---
_id: '11915'
abstract:
- lang: eng
text: This Paper deals with a new Technique for multi-channel separation of speech
signals from convolutive mixtures under coherent noise. We demonstrate how the
scaled transfer functions from the sources to the microphones can be estimated
even in the presence of stationary coherent noise. The key to this are generalized
eigenvalue decompositions of the power spectral density (PSD) matrices of the
noisy speech and noise-only microphone signals with a controlled estimation of
these matrices exploiting time-frequency sparseness of the speech sources. Separation
is further improved by subsequent Gram-Schmidt orthogonalization which places
spatial nulls at the interferers{\rq} directions, while noise reduction is improved
by employing a novel blocking matrix and adaptive interference canceller in a
Generalized Sidelobe Canceller (GSC)-like structure. We report promising experimental
results for 2 speech sources with significant coherent noise in reverberant environments
(RT60=0oms..500ms).
author:
- first_name: Dang Hai
full_name: Tran Vu, Dang Hai
last_name: Tran Vu
- 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: 'Tran Vu DH, Krueger A, Haeb-Umbach R. Generalized Eigenvector Blind Speech
Separation Under Coherent Noise In A GSC Configuration. In: International Workshop
on Acoustic Echo and Noise Control (IWAENC 2008). ; 2008.'
apa: Tran Vu, D. H., Krueger, A., & Haeb-Umbach, R. (2008). Generalized Eigenvector
Blind Speech Separation Under Coherent Noise In A GSC Configuration. In International
Workshop on Acoustic Echo and Noise Control (IWAENC 2008).
bibtex: '@inproceedings{Tran Vu_Krueger_Haeb-Umbach_2008, title={Generalized Eigenvector
Blind Speech Separation Under Coherent Noise In A GSC Configuration}, booktitle={International
Workshop on Acoustic Echo and Noise Control (IWAENC 2008)}, author={Tran Vu, Dang
Hai and Krueger, Alexander and Haeb-Umbach, Reinhold}, year={2008} }'
chicago: Tran Vu, Dang Hai, Alexander Krueger, and Reinhold Haeb-Umbach. “Generalized
Eigenvector Blind Speech Separation Under Coherent Noise In A GSC Configuration.”
In International Workshop on Acoustic Echo and Noise Control (IWAENC 2008),
2008.
ieee: D. H. Tran Vu, A. Krueger, and R. Haeb-Umbach, “Generalized Eigenvector Blind
Speech Separation Under Coherent Noise In A GSC Configuration,” in International
Workshop on Acoustic Echo and Noise Control (IWAENC 2008), 2008.
mla: Tran Vu, Dang Hai, et al. “Generalized Eigenvector Blind Speech Separation
Under Coherent Noise In A GSC Configuration.” International Workshop on Acoustic
Echo and Noise Control (IWAENC 2008), 2008.
short: 'D.H. Tran Vu, A. Krueger, R. Haeb-Umbach, in: International Workshop on
Acoustic Echo and Noise Control (IWAENC 2008), 2008.'
date_created: 2019-07-12T05:30:43Z
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/2008/DaKrHa08.pdf
oa: '1'
publication: International Workshop on Acoustic Echo and Noise Control (IWAENC 2008)
status: public
title: Generalized Eigenvector Blind Speech Separation Under Coherent Noise In A GSC
Configuration
type: conference
user_id: '44006'
year: '2008'
...
---
_id: '11935'
abstract:
- lang: eng
text: The generalized sidelobe canceller by Griffith and Jim is a robust beamforming
method to enhance a desired (speech) signal in the presence of stationary noise.
Its performance depends to a high degree on the construction of the blocking matrix
which produces noise reference signals for the subsequent adaptive interference
canceller. Especially in reverberated environments the beamformer may suffer from
signal leakage and reduced noise suppression. In this paper a new blocking matrix
is proposed. It is based on a generalized eigenvalue problem whose solution provides
an indirect estimation of the transfer functions from the source to the sensors.
