.
  last_name: Hanebeck
- first_name: Reinhold
  full_name: Haeb-Umbach, Reinhold
  id: '242'
  last_name: Haeb-Umbach
- first_name: Roland Y.
  full_name: Siegwart, Roland Y.
  last_name: Siegwart
citation:
  ama: 'Kurz G, Gilitschenski I, Pfaff F, et al. Directional Statistics and Filtering
    Using libDirectional. In: <i>Journal of Statistical Software 89(4)</i>. ; 2019.'
  apa: Kurz, G., Gilitschenski, I., Pfaff, F., Drude, L., Hanebeck, U. D., Haeb-Umbach,
    R., &#38; Siegwart, R. Y. (2019). Directional Statistics and Filtering Using libDirectional.
    In <i>Journal of Statistical Software 89(4)</i>.
  bibtex: '@inproceedings{Kurz_Gilitschenski_Pfaff_Drude_Hanebeck_Haeb-Umbach_Siegwart_2019,
    title={Directional Statistics and Filtering Using libDirectional}, booktitle={Journal
    of Statistical Software 89(4)}, author={Kurz, Gerhard and Gilitschenski, Igor
    and Pfaff, Florian and Drude, Lukas and Hanebeck, Uwe D. and Haeb-Umbach, Reinhold
    and Siegwart, Roland Y.}, year={2019} }'
  chicago: Kurz, Gerhard, Igor Gilitschenski, Florian Pfaff, Lukas Drude, Uwe D. Hanebeck,
    Reinhold Haeb-Umbach, and Roland Y. Siegwart. “Directional Statistics and Filtering
    Using LibDirectional.” In <i>Journal of Statistical Software 89(4)</i>, 2019.
  ieee: G. Kurz <i>et al.</i>, “Directional Statistics and Filtering Using libDirectional,”
    in <i>Journal of Statistical Software 89(4)</i>, 2019.
  mla: Kurz, Gerhard, et al. “Directional Statistics and Filtering Using LibDirectional.”
    <i>Journal of Statistical Software 89(4)</i>, 2019.
  short: 'G. Kurz, I. Gilitschenski, F. Pfaff, L. Drude, U.D. Hanebeck, R. Haeb-Umbach,
    R.Y. Siegwart, in: Journal of Statistical Software 89(4), 2019.'
date_created: 2019-07-23T07:44:59Z
date_updated: 2022-01-06T06:51:22Z
ddc:
- '000'
department:
- _id: '54'
file:
- access_level: open_access
  content_type: application/pdf
  creator: huesera
  date_created: 2019-08-14T07:16:05Z
  date_updated: 2019-08-14T07:16:05Z
  file_id: '12923'
  file_name: JournalofStatisticalSoftware_2019_Drude_Paper.pdf
  file_size: 1522964
  relation: main_file
file_date_updated: 2019-08-14T07:16:05Z
has_accepted_license: '1'
language:
- iso: eng
oa: '1'
publication: Journal of Statistical Software 89(4)
status: public
title: Directional Statistics and Filtering Using libDirectional
type: conference
user_id: '59789'
year: '2019'
...
---
_id: '12890'
abstract:
- lang: eng
  text: 'We formulate a generic framework for blind source separation (BSS), which
    allows integrating data-driven spectro-temporal methods, such as deep clustering
    and deep attractor networks, with physically motivated probabilistic spatial methods,
    such as complex angular central Gaussian mixture models. The integrated model
    exploits the complementary strengths of the two approaches to BSS: the strong
    modeling power of neural networks, which, however, is based on supervised learning,
    and the ease of unsupervised learning of the spatial mixture models whose few
    parameters can be estimated on as little as a single segment of a real mixture
    of speech. Experiments are carried out on both artificially mixed speech and true
    recordings of speech mixtures. The experiments verify that the integrated models
    consistently outperform the individual components. We further extend the models
    to cope with noisy, reverberant speech and introduce a cross-domain teacher–student
    training where the mixture model serves as the teacher to provide training targets
    for the student neural network.'
author:
- first_name: Lukas
  full_name: Drude, Lukas
  id: '11213'
  last_name: Drude
- first_name: Reinhold
  full_name: Haeb-Umbach, Reinhold
  id: '242'
  last_name: Haeb-Umbach
citation:
  ama: Drude L, Haeb-Umbach R. Integration of Neural Networks and Probabilistic Spatial
    Models for Acoustic Blind Source Separation. <i>IEEE Journal of Selected Topics
    in Signal Processing</i>. 2019. doi:<a href="https://doi.org/10.1109/JSTSP.2019.2912565">10.1109/JSTSP.2019.2912565</a>
  apa: Drude, L., &#38; Haeb-Umbach, R. (2019). Integration of Neural Networks and
    Probabilistic Spatial Models for Acoustic Blind Source Separation. <i>IEEE Journal
    of Selected Topics in Signal Processing</i>. <a href="https://doi.org/10.1109/JSTSP.2019.2912565">https://doi.org/10.1109/JSTSP.2019.2912565</a>
  bibtex: '@article{Drude_Haeb-Umbach_2019, title={Integration of Neural Networks
    and Probabilistic Spatial Models for Acoustic Blind Source Separation}, DOI={<a
    href="https://doi.org/10.1109/JSTSP.2019.2912565">10.1109/JSTSP.2019.2912565</a>},
    journal={IEEE Journal of Selected Topics in Signal Processing}, author={Drude,
    Lukas and Haeb-Umbach, Reinhold}, year={2019} }'
  chicago: Drude, Lukas, and Reinhold Haeb-Umbach. “Integration of Neural Networks
    and Probabilistic Spatial Models for Acoustic Blind Source Separation.” <i>IEEE
    Journal of Selected Topics in Signal Processing</i>, 2019. <a href="https://doi.org/10.1109/JSTSP.2019.2912565">https://doi.org/10.1109/JSTSP.2019.2912565</a>.
  ieee: L. Drude and R. Haeb-Umbach, “Integration of Neural Networks and Probabilistic
    Spatial Models for Acoustic Blind Source Separation,” <i>IEEE Journal of Selected
    Topics in Signal Processing</i>, 2019.
  mla: Drude, Lukas, and Reinhold Haeb-Umbach. “Integration of Neural Networks and
    Probabilistic Spatial Models for Acoustic Blind Source Separation.” <i>IEEE Journal
    of Selected Topics in Signal Processing</i>, 2019, doi:<a href="https://doi.org/10.1109/JSTSP.2019.2912565">10.1109/JSTSP.2019.2912565</a>.
  short: L. Drude, R. Haeb-Umbach, IEEE Journal of Selected Topics in Signal Processing
    (2019).
date_created: 2019-07-26T08:38:46Z
date_updated: 2022-01-06T06:51:23Z
ddc:
- '050'
department:
- _id: '54'
doi: 10.1109/JSTSP.2019.2912565
file:
- access_level: open_access
  content_type: application/pdf
  creator: huesera
  date_created: 2019-08-07T07:12:21Z
  date_updated: 2019-08-14T07:11:22Z
  file_id: '12903'
  file_name: IEEE Jounal_2019_Drude_Paper.pdf
  file_size: 967424
  relation: main_file
file_date_updated: 2019-08-14T07:11:22Z
has_accepted_license: '1'
language:
- iso: eng
oa: '1'
project:
- _id: '52'
  name: Computing Resources Provided by the Paderborn Center for Parallel Computing
publication: IEEE Journal of Selected Topics in Signal Processing
publication_identifier:
  eissn:
  - 1941-0484
status: public
title: Integration of Neural Networks and Probabilistic Spatial Models for Acoustic
  Blind Source Separation
type: journal_article
user_id: '11213'
year: '2019'
...
---
_id: '15796'
abstract:
- lang: eng
  text: In this paper we consider human daily activity recognition using an acoustic
    sensor network (ASN) which consists of nodes distributed in a home environment.
    Assuming that the ASN is permanently recording, the vast majority of recordings
    is silence. Therefore, we propose to employ a computationally efficient two-stage
    sound recognition system, consisting of an initial sound activity detection (SAD)
    and a subsequent sound event classification (SEC), which is only activated once
    sound activity has been detected. We show how a low-latency activity detector
    with high temporal resolution can be trained from weak labels with low temporal
    resolution. We further demonstrate the advantage of using spatial features for
    the subsequent event classification task.
author:
- first_name: Janek
  full_name: Ebbers, Janek
  id: '34851'
  last_name: Ebbers
- first_name: Lukas
  full_name: Drude, Lukas
  id: '11213'
  last_name: Drude
- first_name: Reinhold
  full_name: Haeb-Umbach, Reinhold
  id: '242'
  last_name: Haeb-Umbach
- first_name: Andreas
  full_name: Brendel, Andreas
  last_name: Brendel
- first_name: Walter
  full_name: Kellermann, Walter
  last_name: Kellermann
citation:
  ama: 'Ebbers J, Drude L, Haeb-Umbach R, Brendel A, Kellermann W. Weakly Supervised
    Sound Activity Detection and Event Classification in Acoustic Sensor Networks.
    In: <i>CAMSAP 2019, Guadeloupe, West Indies</i>. ; 2019.'
  apa: Ebbers, J., Drude, L., Haeb-Umbach, R., Brendel, A., &#38; Kellermann, W. (2019).
