---
_id: '11744'
abstract:
- lang: eng
  text: A noise power spectral density (PSD) estimation is an indispensable component
    of speech spectral enhancement systems. In this paper we present a noise PSD tracking
    algorithm, which employs a noise presence probability estimate delivered by a
    deep neural network (DNN). The algorithm provides a causal noise PSD estimate
    and can thus be used in speech enhancement systems for communication purposes.
    An extensive performance comparison has been carried out with ten causal state-of-the-art
    noise tracking algorithms taken from the literature and categorized acc. to applied
    techniques. The experiments showed that the proposed DNN-based noise PSD tracker
    outperforms all competing methods with respect to all tested performance measures,
    which include the noise tracking performance and the performance of a speech enhancement
    system employing the noise tracking component.
author:
- first_name: Aleksej
  full_name: Chinaev, Aleksej
  last_name: Chinaev
- 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: 'Chinaev A, Heymann J, Drude L, Haeb-Umbach R. Noise-Presence-Probability-Based
    Noise PSD Estimation by Using DNNs. In: <i>12. ITG Fachtagung Sprachkommunikation
    (ITG 2016)</i>. ; 2016.'
  apa: Chinaev, A., Heymann, J., Drude, L., &#38; Haeb-Umbach, R. (2016). Noise-Presence-Probability-Based
    Noise PSD Estimation by Using DNNs. In <i>12. ITG Fachtagung Sprachkommunikation
    (ITG 2016)</i>.
  bibtex: '@inproceedings{Chinaev_Heymann_Drude_Haeb-Umbach_2016, title={Noise-Presence-Probability-Based
    Noise PSD Estimation by Using DNNs}, booktitle={12. ITG Fachtagung Sprachkommunikation
    (ITG 2016)}, author={Chinaev, Aleksej and Heymann, Jahn and Drude, Lukas and Haeb-Umbach,
    Reinhold}, year={2016} }'
  chicago: Chinaev, Aleksej, Jahn Heymann, Lukas Drude, and Reinhold Haeb-Umbach.
    “Noise-Presence-Probability-Based Noise PSD Estimation by Using DNNs.” In <i>12.
    ITG Fachtagung Sprachkommunikation (ITG 2016)</i>, 2016.
  ieee: A. Chinaev, J. Heymann, L. Drude, and R. Haeb-Umbach, “Noise-Presence-Probability-Based
    Noise PSD Estimation by Using DNNs,” in <i>12. ITG Fachtagung Sprachkommunikation
    (ITG 2016)</i>, 2016.
  mla: Chinaev, Aleksej, et al. “Noise-Presence-Probability-Based Noise PSD Estimation
    by Using DNNs.” <i>12. ITG Fachtagung Sprachkommunikation (ITG 2016)</i>, 2016.
  short: 'A. Chinaev, J. Heymann, L. Drude, R. Haeb-Umbach, in: 12. ITG Fachtagung
    Sprachkommunikation (ITG 2016), 2016.'
date_created: 2019-07-12T05:27:25Z
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/2016/ChHeyDrHa16.pdf
oa: '1'
publication: 12. ITG Fachtagung Sprachkommunikation (ITG 2016)
related_material:
  link:
  - description: Presentation
    relation: supplementary_material
    url: https://groups.uni-paderborn.de/nt/pubs/2016/ChHeyDrHa16_Presentation.pdf
status: public
title: Noise-Presence-Probability-Based Noise PSD Estimation by Using DNNs
type: conference
user_id: '44006'
year: '2016'
...
---
_id: '11751'
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: Reinhold
  full_name: Haeb-Umbach, Reinhold
  id: '242'
  last_name: Haeb-Umbach
citation:
  ama: 'Drude L, Boeddeker C, Haeb-Umbach R. Blind Speech Separation based on Complex
    Spherical k-Mode Clustering. In: <i>Proc. IEEE Intl. Conf. on Acoustics, Speech
    and Signal Processing (ICASSP)</i>. ; 2016.'
  apa: Drude, L., Boeddeker, C., &#38; Haeb-Umbach, R. (2016). Blind Speech Separation
    based on Complex Spherical k-Mode Clustering. In <i>Proc. IEEE Intl. Conf. on
    Acoustics, Speech and Signal Processing (ICASSP)</i>.
  bibtex: '@inproceedings{Drude_Boeddeker_Haeb-Umbach_2016, title={Blind Speech Separation
    based on Complex Spherical k-Mode Clustering}, booktitle={Proc. IEEE Intl. Conf.
    on Acoustics, Speech and Signal Processing (ICASSP)}, author={Drude, Lukas and
    Boeddeker, Christoph and Haeb-Umbach, Reinhold}, year={2016} }'
  chicago: Drude, Lukas, Christoph Boeddeker, and Reinhold Haeb-Umbach. “Blind Speech
    Separation Based on Complex Spherical K-Mode Clustering.” In <i>Proc. IEEE Intl.
