---
_id: '11849'
abstract:
- lang: eng
  text: In this contribution we investigate the effectiveness of Bayesian feature
    enhancement (BFE) on a medium-sized recognition task containing real-world recordings
    of noisy reverberant speech. BFE employs a very coarse model of the acoustic impulse
    response (AIR) from the source to the microphone, which has been shown to be effective
    if the speech to be recognized has been generated by artificially convolving nonreverberant
    speech with a constant AIR. Here we demonstrate that the model is also appropriate
    to be used in feature enhancement of true recordings of noisy reverberant speech.
    On the Multi-Channel Wall Street Journal Audio Visual corpus (MC-WSJ-AV) the word
    error rate is cut in half to 41.9 percent compared to the ETSI Standard Front-End
    using as input the signal of a single distant microphone with a single recognition
    pass.
author:
- first_name: Alexander
  full_name: Krueger, Alexander
  last_name: Krueger
- first_name: Oliver
  full_name: Walter, Oliver
  last_name: Walter
- first_name: Volker
  full_name: Leutnant, Volker
  last_name: Leutnant
- first_name: Reinhold
  full_name: Haeb-Umbach, Reinhold
  id: '242'
  last_name: Haeb-Umbach
citation:
  ama: 'Krueger A, Walter O, Leutnant V, Haeb-Umbach R. Bayesian Feature Enhancement
    for ASR of Noisy Reverberant Real-World Data. In: <i>Proc. Interspeech</i>. Portland,
    USA; 2012.'
  apa: Krueger, A., Walter, O., Leutnant, V., &#38; Haeb-Umbach, R. (2012). Bayesian
    Feature Enhancement for ASR of Noisy Reverberant Real-World Data. In <i>Proc.
    Interspeech</i>. Portland, USA.
  bibtex: '@inproceedings{Krueger_Walter_Leutnant_Haeb-Umbach_2012, place={Portland,
    USA}, title={Bayesian Feature Enhancement for ASR of Noisy Reverberant Real-World
    Data}, booktitle={Proc. Interspeech}, author={Krueger, Alexander and Walter, Oliver
    and Leutnant, Volker and Haeb-Umbach, Reinhold}, year={2012} }'
  chicago: Krueger, Alexander, Oliver Walter, Volker Leutnant, and Reinhold Haeb-Umbach.
    “Bayesian Feature Enhancement for ASR of Noisy Reverberant Real-World Data.” In
    <i>Proc. Interspeech</i>. Portland, USA, 2012.
  ieee: A. Krueger, O. Walter, V. Leutnant, and R. Haeb-Umbach, “Bayesian Feature
    Enhancement for ASR of Noisy Reverberant Real-World Data,” in <i>Proc. Interspeech</i>,
    2012.
  mla: Krueger, Alexander, et al. “Bayesian Feature Enhancement for ASR of Noisy Reverberant
    Real-World Data.” <i>Proc. Interspeech</i>, 2012.
  short: 'A. Krueger, O. Walter, V. Leutnant, R. Haeb-Umbach, in: Proc. Interspeech,
    Portland, USA, 2012.'
date_created: 2019-07-12T05:29:27Z
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/2012/KrWaLeHa2012.pdf
oa: '1'
place: Portland, USA
publication: Proc. Interspeech
status: public
title: Bayesian Feature Enhancement for ASR of Noisy Reverberant Real-World Data
type: conference
user_id: '44006'
year: '2012'
...
---
_id: '11863'
abstract:
- lang: eng
  text: 'In this contribution, a new observation model for the joint compensation
    of reverberation and noise in the logarithmic mel power spectral density domain
    will be considered. The proposed observation model relates the noisy reverberant
    feature to the underlying sequence of clean speech features and the feature of
    the noise. Nevertheless, due to the complex interaction of these variables in
    the target domain, the observationmodel cannot be applied to Bayesian feature
    enhancement directly, calling for approximations that eventually render the observation
    model useful. The performance of the approximated observation model will highly
    depend on the capability of modeling the difference between the model and the
    noisy reverberant observation. A detailed analysis of this observation error will
    be provided in this work. Among others, it will point out the need to account
    for the instantaneous ratio of the reverberant speech power and the noise power.
    Index Terms: Bayesian feature enhancement, observation model for noisy reverberant
    speech'
author:
- first_name: Volker
  full_name: Leutnant, Volker
  last_name: Leutnant
- first_name: Alexander
  full_name: Krueger, Alexander
  last_name: Krueger
- first_name: Reinhold
  full_name: Haeb-Umbach, Reinhold
  id: '242'
  last_name: Haeb-Umbach
citation:
  ama: Leutnant V, Krueger A, Haeb-Umbach R. Investigations Into a Statistical Observation
    Model for Logarithmic Mel Power Spectral Density Features of Noisy Reverberant
    Speech. <i>Speech Communication; 10 ITG Symposium; Proceedings of</i>. 2012:1-4.
  apa: Leutnant, V., Krueger, A., &#38; Haeb-Umbach, R. (2012). Investigations Into
    a Statistical Observation Model for Logarithmic Mel Power Spectral Density Features
    of Noisy Reverberant Speech. <i>Speech Communication; 10. ITG Symposium; Proceedings
    Of</i>, 1–4.
  bibtex: '@article{Leutnant_Krueger_Haeb-Umbach_2012, title={Investigations Into
    a Statistical Observation Model for Logarithmic Mel Power Spectral Density Features
    of Noisy Reverberant Speech}, journal={Speech Communication; 10. ITG Symposium;
    Proceedings of}, author={Leutnant, Volker and Krueger, Alexander and Haeb-Umbach,
    Reinhold}, year={2012}, pages={1–4} }'
  chicago: Leutnant, Volker, Alexander Krueger, and Reinhold Haeb-Umbach. “Investigations
    Into a Statistical Observation Model for Logarithmic Mel Power Spectral Density
    Features of Noisy Reverberant Speech.” <i>Speech Communication; 10. ITG Symposium;
    Proceedings Of</i>, 2012, 1–4.
  ieee: V. Leutnant, A. Krueger, and R. Haeb-Umbach, “Investigations Into a Statistical
    Observation Model for Logarithmic Mel Power Spectral Density Features of Noisy
    Reverberant Speech,” <i>Speech Communication; 10. ITG Symposium; Proceedings of</i>,
    pp. 1–4, 2012.
  mla: Leutnant, Volker, et al. “Investigations Into a Statistical Observation Model
    for Logarithmic Mel Power Spectral Density Features of Noisy Reverberant Speech.”
    <i>Speech Communication; 10. ITG Symposium; Proceedings Of</i>, 2012, pp. 1–4.
  short: V. Leutnant, A. Krueger, R. Haeb-Umbach, Speech Communication; 10. ITG Symposium;
    Proceedings Of (2012) 1–4.
date_created: 2019-07-12T05:29:43Z
date_updated: 2022-01-06T06:51:11Z
department:
- _id: '54'
language:
- iso: eng
main_file_link:
- open_access: '1'
  url: http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=6309628
oa: '1'
page: 1-4
publication: Speech Communication; 10. ITG Symposium; Proceedings of
status: public
title: Investigations Into a Statistical Observation Model for Logarithmic Mel Power
  Spectral Density Features of Noisy Reverberant Speech
type: journal_article
user_id: '44006'
year: '2012'
...
---
_id: '11864'
abstract:
- lang: eng
  text: In this work, an observation model for the joint compensation of noise and
    reverberation in the logarithmic mel power spectral density domain is considered.
    It relates the features of the noisy reverberant speech to those of the non-reverberant
    speech and the noise. In contrast to enhancement of features only corrupted by
    reverberation (reverberant features), enhancement of noisy reverberant features
    requires a more sophisticated model for the error introduced by the proposed observation
    model. In a first consideration, it will be shown that this error is highly dependent
    on the instantaneous ratio of the power of reverberant speech to the power of
    the noise and, moreover, sensitive to the phase between reverberant speech and
    noise in the short-time discrete Fourier domain. Afterwards, a statistically motivated
    approach will be presented allowing for the model of the observation error to
    be inferred from the error model previously used for the reverberation only case.
    Finally, the developed observation error model will be utilized in a Bayesian
    feature enhancement scheme, leading to improvements in word accuracy on the AURORA5
    database.
author:
- first_name: Volker
  full_name: Leutnant, Volker
  last_name: Leutnant
- first_name: Alexander
  full_name: Krueger, Alexander
  last_name: Krueger
- first_name: Reinhold
  full_name: Haeb-Umbach, Reinhold
  id: '242'
  last_name: Haeb-Umbach
citation:
  ama: 'Leutnant V, Krueger A, Haeb-Umbach R. A Statistical Observation Model For
    Noisy Reverberant Speech Features and its Application to Robust ASR. In: <i>Signal
    Processing, Communications and Computing (ICSPCC), 2012 IEEE International Conference
    On</i>. ; 2012.'
  apa: Leutnant, V., Krueger, A., &#38; Haeb-Umbach, R. (2012). A Statistical Observation
    Model For Noisy Reverberant Speech Features and its Application to Robust ASR.