The quality of the new generalized eigenvector blocking matrix is studied in simulated
rooms with different reverberation times and is compared to alternatives proposed
in the literature.
author:
- first_name: Ernst
full_name: Warsitz, Ernst
last_name: Warsitz
- 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: 'Warsitz E, Krueger A, Haeb-Umbach R. Speech enhancement with a new generalized
eigenvector blocking matrix for application in a generalized sidelobe canceller.
In: IEEE International Conference on Acoustics, Speech and Signal Processing
(ICASSP 2008). ; 2008:73-76. doi:10.1109/ICASSP.2008.4517549'
apa: Warsitz, E., Krueger, A., & Haeb-Umbach, R. (2008). Speech enhancement
with a new generalized eigenvector blocking matrix for application in a generalized
sidelobe canceller. In IEEE International Conference on Acoustics, Speech and
Signal Processing (ICASSP 2008) (pp. 73–76). https://doi.org/10.1109/ICASSP.2008.4517549
bibtex: '@inproceedings{Warsitz_Krueger_Haeb-Umbach_2008, title={Speech enhancement
with a new generalized eigenvector blocking matrix for application in a generalized
sidelobe canceller}, DOI={10.1109/ICASSP.2008.4517549},
booktitle={IEEE International Conference on Acoustics, Speech and Signal Processing
(ICASSP 2008)}, author={Warsitz, Ernst and Krueger, Alexander and Haeb-Umbach,
Reinhold}, year={2008}, pages={73–76} }'
chicago: Warsitz, Ernst, Alexander Krueger, and Reinhold Haeb-Umbach. “Speech Enhancement
with a New Generalized Eigenvector Blocking Matrix for Application in a Generalized
Sidelobe Canceller.” In IEEE International Conference on Acoustics, Speech
and Signal Processing (ICASSP 2008), 73–76, 2008. https://doi.org/10.1109/ICASSP.2008.4517549.
ieee: E. Warsitz, A. Krueger, and R. Haeb-Umbach, “Speech enhancement with a new
generalized eigenvector blocking matrix for application in a generalized sidelobe
canceller,” in IEEE International Conference on Acoustics, Speech and Signal
Processing (ICASSP 2008), 2008, pp. 73–76.
mla: Warsitz, Ernst, et al. “Speech Enhancement with a New Generalized Eigenvector
Blocking Matrix for Application in a Generalized Sidelobe Canceller.” IEEE
International Conference on Acoustics, Speech and Signal Processing (ICASSP 2008),
2008, pp. 73–76, doi:10.1109/ICASSP.2008.4517549.
short: 'E. Warsitz, A. Krueger, R. Haeb-Umbach, in: IEEE International Conference
on Acoustics, Speech and Signal Processing (ICASSP 2008), 2008, pp. 73–76.'
date_created: 2019-07-12T05:31:06Z
date_updated: 2022-01-06T06:51:12Z
department:
- _id: '54'
doi: 10.1109/ICASSP.2008.4517549
keyword:
- adaptive interference canceller
- adaptive signal processing
- array signal processing
- beamforming method
- eigenvalues and eigenfunctions
- generalized eigenvector blocking matrix
- generalized sidelobe canceller
- interference suppression
- matrix algebra
- noise suppression
- speech enhancement
- transfer function estimation
- transfer functions
language:
- iso: eng
main_file_link:
- open_access: '1'
url: https://groups.uni-paderborn.de/nt/pubs/2008/WaKrHa08.pdf
oa: '1'
page: 73-76
publication: IEEE International Conference on Acoustics, Speech and Signal Processing
(ICASSP 2008)
status: public
title: Speech enhancement with a new generalized eigenvector blocking matrix for application
in a generalized sidelobe canceller
type: conference
user_id: '44006'
year: '2008'
...
---
_id: '11939'
abstract:
- lang: eng
text: In this paper a switching linear dynamical model (SLDM) approach for speech
feature enhancement is improved by employing more accurate models for the dynamics
of speech and noise. The model of the clean speech feature trajectory is improved
by augmenting the state vector to capture information derived from the delta features.