    Conf. on Acoustics, Speech and Signal Processing (ICASSP)</i>, 2016.
  ieee: L. Drude, C. Boeddeker, and R. Haeb-Umbach, “Blind Speech Separation based
    on Complex Spherical k-Mode Clustering,” in <i>Proc. IEEE Intl. Conf. on Acoustics,
    Speech and Signal Processing (ICASSP)</i>, 2016.
  mla: Drude, Lukas, et al. “Blind Speech Separation Based on Complex Spherical K-Mode
    Clustering.” <i>Proc. IEEE Intl. Conf. on Acoustics, Speech and Signal Processing
    (ICASSP)</i>, 2016.
  short: 'L. Drude, C. Boeddeker, R. Haeb-Umbach, in: Proc. IEEE Intl. Conf. on Acoustics,
    Speech and Signal Processing (ICASSP), 2016.'
date_created: 2019-07-12T05:27:33Z
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/2016/icassp_2016_drude_paper.pdf
oa: '1'
publication: Proc. IEEE Intl. Conf. on Acoustics, Speech and Signal Processing (ICASSP)
related_material:
  link:
  - description: Slides
    relation: supplementary_material
    url: https://groups.uni-paderborn.de/nt/pubs/2016/icassp_2016_drude_slides.pdf
status: public
title: Blind Speech Separation based on Complex Spherical k-Mode Clustering
type: conference
user_id: '44006'
year: '2016'
...
---
_id: '11756'
abstract:
- lang: eng
  text: Although complex-valued neural networks (CVNNs) â?? networks which can operate
    with complex arithmetic â?? have been around for a while, they have not been given
    reconsideration since the breakthrough of deep network architectures. This paper
    presents a critical assessment whether the novel tool set of deep neural networks
    (DNNs) should be extended to complex-valued arithmetic. Indeed, with DNNs making
    inroads in speech enhancement tasks, the use of complex-valued input data, specifically
    the short-time Fourier transform coefficients, is an obvious consideration. In
    particular when it comes to performing tasks that heavily rely on phase information,
    such as acoustic beamforming, complex-valued algorithms are omnipresent. In this
    contribution we recapitulate backpropagation in CVNNs, develop complex-valued
    network elements, such as the split-rectified non-linearity, and compare real-
    and complex-valued networks on a beamforming task. We find that CVNNs hardly provide
    a performance gain and conclude that the effort of developing the complex-valued
    counterparts of the building blocks of modern deep or recurrent neural networks
    can hardly be justified.
author:
- first_name: Lukas
  full_name: Drude, Lukas
  id: '11213'
  last_name: Drude
- first_name: Bhiksha
  full_name: Raj, Bhiksha
  last_name: Raj
- first_name: Reinhold
  full_name: Haeb-Umbach, Reinhold
  id: '242'
  last_name: Haeb-Umbach
citation:
  ama: 'Drude L, Raj B, Haeb-Umbach R. On the appropriateness of complex-valued neural
    networks for speech enhancement. In: <i>INTERSPEECH 2016, San Francisco, USA</i>.
    ; 2016.'
  apa: Drude, L., Raj, B., &#38; Haeb-Umbach, R. (2016). On the appropriateness of
    complex-valued neural networks for speech enhancement. In <i>INTERSPEECH 2016,
    San Francisco, USA</i>.
  bibtex: '@inproceedings{Drude_Raj_Haeb-Umbach_2016, title={On the appropriateness
    of complex-valued neural networks for speech enhancement}, booktitle={INTERSPEECH
    2016, San Francisco, USA}, author={Drude, Lukas and Raj, Bhiksha and Haeb-Umbach,
    Reinhold}, year={2016} }'
  chicago: Drude, Lukas, Bhiksha Raj, and Reinhold Haeb-Umbach. “On the Appropriateness
    of Complex-Valued Neural Networks for Speech Enhancement.” In <i>INTERSPEECH 2016,
    San Francisco, USA</i>, 2016.
  ieee: L. Drude, B. Raj, and R. Haeb-Umbach, “On the appropriateness of complex-valued
    neural networks for speech enhancement,” in <i>INTERSPEECH 2016, San Francisco,
    USA</i>, 2016.
  mla: Drude, Lukas, et al. “On the Appropriateness of Complex-Valued Neural Networks
    for Speech Enhancement.” <i>INTERSPEECH 2016, San Francisco, USA</i>, 2016.
  short: 'L. Drude, B. Raj, R. Haeb-Umbach, in: INTERSPEECH 2016, San Francisco, USA,
    2016.'
date_created: 2019-07-12T05:27:39Z
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/2016/interspeech_2016_drude_paper.pdf
oa: '1'
publication: INTERSPEECH 2016, San Francisco, USA
related_material:
  link:
  - description: Poster
    relation: supplementary_material
    url: https://groups.uni-paderborn.de/nt/pubs/2016/interspeech_2016_drude_slides.pdf
status: public
title: On the appropriateness of complex-valued neural networks for speech enhancement
type: conference
user_id: '44006'
year: '2016'
...
---
_id: '11771'
abstract:
- lang: eng
  text: This paper is concerned with speech presence probability estimation employing
    an explicit model of the temporal and spectral correlations of speech. An undirected
    graphical model is introduced, based on a Factor Graph formulation. It is shown
    that this undirected model cures some of the theoretical issues of an earlier
    directed graphical model. Furthermore, we formulate a message passing inference
    scheme based on an approximate graph factorization, identify this inference scheme
    as a particular message passing schedule based on the turbo principle and suggest
    further alternative schedules. The experiments show an improved performance over
    speech presence probability estimation based on an IID assumption, and a slightly
    better performance of the turbo schedule over the alternatives.
author:
- first_name: Thomas
  full_name: Glarner, Thomas
  id: '14169'
  last_name: Glarner
- first_name: Mohammad
  full_name: Mahdi Momenzadeh, Mohammad
  last_name: Mahdi Momenzadeh
- 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: 'Glarner T, Mahdi Momenzadeh M, Drude L, Haeb-Umbach R. Factor Graph Decoding
    for Speech Presence Probability Estimation. In: <i>12. ITG Fachtagung Sprachkommunikation
    (ITG 2016)</i>. ; 2016.'
  apa: Glarner, T., Mahdi Momenzadeh, M., Drude, L., &#38; Haeb-Umbach, R. (2016).