    In <i>Signal Processing, Communications and Computing (ICSPCC), 2012 IEEE International
    Conference on</i>.
  bibtex: '@inproceedings{Leutnant_Krueger_Haeb-Umbach_2012, title={A Statistical
    Observation Model For Noisy Reverberant Speech Features and its Application to
    Robust ASR}, booktitle={Signal Processing, Communications and Computing (ICSPCC),
    2012 IEEE International Conference on}, author={Leutnant, Volker and Krueger,
    Alexander and Haeb-Umbach, Reinhold}, year={2012} }'
  chicago: Leutnant, Volker, Alexander Krueger, and Reinhold Haeb-Umbach. “A Statistical
    Observation Model For Noisy Reverberant Speech Features and Its Application to
    Robust ASR.” In <i>Signal Processing, Communications and Computing (ICSPCC), 2012
    IEEE International Conference On</i>, 2012.
  ieee: V. Leutnant, A. Krueger, and R. Haeb-Umbach, “A Statistical Observation Model
    For Noisy Reverberant Speech Features and its Application to Robust ASR,” in <i>Signal
    Processing, Communications and Computing (ICSPCC), 2012 IEEE International Conference
    on</i>, 2012.
  mla: Leutnant, Volker, et al. “A Statistical Observation Model For Noisy Reverberant
    Speech Features and Its Application to Robust ASR.” <i>Signal Processing, Communications
    and Computing (ICSPCC), 2012 IEEE International Conference On</i>, 2012.
  short: 'V. Leutnant, A. Krueger, R. Haeb-Umbach, in: Signal Processing, Communications
    and Computing (ICSPCC), 2012 IEEE International Conference On, 2012.'
date_created: 2019-07-12T05:29:44Z
date_updated: 2022-01-06T06:51:11Z
department:
- _id: '54'
keyword:
- Robust Automatic Speech Recognition
- Bayesian feature enhancement
- observation model for reverberant and noisy speech
language:
- iso: eng
main_file_link:
- open_access: '1'
  url: http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=6335731
oa: '1'
publication: Signal Processing, Communications and Computing (ICSPCC), 2012 IEEE International
  Conference on
status: public
title: A Statistical Observation Model For Noisy Reverberant Speech Features and its
  Application to Robust ASR
type: conference
user_id: '44006'
year: '2012'
...
---
_id: '11865'
author:
- first_name: Volker
  full_name: Leutnant, Volker
  last_name: Leutnant
- first_name: Alexander
  full_name: Krueger, Alexander
  last_name: Krueger
- first_name: Reinhold
  full_name: Haeb-Umbach, Reinhold
  id: '242'
  last_name: Haeb-Umbach
citation:
  ama: Leutnant V, Krueger A, Haeb-Umbach R. <i>Derivation of the Power Compensation
    Constant in the Observation Model for Reverberant Speech in the Logarithmic Mel
    Power Spectral Domain</i>.; 2012.
  apa: Leutnant, V., Krueger, A., &#38; Haeb-Umbach, R. (2012). <i>Derivation of the
    Power Compensation Constant in the Observation Model for Reverberant Speech in
    the Logarithmic Mel Power Spectral Domain</i>.
  bibtex: '@book{Leutnant_Krueger_Haeb-Umbach_2012, title={Derivation of the Power
    Compensation Constant in the Observation Model for Reverberant Speech in the Logarithmic
    Mel Power Spectral Domain}, author={Leutnant, Volker and Krueger, Alexander and
    Haeb-Umbach, Reinhold}, year={2012} }'
  chicago: Leutnant, Volker, Alexander Krueger, and Reinhold Haeb-Umbach. <i>Derivation
    of the Power Compensation Constant in the Observation Model for Reverberant Speech
    in the Logarithmic Mel Power Spectral Domain</i>, 2012.
  ieee: V. Leutnant, A. Krueger, and R. Haeb-Umbach, <i>Derivation of the Power Compensation
    Constant in the Observation Model for Reverberant Speech in the Logarithmic Mel
    Power Spectral Domain</i>. 2012.
  mla: Leutnant, Volker, et al. <i>Derivation of the Power Compensation Constant in
    the Observation Model for Reverberant Speech in the Logarithmic Mel Power Spectral
    Domain</i>. 2012.
  short: V. Leutnant, A. Krueger, R. Haeb-Umbach, Derivation of the Power Compensation
    Constant in the Observation Model for Reverberant Speech in the Logarithmic Mel
    Power Spectral Domain, 2012.
date_created: 2019-07-12T05:29:45Z
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/2012/LeuKruHab2012c.pdf
oa: '1'
status: public
title: Derivation of the Power Compensation Constant in the Observation Model for
  Reverberant Speech in the Logarithmic Mel Power Spectral Domain
type: report
user_id: '44006'
year: '2012'
...
---
_id: '11910'
author:
- 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: 'Tran Vu DH, Haeb-Umbach R. Exploiting Temporal Correlations in Joint Multichannel
    Speech Separation and Noise Suppression using Hidden Markov Models. In: <i>International
    Workshop on Acoustic Signal Enhancement (IWAENC2012)</i>. ; 2012.'
  apa: Tran Vu, D. H., &#38; Haeb-Umbach, R. (2012). Exploiting Temporal Correlations
    in Joint Multichannel Speech Separation and Noise Suppression using Hidden Markov
    Models. In <i>International Workshop on Acoustic Signal Enhancement (IWAENC2012)</i>.
  bibtex: '@inproceedings{Tran Vu_Haeb-Umbach_2012, title={Exploiting Temporal Correlations
    in Joint Multichannel Speech Separation and Noise Suppression using Hidden Markov
    Models}, booktitle={International Workshop on Acoustic Signal Enhancement (IWAENC2012)},
    author={Tran Vu, Dang Hai and Haeb-Umbach, Reinhold}, year={2012} }'
  chicago: Tran Vu, Dang Hai, and Reinhold Haeb-Umbach. “Exploiting Temporal Correlations
    in Joint Multichannel Speech Separation and Noise Suppression Using Hidden Markov
    Models.” In <i>International Workshop on Acoustic Signal Enhancement (IWAENC2012)</i>,
    2012.
  ieee: D. H. Tran Vu and R. Haeb-Umbach, “Exploiting Temporal Correlations in Joint
    Multichannel Speech Separation and Noise Suppression using Hidden Markov Models,”
    in <i>International Workshop on Acoustic Signal Enhancement (IWAENC2012)</i>,
    2012.
  mla: Tran Vu, Dang Hai, and Reinhold Haeb-Umbach. “Exploiting Temporal Correlations
    in Joint Multichannel Speech Separation and Noise Suppression Using Hidden Markov
    Models.” <i>International Workshop on Acoustic Signal Enhancement (IWAENC2012)</i>,
    2012.
  short: 'D.H. Tran Vu, R. Haeb-Umbach, in: International Workshop on Acoustic Signal
    Enhancement (IWAENC2012), 2012.'
date_created: 2019-07-12T05:30:37Z
date_updated: 2022-01-06T06:51:12Z
department:
- _id: '54'
language:
- iso: eng
publication: International Workshop on Acoustic Signal Enhancement (IWAENC2012)
status: public
title: Exploiting Temporal Correlations in Joint Multichannel Speech Separation and
  Noise Suppression using Hidden Markov Models
type: conference
user_id: '44006'
year: '2012'
...