    Weakly Supervised Sound Activity Detection and Event Classification in Acoustic
    Sensor Networks. <i>CAMSAP 2019, Guadeloupe, West Indies</i>.
  bibtex: '@inproceedings{Ebbers_Drude_Haeb-Umbach_Brendel_Kellermann_2019, title={Weakly
    Supervised Sound Activity Detection and Event Classification in Acoustic Sensor
    Networks}, booktitle={CAMSAP 2019, Guadeloupe, West Indies}, author={Ebbers, Janek
    and Drude, Lukas and Haeb-Umbach, Reinhold and Brendel, Andreas and Kellermann,
    Walter}, year={2019} }'
  chicago: Ebbers, Janek, Lukas Drude, Reinhold Haeb-Umbach, Andreas Brendel, and
    Walter Kellermann. “Weakly Supervised Sound Activity Detection and Event Classification
    in Acoustic Sensor Networks.” In <i>CAMSAP 2019, Guadeloupe, West Indies</i>,
    2019.
  ieee: J. Ebbers, L. Drude, R. Haeb-Umbach, A. Brendel, and W. Kellermann, “Weakly
    Supervised Sound Activity Detection and Event Classification in Acoustic Sensor
    Networks,” 2019.
  mla: Ebbers, Janek, et al. “Weakly Supervised Sound Activity Detection and Event
    Classification in Acoustic Sensor Networks.” <i>CAMSAP 2019, Guadeloupe, West
    Indies</i>, 2019.
  short: 'J. Ebbers, L. Drude, R. Haeb-Umbach, A. Brendel, W. Kellermann, in: CAMSAP
    2019, Guadeloupe, West Indies, 2019.'
date_created: 2020-02-05T10:20:17Z
date_updated: 2023-11-22T08:29:58Z
ddc:
- '000'
department:
- _id: '54'
file:
- access_level: open_access
  content_type: application/pdf
  creator: huesera
  date_created: 2020-02-05T10:21:39Z
  date_updated: 2020-02-05T10:21:39Z
  file_id: '15797'
  file_name: CAMSAP_2019_WS_Ebbers_Paper.pdf
  file_size: 311887
  relation: main_file
file_date_updated: 2020-02-05T10:21:39Z
has_accepted_license: '1'
language:
- iso: eng
oa: '1'
project:
- _id: '52'
  name: Computing Resources Provided by the Paderborn Center for Parallel Computing
publication: CAMSAP 2019, Guadeloupe, West Indies
quality_controlled: '1'
status: public
title: Weakly Supervised Sound Activity Detection and Event Classification in Acoustic
  Sensor Networks
type: conference
user_id: '34851'
year: '2019'
...
---
_id: '11835'
abstract:
- lang: eng
  text: Signal dereverberation using the weighted prediction error (WPE) method has
    been proven to be an effective means to raise the accuracy of far-field speech
    recognition. But in its original formulation, WPE requires multiple iterations
    over a sufficiently long utterance, rendering it unsuitable for online low-latency
    applications. Recently, two methods have been proposed to overcome this limitation.
    One utilizes a neural network to estimate the power spectral density (PSD) of
    the target signal and works in a block-online fashion. The other method relies
    on a rather simple PSD estimation which smoothes the observed PSD and utilizes
    a recursive formulation which enables it to work on a frame-by-frame basis. In
    this paper, we integrate a deep neural network (DNN) based estimator into the
    recursive frame-online formulation. We evaluate the performance of the recursive
    system with different PSD estimators in comparison to the block-online and offline
    variant on two distinct corpora. The REVERB challenge data, where the signal is
    mainly deteriorated by reverberation, and a database which combines WSJ and VoiceHome
    to also consider (directed) noise sources. The results show that although smoothing
    works surprisingly well, the more sophisticated DNN based estimator shows promising
    improvements and shortens the performance gap between online and offline processing.
author:
- first_name: Jahn
  full_name: Heymann, Jahn
  id: '9168'
  last_name: Heymann
- first_name: Lukas
  full_name: Drude, Lukas
  id: '11213'
  last_name: Drude
- first_name: Reinhold
  full_name: Haeb-Umbach, Reinhold
  id: '242'
  last_name: Haeb-Umbach
- first_name: Keisuke
  full_name: Kinoshita, Keisuke
  last_name: Kinoshita
- first_name: Tomohiro
  full_name: Nakatani, Tomohiro
  last_name: Nakatani
citation:
  ama: 'Heymann J, Drude L, Haeb-Umbach R, Kinoshita K, Nakatani T. Frame-Online DNN-WPE
    Dereverberation. In: <i>IWAENC 2018, Tokio, Japan</i>. ; 2018.'
  apa: Heymann, J., Drude, L., Haeb-Umbach, R., Kinoshita, K., &#38; Nakatani, T.
    (2018). Frame-Online DNN-WPE Dereverberation. In <i>IWAENC 2018, Tokio, Japan</i>.
  bibtex: '@inproceedings{Heymann_Drude_Haeb-Umbach_Kinoshita_Nakatani_2018, title={Frame-Online
    DNN-WPE Dereverberation}, booktitle={IWAENC 2018, Tokio, Japan}, author={Heymann,
    Jahn and Drude, Lukas and Haeb-Umbach, Reinhold and Kinoshita, Keisuke and Nakatani,
    Tomohiro}, year={2018} }'
  chicago: Heymann, Jahn, Lukas Drude, Reinhold Haeb-Umbach, Keisuke Kinoshita, and
    Tomohiro Nakatani. “Frame-Online DNN-WPE Dereverberation.” In <i>IWAENC 2018,
    Tokio, Japan</i>, 2018.
  ieee: J. Heymann, L. Drude, R. Haeb-Umbach, K. Kinoshita, and T. Nakatani, “Frame-Online
    DNN-WPE Dereverberation,” in <i>IWAENC 2018, Tokio, Japan</i>, 2018.
  mla: Heymann, Jahn, et al. “Frame-Online DNN-WPE Dereverberation.” <i>IWAENC 2018,
    Tokio, Japan</i>, 2018.
  short: 'J. Heymann, L. Drude, R. Haeb-Umbach, K. Kinoshita, T. Nakatani, in: IWAENC
    2018, Tokio, Japan, 2018.'
date_created: 2019-07-12T05:29:10Z
date_updated: 2022-01-06T06:51:11Z
department:
- _id: '54'
language:
- iso: eng
main_file_link:
- open_access: '1'
  url: https://groups.uni-paderborn.de/nt/pubs/2018/IWAENC_2018_Heymann_Paper.pdf
oa: '1'
publication: IWAENC 2018, Tokio, Japan
related_material:
  link:
  - description: Poster
    relation: supplementary_material
    url: https://groups.uni-paderborn.de/nt/pubs/2018/IWAENC_2018_Heymann_Poster.pdf
status: public
title: Frame-Online DNN-WPE Dereverberation
type: conference
user_id: '44006'
year: '2018'
...
---
_id: '11872'
abstract:
- lang: eng
  text: 'The weighted prediction error (WPE) algorithm has proven to be a very successful
    dereverberation method for the REVERB challenge. Likewise, neural network based
    mask estimation for beamforming demonstrated very good noise suppression in the
    CHiME 3 and CHiME 4 challenges. Recently, it has been shown that this estimator
    can also be trained to perform dereverberation and denoising jointly. However,
    up to now a comparison of a neural beamformer and WPE is still missing, so is
    an investigation into a combination of the two. Therefore, we here provide an
    extensive evaluation of both and consequently propose variants to integrate deep
    neural network based beamforming with WPE. For these integrated variants we identify
    a consistent word error rate (WER) reduction on two distinct databases. In particular,
    our study shows that deep learning based beamforming benefits from a model-based
    dereverberation technique (i.e. WPE) and vice versa. Our key findings are: (a)
    Neural beamforming yields the lower WERs in comparison to WPE the more channels
    and noise are present. (b) Integration of WPE and a neural beamformer consistently
    outperforms all stand-alone systems.'
author:
- first_name: Lukas
  full_name: Drude, Lukas
  id: '11213'
  last_name: Drude
- first_name: Christoph
  full_name: Boeddeker, Christoph
  id: '40767'
  last_name: Boeddeker
- first_name: Jahn
  full_name: Heymann, Jahn
  id: '9168'
  last_name: Heymann
- first_name: Keisuke
  full_name: Kinoshita, Keisuke
  last_name: Kinoshita
- first_name: Marc
  full_name: Delcroix, Marc
  last_name: Delcroix
- first_name: Tomohiro
  full_name: Nakatani, Tomohiro
  last_name: Nakatani
- first_name: Reinhold
  full_name: Haeb-Umbach, Reinhold
  id: '242'
  last_name: Haeb-Umbach
citation:
  ama: 'Drude L, Boeddeker C, Heymann J, et al. Integration neural network based beamforming
    and weighted prediction error dereverberation. In: <i>INTERSPEECH 2018, Hyderabad,
    India</i>. ; 2018.'