    Factor Graph Decoding for Speech Presence Probability Estimation. In <i>12. ITG
    Fachtagung Sprachkommunikation (ITG 2016)</i>.
  bibtex: '@inproceedings{Glarner_Mahdi Momenzadeh_Drude_Haeb-Umbach_2016, title={Factor
    Graph Decoding for Speech Presence Probability Estimation}, booktitle={12. ITG
    Fachtagung Sprachkommunikation (ITG 2016)}, author={Glarner, Thomas and Mahdi
    Momenzadeh, Mohammad and Drude, Lukas and Haeb-Umbach, Reinhold}, year={2016}
    }'
  chicago: Glarner, Thomas, Mohammad Mahdi Momenzadeh, Lukas Drude, and Reinhold Haeb-Umbach.
    “Factor Graph Decoding for Speech Presence Probability Estimation.” In <i>12.
    ITG Fachtagung Sprachkommunikation (ITG 2016)</i>, 2016.
  ieee: T. Glarner, M. Mahdi Momenzadeh, L. Drude, and R. Haeb-Umbach, “Factor Graph
    Decoding for Speech Presence Probability Estimation,” in <i>12. ITG Fachtagung
    Sprachkommunikation (ITG 2016)</i>, 2016.
  mla: Glarner, Thomas, et al. “Factor Graph Decoding for Speech Presence Probability
    Estimation.” <i>12. ITG Fachtagung Sprachkommunikation (ITG 2016)</i>, 2016.
  short: 'T. Glarner, M. Mahdi Momenzadeh, L. Drude, R. Haeb-Umbach, in: 12. ITG Fachtagung
    Sprachkommunikation (ITG 2016), 2016.'
date_created: 2019-07-12T05:27:56Z
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/2016/itgspeech2016_08_Glarner.pdf
oa: '1'
publication: 12. ITG Fachtagung Sprachkommunikation (ITG 2016)
related_material:
  link:
  - description: Slides
    relation: supplementary_material
    url: https://groups.uni-paderborn.de/nt/pubs/2016/itgspeech2016_08_Glarner_slides.pdf
status: public
title: Factor Graph Decoding for Speech Presence Probability Estimation
type: conference
user_id: '44006'
year: '2016'
...
---
_id: '11812'
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. Neural Network Based Spectral Mask Estimation
    for Acoustic Beamforming. In: <i>Proc. IEEE Intl. Conf. on Acoustics, Speech and
    Signal Processing (ICASSP)</i>. ; 2016.'
  apa: Heymann, J., Drude, L., &#38; Haeb-Umbach, R. (2016). Neural Network Based
    Spectral Mask Estimation for Acoustic Beamforming. In <i>Proc. IEEE Intl. Conf.
    on Acoustics, Speech and Signal Processing (ICASSP)</i>.
  bibtex: '@inproceedings{Heymann_Drude_Haeb-Umbach_2016, title={Neural Network Based
    Spectral Mask Estimation for Acoustic Beamforming}, booktitle={Proc. IEEE Intl.
    Conf. on Acoustics, Speech and Signal Processing (ICASSP)}, author={Heymann, Jahn
    and Drude, Lukas and Haeb-Umbach, Reinhold}, year={2016} }'
  chicago: Heymann, Jahn, Lukas Drude, and Reinhold Haeb-Umbach. “Neural Network Based
    Spectral Mask Estimation for Acoustic Beamforming.” In <i>Proc. IEEE Intl. Conf.
    on Acoustics, Speech and Signal Processing (ICASSP)</i>, 2016.
  ieee: J. Heymann, L. Drude, and R. Haeb-Umbach, “Neural Network Based Spectral Mask
    Estimation for Acoustic Beamforming,” in <i>Proc. IEEE Intl. Conf. on Acoustics,
    Speech and Signal Processing (ICASSP)</i>, 2016.
  mla: Heymann, Jahn, et al. “Neural Network Based Spectral Mask Estimation for Acoustic
    Beamforming.” <i>Proc. IEEE Intl. Conf. on Acoustics, Speech and Signal Processing
    (ICASSP)</i>, 2016.
  short: 'J. Heymann, L. Drude, R. Haeb-Umbach, in: Proc. IEEE Intl. Conf. on Acoustics,
    Speech and Signal Processing (ICASSP), 2016.'
date_created: 2019-07-12T05:28:44Z
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/2016/icassp_2016_heymann_paper.pdf
oa: '1'
publication: Proc. IEEE Intl. Conf. on Acoustics, Speech and Signal Processing (ICASSP)
related_material:
  link:
  - description: Slides
    relation: supplementary_material
    url: https://groups.uni-paderborn.de/nt/pubs/2016/icassp_2016_heymann_slides.pdf
status: public
title: Neural Network Based Spectral Mask Estimation for Acoustic Beamforming
type: conference
user_id: '44006'
year: '2016'
...
---
_id: '11834'
abstract:
- lang: eng
  text: We present a system for the 4th CHiME challenge which significantly increases
    the performance for all three tracks with respect to the provided baseline system.