---
_id: '11833'
abstract:
- lang: eng
  text: In this paper we propose an approach to retrieve the geometry of an acoustic
    sensor network consisting of spatially distributed microphone arrays from unconstrained
    speech input. The calibration relies on Direction of Arrival (DoA) measurements
    which do not require a clock synchronization among the sensor nodes. The calibration
    problem is formulated as a cost function optimization task, which minimizes the
    squared differences between measured and predicted observations and additionally
    avoids the existence of minima that correspond to mirrored versions of the actual
    sensor orientations. Further, outlier measurements caused by reverberation are
    mitigated by a Random Sample Consensus (RANSAC) approach. The experimental results
    show a mean positioning error of at most 25 cm even in highly reverberant environments.
author:
- first_name: Florian
  full_name: Jacob, Florian
  last_name: Jacob
- first_name: Joerg
  full_name: Schmalenstroeer, Joerg
  id: '460'
  last_name: Schmalenstroeer
- first_name: Reinhold
  full_name: Haeb-Umbach, Reinhold
  id: '242'
  last_name: Haeb-Umbach
citation:
  ama: 'Jacob F, Schmalenstroeer J, Haeb-Umbach R. Microphone Array Position Self-Calibration
    from Reverberant Speech Input. In: <i>International Workshop on Acoustic Signal
    Enhancement (IWAENC 2012)</i>. ; 2012.'
  apa: Jacob, F., Schmalenstroeer, J., &#38; Haeb-Umbach, R. (2012). Microphone Array
    Position Self-Calibration from Reverberant Speech Input. <i>International Workshop
    on Acoustic Signal Enhancement (IWAENC 2012)</i>.
  bibtex: '@inproceedings{Jacob_Schmalenstroeer_Haeb-Umbach_2012, title={Microphone
    Array Position Self-Calibration from Reverberant Speech Input}, booktitle={International
    Workshop on Acoustic Signal Enhancement (IWAENC 2012)}, author={Jacob, Florian
    and Schmalenstroeer, Joerg and Haeb-Umbach, Reinhold}, year={2012} }'
  chicago: Jacob, Florian, Joerg Schmalenstroeer, and Reinhold Haeb-Umbach. “Microphone
    Array Position Self-Calibration from Reverberant Speech Input.” In <i>International
    Workshop on Acoustic Signal Enhancement (IWAENC 2012)</i>, 2012.
  ieee: F. Jacob, J. Schmalenstroeer, and R. Haeb-Umbach, “Microphone Array Position
    Self-Calibration from Reverberant Speech Input,” 2012.
  mla: Jacob, Florian, et al. “Microphone Array Position Self-Calibration from Reverberant
    Speech Input.” <i>International Workshop on Acoustic Signal Enhancement (IWAENC
    2012)</i>, 2012.
  short: 'F. Jacob, J. Schmalenstroeer, R. Haeb-Umbach, in: International Workshop
    on Acoustic Signal Enhancement (IWAENC 2012), 2012.'
date_created: 2019-07-12T05:29:08Z
date_updated: 2023-10-26T08:10:52Z
department:
- _id: '54'
keyword:
- Unsupervised
- geometry calibration
- microphone arrays
- position self-calibration
language:
- iso: eng
main_file_link:
- open_access: '1'
  url: https://groups.uni-paderborn.de/nt/pubs/2012/JaScHa12.pdf
oa: '1'
publication: International Workshop on Acoustic Signal Enhancement (IWAENC 2012)
quality_controlled: '1'
related_material:
  link:
  - description: Video
    relation: supplementary_material
    url: https://groups.uni-paderborn.de/nt/pubs/2012/Microphine_Array_Position_Self-Calibration_from_Reverberant_Speech_Input.mp4
  - description: Poster
    relation: supplementary_material
    url: https://groups.uni-paderborn.de/nt/pubs/2012/JaScHa12_Poster.pdf
  - description: Demonstrator
    relation: supplementary_material
    url: https://groups.uni-paderborn.de/nt/pubs/2012/JaScHa12_Demonstrator.pdf
status: public
title: Microphone Array Position Self-Calibration from Reverberant Speech Input
type: conference
user_id: '460'
year: '2012'
...
---
_id: '11925'
abstract:
- lang: eng
  text: In this paper we present a system for car navigation by fusing sensor data
    on an Android smartphone. The key idea is to use both the internal sensors of
    the smartphone (e.g., gyroscope) and sensor data from the car (e.g., speed information)
    to support navigation via GPS. To this end we employ a CAN-Bus-to-Bluetooth adapter
    to establish a wireless connection between the smartphone and the CAN-Bus of the
    car. On the smartphone a strapdown algorithm and an error-state Kalman filter
    are used to fuse the different sensor data streams. The experimental results show
    that the system is able to maintain higher positioning accuracy during GPS dropouts,
    thus improving the availability and reliability, compared to GPS-only solutions.
author:
- first_name: Oliver
  full_name: Walter, Oliver
  last_name: Walter
- first_name: Joerg
  full_name: Schmalenstroeer, Joerg
  id: '460'
  last_name: Schmalenstroeer
- first_name: Andreas
  full_name: Engler, Andreas
  last_name: Engler
- first_name: Reinhold
  full_name: Haeb-Umbach, Reinhold
  id: '242'
  last_name: Haeb-Umbach
citation:
  ama: 'Walter O, Schmalenstroeer J, Engler A, Haeb-Umbach R. Smartphone-Based Sensor
    Fusion for Improved Vehicular Navigation. In: <i>9th Workshop on Positioning Navigation
    and Communication (WPNC 2012)</i>. ; 2012.'
  apa: Walter, O., Schmalenstroeer, J., Engler, A., &#38; Haeb-Umbach, R. (2012).
    Smartphone-Based Sensor Fusion for Improved Vehicular Navigation. <i>9th Workshop
    on Positioning Navigation and Communication (WPNC 2012)</i>.
  bibtex: '@inproceedings{Walter_Schmalenstroeer_Engler_Haeb-Umbach_2012, title={Smartphone-Based
    Sensor Fusion for Improved Vehicular Navigation}, booktitle={9th Workshop on Positioning
    Navigation and Communication (WPNC 2012)}, author={Walter, Oliver and Schmalenstroeer,
    Joerg and Engler, Andreas and Haeb-Umbach, Reinhold}, year={2012} }'
  chicago: Walter, Oliver, Joerg Schmalenstroeer, Andreas Engler, and Reinhold Haeb-Umbach.
    “Smartphone-Based Sensor Fusion for Improved Vehicular Navigation.” In <i>9th
    Workshop on Positioning Navigation and Communication (WPNC 2012)</i>, 2012.
  ieee: O. Walter, J. Schmalenstroeer, A. Engler, and R. Haeb-Umbach, “Smartphone-Based
    Sensor Fusion for Improved Vehicular Navigation,” 2012.
  mla: Walter, Oliver, et al. “Smartphone-Based Sensor Fusion for Improved Vehicular
    Navigation.” <i>9th Workshop on Positioning Navigation and Communication (WPNC
    2012)</i>, 2012.
  short: 'O. Walter, J. Schmalenstroeer, A. Engler, R. Haeb-Umbach, in: 9th Workshop
    on Positioning Navigation and Communication (WPNC 2012), 2012.'
date_created: 2019-07-12T05:30:54Z
date_updated: 2023-10-26T08:13:27Z
department:
- _id: '54'
keyword:
- Smartphone
- navigation
- sensor fusion
language:
- iso: eng
main_file_link:
- open_access: '1'
  url: https://groups.uni-paderborn.de/nt/pubs/2012/WaScEnHa12.pdf
oa: '1'
publication: 9th Workshop on Positioning Navigation and Communication (WPNC 2012)
quality_controlled: '1'
status: public
title: Smartphone-Based Sensor Fusion for Improved Vehicular Navigation
type: conference
user_id: '460'
year: '2012'
...
---
_id: '11721'
author:
- first_name: Maik
  full_name: Bevermeier, Maik
  last_name: Bevermeier
- first_name: Stephan
  full_name: Flanke, Stephan
  last_name: Flanke
- first_name: Reinhold
  full_name: Haeb-Umbach, Reinhold
  id: '242'
  last_name: Haeb-Umbach
- first_name: Jan
  full_name: Stehr, Jan
  last_name: Stehr
citation:
  ama: 'Bevermeier M, Flanke S, Haeb-Umbach R, Stehr J. A Platform for efficient Supply
    Chain Management Support in Logistics. In: <i>International Workshop on Intelligent
    Transportation (WIT 2011)</i>. ; 2011.'
  apa: Bevermeier, M., Flanke, S., Haeb-Umbach, R., &#38; Stehr, J. (2011). A Platform
    for efficient Supply Chain Management Support in Logistics. In <i>International
    Workshop on Intelligent Transportation (WIT 2011)</i>.
  bibtex: '@inproceedings{Bevermeier_Flanke_Haeb-Umbach_Stehr_2011, title={A Platform
    for efficient Supply Chain Management Support in Logistics}, booktitle={International
    Workshop on Intelligent Transportation (WIT 2011)}, author={Bevermeier, Maik and
    Flanke, Stephan and Haeb-Umbach, Reinhold and Stehr, Jan}, year={2011} }'
  chicago: Bevermeier, Maik, Stephan Flanke, Reinhold Haeb-Umbach, and Jan Stehr.