Further a hidden noise state variable is introduced to obtain a more elaborated
model for the noise dynamics. Approximate Bayesian inference in the SLDM is carried
out by a bank of extended Kalman filters, whose outputs are combined according
to the a posteriori probability of the individual state models. Experimental results
on the AURORA2 database show improved recognition accuracy.
author:
- first_name: Stefan
full_name: Windmann, Stefan
last_name: Windmann
- first_name: Reinhold
full_name: Haeb-Umbach, Reinhold
id: '242'
last_name: Haeb-Umbach
citation:
ama: 'Windmann S, Haeb-Umbach R. Modeling the dynamics of speech and noise for speech
feature enhancement in ASR. In: IEEE International Conference on Acoustics,
Speech and Signal Processing (ICASSP 2008). ; 2008:4409-4412. doi:10.1109/ICASSP.2008.4518633'
apa: Windmann, S., & Haeb-Umbach, R. (2008). Modeling the dynamics of speech
and noise for speech feature enhancement in ASR. In IEEE International Conference
on Acoustics, Speech and Signal Processing (ICASSP 2008) (pp. 4409–4412).
https://doi.org/10.1109/ICASSP.2008.4518633
bibtex: '@inproceedings{Windmann_Haeb-Umbach_2008, title={Modeling the dynamics
of speech and noise for speech feature enhancement in ASR}, DOI={10.1109/ICASSP.2008.4518633},
booktitle={IEEE International Conference on Acoustics, Speech and Signal Processing
(ICASSP 2008)}, author={Windmann, Stefan and Haeb-Umbach, Reinhold}, year={2008},
pages={4409–4412} }'
chicago: Windmann, Stefan, and Reinhold Haeb-Umbach. “Modeling the Dynamics of Speech
and Noise for Speech Feature Enhancement in ASR.” In IEEE International Conference
on Acoustics, Speech and Signal Processing (ICASSP 2008), 4409–12, 2008. https://doi.org/10.1109/ICASSP.2008.4518633.
ieee: S. Windmann and R. Haeb-Umbach, “Modeling the dynamics of speech and noise
for speech feature enhancement in ASR,” in IEEE International Conference on
Acoustics, Speech and Signal Processing (ICASSP 2008), 2008, pp. 4409–4412.
mla: Windmann, Stefan, and Reinhold Haeb-Umbach. “Modeling the Dynamics of Speech
and Noise for Speech Feature Enhancement in ASR.” IEEE International Conference
on Acoustics, Speech and Signal Processing (ICASSP 2008), 2008, pp. 4409–12,
doi:10.1109/ICASSP.2008.4518633.
short: 'S. Windmann, R. Haeb-Umbach, in: IEEE International Conference on Acoustics,
Speech and Signal Processing (ICASSP 2008), 2008, pp. 4409–4412.'
date_created: 2019-07-12T05:31:11Z
date_updated: 2022-01-06T06:51:12Z
department:
- _id: '54'
doi: 10.1109/ICASSP.2008.4518633
keyword:
- a posteriori probability
- AURORA2 database
- Bayesian inference
- Bayes methods
- channel bank filters
- extended Kalman filter banks
- hidden noise state variable
- Kalman filters
- noise dynamics
- speech enhancement
- speech feature enhancement
- speech feature trajectory
- switching linear dynamical model approach
language:
- iso: eng
main_file_link:
- open_access: '1'
url: https://groups.uni-paderborn.de/nt/pubs/2008/WiHa08-1.pdf
oa: '1'
page: 4409-4412
publication: IEEE International Conference on Acoustics, Speech and Signal Processing
(ICASSP 2008)
status: public
title: Modeling the dynamics of speech and noise for speech feature enhancement in
ASR
type: conference
user_id: '44006'
year: '2008'
...
---
_id: '11940'
abstract:
- lang: eng
text: 'In this paper, the noise estimation for model-based speech feature enhancement
in automatic speech recognition (ASR) is investigated. Beside a stationary noise
prior, three linear state space models for the (cepstral) noise process are considered.