    The front-end uses a bi-directional Long Short-Term Memory (BLSTM)-based neural
    network to estimate signal statistics. These then steer a Generalized Eigenvalue
    beamformer. The back-end consists of a 22 layer deep Wide Residual Network and
    two extra BLSTM layers. Working on a whole utterance instead of frames allows
    us to refine Batch-Normalization. We also train our own BLSTM-based language model.
    Adding a discriminative speaker adaptation leads to further gains. The final system
    achieves a word error rate on the six channel real test data of 3.48%. For the
    two channel track we achieve 5.96% and for the one channel track 9.34%. This is
    the best reported performance on the challenge achieved by a single system, i.e.,
    a configuration, which does not combine multiple systems. At the same time, our
    system is independent of the microphone configuration. We can thus use the same
    components for all three tracks.
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. Wide Residual BLSTM Network with Discriminative
    Speaker Adaptation for Robust Speech Recognition. In: <i>Computer Speech and Language</i>.
    ; 2016.'
  apa: Heymann, J., Drude, L., &#38; Haeb-Umbach, R. (2016). Wide Residual BLSTM Network
    with Discriminative Speaker Adaptation for Robust Speech Recognition. In <i>Computer
    Speech and Language</i>.
  bibtex: '@inproceedings{Heymann_Drude_Haeb-Umbach_2016, title={Wide Residual BLSTM
    Network with Discriminative Speaker Adaptation for Robust Speech Recognition},
    booktitle={Computer Speech and Language}, author={Heymann, Jahn and Drude, Lukas
    and Haeb-Umbach, Reinhold}, year={2016} }'
  chicago: Heymann, Jahn, Lukas Drude, and Reinhold Haeb-Umbach. “Wide Residual BLSTM
    Network with Discriminative Speaker Adaptation for Robust Speech Recognition.”
    In <i>Computer Speech and Language</i>, 2016.
  ieee: J. Heymann, L. Drude, and R. Haeb-Umbach, “Wide Residual BLSTM Network with
    Discriminative Speaker Adaptation for Robust Speech Recognition,” in <i>Computer
    Speech and Language</i>, 2016.
  mla: Heymann, Jahn, et al. “Wide Residual BLSTM Network with Discriminative Speaker
    Adaptation for Robust Speech Recognition.” <i>Computer Speech and Language</i>,
    2016.
  short: 'J. Heymann, L. Drude, R. Haeb-Umbach, in: Computer Speech and Language,
    2016.'
date_created: 2019-07-12T05:29:09Z
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/2016/chime4_upbonly_paper.pdf
oa: '1'
publication: Computer Speech and Language
related_material:
  link:
  - description: Poster
    relation: supplementary_material
    url: https://groups.uni-paderborn.de/nt/pubs/2016/chime4_upbonly_poster.pdf
status: public
title: Wide Residual BLSTM Network with Discriminative Speaker Adaptation for Robust
  Speech Recognition
type: conference
user_id: '44006'
year: '2016'
...
---
_id: '11908'
abstract:
- lang: eng
  text: 'This paper describes automatic speech recognition (ASR) systems developed
    jointly by RWTH, UPB and FORTH for the 1ch, 2ch and 6ch track of the 4th CHiME
    Challenge. In the 2ch and 6ch tracks the final system output is obtained by a
    Confusion Network Combination (CNC) of multiple systems. The Acoustic Model (AM)
    is a deep neural network based on Bidirectional Long Short-Term Memory (BLSTM)
    units. The systems differ by front ends and training sets used for the acoustic
    training. The model for the 1ch track is trained without any preprocessing. For
    each front end we trained and evaluated individual acoustic models. We compare
    the ASR performance of different beamforming approaches: a conventional superdirective
    beamformer [1] and an MVDR beamformer as in [2], where the steering vector is
    estimated based on [3]. Furthermore we evaluated a BLSTM supported Generalized
    Eigenvalue beamformer using NN-GEV [4]. The back end is implemented using RWTH?s
    open-source toolkits RASR [5], RETURNN [6] and rwthlm [7]. We rescore lattices
    with a Long Short-Term Memory (LSTM) based language model. The overall best results
    are obtained by a system combination that includes the lattices from the system
    of UPB?s submission [8]. Our final submission scored second in each of the three
    tracks of the 4th CHiME Challenge.'
author:
- first_name: Tobias
  full_name: Menne, Tobias
  last_name: Menne
- first_name: Jahn
  full_name: Heymann, Jahn
  id: '9168'
  last_name: Heymann
- first_name: Anastasios
  full_name: Alexandridis, Anastasios
  last_name: Alexandridis
- first_name: Kazuki
  full_name: Irie, Kazuki
  last_name: Irie
- first_name: Albert
  full_name: Zeyer, Albert
  last_name: Zeyer
- first_name: Markus
  full_name: Kitza, Markus
  last_name: Kitza
- first_name: Pavel
  full_name: Golik, Pavel
  last_name: Golik
- first_name: Ilia
  full_name: Kulikov, Ilia
  last_name: Kulikov
- first_name: Lukas
  full_name: Drude, Lukas
  id: '11213'
  last_name: Drude
- first_name: Ralf
  full_name: Schlüter, Ralf
  last_name: Schlüter
- first_name: Hermann
  full_name: Ney, Hermann
  last_name: Ney
- first_name: Reinhold
  full_name: Haeb-Umbach, Reinhold
  id: '242'
  last_name: Haeb-Umbach
- first_name: Athanasios
  full_name: Mouchtaris, Athanasios
  last_name: Mouchtaris
citation:
  ama: 'Menne T, Heymann J, Alexandridis A, et al. The RWTH/UPB/FORTH System Combination
    for the 4th CHiME Challenge Evaluation. In: <i>Computer Speech and Language</i>.