    “A Platform for Efficient Supply Chain Management Support in Logistics.” In <i>International
    Workshop on Intelligent Transportation (WIT 2011)</i>, 2011.
  ieee: M. Bevermeier, S. Flanke, R. Haeb-Umbach, and J. Stehr, “A Platform for efficient
    Supply Chain Management Support in Logistics,” in <i>International Workshop on
    Intelligent Transportation (WIT 2011)</i>, 2011.
  mla: Bevermeier, Maik, et al. “A Platform for Efficient Supply Chain Management
    Support in Logistics.” <i>International Workshop on Intelligent Transportation
    (WIT 2011)</i>, 2011.
  short: 'M. Bevermeier, S. Flanke, R. Haeb-Umbach, J. Stehr, in: International Workshop
    on Intelligent Transportation (WIT 2011), 2011.'
date_created: 2019-07-12T05:26:58Z
date_updated: 2022-01-06T06:51:07Z
department:
- _id: '54'
language:
- iso: eng
main_file_link:
- open_access: '1'
  url: https://groups.uni-paderborn.de/nt/pubs/2011/BeFlHaSt11.pdf
oa: '1'
publication: International Workshop on Intelligent Transportation (WIT 2011)
status: public
title: A Platform for efficient Supply Chain Management Support in Logistics
type: conference
user_id: '44006'
year: '2011'
...
---
_id: '11774'
abstract:
- lang: eng
  text: In this contribution classification rules for HMM-based speech recognition
    in the presence of a mismatch between training and test data are presented. The
    observed feature vectors are regarded as corrupted versions of underlying and
    unobservable clean feature vectors, which have the same statistics as the training
    data. Optimal classification then consists of two steps. First, the posterior
    density of the clean feature vector, given the observed feature vectors, has to
    be determined, and second, this posterior is employed in a modified classification
    rule, which accounts for imperfect estimates. We discuss different variants of
    the classification rule and further elaborate on the estimation of the clean speech
    feature posterior, using conditional Bayesian estimation. It is shown that this
    concept is fairly general and can be applied to different scenarios, such as noisy
    or reverberant speech recognition.
author:
- first_name: Reinhold
  full_name: Haeb-Umbach, Reinhold
  id: '242'
  last_name: Haeb-Umbach
citation:
  ama: 'Haeb-Umbach R. Uncertainty Decoding and Conditional Bayesian Estimation. In:
    Haeb-Umbach R, Kolossa D, eds. <i>Robust Speech Recognition of Uncertain or Missing
    Data</i>. Springer; 2011.'
  apa: Haeb-Umbach, R. (2011). Uncertainty Decoding and Conditional Bayesian Estimation.
    In R. Haeb-Umbach &#38; D. Kolossa (Eds.), <i>Robust Speech Recognition of Uncertain
    or Missing Data</i>. Springer.
  bibtex: '@inbook{Haeb-Umbach_2011, title={Uncertainty Decoding and Conditional Bayesian
    Estimation}, booktitle={Robust Speech Recognition of Uncertain or Missing Data},
    publisher={Springer}, author={Haeb-Umbach, Reinhold}, editor={Haeb-Umbach, Reinhold
    and Kolossa, DorotheaEditors}, year={2011} }'
  chicago: Haeb-Umbach, Reinhold. “Uncertainty Decoding and Conditional Bayesian Estimation.”
    In <i>Robust Speech Recognition of Uncertain or Missing Data</i>, edited by Reinhold
    Haeb-Umbach and Dorothea Kolossa. Springer, 2011.
  ieee: R. Haeb-Umbach, “Uncertainty Decoding and Conditional Bayesian Estimation,”
    in <i>Robust Speech Recognition of Uncertain or Missing Data</i>, R. Haeb-Umbach
    and D. Kolossa, Eds. Springer, 2011.
  mla: Haeb-Umbach, Reinhold. “Uncertainty Decoding and Conditional Bayesian Estimation.”
    <i>Robust Speech Recognition of Uncertain or Missing Data</i>, edited by Reinhold
    Haeb-Umbach and Dorothea Kolossa, Springer, 2011.
  short: 'R. Haeb-Umbach, in: R. Haeb-Umbach, D. Kolossa (Eds.), Robust Speech Recognition
    of Uncertain or Missing Data, Springer, 2011.'
date_created: 2019-07-12T05:28:00Z
date_updated: 2022-01-06T06:51:08Z
department:
- _id: '54'
editor:
- first_name: Reinhold
  full_name: Haeb-Umbach, Reinhold
  last_name: Haeb-Umbach
- first_name: Dorothea
  full_name: Kolossa, Dorothea
  last_name: Kolossa
language:
- iso: eng
publication: Robust Speech Recognition of Uncertain or Missing Data
publisher: Springer
status: public
title: Uncertainty Decoding and Conditional Bayesian Estimation
type: book_chapter
user_id: '44006'
year: '2011'
...
---
_id: '11775'
author:
- first_name: Reinhold
  full_name: Haeb-Umbach, Reinhold
  id: '242'
  last_name: Haeb-Umbach
citation:
  ama: 'Haeb-Umbach R. Können Computer sprechen und hören, sollen sie es überhaupt
    können? Sprachverarbeitung und ambiente Intelligenz. In: <i>Baustelle Informationsgesellschaft
    Und Universität Heute</i>. Ferdinand Schoeningh Verlag, Paderborn; 2011.'
  apa: Haeb-Umbach, R. (2011). Können Computer sprechen und hören, sollen sie es überhaupt
    können? Sprachverarbeitung und ambiente Intelligenz. In <i>Baustelle Informationsgesellschaft
    und Universität heute</i>. Ferdinand Schoeningh Verlag, Paderborn.
  bibtex: '@inbook{Haeb-Umbach_2011, title={Können Computer sprechen und hören, sollen
    sie es überhaupt können? Sprachverarbeitung und ambiente Intelligenz}, booktitle={Baustelle
    Informationsgesellschaft und Universität heute}, publisher={Ferdinand Schoeningh
    Verlag, Paderborn}, author={Haeb-Umbach, Reinhold}, year={2011} }'
  chicago: Haeb-Umbach, Reinhold. “Können Computer Sprechen Und Hören, Sollen Sie
    Es Überhaupt Können? Sprachverarbeitung Und Ambiente Intelligenz.” In <i>Baustelle
    Informationsgesellschaft Und Universität Heute</i>. Ferdinand Schoeningh Verlag,
    Paderborn, 2011.
  ieee: R. Haeb-Umbach, “Können Computer sprechen und hören, sollen sie es überhaupt
    können? Sprachverarbeitung und ambiente Intelligenz,” in <i>Baustelle Informationsgesellschaft
    und Universität heute</i>, Ferdinand Schoeningh Verlag, Paderborn, 2011.
  mla: Haeb-Umbach, Reinhold. “Können Computer Sprechen Und Hören, Sollen Sie Es Überhaupt
    Können? Sprachverarbeitung Und Ambiente Intelligenz.” <i>Baustelle Informationsgesellschaft
    Und Universität Heute</i>, Ferdinand Schoeningh Verlag, Paderborn, 2011.
  short: 'R. Haeb-Umbach, in: Baustelle Informationsgesellschaft Und Universität Heute,
    Ferdinand Schoeningh Verlag, Paderborn, 2011.'
date_created: 2019-07-12T05:28:01Z
date_updated: 2022-01-06T06:51:08Z
department:
- _id: '54'
language:
- iso: eng
publication: Baustelle Informationsgesellschaft und Universität heute
publisher: Ferdinand Schoeningh Verlag, Paderborn
status: public
title: Können Computer sprechen und hören, sollen sie es überhaupt können? Sprachverarbeitung
  und ambiente Intelligenz
type: book_chapter
user_id: '44006'
year: '2011'
...
---
_id: '11807'
author:
- first_name: Tobias
  full_name: Herbig, Tobias
  last_name: Herbig
- first_name: Franz
  full_name: Gerl, Franz
  last_name: Gerl
- first_name: Wolfgang
  full_name: Minker, Wolfgang
  last_name: Minker
- first_name: Reinhold
  full_name: Haeb-Umbach, Reinhold
  id: '242'
  last_name: Haeb-Umbach
citation:
  ama: Herbig T, Gerl F, Minker W, Haeb-Umbach R. Adaptive Systems for Unsupervised
    Speaker Tracking and Speech Recognition. <i>Evolving Systems</i>. 2011;2(3):199-214.
  apa: Herbig, T., Gerl, F., Minker, W., &#38; Haeb-Umbach, R. (2011). Adaptive Systems
    for Unsupervised Speaker Tracking and Speech Recognition. <i>Evolving Systems</i>,
    <i>2</i>(3), 199–214.
  bibtex: '@article{Herbig_Gerl_Minker_Haeb-Umbach_2011, title={Adaptive Systems for
    Unsupervised Speaker Tracking and Speech Recognition}, volume={2}, number={3},
    journal={Evolving Systems}, author={Herbig, Tobias and Gerl, Franz and Minker,
    Wolfgang and Haeb-Umbach, Reinhold}, year={2011}, pages={199–214} }'
  chicago: 'Herbig, Tobias, Franz Gerl, Wolfgang Minker, and Reinhold Haeb-Umbach.