We have derived novel EM algorithms for the estimation of the noise model parameters:
A blockwise EM algorithm is applied on noise-only input data. It is supposed to
be used during the offline training mode of the recognizer. Further a sequential
online EM algorithm is employed to adapt the observation variance in recognition
mode which works as well under the asumption of a stationary noise prior and a
linear state model for the noise. Experiments on the AURORA4 database lead to
improved recognition results with the new state model compared to the assumption
of stationary noise.'
author:
- first_name: Stefan
full_name: Windmann, Stefan
last_name: Windmann
- first_name: Reinhold
full_name: Haeb-Umbach, Reinhold
id: '242'
last_name: Haeb-Umbach
citation:
ama: Windmann S, Haeb-Umbach R. A novel approach to noise estimation in model-based
speech feature enhancement. 2008 ITG Conference on Voice Communication (SprachKommunikation).
2008:1-4.
apa: Windmann, S., & Haeb-Umbach, R. (2008). A novel approach to noise estimation
in model-based speech feature enhancement. 2008 ITG Conference on Voice Communication
(SprachKommunikation), 1–4.
bibtex: '@article{Windmann_Haeb-Umbach_2008, title={A novel approach to noise estimation
in model-based speech feature enhancement}, journal={2008 ITG Conference on Voice
Communication (SprachKommunikation)}, author={Windmann, Stefan and Haeb-Umbach,
Reinhold}, year={2008}, pages={1–4} }'
chicago: Windmann, Stefan, and Reinhold Haeb-Umbach. “A Novel Approach to Noise
Estimation in Model-Based Speech Feature Enhancement.” 2008 ITG Conference
on Voice Communication (SprachKommunikation), 2008, 1–4.
ieee: S. Windmann and R. Haeb-Umbach, “A novel approach to noise estimation in model-based
speech feature enhancement,” 2008 ITG Conference on Voice Communication (SprachKommunikation),
pp. 1–4, 2008.
mla: Windmann, Stefan, and Reinhold Haeb-Umbach. “A Novel Approach to Noise Estimation
in Model-Based Speech Feature Enhancement.” 2008 ITG Conference on Voice Communication
(SprachKommunikation), 2008, pp. 1–4.
short: S. Windmann, R. Haeb-Umbach, 2008 ITG Conference on Voice Communication (SprachKommunikation)
(2008) 1–4.
date_created: 2019-07-12T05:31:12Z
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/2008/WiHa08-2.pdf
oa: '1'
page: 1-4
publication: 2008 ITG Conference on Voice Communication (SprachKommunikation)
status: public
title: A novel approach to noise estimation in model-based speech feature enhancement
type: journal_article
user_id: '44006'
year: '2008'
...
---
_id: '11944'
abstract:
- lang: eng
text: In this paper, a novel segmental Hidden Markov Model (HMM) is proposed. The
model is based on a modified emission density where additional statistical dependencies
between subsequent frames of the speech signal are considered. In the following
we derive an effective search strategy for the modified statistical model. Further
an approach to parameter reduction is introduced. Experiments were carried out
on the AURORA2 database where consistent im
author:
- first_name: Stefan
full_name: Windmann, Stefan
last_name: Windmann
- first_name: Reinhold
full_name: Haeb-Umbach, Reinhold
id: '242'
last_name: Haeb-Umbach
- first_name: Volker
full_name: Leutnant, Volker
last_name: Leutnant
citation:
ama: Windmann S, Haeb-Umbach R, Leutnant V. A segmental HMM based on a modified
emission probability. 2008 ITG Conference on Voice Communication (SprachKommunikation).