    ; 2016.'
  apa: Menne, T., Heymann, J., Alexandridis, A., Irie, K., Zeyer, A., Kitza, M., …
    Mouchtaris, A. (2016). The RWTH/UPB/FORTH System Combination for the 4th CHiME
    Challenge Evaluation. In <i>Computer Speech and Language</i>.
  bibtex: '@inproceedings{Menne_Heymann_Alexandridis_Irie_Zeyer_Kitza_Golik_Kulikov_Drude_Schlüter_et
    al._2016, title={The RWTH/UPB/FORTH System Combination for the 4th CHiME Challenge
    Evaluation}, booktitle={Computer Speech and Language}, author={Menne, Tobias and
    Heymann, Jahn and Alexandridis, Anastasios and Irie, Kazuki and Zeyer, Albert
    and Kitza, Markus and Golik, Pavel and Kulikov, Ilia and Drude, Lukas and Schlüter,
    Ralf and et al.}, year={2016} }'
  chicago: Menne, Tobias, Jahn Heymann, Anastasios Alexandridis, Kazuki Irie, Albert
    Zeyer, Markus Kitza, Pavel Golik, et al. “The RWTH/UPB/FORTH System Combination
    for the 4th CHiME Challenge Evaluation.” In <i>Computer Speech and Language</i>,
    2016.
  ieee: T. Menne <i>et al.</i>, “The RWTH/UPB/FORTH System Combination for the 4th
    CHiME Challenge Evaluation,” in <i>Computer Speech and Language</i>, 2016.
  mla: Menne, Tobias, et al. “The RWTH/UPB/FORTH System Combination for the 4th CHiME
    Challenge Evaluation.” <i>Computer Speech and Language</i>, 2016.
  short: 'T. Menne, J. Heymann, A. Alexandridis, K. Irie, A. Zeyer, M. Kitza, P. Golik,
    I. Kulikov, L. Drude, R. Schlüter, H. Ney, R. Haeb-Umbach, A. Mouchtaris, in:
    Computer Speech and Language, 2016.'
date_created: 2019-07-12T05:30:35Z
date_updated: 2022-01-06T06:51:12Z
department:
- _id: '54'
language:
- iso: eng
main_file_link:
- open_access: '1'
  url: https://groups.uni-paderborn.de/nt/pubs/2016/chime4_rwthupbforth_paper.pdf
oa: '1'
publication: Computer Speech and Language
status: public
title: The RWTH/UPB/FORTH System Combination for the 4th CHiME Challenge Evaluation
type: conference
user_id: '44006'
year: '2016'
...
---
_id: '11755'
abstract:
- lang: eng
  text: This contribution presents a Direction of Arrival (DoA) estimation algorithm
    based on the complex Watson distribution to incorporate both phase and level differences
    of captured micro- phone array signals. The derived algorithm is reviewed in the
    context of the Generalized State Coherence Transform (GSCT) on the one hand and
    a kernel density estimation method on the other hand. A thorough simulative evaluation
    yields insight into parameter selection and provides details on the performance
    for both directional and omni-directional microphones. A comparison to the well
    known Steered Response Power with Phase Transform (SRP-PHAT) algorithm and a state
    of the art DoA estimator which explicitly accounts for aliasing, shows in particular
    the advantages of presented algorithm if inter-sensor level differences are indicative
    of the DoA, as with directional microphones.
author:
- first_name: Lukas
  full_name: Drude, Lukas
  id: '11213'
  last_name: Drude
- first_name: Florian
  full_name: Jacob, Florian
  last_name: Jacob
- first_name: Reinhold
  full_name: Haeb-Umbach, Reinhold
  id: '242'
  last_name: Haeb-Umbach
citation:
  ama: 'Drude L, Jacob F, Haeb-Umbach R. DOA-Estimation based on a Complex Watson
    Kernel Method. In: <i>23th European Signal Processing Conference (EUSIPCO 2015)</i>.
    ; 2015.'
  apa: Drude, L., Jacob, F., &#38; Haeb-Umbach, R. (2015). DOA-Estimation based on
    a Complex Watson Kernel Method. In <i>23th European Signal Processing Conference
    (EUSIPCO 2015)</i>.
  bibtex: '@inproceedings{Drude_Jacob_Haeb-Umbach_2015, title={DOA-Estimation based
    on a Complex Watson Kernel Method}, booktitle={23th European Signal Processing
    Conference (EUSIPCO 2015)}, author={Drude, Lukas and Jacob, Florian and Haeb-Umbach,
    Reinhold}, year={2015} }'
  chicago: Drude, Lukas, Florian Jacob, and Reinhold Haeb-Umbach. “DOA-Estimation
    Based on a Complex Watson Kernel Method.” In <i>23th European Signal Processing
    Conference (EUSIPCO 2015)</i>, 2015.
  ieee: L. Drude, F. Jacob, and R. Haeb-Umbach, “DOA-Estimation based on a Complex
    Watson Kernel Method,” in <i>23th European Signal Processing Conference (EUSIPCO
    2015)</i>, 2015.
  mla: Drude, Lukas, et al. “DOA-Estimation Based on a Complex Watson Kernel Method.”