    “Adaptive Systems for Unsupervised Speaker Tracking and Speech Recognition.” <i>Evolving
    Systems</i> 2, no. 3 (2011): 199–214.'
  ieee: T. Herbig, F. Gerl, W. Minker, and R. Haeb-Umbach, “Adaptive Systems for Unsupervised
    Speaker Tracking and Speech Recognition,” <i>Evolving Systems</i>, vol. 2, no.
    3, pp. 199–214, 2011.
  mla: Herbig, Tobias, et al. “Adaptive Systems for Unsupervised Speaker Tracking
    and Speech Recognition.” <i>Evolving Systems</i>, vol. 2, no. 3, 2011, pp. 199–214.
  short: T. Herbig, F. Gerl, W. Minker, R. Haeb-Umbach, Evolving Systems 2 (2011)
    199–214.
date_created: 2019-07-12T05:28:38Z
date_updated: 2022-01-06T06:51:09Z
department:
- _id: '54'
intvolume: '         2'
issue: '3'
language:
- iso: eng
page: 199-214
publication: Evolving Systems
status: public
title: Adaptive Systems for Unsupervised Speaker Tracking and Speech Recognition
type: journal_article
user_id: '44006'
volume: 2
year: '2011'
...
---
_id: '11843'
abstract:
- lang: eng
  text: Employing automatic speech recognition systems in hands-free communication
    applications is accompanied by perfomance degradation due to background noise
    and, in particular, due to reverberation. These two kinds of distortion alter
    the shape of the feature vector trajectory extracted from the microphone signal
    and consequently lead to a discrepancy between training and testing conditions
    for the recognizer. In this chapter we present a feature enhancement approach
    aiming at the joint compensation of noise and reverberation to improve the performance
    by restoring the training conditions. For the enhancement we concentrate on the
    logarithmic mel power spectral coefficients as features, which are computed at
    an intermediate stage to obtain the widely used mel frequency cepstral coefficients.
    The proposed technique is based on a Bayesian framework, to attempt to infer the
    posterior distribution of the clean features given the observation of all past
    corrupted features. It exploits information from a priori models describing the
    dynamics of clean speech and noise-only feature vector trajectories as well as
    from an observation model relating the reverberant noisy to the clean features.
    The observation model relies on a simplified stochastic model of the room impulse
    response (RIR) between the speaker and the microphone, having only two parameters,
    namely RIR energy and reverberation time, which can be estimated from the captured
    microphone signal. The performance of the proposed enhancement technique is finally
    experimentally studied by means of recognition accuracy obtained for a connected
    digits recognition task under different noise and reverberation conditions using
    the Aurora~5 database.
author:
- first_name: Alexander
  full_name: Krueger, Alexander
  last_name: Krueger
- first_name: Reinhold
  full_name: Haeb-Umbach, Reinhold
  id: '242'
  last_name: Haeb-Umbach
citation:
  ama: 'Krueger A, Haeb-Umbach R. A Model-Based Approach to Joint Compensation of
    Noise and Reverberation for Speech Recognition. In: Haeb-Umbach R, Kolossa D,
    eds. <i>Robust Speech Recognition of Uncertain or Missing Data</i>. Springer;
    2011.'
  apa: Krueger, A., &#38; Haeb-Umbach, R. (2011). A Model-Based Approach to Joint
    Compensation of Noise and Reverberation for Speech Recognition. In R. Haeb-Umbach
    &#38; D. Kolossa (Eds.), <i>Robust Speech Recognition of Uncertain or Missing
    Data</i>. Springer.
  bibtex: '@inbook{Krueger_Haeb-Umbach_2011, title={A Model-Based Approach to Joint
    Compensation of Noise and Reverberation for Speech Recognition}, booktitle={Robust
    Speech Recognition of Uncertain or Missing Data}, publisher={Springer}, author={Krueger,
    Alexander and Haeb-Umbach, Reinhold}, editor={Haeb-Umbach, Reinhold and Kolossa,
    DorotheaEditors}, year={2011} }'
  chicago: Krueger, Alexander, and Reinhold Haeb-Umbach. “A Model-Based Approach to
    Joint Compensation of Noise and Reverberation for Speech Recognition.” In <i>Robust
    Speech Recognition of Uncertain or Missing Data</i>, edited by Reinhold Haeb-Umbach
    and Dorothea Kolossa. Springer, 2011.
  ieee: A. Krueger and R. Haeb-Umbach, “A Model-Based Approach to Joint Compensation
    of Noise and Reverberation for Speech Recognition,” in <i>Robust Speech Recognition
    of Uncertain or Missing Data</i>, R. Haeb-Umbach and D. Kolossa, Eds. Springer,
    2011.
  mla: Krueger, Alexander, and Reinhold Haeb-Umbach. “A Model-Based Approach to Joint
    Compensation of Noise and Reverberation for Speech Recognition.” <i>Robust Speech
    Recognition of Uncertain or Missing Data</i>, edited by Reinhold Haeb-Umbach and
    Dorothea Kolossa, Springer, 2011.
  short: 'A. Krueger, R. Haeb-Umbach, in: R. Haeb-Umbach, D. Kolossa (Eds.), Robust
    Speech Recognition of Uncertain or Missing Data, Springer, 2011.'
date_created: 2019-07-12T05:29:20Z
date_updated: 2022-01-06T06:51:11Z
department:
- _id: '54'
editor:
- first_name: Reinhold
  full_name: Haeb-Umbach, Reinhold
  last_name: Haeb-Umbach
- first_name: Dorothea
  full_name: Kolossa, Dorothea
  last_name: Kolossa
language:
- iso: eng
publication: Robust Speech Recognition of Uncertain or Missing Data
publisher: Springer
status: public
title: A Model-Based Approach to Joint Compensation of Noise and Reverberation for
  Speech Recognition
type: book_chapter
user_id: '44006'
year: '2011'
...
---
_id: '11845'
abstract:
- lang: eng
  text: The paper proposes a modification of the standard maximum a posteriori (MAP)
    method for the estimation of the parameters of a Gaussian process for cases where
    the process is superposed by additive Gaussian observation errors of known variance.
    Simulations on artificially generated data demonstrate the superiority of the
    proposed method. While reducing to the ordinary MAP approach in the absence of
    observation noise, the improvement becomes the more pronounced the larger the
    variance of the observation noise. The method is further extended to track the
    parameters in case of non-stationary Gaussian processes.
author:
- first_name: Alexander
  full_name: Krueger, Alexander
  last_name: Krueger
- first_name: Reinhold
  full_name: Haeb-Umbach, Reinhold
  id: '242'
  last_name: Haeb-Umbach
citation:
  ama: 'Krueger A, Haeb-Umbach R. MAP-based estimation of the parameters of non-stationary
    Gaussian processes from noisy observations. In: <i>IEEE International Conference
    on Acoustics, Speech and Signal Processing (ICASSP 2011)</i>. ; 2011:3596-3599.
    doi:<a href="https://doi.org/10.1109/ICASSP.2011.5946256">10.1109/ICASSP.2011.5946256</a>'
  apa: Krueger, A., &#38; Haeb-Umbach, R. (2011). MAP-based estimation of the parameters
    of non-stationary Gaussian processes from noisy observations. In <i>IEEE International
    Conference on Acoustics, Speech and Signal Processing (ICASSP 2011)</i> (pp. 3596–3599).
    <a href="https://doi.org/10.1109/ICASSP.2011.5946256">https://doi.org/10.1109/ICASSP.2011.5946256</a>
  bibtex: '@inproceedings{Krueger_Haeb-Umbach_2011, title={MAP-based estimation of
    the parameters of non-stationary Gaussian processes from noisy observations},
    DOI={<a href="https://doi.org/10.1109/ICASSP.2011.5946256">10.1109/ICASSP.2011.5946256</a>},
    booktitle={IEEE International Conference on Acoustics, Speech and Signal Processing
    (ICASSP 2011)}, author={Krueger, Alexander and Haeb-Umbach, Reinhold}, year={2011},
    pages={3596–3599} }'
  chicago: Krueger, Alexander, and Reinhold Haeb-Umbach. “MAP-Based Estimation of
    the Parameters of Non-Stationary Gaussian Processes from Noisy Observations.”