  apa: Drude, L., Boeddeker, C., Heymann, J., Kinoshita, K., Delcroix, M., Nakatani,
    T., &#38; Haeb-Umbach, R. (2018). Integration neural network based beamforming
    and weighted prediction error dereverberation. In <i>INTERSPEECH 2018, Hyderabad,
    India</i>.
  bibtex: '@inproceedings{Drude_Boeddeker_Heymann_Kinoshita_Delcroix_Nakatani_Haeb-Umbach_2018,
    title={Integration neural network based beamforming and weighted prediction error
    dereverberation}, booktitle={INTERSPEECH 2018, Hyderabad, India}, author={Drude,
    Lukas and Boeddeker, Christoph and Heymann, Jahn and Kinoshita, Keisuke and Delcroix,
    Marc and Nakatani, Tomohiro and Haeb-Umbach, Reinhold}, year={2018} }'
  chicago: Drude, Lukas, Christoph Boeddeker, Jahn Heymann, Keisuke Kinoshita, Marc
    Delcroix, Tomohiro Nakatani, and Reinhold Haeb-Umbach. “Integration Neural Network
    Based Beamforming and Weighted Prediction Error Dereverberation.” In <i>INTERSPEECH
    2018, Hyderabad, India</i>, 2018.
  ieee: L. Drude <i>et al.</i>, “Integration neural network based beamforming and
    weighted prediction error dereverberation,” in <i>INTERSPEECH 2018, Hyderabad,
    India</i>, 2018.
  mla: Drude, Lukas, et al. “Integration Neural Network Based Beamforming and Weighted
    Prediction Error Dereverberation.” <i>INTERSPEECH 2018, Hyderabad, India</i>,
    2018.
  short: 'L. Drude, C. Boeddeker, J. Heymann, K. Kinoshita, M. Delcroix, T. Nakatani,
    R. Haeb-Umbach, in: INTERSPEECH 2018, Hyderabad, India, 2018.'
date_created: 2019-07-12T05:29:53Z
date_updated: 2022-01-06T06:51:11Z
department:
- _id: '54'
language:
- iso: eng
main_file_link:
- open_access: '1'
  url: https://groups.uni-paderborn.de/nt/pubs/2018/INTERSPEECH_2018_Drude_Paper.pdf
oa: '1'
project:
- _id: '52'
  name: Computing Resources Provided by the Paderborn Center for Parallel Computing
publication: INTERSPEECH 2018, Hyderabad, India
related_material:
  link:
  - description: Slides
    relation: supplementary_material
    url: https://groups.uni-paderborn.de/nt/pubs/2018/INTERSPEECH_2018_Drude_Slides.pdf
status: public
title: Integration neural network based beamforming and weighted prediction error
  dereverberation
type: conference
user_id: '40767'
year: '2018'
...
---
_id: '11873'
abstract:
- lang: eng
  text: NARA-WPE is a Python software package providing implementations of the weighted
    prediction error (WPE) dereverberation algorithm. WPE has been shown to be a highly
    effective tool for speech dereverberation, thus improving the perceptual quality
    of the signal and improving the recognition performance of downstream automatic
    speech recognition (ASR). It is suitable both for single-channel and multi-channel
    applications. The package consist of (1) a Numpy implementation which can easily
    be integrated into a custom Python toolchain, and (2) a TensorFlow implementation
    which allows integration into larger computational graphs and enables backpropagation
    through WPE to train more advanced front-ends. This package comprises of an iterative
    offline (batch) version, a block-online version, and a frame-online version which
    can be used in moderately low latency applications, e.g. digital speech assistants.
author:
- first_name: Lukas
  full_name: Drude, Lukas
  id: '11213'
  last_name: Drude
- first_name: Jahn
  full_name: Heymann, Jahn
  id: '9168'
  last_name: Heymann
- first_name: Christoph
  full_name: Boeddeker, Christoph
  id: '40767'
  last_name: Boeddeker
- first_name: Reinhold
  full_name: Haeb-Umbach, Reinhold
  id: '242'
  last_name: Haeb-Umbach
citation:
  ama: 'Drude L, Heymann J, Boeddeker C, Haeb-Umbach R. NARA-WPE: A Python package
    for weighted prediction error dereverberation in Numpy and Tensorflow for online
    and offline processing. In: <i>ITG 2018, Oldenburg, Germany</i>. ; 2018.'
  apa: 'Drude, L., Heymann, J., Boeddeker, C., &#38; Haeb-Umbach, R. (2018). NARA-WPE:
    A Python package for weighted prediction error dereverberation in Numpy and Tensorflow
    for online and offline processing. In <i>ITG 2018, Oldenburg, Germany</i>.'
  bibtex: '@inproceedings{Drude_Heymann_Boeddeker_Haeb-Umbach_2018, title={NARA-WPE:
    A Python package for weighted prediction error dereverberation in Numpy and Tensorflow
    for online and offline processing}, booktitle={ITG 2018, Oldenburg, Germany},
    author={Drude, Lukas and Heymann, Jahn and Boeddeker, Christoph and Haeb-Umbach,
    Reinhold}, year={2018} }'
  chicago: 'Drude, Lukas, Jahn Heymann, Christoph Boeddeker, and Reinhold Haeb-Umbach.
    “NARA-WPE: A Python Package for Weighted Prediction Error Dereverberation in Numpy
    and Tensorflow for Online and Offline Processing.” In <i>ITG 2018, Oldenburg,
    Germany</i>, 2018.'
  ieee: 'L. Drude, J. Heymann, C. Boeddeker, and R. Haeb-Umbach, “NARA-WPE: A Python
    package for weighted prediction error dereverberation in Numpy and Tensorflow
    for online and offline processing,” in <i>ITG 2018, Oldenburg, Germany</i>, 2018.'
  mla: 'Drude, Lukas, et al. “NARA-WPE: A Python Package for Weighted Prediction Error
    Dereverberation in Numpy and Tensorflow for Online and Offline Processing.” <i>ITG
    2018, Oldenburg, Germany</i>, 2018.'
  short: 'L. Drude, J. Heymann, C. Boeddeker, R. Haeb-Umbach, in: ITG 2018, Oldenburg,
    Germany, 2018.'
date_created: 2019-07-12T05:29:54Z
date_updated: 2022-01-06T06:51:11Z
department:
- _id: '54'
language:
- iso: eng
main_file_link:
- open_access: '1'
  url: https://groups.uni-paderborn.de/nt/pubs/2018/ITG_2018_Drude_Paper.pdf
oa: '1'
project:
- _id: '52'
  name: Computing Resources Provided by the Paderborn Center for Parallel Computing
publication: ITG 2018, Oldenburg, Germany
related_material:
  link:
  - description: Poster
    relation: supplementary_material
    url: https://groups.uni-paderborn.de/nt/pubs/2018/ITG_2018_Drude_Poster.pdf
status: public
title: 'NARA-WPE: A Python package for weighted prediction error dereverberation in
  Numpy and Tensorflow for online and offline processing'
type: conference
user_id: '40767'
year: '2018'
...
---
_id: '12898'
abstract:
- lang: eng
  text: Deep clustering (DC) and deep attractor networks (DANs) are a data-driven
    way to monaural blind source separation. Both approaches provide astonishing single
    channel performance but have not yet been generalized to block-online processing.
    When separating speech in a continuous stream with a block-online algorithm, it
    needs to be determined in each block which of the output streams belongs to whom.
    In this contribution we solve this block permutation problem by introducing an
    additional speaker identification embedding to the DAN model structure. We motivate
    this model decision by analyzing the embedding topology of DC and DANs and show,
    that DC and DANs themselves are not sufficient for speaker identification. This
    model structure (a) improves the signal to distortion ratio (SDR) over a DAN baseline
    and (b) provides up to 61% and up to 34% relative reduction in permutation error
    rate and re-identification error rate compared to an i-vector baseline, respectively.
author:
- first_name: Lukas
  full_name: Drude, Lukas
  id: '11213'
  last_name: Drude
- first_name: Thilo
  full_name: von Neumann, Thilo
  last_name: von Neumann
- first_name: Reinhold
  full_name: Haeb-Umbach, Reinhold
  id: '242'
  last_name: Haeb-Umbach
citation:
  ama: 'Drude L, von Neumann T, Haeb-Umbach R. Deep Attractor Networks for Speaker
    Re-Identifikation and Blind Source Separation. In: <i>ICASSP 2018, Calgary, Canada</i>.