    <i>23th European Signal Processing Conference (EUSIPCO 2015)</i>, 2015.
  short: 'L. Drude, F. Jacob, R. Haeb-Umbach, in: 23th European Signal Processing
    Conference (EUSIPCO 2015), 2015.'
date_created: 2019-07-12T05:27:38Z
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/2015/DrJaHa15.pdf
oa: '1'
publication: 23th European Signal Processing Conference (EUSIPCO 2015)
related_material:
  link:
  - description: Presentation
    relation: supplementary_material
    url: https://groups.uni-paderborn.de/nt/pubs/2015/DrJaHa15_Presentation.pdf
status: public
title: DOA-Estimation based on a Complex Watson Kernel Method
type: conference
user_id: '44006'
year: '2015'
...
---
_id: '11810'
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: Aleksej
  full_name: Chinaev, Aleksej
  last_name: Chinaev
- first_name: Reinhold
  full_name: Haeb-Umbach, Reinhold
  id: '242'
  last_name: Haeb-Umbach
citation:
  ama: 'Heymann J, Drude L, Chinaev A, Haeb-Umbach R. BLSTM supported GEV Beamformer
    Front-End for the 3RD CHiME Challenge. In: <i>Automatic Speech Recognition and
    Understanding Workshop (ASRU 2015)</i>. ; 2015.'
  apa: Heymann, J., Drude, L., Chinaev, A., &#38; Haeb-Umbach, R. (2015). BLSTM supported
    GEV Beamformer Front-End for the 3RD CHiME Challenge. In <i>Automatic Speech Recognition
    and Understanding Workshop (ASRU 2015)</i>.
  bibtex: '@inproceedings{Heymann_Drude_Chinaev_Haeb-Umbach_2015, title={BLSTM supported
    GEV Beamformer Front-End for the 3RD CHiME Challenge}, booktitle={Automatic Speech
    Recognition and Understanding Workshop (ASRU 2015)}, author={Heymann, Jahn and
    Drude, Lukas and Chinaev, Aleksej and Haeb-Umbach, Reinhold}, year={2015} }'
  chicago: Heymann, Jahn, Lukas Drude, Aleksej Chinaev, and Reinhold Haeb-Umbach.
    “BLSTM Supported GEV Beamformer Front-End for the 3RD CHiME Challenge.” In <i>Automatic
    Speech Recognition and Understanding Workshop (ASRU 2015)</i>, 2015.
  ieee: J. Heymann, L. Drude, A. Chinaev, and R. Haeb-Umbach, “BLSTM supported GEV
    Beamformer Front-End for the 3RD CHiME Challenge,” in <i>Automatic Speech Recognition
    and Understanding Workshop (ASRU 2015)</i>, 2015.
  mla: Heymann, Jahn, et al. “BLSTM Supported GEV Beamformer Front-End for the 3RD
    CHiME Challenge.” <i>Automatic Speech Recognition and Understanding Workshop (ASRU
    2015)</i>, 2015.
  short: 'J. Heymann, L. Drude, A. Chinaev, R. Haeb-Umbach, in: Automatic Speech Recognition
    and Understanding Workshop (ASRU 2015), 2015.'
date_created: 2019-07-12T05:28:41Z
date_updated: 2022-01-06T06:51:09Z
department:
- _id: '54'
language:
- iso: eng
publication: Automatic Speech Recognition and Understanding Workshop (ASRU 2015)
status: public
title: BLSTM supported GEV Beamformer Front-End for the 3RD CHiME Challenge
type: conference
user_id: '44006'
year: '2015'
...
---
_id: '11919'
abstract:
- lang: eng
  text: In this paper we present a source counting algorithm to determine the number
    of speakers in a speech mixture. In our proposed method, we model the histogram
    of estimated directions of arrival with a nonparametric Bayesian infinite Gaussian
    mixture model. As an alternative to classical model selection criteria and to
    avoid specifying the maximum number of mixture components in advance, a Dirichlet
    process prior is employed over the mixture components. This allows to automatically
    determine the optimal number of mixture components that most probably model the
    observations. We demonstrate by experiments that this model outperforms a parametric
    approach using a finite Gaussian mixture model with a Dirichlet distribution prior
    over the mixture weights.
author:
- first_name: Oliver
  full_name: Walter, Oliver
  last_name: Walter
- 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: 'Walter O, Drude L, Haeb-Umbach R. Source Counting in Speech Mixtures by Nonparametric
    Bayesian Estimation of an infinite Gaussian Mixture Model. In: <i>40th International
    Conference on Acoustics, Speech and Signal Processing (ICASSP 2015)</i>. ; 2015.'
  apa: Walter, O., Drude, L., &#38; Haeb-Umbach, R. (2015). Source Counting in Speech
    Mixtures by Nonparametric Bayesian Estimation of an infinite Gaussian Mixture
    Model. In <i>40th International Conference on Acoustics, Speech and Signal Processing
    (ICASSP 2015)</i>.