    In <i>IEEE International Conference on Acoustics, Speech and Signal Processing
    (ICASSP 2011)</i>, 3596–99, 2011. <a href="https://doi.org/10.1109/ICASSP.2011.5946256">https://doi.org/10.1109/ICASSP.2011.5946256</a>.
  ieee: A. Krueger and R. Haeb-Umbach, “MAP-based estimation of the parameters of
    non-stationary Gaussian processes from noisy observations,” in <i>IEEE International
    Conference on Acoustics, Speech and Signal Processing (ICASSP 2011)</i>, 2011,
    pp. 3596–3599.
  mla: Krueger, Alexander, and Reinhold Haeb-Umbach. “MAP-Based Estimation of the
    Parameters of Non-Stationary Gaussian Processes from Noisy Observations.” <i>IEEE
    International Conference on Acoustics, Speech and Signal Processing (ICASSP 2011)</i>,
    2011, pp. 3596–99, doi:<a href="https://doi.org/10.1109/ICASSP.2011.5946256">10.1109/ICASSP.2011.5946256</a>.
  short: 'A. Krueger, R. Haeb-Umbach, in: IEEE International Conference on Acoustics,
    Speech and Signal Processing (ICASSP 2011), 2011, pp. 3596–3599.'
date_created: 2019-07-12T05:29:22Z
date_updated: 2022-01-06T06:51:11Z
department:
- _id: '54'
doi: 10.1109/ICASSP.2011.5946256
keyword:
- Gaussian processes
- MAP-based estimation
- maximum a posteriori method
- maximum likelihood estimation
- nonstationary Gaussian processes
language:
- iso: eng
main_file_link:
- open_access: '1'
  url: https://groups.uni-paderborn.de/nt/pubs/2011/KrHa11.pdf
oa: '1'
page: 3596-3599
publication: IEEE International Conference on Acoustics, Speech and Signal Processing
  (ICASSP 2011)
status: public
title: MAP-based estimation of the parameters of non-stationary Gaussian processes
  from noisy observations
type: conference
user_id: '44006'
year: '2011'
...
---
_id: '11850'
abstract:
- lang: eng
  text: In this paper, we present a novel blocking matrix and fixed beamformer design
    for a generalized sidelobe canceler for speech enhancement in a reverberant enclosure.
    They are based on a new method for estimating the acoustical transfer function
    ratios in the presence of stationary noise. The estimation method relies on solving
    a generalized eigenvalue problem in each frequency bin. An adaptive eigenvector
    tracking utilizing the power iteration method is employed and shown to achieve
    a high convergence speed. Simulation results demonstrate that the proposed beamformer
    leads to better noise and interference reduction and reduced speech distortions
    compared to other blocking matrix designs from the literature.
author:
- first_name: Alexander
  full_name: Krueger, Alexander
  last_name: Krueger
- first_name: Ernst
  full_name: Warsitz, Ernst
  last_name: Warsitz
- first_name: Reinhold
  full_name: Haeb-Umbach, Reinhold
  id: '242'
  last_name: Haeb-Umbach
citation:
  ama: Krueger A, Warsitz E, Haeb-Umbach R. Speech Enhancement With a GSC-Like Structure
    Employing Eigenvector-Based Transfer Function Ratios Estimation. <i>IEEE Transactions
    on Audio, Speech, and Language Processing</i>. 2011;19(1):206-219. doi:<a href="https://doi.org/10.1109/TASL.2010.2047324">10.1109/TASL.2010.2047324</a>
  apa: Krueger, A., Warsitz, E., &#38; Haeb-Umbach, R. (2011). Speech Enhancement
    With a GSC-Like Structure Employing Eigenvector-Based Transfer Function Ratios
    Estimation. <i>IEEE Transactions on Audio, Speech, and Language Processing</i>,
    <i>19</i>(1), 206–219. <a href="https://doi.org/10.1109/TASL.2010.2047324">https://doi.org/10.1109/TASL.2010.2047324</a>
  bibtex: '@article{Krueger_Warsitz_Haeb-Umbach_2011, title={Speech Enhancement With
    a GSC-Like Structure Employing Eigenvector-Based Transfer Function Ratios Estimation},
    volume={19}, DOI={<a href="https://doi.org/10.1109/TASL.2010.2047324">10.1109/TASL.2010.2047324</a>},
    number={1}, journal={IEEE Transactions on Audio, Speech, and Language Processing},
    author={Krueger, Alexander and Warsitz, Ernst and Haeb-Umbach, Reinhold}, year={2011},
    pages={206–219} }'
  chicago: 'Krueger, Alexander, Ernst Warsitz, and Reinhold Haeb-Umbach. “Speech Enhancement
    With a GSC-Like Structure Employing Eigenvector-Based Transfer Function Ratios
    Estimation.” <i>IEEE Transactions on Audio, Speech, and Language Processing</i>
    19, no. 1 (2011): 206–19. <a href="https://doi.org/10.1109/TASL.2010.2047324">https://doi.org/10.1109/TASL.2010.2047324</a>.'
  ieee: A. Krueger, E. Warsitz, and R. Haeb-Umbach, “Speech Enhancement With a GSC-Like
    Structure Employing Eigenvector-Based Transfer Function Ratios Estimation,” <i>IEEE
    Transactions on Audio, Speech, and Language Processing</i>, vol. 19, no. 1, pp.
    206–219, 2011.
  mla: Krueger, Alexander, et al. “Speech Enhancement With a GSC-Like Structure Employing
    Eigenvector-Based Transfer Function Ratios Estimation.” <i>IEEE Transactions on
    Audio, Speech, and Language Processing</i>, vol. 19, no. 1, 2011, pp. 206–19,
    doi:<a href="https://doi.org/10.1109/TASL.2010.2047324">10.1109/TASL.2010.2047324</a>.
  short: A. Krueger, E. Warsitz, R. Haeb-Umbach, IEEE Transactions on Audio, Speech,
    and Language Processing 19 (2011) 206–219.
date_created: 2019-07-12T05:29:28Z
date_updated: 2022-01-06T06:51:11Z
department:
- _id: '54'
doi: 10.1109/TASL.2010.2047324
intvolume: '        19'
issue: '1'
keyword:
- acoustical transfer function ratio
- adaptive eigenvector tracking
- array signal processing
- beamformer design
- blocking matrix
- eigenvalues and eigenfunctions
- eigenvector-based transfer function ratios estimation
- generalized sidelobe canceler
- interference reduction
- iterative methods
- power iteration method
- reduced speech distortions
- reverberant enclosure
- reverberation
- speech enhancement
- stationary noise
language:
- iso: eng
main_file_link:
- open_access: '1'
  url: https://groups.uni-paderborn.de/nt/pubs/2011/KrWaHa11.pdf
oa: '1'
page: 206-219
publication: IEEE Transactions on Audio, Speech, and Language Processing
status: public
title: Speech Enhancement With a GSC-Like Structure Employing Eigenvector-Based Transfer
  Function Ratios Estimation
type: journal_article
user_id: '44006'
volume: 19
year: '2011'
...
---
_id: '11856'
abstract:
- lang: eng
  text: 'In this contribution, conditional Bayesian estimation employing a phase-sensitive
    observation model for noise robust speech recognition will be studied. After a
    review of speech recognition under the presence of corrupted features, termed
    uncertainty decoding, the estimation of the posterior distribution of the uncorrupted
    (clean) feature vector will be shown to be a key element of noise robust speech
    recognition. The estimation process will be based on three major components: an
    a priori model of the unobservable data, an observation model relating the unobservable
    data to the corrupted observation and an inference algorithm, finally allowing
    for a computationally tractable solution. Special stress will be laid on a detailed
    derivation of the phase-sensitive observation model and the required moments of
    the phase factor distribution. Thereby, it will not only be proven analytically
    that the phase factor distribution is non-Gaussian but also that all central moments
    can (approximately) be computed solely based on the used mel filter bank, finally
    rendering the moments independent of noise type and signal-to-noise ratio. The
    phase-sensitive observation model will then be incorporated into a model-based
    feature enhancement scheme and recognition experiments will be carried out on
    the Aurora~2 and Aurora~4 databases. The importance of incorporating phase factor
    information into the enhancement scheme is pointed out by all recognition results.
    Application of the proposed scheme under the derived uncertainty decoding framework
    further leads to significant improvements in both recognition tasks, eventually
    reaching the performance achieved with the ETSI advanced front-end.'
author:
- first_name: Volker
  full_name: Leutnant, Volker
  last_name: Leutnant
- first_name: Reinhold
  full_name: Haeb-Umbach, Reinhold
  id: '242'
  last_name: Haeb-Umbach
citation:
  ama: 'Leutnant V, Haeb-Umbach R. Conditional Bayesian Estimation Employing a Phase-Sensitive
    Observation Model for Noise Robust Speech Recognition. In: Haeb-Umbach R, Kolossa
    D, eds. <i>Robust Speech Recognition of Uncertain or Missing Data</i>. Springer;
    2011.'
  apa: Leutnant, V., &#38; Haeb-Umbach, R. (2011). Conditional Bayesian Estimation
    Employing a Phase-Sensitive Observation Model for Noise Robust Speech Recognition.