    ; 2018.'
  apa: Drude, L., von Neumann, T., &#38; Haeb-Umbach, R. (2018). Deep Attractor Networks
    for Speaker Re-Identifikation and Blind Source Separation. In <i>ICASSP 2018,
    Calgary, Canada</i>.
  bibtex: '@inproceedings{Drude_von Neumann_Haeb-Umbach_2018, title={Deep Attractor
    Networks for Speaker Re-Identifikation and Blind Source Separation}, booktitle={ICASSP
    2018, Calgary, Canada}, author={Drude, Lukas and von Neumann, Thilo and Haeb-Umbach,
    Reinhold}, year={2018} }'
  chicago: Drude, Lukas, Thilo von Neumann, and Reinhold Haeb-Umbach. “Deep Attractor
    Networks for Speaker Re-Identifikation and Blind Source Separation.” In <i>ICASSP
    2018, Calgary, Canada</i>, 2018.
  ieee: L. Drude, T. von Neumann, and R. Haeb-Umbach, “Deep Attractor Networks for
    Speaker Re-Identifikation and Blind Source Separation,” in <i>ICASSP 2018, Calgary,
    Canada</i>, 2018.
  mla: Drude, Lukas, et al. “Deep Attractor Networks for Speaker Re-Identifikation
    and Blind Source Separation.” <i>ICASSP 2018, Calgary, Canada</i>, 2018.
  short: 'L. Drude, T. von Neumann, R. Haeb-Umbach, in: ICASSP 2018, Calgary, Canada,
    2018.'
date_created: 2019-07-30T14:22:53Z
date_updated: 2022-01-06T06:51:24Z
department:
- _id: '54'
language:
- iso: eng
main_file_link:
- open_access: '1'
  url: https://groups.uni-paderborn.de/nt/pubs/2018/ICASSP_2018_Drude2_Paper.pdf
oa: '1'
publication: ICASSP 2018, Calgary, Canada
related_material:
  link:
  - description: Slides
    relation: supplementary_material
    url: https://groups.uni-paderborn.de/nt/pubs/2018/ICASSP_2018_Drude2_Slides.pdf
status: public
title: Deep Attractor Networks for Speaker Re-Identifikation and Blind Source Separation
type: conference
user_id: '44006'
year: '2018'
...
---
_id: '12900'
abstract:
- lang: eng
  text: 'Deep attractor networks (DANs) are a recently introduced method to blindly
    separate sources from spectral features of a monaural recording using bidirectional
    long short-term memory networks (BLSTMs). Due to the nature of BLSTMs, this is
    inherently not online-ready and resorting to operating on blocks yields a block
    permutation problem in that the index of each speaker may change between blocks.
    We here propose the joint modeling of spatial and spectral features to solve the
    block permutation problem and generalize DANs to multi-channel meeting recordings:
    The DAN acts as a spectral feature extractor for a subsequent model-based clustering
    approach. We first analyze different joint models in batch-processing scenarios
    and finally propose a block-online blind source separation algorithm. The efficacy
    of the proposed models is demonstrated on reverberant mixtures corrupted by real
    recordings of multi-channel background noise. We demonstrate that both the proposed
    batch-processing and the proposed block-online system outperform (a) a spatial-only
    model with a state-of-the-art frequency permutation solver and (b) a spectral-only
    model with an oracle block permutation solver in terms of signal to distortion
    ratio (SDR) gains.'
author:
- first_name: Lukas
  full_name: Drude, Lukas
  id: '11213'
  last_name: Drude
- first_name: ' Takuya '
  full_name: 'Higuchi,,  Takuya '
  last_name: Higuchi,
- first_name: 'Keisuke '
  full_name: 'Kinoshita, Keisuke '
  last_name: Kinoshita
- first_name: 'Tomohiro '
  full_name: 'Nakatani, Tomohiro '
  last_name: Nakatani
- first_name: Reinhold
  full_name: Haeb-Umbach, Reinhold
  id: '242'
  last_name: Haeb-Umbach
citation:
  ama: 'Drude L, Higuchi,  Takuya , Kinoshita K, Nakatani T, Haeb-Umbach R. Dual Frequency-
    and Block-Permutation Alignment for Deep Learning Based Block-Online Blind Source
    Separation. In: <i>ICASSP 2018, Calgary, Canada</i>. ; 2018.'
  apa: Drude, L., Higuchi,  Takuya , Kinoshita, K., Nakatani, T., &#38; Haeb-Umbach,
    R. (2018). Dual Frequency- and Block-Permutation Alignment for Deep Learning Based
    Block-Online Blind Source Separation. In <i>ICASSP 2018, Calgary, Canada</i>.
  bibtex: '@inproceedings{Drude_Higuchi,_Kinoshita_Nakatani_Haeb-Umbach_2018, title={Dual
    Frequency- and Block-Permutation Alignment for Deep Learning Based Block-Online
    Blind Source Separation}, booktitle={ICASSP 2018, Calgary, Canada}, author={Drude,
    Lukas and Higuchi,  Takuya  and Kinoshita, Keisuke  and Nakatani, Tomohiro  and
    Haeb-Umbach, Reinhold}, year={2018} }'
  chicago: Drude, Lukas,  Takuya  Higuchi, Keisuke  Kinoshita, Tomohiro  Nakatani,
    and Reinhold Haeb-Umbach. “Dual Frequency- and Block-Permutation Alignment for
    Deep Learning Based Block-Online Blind Source Separation.” In <i>ICASSP 2018,
    Calgary, Canada</i>, 2018.
  ieee: L. Drude,  Takuya  Higuchi, K. Kinoshita, T. Nakatani, and R. Haeb-Umbach,
    “Dual Frequency- and Block-Permutation Alignment for Deep Learning Based Block-Online
    Blind Source Separation,” in <i>ICASSP 2018, Calgary, Canada</i>, 2018.
  mla: Drude, Lukas, et al. “Dual Frequency- and Block-Permutation Alignment for Deep
    Learning Based Block-Online Blind Source Separation.” <i>ICASSP 2018, Calgary,
    Canada</i>, 2018.
  short: 'L. Drude,  Takuya  Higuchi, K. Kinoshita, T. Nakatani, R. Haeb-Umbach, in:
    ICASSP 2018, Calgary, Canada, 2018.'
date_created: 2019-07-30T14:42:15Z
date_updated: 2022-01-06T06:51:24Z
department:
- _id: '54'
language:
- iso: eng
main_file_link:
- open_access: '1'
  url: https://groups.uni-paderborn.de/nt/pubs/2018/ICASSP_2018_Drude_Paper.pdf
oa: '1'
publication: ICASSP 2018, Calgary, Canada
related_material:
  link:
  - description: Poster
    relation: supplementary_material
    url: https://groups.uni-paderborn.de/nt/pubs/2018/ICASSP_2018_Drude_Poster.pdf
status: public
title: Dual Frequency- and Block-Permutation Alignment for Deep Learning Based Block-Online
  Blind Source Separation
type: conference
user_id: '44006'
year: '2018'
...
---
_id: '12899'
abstract:
- lang: eng
  text: This contribution presents a speech enhancement system for the CHiME-5 Dinner
    Party Scenario. The front-end employs multi-channel linear time-variant filtering
    and achieves its gains without the use of a neural network. We present an adaptation
    of blind source separation techniques to the CHiME-5 database which we call Guided
    Source Separation (GSS). Using the baseline acoustic and language model, the combination
    of Weighted Prediction Error based dereverberation, guided source separation,
    and beamforming reduces the WER by 10:54% (relative) for the single array track
    and by 21:12% (relative) on the multiple array track.
author:
- first_name: Christoph
  full_name: Boeddeker, Christoph
  id: '40767'
  last_name: Boeddeker
- first_name: Jens
  full_name: Heitkaemper, Jens
  id: '27643'
  last_name: Heitkaemper
- first_name: Joerg
  full_name: Schmalenstroeer, Joerg
  id: '460'
  last_name: Schmalenstroeer
- first_name: Lukas
  full_name: Drude, Lukas
  id: '11213'
  last_name: Drude
- first_name: Jahn
  full_name: Heymann, Jahn
  last_name: Heymann
- first_name: Reinhold
  full_name: Haeb-Umbach, Reinhold
  id: '242'
  last_name: Haeb-Umbach
citation:
  ama: 'Boeddeker C, Heitkaemper J, Schmalenstroeer J, Drude L, Heymann J, Haeb-Umbach
    R. Front-End Processing for the CHiME-5 Dinner Party Scenario. In: <i>Proc. CHiME
    2018 Workshop on Speech Processing in Everyday Environments, Hyderabad, India</i>.
    ; 2018.'
  apa: Boeddeker, C., Heitkaemper, J., Schmalenstroeer, J., Drude, L., Heymann, J.,
    &#38; Haeb-Umbach, R. (2018). Front-End Processing for the CHiME-5 Dinner Party
    Scenario. <i>Proc. CHiME 2018 Workshop on Speech Processing in Everyday Environments,
    Hyderabad, India</i>.
  bibtex: '@inproceedings{Boeddeker_Heitkaemper_Schmalenstroeer_Drude_Heymann_Haeb-Umbach_2018,
    title={Front-End Processing for the CHiME-5 Dinner Party Scenario}, booktitle={Proc.