  bibtex: '@inproceedings{Walter_Drude_Haeb-Umbach_2015, title={Source Counting in
    Speech Mixtures by Nonparametric Bayesian Estimation of an infinite Gaussian Mixture
    Model}, booktitle={40th International Conference on Acoustics, Speech and Signal
    Processing (ICASSP 2015)}, author={Walter, Oliver and Drude, Lukas and Haeb-Umbach,
    Reinhold}, year={2015} }'
  chicago: Walter, Oliver, Lukas Drude, and Reinhold Haeb-Umbach. “Source Counting
    in Speech Mixtures by Nonparametric Bayesian Estimation of an Infinite Gaussian
    Mixture Model.” In <i>40th International Conference on Acoustics, Speech and Signal
    Processing (ICASSP 2015)</i>, 2015.
  ieee: O. Walter, L. Drude, and R. Haeb-Umbach, “Source Counting in Speech Mixtures
    by Nonparametric Bayesian Estimation of an infinite Gaussian Mixture Model,” in
    <i>40th International Conference on Acoustics, Speech and Signal Processing (ICASSP
    2015)</i>, 2015.
  mla: Walter, Oliver, et al. “Source Counting in Speech Mixtures by Nonparametric
    Bayesian Estimation of an Infinite Gaussian Mixture Model.” <i>40th International
    Conference on Acoustics, Speech and Signal Processing (ICASSP 2015)</i>, 2015.
  short: 'O. Walter, L. Drude, R. Haeb-Umbach, in: 40th International Conference on
    Acoustics, Speech and Signal Processing (ICASSP 2015), 2015.'
date_created: 2019-07-12T05:30:47Z
date_updated: 2022-01-06T06:51:12Z
department:
- _id: '54'
language:
- iso: eng
main_file_link:
- open_access: '1'
  url: https://groups.uni-paderborn.de/nt/pubs/2015/WaDrHa15.pdf
oa: '1'
publication: 40th International Conference on Acoustics, Speech and Signal Processing
  (ICASSP 2015)
related_material:
  link:
  - description: Poster
    relation: supplementary_material
    url: https://groups.uni-paderborn.de/nt/pubs/2015/WaDrHa15_Poster.pdf
status: public
title: Source Counting in Speech Mixtures by Nonparametric Bayesian Estimation of
  an infinite Gaussian Mixture Model
type: conference
user_id: '44006'
year: '2015'
...
---
_id: '11752'
abstract:
- lang: eng
  text: ' "In this contribution we derive a variational EM (VEM) algorithm for model
    selection in complex Watson mixture models, which have been recently proposed
    as a model of the distribution of normalized microphone array signals in the short-time
    Fourier transform domain. The VEM algorithm is applied to count the number of
    active sources in a speech mixture by iteratively estimating the mode vectors
    of the Watson distributions and suppressing the signals from the corresponding
    directions. A key theoretical contribution is the derivation of the MMSE estimate
    of a quadratic form involving the mode vector of the Watson distribution. The
    experimental results demonstrate the effectiveness of the source counting approach
    at moderately low SNR. It is further shown that the VEM algorithm is more robust
    w.r.t. used threshold values." '
author:
- first_name: Lukas
  full_name: Drude, Lukas
  id: '11213'
  last_name: Drude
- first_name: Aleksej
  full_name: Chinaev, Aleksej
  last_name: Chinaev
- first_name: Dang Hai
  full_name: Tran Vu, Dang Hai
  last_name: Tran Vu
- first_name: Reinhold
  full_name: Haeb-Umbach, Reinhold
  id: '242'
  last_name: Haeb-Umbach
citation:
  ama: 'Drude L, Chinaev A, Tran Vu DH, Haeb-Umbach R. Source Counting in Speech Mixtures
    Using a Variational EM Approach for Complexwatson Mixture Models. In: <i>39th
    International Conference on Acoustics, Speech and Signal Processing (ICASSP 2014)</i>.
    ; 2014.'
  apa: Drude, L., Chinaev, A., Tran Vu, D. H., &#38; Haeb-Umbach, R. (2014). Source
    Counting in Speech Mixtures Using a Variational EM Approach for Complexwatson
    Mixture Models. In <i>39th International Conference on Acoustics, Speech and Signal
    Processing (ICASSP 2014)</i>.
  bibtex: '@inproceedings{Drude_Chinaev_Tran Vu_Haeb-Umbach_2014, title={Source Counting
    in Speech Mixtures Using a Variational EM Approach for Complexwatson Mixture Models},
    booktitle={39th International Conference on Acoustics, Speech and Signal Processing
    (ICASSP 2014)}, author={Drude, Lukas and Chinaev, Aleksej and Tran Vu, Dang Hai
    and Haeb-Umbach, Reinhold}, year={2014} }'
  chicago: Drude, Lukas, Aleksej Chinaev, Dang Hai Tran Vu, and Reinhold Haeb-Umbach.
    “Source Counting in Speech Mixtures Using a Variational EM Approach for Complexwatson
    Mixture Models.” In <i>39th International Conference on Acoustics, Speech and
    Signal Processing (ICASSP 2014)</i>, 2014.
  ieee: L. Drude, A. Chinaev, D. H. Tran Vu, and R. Haeb-Umbach, “Source Counting
    in Speech Mixtures Using a Variational EM Approach for Complexwatson Mixture Models,”
    in <i>39th International Conference on Acoustics, Speech and Signal Processing
    (ICASSP 2014)</i>, 2014.
  mla: Drude, Lukas, et al. “Source Counting in Speech Mixtures Using a Variational
    EM Approach for Complexwatson Mixture Models.” <i>39th International Conference
    on Acoustics, Speech and Signal Processing (ICASSP 2014)</i>, 2014.
  short: 'L. Drude, A. Chinaev, D.H. Tran Vu, R. Haeb-Umbach, in: 39th International
    Conference on Acoustics, Speech and Signal Processing (ICASSP 2014), 2014.'
date_created: 2019-07-12T05:27:34Z
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/2014/DrChTrHa2014.pdf
oa: '1'
publication: 39th International Conference on Acoustics, Speech and Signal Processing
  (ICASSP 2014)
related_material:
  link:
  - description: Poster
    relation: supplementary_material
    url: https://groups.uni-paderborn.de/nt/pubs/2014/DrChTrHa2014_Poster.pdf
status: public
title: Source Counting in Speech Mixtures Using a Variational EM Approach for Complexwatson
  Mixture Models
type: conference
user_id: '44006'
year: '2014'
...