    In R. Haeb-Umbach &#38; D. Kolossa (Eds.), <i>Robust Speech Recognition of Uncertain
    or Missing Data</i>. Springer.
  bibtex: '@inbook{Leutnant_Haeb-Umbach_2011, title={Conditional Bayesian Estimation
    Employing a Phase-Sensitive Observation Model for Noise Robust Speech Recognition},
    booktitle={Robust Speech Recognition of Uncertain or Missing Data}, publisher={Springer},
    author={Leutnant, Volker and Haeb-Umbach, Reinhold}, editor={Haeb-Umbach, Reinhold
    and Kolossa, DorotheaEditors}, year={2011} }'
  chicago: Leutnant, Volker, and Reinhold Haeb-Umbach. “Conditional Bayesian Estimation
    Employing a Phase-Sensitive Observation Model for Noise Robust Speech Recognition.”
    In <i>Robust Speech Recognition of Uncertain or Missing Data</i>, edited by Reinhold
    Haeb-Umbach and Dorothea Kolossa. Springer, 2011.
  ieee: V. Leutnant and R. Haeb-Umbach, “Conditional Bayesian Estimation Employing
    a Phase-Sensitive Observation Model for Noise Robust Speech Recognition,” in <i>Robust
    Speech Recognition of Uncertain or Missing Data</i>, R. Haeb-Umbach and D. Kolossa,
    Eds. Springer, 2011.
  mla: Leutnant, Volker, and Reinhold Haeb-Umbach. “Conditional Bayesian Estimation
    Employing a Phase-Sensitive Observation Model for Noise Robust Speech Recognition.”
    <i>Robust Speech Recognition of Uncertain or Missing Data</i>, edited by Reinhold
    Haeb-Umbach and Dorothea Kolossa, Springer, 2011.
  short: 'V. Leutnant, R. Haeb-Umbach, in: R. Haeb-Umbach, D. Kolossa (Eds.), Robust
    Speech Recognition of Uncertain or Missing Data, Springer, 2011.'
date_created: 2019-07-12T05:29:35Z
date_updated: 2022-01-06T06:51:11Z
department:
- _id: '54'
editor:
- first_name: Reinhold
  full_name: Haeb-Umbach, Reinhold
  last_name: Haeb-Umbach
- first_name: Dorothea
  full_name: Kolossa, Dorothea
  last_name: Kolossa
language:
- iso: eng
publication: Robust Speech Recognition of Uncertain or Missing Data
publisher: Springer
status: public
title: Conditional Bayesian Estimation Employing a Phase-Sensitive Observation Model
  for Noise Robust Speech Recognition
type: book_chapter
user_id: '44006'
year: '2011'
...
---
_id: '11866'
abstract:
- lang: eng
  text: In this work, a splitting and weighting scheme that allows for splitting a
    Gaussian density into a Gaussian mixture density (GMM) is extended to allow the
    mixture components to be arranged along arbitrary directions. The parameters of
    the Gaussian mixture are chosen such that the GMM and the original Gaussian still
    exhibit equal central moments up to an order of four. The resulting mixtures{\rq}
    covariances will have eigenvalues that are smaller than those of the covariance
    of the original distribution, which is a desirable property in the context of
    non-linear state estimation, since the underlying assumptions of the extended
    K ALMAN filter are better justified in this case. Application to speech feature
    enhancement in the context of noise-robust automatic speech recognition reveals
    the beneficial properties of the proposed approach in terms of a reduced word
    error rate on the Aurora 2 recognition task.
author:
- first_name: Volker
  full_name: Leutnant, Volker
  last_name: Leutnant
- first_name: Alexander
  full_name: Krueger, Alexander
  last_name: Krueger
- first_name: Reinhold
  full_name: Haeb-Umbach, Reinhold
  id: '242'
  last_name: Haeb-Umbach
citation:
  ama: 'Leutnant V, Krueger A, Haeb-Umbach R. A versatile Gaussian splitting approach
    to non-linear state estimation and its application to noise-robust ASR. In: <i>Interspeech
    2011</i>. ; 2011.'
  apa: Leutnant, V., Krueger, A., &#38; Haeb-Umbach, R. (2011). A versatile Gaussian
    splitting approach to non-linear state estimation and its application to noise-robust
    ASR. In <i>Interspeech 2011</i>.
  bibtex: '@inproceedings{Leutnant_Krueger_Haeb-Umbach_2011, title={A versatile Gaussian
    splitting approach to non-linear state estimation and its application to noise-robust
    ASR}, booktitle={Interspeech 2011}, author={Leutnant, Volker and Krueger, Alexander
    and Haeb-Umbach, Reinhold}, year={2011} }'
  chicago: Leutnant, Volker, Alexander Krueger, and Reinhold Haeb-Umbach. “A Versatile
    Gaussian Splitting Approach to Non-Linear State Estimation and Its Application
    to Noise-Robust ASR.” In <i>Interspeech 2011</i>, 2011.
  ieee: V. Leutnant, A. Krueger, and R. Haeb-Umbach, “A versatile Gaussian splitting
    approach to non-linear state estimation and its application to noise-robust ASR,”
    in <i>Interspeech 2011</i>, 2011.
  mla: Leutnant, Volker, et al. “A Versatile Gaussian Splitting Approach to Non-Linear
    State Estimation and Its Application to Noise-Robust ASR.” <i>Interspeech 2011</i>,
    2011.
  short: 'V. Leutnant, A. Krueger, R. Haeb-Umbach, in: Interspeech 2011, 2011.'
date_created: 2019-07-12T05:29:46Z
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/2011/LeKrHa11.pdf
oa: '1'
publication: Interspeech 2011
status: public
title: A versatile Gaussian splitting approach to non-linear state estimation and
  its application to noise-robust ASR
type: conference
user_id: '44006'
year: '2011'
...
---
_id: '11911'
abstract:
- lang: eng
  text: In this paper we address the problem of initial seed selection for frequency
    domain iterative blind speech separation (BSS) algorithms. The derivation of the
    seeding algorithm is guided by the goal to select samples which are likely to
    be caused by source activity and not by noise and at the same time originate from
    different sources. The proposed algorithm has moderate computational complexity
    and finds better seed values than alternative schemes, as is demonstrated by experiments
    on the database of the SiSEC2010 challenge.
author:
- 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: 'Tran Vu DH, Haeb-Umbach R. On Initial Seed Selection for Frequency Domain
    Blind Speech Separation. In: <i>Interspeech 2011</i>. ; 2011.'
  apa: Tran Vu, D. H., &#38; Haeb-Umbach, R. (2011). On Initial Seed Selection for
    Frequency Domain Blind Speech Separation. In <i>Interspeech 2011</i>.
  bibtex: '@inproceedings{Tran Vu_Haeb-Umbach_2011, title={On Initial Seed Selection
    for Frequency Domain Blind Speech Separation}, booktitle={Interspeech 2011}, author={Tran
    Vu, Dang Hai and Haeb-Umbach, Reinhold}, year={2011} }'
  chicago: Tran Vu, Dang Hai, and Reinhold Haeb-Umbach. “On Initial Seed Selection
    for Frequency Domain Blind Speech Separation.” In <i>Interspeech 2011</i>, 2011.
  ieee: D. H. Tran Vu and R. Haeb-Umbach, “On Initial Seed Selection for Frequency
    Domain Blind Speech Separation,” in <i>Interspeech 2011</i>, 2011.
  mla: Tran Vu, Dang Hai, and Reinhold Haeb-Umbach. “On Initial Seed Selection for
    Frequency Domain Blind Speech Separation.” <i>Interspeech 2011</i>, 2011.
  short: 'D.H. Tran Vu, R. Haeb-Umbach, in: Interspeech 2011, 2011.'
date_created: 2019-07-12T05:30:38Z
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/2011/TrHa11.pdf
oa: '1'
publication: Interspeech 2011
status: public
title: On Initial Seed Selection for Frequency Domain Blind Speech Separation
type: conference
user_id: '44006'
year: '2011'
...