    CHiME 2018 Workshop on Speech Processing in Everyday Environments, Hyderabad,
    India}, author={Boeddeker, Christoph and Heitkaemper, Jens and Schmalenstroeer,
    Joerg and Drude, Lukas and Heymann, Jahn and Haeb-Umbach, Reinhold}, year={2018}
    }'
  chicago: Boeddeker, Christoph, Jens Heitkaemper, Joerg Schmalenstroeer, Lukas Drude,
    Jahn Heymann, and Reinhold Haeb-Umbach. “Front-End Processing for the CHiME-5
    Dinner Party Scenario.” In <i>Proc. CHiME 2018 Workshop on Speech Processing in
    Everyday Environments, Hyderabad, India</i>, 2018.
  ieee: C. Boeddeker, J. Heitkaemper, J. Schmalenstroeer, L. Drude, J. Heymann, and
    R. Haeb-Umbach, “Front-End Processing for the CHiME-5 Dinner Party Scenario,”
    2018.
  mla: Boeddeker, Christoph, et al. “Front-End Processing for the CHiME-5 Dinner Party
    Scenario.” <i>Proc. CHiME 2018 Workshop on Speech Processing in Everyday Environments,
    Hyderabad, India</i>, 2018.
  short: 'C. Boeddeker, J. Heitkaemper, J. Schmalenstroeer, L. Drude, J. Heymann,
    R. Haeb-Umbach, in: Proc. CHiME 2018 Workshop on Speech Processing in Everyday
    Environments, Hyderabad, India, 2018.'
date_created: 2019-07-30T14:35:15Z
date_updated: 2023-10-26T08:14:15Z
department:
- _id: '54'
language:
- iso: eng
main_file_link:
- open_access: '1'
  url: https://groups.uni-paderborn.de/nt/pubs/2018/INTERSPEECH_2018_Heitkaemper_Paper.pdf
oa: '1'
project:
- _id: '52'
  name: Computing Resources Provided by the Paderborn Center for Parallel Computing
publication: Proc. CHiME 2018 Workshop on Speech Processing in Everyday Environments,
  Hyderabad, India
quality_controlled: '1'
related_material:
  link:
  - description: Poster
    relation: supplementary_material
    url: https://groups.uni-paderborn.de/nt/pubs/2018/INTERSPEECH_2018_Heitkaemper_Poster.pdf
status: public
title: Front-End Processing for the CHiME-5 Dinner Party Scenario
type: conference
user_id: '460'
year: '2018'
...
---
_id: '11876'
abstract:
- lang: eng
  text: This paper describes the systems for the single-array track and the multiple-array
    track of the 5th CHiME Challenge. The final system is a combination of multiple
    systems, using Confusion Network Combination (CNC). The different systems presented
    here are utilizing different front-ends and training sets for a Bidirectional
    Long Short-Term Memory (BLSTM) Acoustic Model (AM). The front-end was replaced
    by enhancements provided by Paderborn University [1]. The back-end has been implemented
    using RASR [2] and RETURNN [3]. Additionally, a system combination including the
    hypothesis word graphs from the system of the submission [1] has been performed,
    which results in the final best system.
author:
- first_name: Markus
  full_name: Kitza, Markus
  last_name: Kitza
- first_name: Wilfried
  full_name: Michel, Wilfried
  last_name: Michel
- first_name: Christoph
  full_name: Boeddeker, Christoph
  id: '40767'
  last_name: Boeddeker
- first_name: Jens
  full_name: Heitkaemper, Jens
  id: '27643'
  last_name: Heitkaemper
- first_name: Tobias
  full_name: Menne, Tobias
  last_name: Menne
- first_name: Ralf
  full_name: Schlüter, Ralf
  last_name: Schlüter
- first_name: Hermann
  full_name: Ney, Hermann
  last_name: Ney
- first_name: Joerg
  full_name: Schmalenstroeer, Joerg
  id: '460'
  last_name: Schmalenstroeer
- first_name: Lukas
  full_name: Drude, Lukas
  id: '11213'
  last_name: Drude
- first_name: Jahn
  full_name: Heymann, Jahn
  id: '9168'
  last_name: Heymann
- first_name: Reinhold
  full_name: Haeb-Umbach, Reinhold
  id: '242'
  last_name: Haeb-Umbach
citation:
  ama: 'Kitza M, Michel W, Boeddeker C, et al. The RWTH/UPB System Combination for
    the CHiME 2018 Workshop. In: <i>Proc. CHiME 2018 Workshop on Speech Processing
    in Everyday Environments, Hyderabad, India</i>. ; 2018.'
  apa: Kitza, M., Michel, W., Boeddeker, C., Heitkaemper, J., Menne, T., Schlüter,
    R., Ney, H., Schmalenstroeer, J., Drude, L., Heymann, J., &#38; Haeb-Umbach, R.
    (2018). The RWTH/UPB System Combination for the CHiME 2018 Workshop. <i>Proc.
    CHiME 2018 Workshop on Speech Processing in Everyday Environments, Hyderabad,
    India</i>.
  bibtex: '@inproceedings{Kitza_Michel_Boeddeker_Heitkaemper_Menne_Schlüter_Ney_Schmalenstroeer_Drude_Heymann_et
    al._2018, title={The RWTH/UPB System Combination for the CHiME 2018 Workshop},
    booktitle={Proc. CHiME 2018 Workshop on Speech Processing in Everyday Environments,
    Hyderabad, India}, author={Kitza, Markus and Michel, Wilfried and Boeddeker, Christoph
    and Heitkaemper, Jens and Menne, Tobias and Schlüter, Ralf and Ney, Hermann and
    Schmalenstroeer, Joerg and Drude, Lukas and Heymann, Jahn and et al.}, year={2018}
    }'
  chicago: Kitza, Markus, Wilfried Michel, Christoph Boeddeker, Jens Heitkaemper,
    Tobias Menne, Ralf Schlüter, Hermann Ney, et al. “The RWTH/UPB System Combination
    for the CHiME 2018 Workshop.” In <i>Proc. CHiME 2018 Workshop on Speech Processing
    in Everyday Environments, Hyderabad, India</i>, 2018.
  ieee: M. Kitza <i>et al.</i>, “The RWTH/UPB System Combination for the CHiME 2018
    Workshop,” 2018.
  mla: Kitza, Markus, et al. “The RWTH/UPB System Combination for the CHiME 2018 Workshop.”
    <i>Proc. CHiME 2018 Workshop on Speech Processing in Everyday Environments, Hyderabad,
    India</i>, 2018.
  short: 'M. Kitza, W. Michel, C. Boeddeker, J. Heitkaemper, T. Menne, R. Schlüter,
    H. Ney, J. Schmalenstroeer, L. Drude, J. Heymann, R. Haeb-Umbach, in: Proc. CHiME
    2018 Workshop on Speech Processing in Everyday Environments, Hyderabad, India,
    2018.'
date_created: 2019-07-12T05:29:58Z
date_updated: 2023-10-26T08:12:14Z
department:
- _id: '54'
language:
- iso: eng
main_file_link:
- open_access: '1'
  url: https://groups.uni-paderborn.de/nt/pubs/2018/INTERSPEECH_2018_Heitkaemper_RWTH_Paper.pdf
oa: '1'
publication: Proc. CHiME 2018 Workshop on Speech Processing in Everyday Environments,
  Hyderabad, India
quality_controlled: '1'
status: public
title: The RWTH/UPB System Combination for the CHiME 2018 Workshop
type: conference
user_id: '460'
year: '2018'
...
---
_id: '11735'
abstract:
- lang: eng
  text: This report describes the computation of gradients by algorithmic differentiation
    for statistically optimum beamforming operations. Especially the derivation of
    complex-valued functions is a key component of this approach. Therefore the real-valued
    algorithmic differentiation is extended via the complex-valued chain rule. In
    addition to the basic mathematic operations the derivative of the eigenvalue problem
    with complex-valued eigenvectors is one of the key results of this report. The
    potential of this approach is shown with experimental results on the CHiME-3 challenge
    database. There, the beamforming task is used as a front-end for an ASR system.
    With the developed derivatives a joint optimization of a speech enhancement and
    speech recognition system w.r.t. the recognition optimization criterion is possible.
author:
- first_name: Christoph
  full_name: Boeddeker, Christoph
  id: '40767'
  last_name: Boeddeker
- first_name: Patrick
  full_name: Hanebrink, Patrick
  last_name: Hanebrink
- first_name: Lukas
  full_name: Drude, Lukas
  id: '11213'
  last_name: Drude
- first_name: Jahn
  full_name: Heymann, Jahn
  id: '9168'
  last_name: Heymann
- first_name: Reinhold
  full_name: Haeb-Umbach, Reinhold
  id: '242'
  last_name: Haeb-Umbach
citation:
  ama: Boeddeker C, Hanebrink P, Drude L, Heymann J, Haeb-Umbach R. <i>On the Computation
    of Complex-Valued Gradients with Application to Statistically Optimum Beamforming</i>.;
    2017.
  apa: Boeddeker, C., Hanebrink, P., Drude, L., Heymann, J., &#38; Haeb-Umbach, R.