2008:1-4.
apa: Windmann, S., Haeb-Umbach, R., & Leutnant, V. (2008). A segmental HMM based
on a modified emission probability. 2008 ITG Conference on Voice Communication
(SprachKommunikation), 1–4.
bibtex: '@article{Windmann_Haeb-Umbach_Leutnant_2008, title={A segmental HMM based
on a modified emission probability}, journal={2008 ITG Conference on Voice Communication
(SprachKommunikation)}, author={Windmann, Stefan and Haeb-Umbach, Reinhold and
Leutnant, Volker}, year={2008}, pages={1–4} }'
chicago: Windmann, Stefan, Reinhold Haeb-Umbach, and Volker Leutnant. “A Segmental
HMM Based on a Modified Emission Probability.” 2008 ITG Conference on Voice
Communication (SprachKommunikation), 2008, 1–4.
ieee: S. Windmann, R. Haeb-Umbach, and V. Leutnant, “A segmental HMM based on a
modified emission probability,” 2008 ITG Conference on Voice Communication
(SprachKommunikation), pp. 1–4, 2008.
mla: Windmann, Stefan, et al. “A Segmental HMM Based on a Modified Emission Probability.”
2008 ITG Conference on Voice Communication (SprachKommunikation), 2008,
pp. 1–4.
short: S. Windmann, R. Haeb-Umbach, V. Leutnant, 2008 ITG Conference on Voice Communication
(SprachKommunikation) (2008) 1–4.
date_created: 2019-07-12T05:31:16Z
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/2008/WiHaLe08.pdf
oa: '1'
page: 1-4
publication: 2008 ITG Conference on Voice Communication (SprachKommunikation)
status: public
title: A segmental HMM based on a modified emission probability
type: journal_article
user_id: '44006'
year: '2008'
...
---
_id: '11720'
author:
- first_name: Maik
full_name: Bevermeier, Maik
last_name: Bevermeier
- first_name: Tobias
full_name: Ebel, Tobias
last_name: Ebel
- first_name: Reinhold
full_name: Haeb-Umbach, Reinhold
id: '242'
last_name: Haeb-Umbach
citation:
ama: 'Bevermeier M, Ebel T, Haeb-Umbach R. Channel Estimation by Exploiting Sublayer
Information in OFDM Systems. In: Multi-Carrier Spread Spectrum 2007. ;
2007.'
apa: Bevermeier, M., Ebel, T., & Haeb-Umbach, R. (2007). Channel Estimation
by Exploiting Sublayer Information in OFDM Systems. In Multi-Carrier Spread
Spectrum 2007.
bibtex: '@inproceedings{Bevermeier_Ebel_Haeb-Umbach_2007, title={Channel Estimation
by Exploiting Sublayer Information in OFDM Systems}, booktitle={Multi-Carrier
Spread Spectrum 2007}, author={Bevermeier, Maik and Ebel, Tobias and Haeb-Umbach,
Reinhold}, year={2007} }'
chicago: Bevermeier, Maik, Tobias Ebel, and Reinhold Haeb-Umbach. “Channel Estimation
by Exploiting Sublayer Information in OFDM Systems.” In Multi-Carrier Spread
Spectrum 2007, 2007.
ieee: M. Bevermeier, T. Ebel, and R. Haeb-Umbach, “Channel Estimation by Exploiting
Sublayer Information in OFDM Systems,” in Multi-Carrier Spread Spectrum 2007,
2007.
mla: Bevermeier, Maik, et al. “Channel Estimation by Exploiting Sublayer Information
in OFDM Systems.” Multi-Carrier Spread Spectrum 2007, 2007.
short: 'M. Bevermeier, T. Ebel, R. Haeb-Umbach, in: Multi-Carrier Spread Spectrum
2007, 2007.'
date_created: 2019-07-12T05:26:57Z
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/2007/BeEbHa07.pdf
oa: '1'
publication: Multi-Carrier Spread Spectrum 2007
status: public
title: Channel Estimation by Exploiting Sublayer Information in OFDM Systems
type: conference
user_id: '44006'
year: '2007'
...