---
_id: '11753'
abstract:
- lang: eng
  text: This contribution describes a step-wise source counting algorithm to determine
    the number of speakers in an offline scenario. Each speaker is identified by a
    variational expectation maximization (VEM) algorithm for complex Watson mixture
    models and therefore directly yields beamforming vectors for a subsequent speech
    separation process. An observation selection criterion is proposed which improves
    the robustness of the source counting in noise. The algorithm is compared to an
    alternative VEM approach with Gaussian mixture models based on directions of arrival
    and shown to deliver improved source counting accuracy. The article concludes
    by extending the offline algorithm towards a low-latency online estimation of
    the number of active sources from the streaming input data.
author:
- first_name: Lukas
  full_name: Drude, Lukas
  id: '11213'
  last_name: Drude
- first_name: Aleksej
  full_name: Chinaev, Aleksej
  last_name: Chinaev
- first_name: Dang Hai
  full_name: Tran Vu, Dang Hai
  last_name: Tran Vu
- first_name: Reinhold
  full_name: Haeb-Umbach, Reinhold
  id: '242'
  last_name: Haeb-Umbach
citation:
  ama: 'Drude L, Chinaev A, Tran Vu DH, Haeb-Umbach R. Towards Online Source Counting
    in Speech Mixtures Applying a Variational EM for Complex Watson Mixture Models.
    In: <i>14th International Workshop on Acoustic Signal Enhancement (IWAENC 2014)</i>.
    ; 2014:213-217.'
  apa: Drude, L., Chinaev, A., Tran Vu, D. H., &#38; Haeb-Umbach, R. (2014). Towards
    Online Source Counting in Speech Mixtures Applying a Variational EM for Complex
    Watson Mixture Models. In <i>14th International Workshop on Acoustic Signal Enhancement
    (IWAENC 2014)</i> (pp. 213–217).
  bibtex: '@inproceedings{Drude_Chinaev_Tran Vu_Haeb-Umbach_2014, title={Towards Online
    Source Counting in Speech Mixtures Applying a Variational EM for Complex Watson
    Mixture Models}, booktitle={14th International Workshop on Acoustic Signal Enhancement
    (IWAENC 2014)}, author={Drude, Lukas and Chinaev, Aleksej and Tran Vu, Dang Hai
    and Haeb-Umbach, Reinhold}, year={2014}, pages={213–217} }'
  chicago: Drude, Lukas, Aleksej Chinaev, Dang Hai Tran Vu, and Reinhold Haeb-Umbach.
    “Towards Online Source Counting in Speech Mixtures Applying a Variational EM for
    Complex Watson Mixture Models.” In <i>14th International Workshop on Acoustic
    Signal Enhancement (IWAENC 2014)</i>, 213–17, 2014.
  ieee: L. Drude, A. Chinaev, D. H. Tran Vu, and R. Haeb-Umbach, “Towards Online Source
    Counting in Speech Mixtures Applying a Variational EM for Complex Watson Mixture
    Models,” in <i>14th International Workshop on Acoustic Signal Enhancement (IWAENC
    2014)</i>, 2014, pp. 213–217.
  mla: Drude, Lukas, et al. “Towards Online Source Counting in Speech Mixtures Applying
    a Variational EM for Complex Watson Mixture Models.” <i>14th International Workshop
    on Acoustic Signal Enhancement (IWAENC 2014)</i>, 2014, pp. 213–17.
  short: 'L. Drude, A. Chinaev, D.H. Tran Vu, R. Haeb-Umbach, in: 14th International
    Workshop on Acoustic Signal Enhancement (IWAENC 2014), 2014, pp. 213–217.'
date_created: 2019-07-12T05:27:35Z
date_updated: 2022-01-06T06:51:08Z
department:
- _id: '54'
keyword:
- Accuracy
- Acoustics
- Estimation
- Mathematical model
- Soruce separation
- Speech
- Vectors
- Bayes methods
- Blind source separation
- Directional statistics
- Number of speakers
- Speaker diarization
language:
- iso: eng
main_file_link:
- open_access: '1'
  url: https://groups.uni-paderborn.de/nt/pubs/2014/DrChTrHaeb14.pdf
oa: '1'
page: 213-217
publication: 14th International Workshop on Acoustic Signal Enhancement (IWAENC 2014)
related_material:
  link:
  - description: Poster
    relation: supplementary_material
    url: https://groups.uni-paderborn.de/nt/pubs/2014/DrChTrHaeb14_Poster.pdf
status: public
title: Towards Online Source Counting in Speech Mixtures Applying a Variational EM
  for Complex Watson Mixture Models
type: conference
user_id: '44006'
year: '2014'
...