    (2017). <i>On the Computation of Complex-valued Gradients with Application to
    Statistically Optimum Beamforming</i>.
  bibtex: '@book{Boeddeker_Hanebrink_Drude_Heymann_Haeb-Umbach_2017, title={On the
    Computation of Complex-valued Gradients with Application to Statistically Optimum
    Beamforming}, author={Boeddeker, Christoph and Hanebrink, Patrick and Drude, Lukas
    and Heymann, Jahn and Haeb-Umbach, Reinhold}, year={2017} }'
  chicago: Boeddeker, Christoph, Patrick Hanebrink, Lukas Drude, Jahn Heymann, and
    Reinhold Haeb-Umbach. <i>On the Computation of Complex-Valued Gradients with Application
    to Statistically Optimum Beamforming</i>, 2017.
  ieee: C. Boeddeker, P. Hanebrink, L. Drude, J. Heymann, and R. Haeb-Umbach, <i>On
    the Computation of Complex-valued Gradients with Application to Statistically
    Optimum Beamforming</i>. 2017.
  mla: Boeddeker, Christoph, et al. <i>On the Computation of Complex-Valued Gradients
    with Application to Statistically Optimum Beamforming</i>. 2017.
  short: C. Boeddeker, P. Hanebrink, L. Drude, J. Heymann, R. Haeb-Umbach, On the
    Computation of Complex-Valued Gradients with Application to Statistically Optimum
    Beamforming, 2017.
date_created: 2019-07-12T05:27:15Z
date_updated: 2022-01-06T06:51:08Z
department:
- _id: '54'
language:
- iso: eng
main_file_link:
- open_access: '1'
  url: https://groups.uni-paderborn.de/nt/pubs/2017/ArXiv_2017_BoeddekerHanebrinkHaeb_Article.pdf
oa: '1'
status: public
title: On the Computation of Complex-valued Gradients with Application to Statistically
  Optimum Beamforming
type: report
user_id: '40767'
year: '2017'
...
---
_id: '11736'
abstract:
- lang: eng
  text: In this paper we show how a neural network for spectral mask estimation for
    an acoustic beamformer can be optimized by algorithmic differentiation. Using
    the beamformer output SNR as the objective function to maximize, the gradient
    is propagated through the beamformer all the way to the neural network which provides
    the clean speech and noise masks from which the beamformer coefficients are estimated
    by eigenvalue decomposition. A key theoretical result is the derivative of an
    eigenvalue problem involving complex-valued eigenvectors. Experimental results
    on the CHiME-3 challenge database demonstrate the effectiveness of the approach.
    The tools developed in this paper are a key component for an end-to-end optimization
    of speech enhancement and speech recognition.
author:
- first_name: Christoph
  full_name: Boeddeker, Christoph
  id: '40767'
  last_name: Boeddeker
- first_name: Patrick
  full_name: Hanebrink, Patrick
  last_name: Hanebrink
- first_name: Lukas
  full_name: Drude, Lukas
  id: '11213'
  last_name: Drude
- first_name: Jahn
  full_name: Heymann, Jahn
  id: '9168'
  last_name: Heymann
- first_name: Reinhold
  full_name: Haeb-Umbach, Reinhold
  id: '242'
  last_name: Haeb-Umbach
citation:
  ama: 'Boeddeker C, Hanebrink P, Drude L, Heymann J, Haeb-Umbach R. Optimizing Neural-Network
    Supported Acoustic Beamforming by Algorithmic Differentiation. In: <i>Proc. IEEE
    Intl. Conf. on Acoustics, Speech and Signal Processing (ICASSP)</i>. ; 2017.'
  apa: Boeddeker, C., Hanebrink, P., Drude, L., Heymann, J., &#38; Haeb-Umbach, R.
    (2017). Optimizing Neural-Network Supported Acoustic Beamforming by Algorithmic
    Differentiation. In <i>Proc. IEEE Intl. Conf. on Acoustics, Speech and Signal
    Processing (ICASSP)</i>.
  bibtex: '@inproceedings{Boeddeker_Hanebrink_Drude_Heymann_Haeb-Umbach_2017, title={Optimizing
    Neural-Network Supported Acoustic Beamforming by Algorithmic Differentiation},
    booktitle={Proc. IEEE Intl. Conf. on Acoustics, Speech and Signal Processing (ICASSP)},
    author={Boeddeker, Christoph and Hanebrink, Patrick and Drude, Lukas and Heymann,
    Jahn and Haeb-Umbach, Reinhold}, year={2017} }'
  chicago: Boeddeker, Christoph, Patrick Hanebrink, Lukas Drude, Jahn Heymann, and
    Reinhold Haeb-Umbach. “Optimizing Neural-Network Supported Acoustic Beamforming
    by Algorithmic Differentiation.” In <i>Proc. IEEE Intl. Conf. on Acoustics, Speech
    and Signal Processing (ICASSP)</i>, 2017.
  ieee: C. Boeddeker, P. Hanebrink, L. Drude, J. Heymann, and R. Haeb-Umbach, “Optimizing
    Neural-Network Supported Acoustic Beamforming by Algorithmic Differentiation,”
    in <i>Proc. IEEE Intl. Conf. on Acoustics, Speech and Signal Processing (ICASSP)</i>,
    2017.
  mla: Boeddeker, Christoph, et al. “Optimizing Neural-Network Supported Acoustic
    Beamforming by Algorithmic Differentiation.” <i>Proc. IEEE Intl. Conf. on Acoustics,
    Speech and Signal Processing (ICASSP)</i>, 2017.
  short: 'C. Boeddeker, P. Hanebrink, L. Drude, J. Heymann, R. Haeb-Umbach, in: Proc.
    IEEE Intl. Conf. on Acoustics, Speech and Signal Processing (ICASSP), 2017.'
date_created: 2019-07-12T05:27:16Z
date_updated: 2022-01-06T06:51:08Z
department:
- _id: '54'
language:
- iso: eng
main_file_link:
- open_access: '1'
  url: https://groups.uni-paderborn.de/nt/pubs/2017/icassp_2017_boeddeker_paper.pdf
oa: '1'
publication: Proc. IEEE Intl. Conf. on Acoustics, Speech and Signal Processing (ICASSP)
status: public
title: Optimizing Neural-Network Supported Acoustic Beamforming by Algorithmic Differentiation
type: conference
user_id: '44006'
year: '2017'
...
---
_id: '11754'
abstract:
- lang: eng
  text: Recent advances in discriminatively trained mask estimation networks to extract
    a single source utilizing beamforming techniques demonstrate, that the integration
    of statistical models and deep neural networks (DNNs) are a promising approach
    for robust automatic speech recognition (ASR) applications. In this contribution
    we demonstrate how discriminatively trained embeddings on spectral features can
    be tightly integrated into statistical model-based source separation to separate
    and transcribe overlapping speech. Good generalization to unseen spatial configurations
    is achieved by estimating a statistical model at test time, while still leveraging
    discriminative training of deep clustering embeddings on a separate training set.
    We formulate an expectation maximization (EM) algorithm which jointly estimates
    a model for deep clustering embeddings and complex-valued spatial observations
    in the short time Fourier transform (STFT) domain at test time. Extensive simulations
    confirm, that the integrated model outperforms (a) a deep clustering model with
    a subsequent beamforming step and (b) an EM-based model with a beamforming step
    alone in terms of signal to distortion ratio (SDR) and perceptually motivated
    metric (PESQ) gains. ASR results on a reverberated dataset further show, that
    the aforementioned gains translate to reduced word error rates (WERs) even in
    reverberant environments.
author:
- first_name: Lukas
  full_name: Drude, Lukas
  id: '11213'
  last_name: Drude
- first_name: Reinhold
  full_name: Haeb-Umbach, Reinhold
  id: '242'
  last_name: Haeb-Umbach
citation:
  ama: 'Drude L, Haeb-Umbach R. Tight integration of spatial and spectral features
    for BSS with Deep Clustering embeddings. In: <i>INTERSPEECH 2017, Stockholm, Schweden</i>.
    ; 2017.'
  apa: Drude, L., &#38; Haeb-Umbach, R. (2017). Tight integration of spatial and spectral
    features for BSS with Deep Clustering embeddings. In <i>INTERSPEECH 2017, Stockholm,
    Schweden</i>.
  bibtex: '@inproceedings{Drude_Haeb-Umbach_2017, title={Tight integration of spatial
    and spectral features for BSS with Deep Clustering embeddings}, booktitle={INTERSPEECH
    2017, Stockholm, Schweden}, author={Drude, Lukas and Haeb-Umbach, Reinhold}, year={2017}
    }'
  chicago: Drude, Lukas, and Reinhold Haeb-Umbach. “Tight Integration of Spatial and
    Spectral Features for BSS with Deep Clustering Embeddings.” In <i>INTERSPEECH
    2017, Stockholm, Schweden</i>, 2017.
  ieee: L. Drude and R. Haeb-Umbach, “Tight integration of spatial and spectral features
    for BSS with Deep Clustering embeddings,” in <i>INTERSPEECH 2017, Stockholm, Schweden</i>,
    2017.
  mla: Drude, Lukas, and Reinhold Haeb-Umbach. “Tight Integration of Spatial and Spectral
    Features for BSS with Deep Clustering Embeddings.” <i>INTERSPEECH 2017, Stockholm,
    Schweden</i>, 2017.
  short: 'L. Drude, R. Haeb-Umbach, in: INTERSPEECH 2017, Stockholm, Schweden, 2017.'
date_created: 2019-07-12T05:27:37Z
date_updated: 2022-01-06T06:51:08Z
department:
- _id: '54'
language:
- iso: eng
main_file_link:
- open_access: '1'
  url: https://groups.uni-paderborn.de/nt/pubs/2017/INTERSPEECH_2017_Drude_paper.pdf
oa: '1'
publication: INTERSPEECH 2017, Stockholm, Schweden
related_material:
  link:
  - description: Slides
    relation: supplementary_material
    url: https://groups.uni-paderborn.de/nt/pubs/2017/INTERSPEECH_2017_Drude_slides.pdf
status: public
title: Tight integration of spatial and spectral features for BSS with Deep Clustering
  embeddings
type: conference
user_id: '44006'
year: '2017'
...