---
_id: '11722'
author:
- first_name: Maik
full_name: Bevermeier, Maik
last_name: Bevermeier
- first_name: Reinhold
full_name: Haeb-Umbach, Reinhold
id: '242'
last_name: Haeb-Umbach
citation:
ama: 'Bevermeier M, Haeb-Umbach R. Combined Time and Frequency Domain OFDM Channel
Estimation. In: Multi-Carrier Spread Spectrum 2007. ; 2007.'
apa: Bevermeier, M., & Haeb-Umbach, R. (2007). Combined Time and Frequency Domain
OFDM Channel Estimation. In Multi-Carrier Spread Spectrum 2007.
bibtex: '@inproceedings{Bevermeier_Haeb-Umbach_2007, title={Combined Time and Frequency
Domain OFDM Channel Estimation}, booktitle={Multi-Carrier Spread Spectrum 2007},
author={Bevermeier, Maik and Haeb-Umbach, Reinhold}, year={2007} }'
chicago: Bevermeier, Maik, and Reinhold Haeb-Umbach. “Combined Time and Frequency
Domain OFDM Channel Estimation.” In Multi-Carrier Spread Spectrum 2007,
2007.
ieee: M. Bevermeier and R. Haeb-Umbach, “Combined Time and Frequency Domain OFDM
Channel Estimation,” in Multi-Carrier Spread Spectrum 2007, 2007.
mla: Bevermeier, Maik, and Reinhold Haeb-Umbach. “Combined Time and Frequency Domain
OFDM Channel Estimation.” Multi-Carrier Spread Spectrum 2007, 2007.
short: 'M. Bevermeier, R. Haeb-Umbach, in: Multi-Carrier Spread Spectrum 2007, 2007.'
date_created: 2019-07-12T05:27:00Z
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/2007/BeEb07.pdf
oa: '1'
publication: Multi-Carrier Spread Spectrum 2007
status: public
title: Combined Time and Frequency Domain OFDM Channel Estimation
type: conference
user_id: '44006'
year: '2007'
...
---
_id: '11785'
abstract:
- lang: eng
text: 'In this paper we present a novel channel impulse response estimation technique
for block-oriented OFDM transmission based on combining estimators: the estimates
provided by a Kalman filter operating in the time domain and a Wiener filter in
the frequency domain are optimally combined by taking into account their estimated
error covariances. The resulting estimator turns out to be identical to the MAP
estimator of correlated jointly Gaussian mean vectors. Different variants of the
proposed scheme are experimentally investigated in an EEEE 802.11a-like system
setup. They compare favourably with known approaches from the literature resulting
in reduced mean square estimation error and bit error rate. Further, robustness
and complexity issues are discussed'
author:
- first_name: Reinhold
full_name: Haeb-Umbach, Reinhold
id: '242'
last_name: Haeb-Umbach
- first_name: Maik
full_name: Bevermeier, Maik
last_name: Bevermeier
citation:
ama: 'Haeb-Umbach R, Bevermeier M. OFDM Channel Estimation Based on Combined Estimation
in Time and Frequency Domain. In: IEEE International Conference on Acoustics,
Speech and Signal Processing (ICASSP 2007). Vol 3. ; 2007:III-277-III-280.
doi:10.1109/ICASSP.2007.366526'
apa: Haeb-Umbach, R., & Bevermeier, M. (2007). OFDM Channel Estimation Based
on Combined Estimation in Time and Frequency Domain. In IEEE International
Conference on Acoustics, Speech and Signal Processing (ICASSP 2007) (Vol.
3, pp. III-277-III–280). https://doi.org/10.1109/ICASSP.2007.366526
bibtex: '@inproceedings{Haeb-Umbach_Bevermeier_2007, title={OFDM Channel Estimation
Based on Combined Estimation in Time and Frequency Domain}, volume={3}, DOI={10.1109/ICASSP.2007.366526},
booktitle={IEEE International Conference on Acoustics, Speech and Signal Processing
(ICASSP 2007)}, author={Haeb-Umbach, Reinhold and Bevermeier, Maik}, year={2007},
pages={III-277-III–280} }'
chicago: Haeb-Umbach, Reinhold, and Maik Bevermeier. “OFDM Channel Estimation Based
on Combined Estimation in Time and Frequency Domain.” In IEEE International
Conference on Acoustics, Speech and Signal Processing (ICASSP 2007), 3:III-277-III–280,
2007. https://doi.org/10.1109/ICASSP.2007.366526.
ieee: R. Haeb-Umbach and M. Bevermeier, “OFDM Channel Estimation Based on Combined
Estimation in Time and Frequency Domain,” in IEEE International Conference
on Acoustics, Speech and Signal Processing (ICASSP 2007), 2007, vol. 3, pp.