---
_id: '11945'
citation:
  ama: Kolossa D, Haeb-Umbach R, eds. <i>Robust Speech Recognition of Uncertain or
    Missing Data --- Theory and Applications</i>. Springer; 2011.
  apa: Kolossa, D., &#38; Haeb-Umbach, R. (Eds.). (2011). <i>Robust Speech Recognition
    of Uncertain or Missing Data --- Theory and Applications</i>. Springer.
  bibtex: '@book{Kolossa_Haeb-Umbach_2011, title={Robust Speech Recognition of Uncertain
    or Missing Data --- Theory and Applications}, publisher={Springer}, year={2011}
    }'
  chicago: Kolossa, Dorothea, and Reinhold Haeb-Umbach, eds. <i>Robust Speech Recognition
    of Uncertain or Missing Data --- Theory and Applications</i>. Springer, 2011.
  ieee: D. Kolossa and R. Haeb-Umbach, Eds., <i>Robust Speech Recognition of Uncertain
    or Missing Data --- Theory and Applications</i>. Springer, 2011.
  mla: Kolossa, Dorothea, and Reinhold Haeb-Umbach, editors. <i>Robust Speech Recognition
    of Uncertain or Missing Data --- Theory and Applications</i>. Springer, 2011.
  short: D. Kolossa, R. Haeb-Umbach, eds., Robust Speech Recognition of Uncertain
    or Missing Data --- Theory and Applications, Springer, 2011.
date_created: 2019-07-12T05:31:17Z
date_updated: 2022-01-06T06:51:12Z
department:
- _id: '54'
editor:
- first_name: Dorothea
  full_name: Kolossa, Dorothea
  last_name: Kolossa
- first_name: Reinhold
  full_name: Haeb-Umbach, Reinhold
  id: '242'
  last_name: Haeb-Umbach
language:
- iso: eng
main_file_link:
- open_access: '1'
  url: http://www.springer.com/engineering/signals/book/978-3-642-21316-8?detailsPage=authorsAndEditors
oa: '1'
publisher: Springer
status: public
title: Robust Speech Recognition of Uncertain or Missing Data --- Theory and Applications
type: book_editor
user_id: '44006'
year: '2011'
...
---
_id: '11889'
abstract:
- lang: eng
  text: In this paper we propose to jointly consider Segmental Dynamic Time Warping
    and distance clustering for the unsupervised learning of acoustic events. As a
    result, the computational complexity increases only linearly with the dababase
    size compared to a quadratic increase in a sequential setup, where all pairwise
    SDTW distances between segments are computed prior to clustering. Further, we
    discuss options for seed value selection for clustering and show that drawing
    seeds with a probability proportional to the distance from the already drawn seeds,
    known as K-means++ clustering, results in a significantly higher probability of
    finding representatives of each of the underlying classes, compared to the commonly
    used draws from a uniform distribution. Experiments are performed on an acoustic
    event classification and an isolated digit recognition task, where on the latter
    the final word accuracy approaches that of supervised training.
author:
- first_name: Joerg
  full_name: Schmalenstroeer, Joerg
  id: '460'
  last_name: Schmalenstroeer
- first_name: Markus
  full_name: Bartek, Markus
  last_name: Bartek
- first_name: Reinhold
  full_name: Haeb-Umbach, Reinhold
  id: '242'
  last_name: Haeb-Umbach
citation:
  ama: 'Schmalenstroeer J, Bartek M, Haeb-Umbach R. Unsupervised learning of acoustic
    events using dynamic time warping and hierarchical K-means++ clustering. In: <i>Interspeech
    2011</i>. ; 2011.'
  apa: Schmalenstroeer, J., Bartek, M., &#38; Haeb-Umbach, R. (2011). Unsupervised
    learning of acoustic events using dynamic time warping and hierarchical K-means++
    clustering. <i>Interspeech 2011</i>.
  bibtex: '@inproceedings{Schmalenstroeer_Bartek_Haeb-Umbach_2011, title={Unsupervised
    learning of acoustic events using dynamic time warping and hierarchical K-means++
    clustering}, booktitle={Interspeech 2011}, author={Schmalenstroeer, Joerg and
    Bartek, Markus and Haeb-Umbach, Reinhold}, year={2011} }'
  chicago: Schmalenstroeer, Joerg, Markus Bartek, and Reinhold Haeb-Umbach. “Unsupervised
    Learning of Acoustic Events Using Dynamic Time Warping and Hierarchical K-Means++
    Clustering.” In <i>Interspeech 2011</i>, 2011.
  ieee: J. Schmalenstroeer, M. Bartek, and R. Haeb-Umbach, “Unsupervised learning
    of acoustic events using dynamic time warping and hierarchical K-means++ clustering,”
    2011.
  mla: Schmalenstroeer, Joerg, et al. “Unsupervised Learning of Acoustic Events Using
    Dynamic Time Warping and Hierarchical K-Means++ Clustering.” <i>Interspeech 2011</i>,
    2011.
  short: 'J. Schmalenstroeer, M. Bartek, R. Haeb-Umbach, in: Interspeech 2011, 2011.'
date_created: 2019-07-12T05:30:13Z
date_updated: 2023-10-26T08:10:44Z
department:
- _id: '54'
language:
- iso: eng
main_file_link:
- open_access: '1'
  url: https://groups.uni-paderborn.de/nt/pubs/2011/ScBaHa11-2.pdf
oa: '1'
publication: Interspeech 2011
quality_controlled: '1'
status: public
title: Unsupervised learning of acoustic events using dynamic time warping and hierarchical
  K-means++ clustering
type: conference
user_id: '460'
year: '2011'
...
---
_id: '11896'
abstract:
- lang: eng
  text: In this paper we propose a procedure for estimating the geometric configuration
    of an arbitrary acoustic sensor placement. It determines the position and the
    orientation of microphone arrays in 2D while locating a source by direction-of-arrival
    (DoA) estimation. Neither artificial calibration signals nor unnatural user activity
    are required. The problem of scale indeterminacy inherent to DoA-only observations
    is solved by adding time difference of arrival (TDOA) measurements. The geometry
    calibration method is numerically stable and delivers precise results in moderately
    reverberated rooms. Simulation results are confirmed by laboratory experiments.
author:
- first_name: Joerg
  full_name: Schmalenstroeer, Joerg
  id: '460'
  last_name: Schmalenstroeer
- first_name: Florian
  full_name: Jacob, Florian
  last_name: Jacob
- first_name: Reinhold
  full_name: Haeb-Umbach, Reinhold
  id: '242'
  last_name: Haeb-Umbach
- first_name: Marius
  full_name: Hennecke, Marius
  last_name: Hennecke
- first_name: Gernot A.
  full_name: Fink, Gernot A.
  last_name: Fink
citation:
  ama: 'Schmalenstroeer J, Jacob F, Haeb-Umbach R, Hennecke M, Fink GA. Unsupervised
    Geometry Calibration of Acoustic Sensor Networks Using Source Correspondences.
    In: <i>Interspeech 2011</i>. ; 2011.'
  apa: Schmalenstroeer, J., Jacob, F., Haeb-Umbach, R., Hennecke, M., &#38; Fink,
    G. A. (2011). Unsupervised Geometry Calibration of Acoustic Sensor Networks Using
    Source Correspondences. <i>Interspeech 2011</i>.
  bibtex: '@inproceedings{Schmalenstroeer_Jacob_Haeb-Umbach_Hennecke_Fink_2011, title={Unsupervised
    Geometry Calibration of Acoustic Sensor Networks Using Source Correspondences},
    booktitle={Interspeech 2011}, author={Schmalenstroeer, Joerg and Jacob, Florian
    and Haeb-Umbach, Reinhold and Hennecke, Marius and Fink, Gernot A.}, year={2011}
    }'
  chicago: Schmalenstroeer, Joerg, Florian Jacob, Reinhold Haeb-Umbach, Marius Hennecke,
    and Gernot A. Fink. “Unsupervised Geometry Calibration of Acoustic Sensor Networks
    Using Source Correspondences.” In <i>Interspeech 2011</i>, 2011.
  ieee: J. Schmalenstroeer, F. Jacob, R. Haeb-Umbach, M. Hennecke, and G. A. Fink,
    “Unsupervised Geometry Calibration of Acoustic Sensor Networks Using Source Correspondences,”
    2011.
  mla: Schmalenstroeer, Joerg, et al. “Unsupervised Geometry Calibration of Acoustic
    Sensor Networks Using Source Correspondences.” <i>Interspeech 2011</i>, 2011.
  short: 'J. Schmalenstroeer, F. Jacob, R. Haeb-Umbach, M. Hennecke, G.A. Fink, in:
    Interspeech 2011, 2011.'
date_created: 2019-07-12T05:30:21Z
date_updated: 2023-10-26T08:10:28Z
department:
- _id: '54'
language:
- iso: eng
main_file_link:
- open_access: '1'
  url: https://groups.uni-paderborn.de/nt/pubs/2011/ScJaHaHeFi11.pdf
oa: '1'
publication: Interspeech 2011
quality_controlled: '1'
status: public
title: Unsupervised Geometry Calibration of Acoustic Sensor Networks Using Source
  Correspondences
type: conference
user_id: '460'
year: '2011'
...