---
_id: '11809'
abstract:
- lang: eng
  text: This paper presents an end-to-end training approach for a beamformer-supported
    multi-channel ASR system. A neural network which estimates masks for a statistically
    optimum beamformer is jointly trained with a network for acoustic modeling. To
    update its parameters, we propagate the gradients from the acoustic model all
    the way through feature extraction and the complex valued beamforming operation.
    Besides avoiding a mismatch between the front-end and the back-end, this approach
    also eliminates the need for stereo data, i.e., the parallel availability of clean
    and noisy versions of the signals. Instead, it can be trained with real noisy
    multichannel data only. Also, relying on the signal statistics for beamforming,
    the approach makes no assumptions on the configuration of the microphone array.
    We further observe a performance gain through joint training in terms of word
    error rate in an evaluation of the system on the CHiME 4 dataset.
author:
- first_name: Jahn
  full_name: Heymann, Jahn
  id: '9168'
  last_name: Heymann
- first_name: Lukas
  full_name: Drude, Lukas
  id: '11213'
  last_name: Drude
- first_name: Christoph
  full_name: Boeddeker, Christoph
  id: '40767'
  last_name: Boeddeker
- first_name: Patrick
  full_name: Hanebrink, Patrick
  last_name: Hanebrink
- first_name: Reinhold
  full_name: Haeb-Umbach, Reinhold
  id: '242'
  last_name: Haeb-Umbach
citation:
  ama: 'Heymann J, Drude L, Boeddeker C, Hanebrink P, Haeb-Umbach R. BEAMNET: End-to-End
    Training of a Beamformer-Supported Multi-Channel ASR System. In: <i>Proc. IEEE
    Intl. Conf. on Acoustics, Speech and Signal Processing (ICASSP)</i>. ; 2017.'
  apa: 'Heymann, J., Drude, L., Boeddeker, C., Hanebrink, P., &#38; Haeb-Umbach, R.
    (2017). BEAMNET: End-to-End Training of a Beamformer-Supported Multi-Channel ASR
    System. In <i>Proc. IEEE Intl. Conf. on Acoustics, Speech and Signal Processing
    (ICASSP)</i>.'
  bibtex: '@inproceedings{Heymann_Drude_Boeddeker_Hanebrink_Haeb-Umbach_2017, title={BEAMNET:
    End-to-End Training of a Beamformer-Supported Multi-Channel ASR System}, booktitle={Proc.
    IEEE Intl. Conf. on Acoustics, Speech and Signal Processing (ICASSP)}, author={Heymann,
    Jahn and Drude, Lukas and Boeddeker, Christoph and Hanebrink, Patrick and Haeb-Umbach,
    Reinhold}, year={2017} }'
  chicago: 'Heymann, Jahn, Lukas Drude, Christoph Boeddeker, Patrick Hanebrink, and
    Reinhold Haeb-Umbach. “BEAMNET: End-to-End Training of a Beamformer-Supported
    Multi-Channel ASR System.” In <i>Proc. IEEE Intl. Conf. on Acoustics, Speech and
    Signal Processing (ICASSP)</i>, 2017.'
  ieee: 'J. Heymann, L. Drude, C. Boeddeker, P. Hanebrink, and R. Haeb-Umbach, “BEAMNET:
    End-to-End Training of a Beamformer-Supported Multi-Channel ASR System,” in <i>Proc.
    IEEE Intl. Conf. on Acoustics, Speech and Signal Processing (ICASSP)</i>, 2017.'
  mla: 'Heymann, Jahn, et al. “BEAMNET: End-to-End Training of a Beamformer-Supported
    Multi-Channel ASR System.” <i>Proc. IEEE Intl. Conf. on Acoustics, Speech and
    Signal Processing (ICASSP)</i>, 2017.'
  short: 'J. Heymann, L. Drude, C. Boeddeker, P. Hanebrink, R. Haeb-Umbach, in: Proc.
    IEEE Intl. Conf. on Acoustics, Speech and Signal Processing (ICASSP), 2017.'
date_created: 2019-07-12T05:28:40Z
date_updated: 2022-01-06T06:51:09Z
department:
- _id: '54'
language:
- iso: eng
main_file_link:
- open_access: '1'
  url: https://groups.uni-paderborn.de/nt/pubs/2017/icassp_2017_heymann_paper.pdf
oa: '1'
project:
- _id: '52'
  name: Computing Resources Provided by the Paderborn Center for Parallel Computing
publication: Proc. IEEE Intl. Conf. on Acoustics, Speech and Signal Processing (ICASSP)
related_material:
  link:
  - description: Poster
    relation: supplementary_material
    url: https://groups.uni-paderborn.de/nt/pubs/2017/icassp_2017_heymann_poster.pdf
status: public
title: 'BEAMNET: End-to-End Training of a Beamformer-Supported Multi-Channel ASR System'
type: conference
user_id: '40767'
year: '2017'
...
---
_id: '11811'
abstract:
- lang: eng
  text: 'Acoustic beamforming can greatly improve the performance of Automatic Speech
    Recognition (ASR) and speech enhancement systems when multiple channels are available.
    We recently proposed a way to support the model-based Generalized Eigenvalue beamforming
    operation with a powerful neural network for spectral mask estimation. The enhancement
    system has a number of desirable properties. In particular, neither assumptions
    need to be made about the nature of the acoustic transfer function (e.g., being
    anechonic), nor does the array configuration need to be known. While the system
    has been originally developed to enhance speech in noisy environments, we show
    in this article that it is also effective in suppressing reverberation, thus leading
    to a generic trainable multi-channel speech enhancement system for robust speech
    processing. To support this claim, we consider two distinct datasets: The CHiME
    3 challenge, which features challenging real-world noise distortions, and the
    Reverb challenge, which focuses on distortions caused by reverberation. We evaluate
    the system both with respect to a speech enhancement and a recognition task. For
    the first task we propose a new way to cope with the distortions introduced by
    the Generalized Eigenvalue beamformer by renormalizing the target energy for each
    frequency bin, and measure its effectiveness in terms of the PESQ score. For the
    latter we feed the enhanced signal to a strong DNN back-end and achieve state-of-the-art
    ASR results on both datasets. We further experiment with different network architectures
    for spectral mask estimation: One small feed-forward network with only one hidden
    layer, one Convolutional Neural Network and one bi-directional Long Short-Term
    Memory network, showing that even a small network is capable of delivering significant
    performance improvements.'
author:
- first_name: Jahn
  full_name: Heymann, Jahn
  id: '9168'
  last_name: Heymann
- first_name: Lukas
  full_name: Drude, Lukas
  id: '11213'
  last_name: Drude
- first_name: Reinhold
  full_name: Haeb-Umbach, Reinhold
  id: '242'
  last_name: Haeb-Umbach
citation:
  ama: Heymann J, Drude L, Haeb-Umbach R. A Generic Neural Acoustic Beamforming Architecture
    for Robust Multi-Channel Speech Processing. <i>Computer Speech and Language</i>.
    2017.
  apa: Heymann, J., Drude, L., &#38; Haeb-Umbach, R. (2017). A Generic Neural Acoustic
    Beamforming Architecture for Robust Multi-Channel Speech Processing. <i>Computer
    Speech and Language</i>.
  bibtex: '@article{Heymann_Drude_Haeb-Umbach_2017, title={A Generic Neural Acoustic
    Beamforming Architecture for Robust Multi-Channel Speech Processing}, journal={Computer
    Speech and Language}, author={Heymann, Jahn and Drude, Lukas and Haeb-Umbach,
    Reinhold}, year={2017} }'
  chicago: Heymann, Jahn, Lukas Drude, and Reinhold Haeb-Umbach. “A Generic Neural
    Acoustic Beamforming Architecture for Robust Multi-Channel Speech Processing.”
    <i>Computer Speech and Language</i>, 2017.
  ieee: J. Heymann, L. Drude, and R. Haeb-Umbach, “A Generic Neural Acoustic Beamforming
    Architecture for Robust Multi-Channel Speech Processing,” <i>Computer Speech and
    Language</i>, 2017.
  mla: Heymann, Jahn, et al. “A Generic Neural Acoustic Beamforming Architecture for
    Robust Multi-Channel Speech Processing.” <i>Computer Speech and Language</i>,
    2017.
  short: J. Heymann, L. Drude, R. Haeb-Umbach, Computer Speech and Language (2017).
date_created: 2019-07-12T05:28:43Z
date_updated: 2022-01-06T06:51:09Z
department:
- _id: '54'
language:
- iso: eng
main_file_link:
- open_access: '1'
  url: https://groups.uni-paderborn.de/nt/pubs/2017/ComputerSpeechLanguage_2017_heymann_paper.pdf
oa: '1'
publication: Computer Speech and Language
status: public
title: A Generic Neural Acoustic Beamforming Architecture for Robust Multi-Channel
  Speech Processing
type: journal_article
user_id: '44006'
year: '2017'
...
---
_id: '11759'
abstract:
- lang: eng
  text: 'Variational Autoencoders (VAEs) have been shown to provide efficient neural-network-based
    approximate Bayesian inference for observation models for which exact inference
    is intractable. Its extension, the so-called Structured VAE (SVAE) allows inference
    in the presence of both discrete and continuous latent variables. Inspired by
    this extension, we developed a VAE with Hidden Markov Models (HMMs) as latent
    models. We applied the resulting HMM-VAE to the task of acoustic unit discovery
    in a zero resource scenario. Starting from an initial model based on variational
    inference in an HMM with Gaussian Mixture Model (GMM) emission probabilities,
    the accuracy of the acoustic unit discovery could be significantly improved by
    the HMM-VAE. In doing so we were able to demonstrate for an unsupervised learning
    task what is well-known in the supervised learning case: Neural networks provide
    superior modeling power compared to GMMs.'
author:
- first_name: Janek
  full_name: Ebbers, Janek
  id: '34851'
  last_name: Ebbers
- first_name: Jahn
  full_name: Heymann, Jahn
  id: '9168'
  last_name: Heymann
- first_name: Lukas
  full_name: Drude, Lukas
  id: '11213'
  last_name: Drude
- first_name: Thomas
  full_name: Glarner, Thomas
  id: '14169'
  last_name: Glarner
- first_name: Reinhold
  full_name: Haeb-Umbach, Reinhold
  id: '242'
  last_name: Haeb-Umbach
- first_name: Bhiksha
  full_name: Raj, Bhiksha
  last_name: Raj
citation:
  ama: 'Ebbers J, Heymann J, Drude L, Glarner T, Haeb-Umbach R, Raj B. Hidden Markov
    Model Variational Autoencoder for Acoustic Unit Discovery. In: <i>INTERSPEECH
    2017, Stockholm, Schweden</i>. ; 2017.'
  apa: Ebbers, J., Heymann, J., Drude, L., Glarner, T., Haeb-Umbach, R., &#38; Raj,
    B. (2017). Hidden Markov Model Variational Autoencoder for Acoustic Unit Discovery.
    <i>INTERSPEECH 2017, Stockholm, Schweden</i>.
  bibtex: '@inproceedings{Ebbers_Heymann_Drude_Glarner_Haeb-Umbach_Raj_2017, title={Hidden
    Markov Model Variational Autoencoder for Acoustic Unit Discovery}, booktitle={INTERSPEECH
    2017, Stockholm, Schweden}, author={Ebbers, Janek and Heymann, Jahn and Drude,
    Lukas and Glarner, Thomas and Haeb-Umbach, Reinhold and Raj, Bhiksha}, year={2017}
    }'
  chicago: Ebbers, Janek, Jahn Heymann, Lukas Drude, Thomas Glarner, Reinhold Haeb-Umbach,
    and Bhiksha Raj. “Hidden Markov Model Variational Autoencoder for Acoustic Unit
    Discovery.” In <i>INTERSPEECH 2017, Stockholm, Schweden</i>, 2017.
  ieee: J. Ebbers, J. Heymann, L. Drude, T. Glarner, R. Haeb-Umbach, and B. Raj, “Hidden
    Markov Model Variational Autoencoder for Acoustic Unit Discovery,” 2017.
  mla: Ebbers, Janek, et al. “Hidden Markov Model Variational Autoencoder for Acoustic
    Unit Discovery.” <i>INTERSPEECH 2017, Stockholm, Schweden</i>, 2017.
  short: 'J. Ebbers, J. Heymann, L. Drude, T. Glarner, R. Haeb-Umbach, B. Raj, in:
    INTERSPEECH 2017, Stockholm, Schweden, 2017.'
date_created: 2019-07-12T05:27:42Z
date_updated: 2023-11-22T08:29:06Z
department:
- _id: '54'
language:
- iso: eng
main_file_link:
- open_access: '1'
  url: https://groups.uni-paderborn.de/nt/pubs/2017/INTERSPEECH_2017_Ebbers_paper.pdf
oa: '1'
publication: INTERSPEECH 2017, Stockholm, Schweden
quality_controlled: '1'
related_material:
  link:
  - description: Poster
    relation: supplementary_material
    url: https://groups.uni-paderborn.de/nt/pubs/2017/INTERSPEECH_2017_Ebbers_poster.pdf
  - description: Slides
    relation: supplementary_material
    url: https://groups.uni-paderborn.de/nt/pubs/2017/INTERSPEECH_2017_Ebbers_slides.pdf
status: public
title: Hidden Markov Model Variational Autoencoder for Acoustic Unit Discovery
type: conference
user_id: '34851'
year: '2017'
...
---
_id: '11895'
abstract:
- lang: eng
  text: Multi-channel speech enhancement algorithms rely on a synchronous sampling
    of the microphone signals. This, however, cannot always be guaranteed, especially
    if the sensors are distributed in an environment. To avoid performance degradation
    the sampling rate offset needs to be estimated and compensated for. In this contribution
    we extend the recently proposed coherence drift based method in two important
    directions. First, the increasing phase shift in the short-time Fourier transform
    domain is estimated from the coherence drift in a Matched Filterlike fashion,
    where intermediate estimates are weighted by their instantaneous SNR. Second,
    an observed bias is removed by iterating between offset estimation and compensation
    by resampling a couple of times. The effectiveness of the proposed method is demonstrated
    by speech recognition results on the output of a beamformer with and without sampling
    rate offset compensation between the input channels. We compare MVDR and maximum-SNR
    beamformers in reverberant environments and further show that both benefit from
    a novel phase normalization, which we also propose in this contribution.
author:
- first_name: Joerg
  full_name: Schmalenstroeer, Joerg
  id: '460'
  last_name: Schmalenstroeer
- first_name: Jahn
  full_name: Heymann, Jahn
  id: '9168'
  last_name: Heymann
- first_name: Lukas
  full_name: Drude, Lukas
  id: '11213'
  last_name: Drude
- first_name: Christoph
  full_name: Boeddeker, Christoph
  id: '40767'
  last_name: Boeddeker
- first_name: Reinhold
  full_name: Haeb-Umbach, Reinhold
  id: '242'
  last_name: Haeb-Umbach
citation:
  ama: 'Schmalenstroeer J, Heymann J, Drude L, Boeddeker C, Haeb-Umbach R. Multi-Stage
    Coherence Drift Based Sampling Rate Synchronization for Acoustic Beamforming.
    In: <i>IEEE 19th International Workshop on Multimedia Signal Processing (MMSP)</i>.
    ; 2017.'
  apa: Schmalenstroeer, J., Heymann, J., Drude, L., Boeddeker, C., &#38; Haeb-Umbach,
    R. (2017). Multi-Stage Coherence Drift Based Sampling Rate Synchronization for
    Acoustic Beamforming. <i>IEEE 19th International Workshop on Multimedia Signal
    Processing (MMSP)</i>.
  bibtex: '@inproceedings{Schmalenstroeer_Heymann_Drude_Boeddeker_Haeb-Umbach_2017,
    title={Multi-Stage Coherence Drift Based Sampling Rate Synchronization for Acoustic
    Beamforming}, booktitle={IEEE 19th International Workshop on Multimedia Signal
    Processing (MMSP)}, author={Schmalenstroeer, Joerg and Heymann, Jahn and Drude,
    Lukas and Boeddeker, Christoph and Haeb-Umbach, Reinhold}, year={2017} }'
  chicago: Schmalenstroeer, Joerg, Jahn Heymann, Lukas Drude, Christoph Boeddeker,
    and Reinhold Haeb-Umbach. “Multi-Stage Coherence Drift Based Sampling Rate Synchronization
    for Acoustic Beamforming.” In <i>IEEE 19th International Workshop on Multimedia
    Signal Processing (MMSP)</i>, 2017.
  ieee: J. Schmalenstroeer, J. Heymann, L. Drude, C. Boeddeker, and R. Haeb-Umbach,
    “Multi-Stage Coherence Drift Based Sampling Rate Synchronization for Acoustic
    Beamforming,” 2017.
  mla: Schmalenstroeer, Joerg, et al. “Multi-Stage Coherence Drift Based Sampling
    Rate Synchronization for Acoustic Beamforming.” <i>IEEE 19th International Workshop
    on Multimedia Signal Processing (MMSP)</i>, 2017.
  short: 'J. Schmalenstroeer, J. Heymann, L. Drude, C. Boeddeker, R. Haeb-Umbach,
    in: IEEE 19th International Workshop on Multimedia Signal Processing (MMSP), 2017.'
date_created: 2019-07-12T05:30:20Z
date_updated: 2023-10-26T08:12:05Z
department:
- _id: '54'
language:
- iso: eng
main_file_link:
- open_access: '1'
  url: https://groups.uni-paderborn.de/nt/pubs/2017/MMSP_2017_SchHaeb.pdf
oa: '1'
publication: IEEE 19th International Workshop on Multimedia Signal Processing (MMSP)
quality_controlled: '1'
related_material:
  link:
  - description: Poster
    relation: supplementary_material
    url: https://groups.uni-paderborn.de/nt/pubs/2017/MMSP_2017_SchHaeb_poster.pdf
status: public
title: Multi-Stage Coherence Drift Based Sampling Rate Synchronization for Acoustic
  Beamforming
type: conference
user_id: '460'
year: '2017'
...