III-277-III–280.
mla: Haeb-Umbach, Reinhold, and Maik Bevermeier. “OFDM Channel Estimation Based
on Combined Estimation in Time and Frequency Domain.” IEEE International Conference
on Acoustics, Speech and Signal Processing (ICASSP 2007), vol. 3, 2007, pp.
III-277-III–280, doi:10.1109/ICASSP.2007.366526.
short: 'R. Haeb-Umbach, M. Bevermeier, in: IEEE International Conference on Acoustics,
Speech and Signal Processing (ICASSP 2007), 2007, pp. III-277-III–280.'
date_created: 2019-07-12T05:28:13Z
date_updated: 2022-01-06T06:51:08Z
department:
- _id: '54'
doi: 10.1109/ICASSP.2007.366526
intvolume: ' 3'
keyword:
- bit error rate
- block-oriented OFDM transmission
- channel estimation
- channel impulse response estimation
- combining estimators
- error statistics
- frequency domain estimation
- Gaussian mean vectors
- Gaussian processes
- Kalman filter
- Kalman filters
- MAP estimator
- maximum likelihood estimation
- OFDM channel estimation
- OFDM modulation
- time domain estimation
- time-frequency analysis
- Wiener filter
- Wiener filters
language:
- iso: eng
main_file_link:
- open_access: '1'
url: https://groups.uni-paderborn.de/nt/pubs/2007/HaBe07.pdf
oa: '1'
page: III-277-III-280
publication: IEEE International Conference on Acoustics, Speech and Signal Processing
(ICASSP 2007)
status: public
title: OFDM Channel Estimation Based on Combined Estimation in Time and Frequency
Domain
type: conference
user_id: '44006'
volume: 3
year: '2007'
...
---
_id: '11799'
abstract:
- lang: eng
text: In this paper, we propose a novel similarity measure to be used for localizing
mobile terminals by comparing measured signal power levels with a database of
predictions. The proposed measure provides the possibility to incorporate inherent
information about signal power level measurements requested by the serving base
station but not reported by the mobile terminal. Increased positioning accuracy
was observed both in simulations and with real field data
author:
- first_name: Reinhold
full_name: Haeb-Umbach, Reinhold
id: '242'
last_name: Haeb-Umbach
- first_name: Sven
full_name: Peschke, Sven
last_name: Peschke
citation:
ama: Haeb-Umbach R, Peschke S. A Novel Similarity Measure for Positioning Cellular
Phones by a Comparison With a Database of Signal Power Levels. IEEE Transactions
on Vehicular Technology. 2007;56(1):368-372. doi:10.1109/TVT.2006.889563
apa: Haeb-Umbach, R., & Peschke, S. (2007). A Novel Similarity Measure for Positioning
Cellular Phones by a Comparison With a Database of Signal Power Levels. IEEE
Transactions on Vehicular Technology, 56(1), 368–372. https://doi.org/10.1109/TVT.2006.889563
bibtex: '@article{Haeb-Umbach_Peschke_2007, title={A Novel Similarity Measure for
Positioning Cellular Phones by a Comparison With a Database of Signal Power Levels},
volume={56}, DOI={10.1109/TVT.2006.889563},
number={1}, journal={IEEE Transactions on Vehicular Technology}, author={Haeb-Umbach,
Reinhold and Peschke, Sven}, year={2007}, pages={368–372} }'
chicago: 'Haeb-Umbach, Reinhold, and Sven Peschke. “A Novel Similarity Measure for
Positioning Cellular Phones by a Comparison With a Database of Signal Power Levels.”
IEEE Transactions on Vehicular Technology 56, no. 1 (2007): 368–72. https://doi.org/10.1109/TVT.2006.889563.'
ieee: R. Haeb-Umbach and S. Peschke, “A Novel Similarity Measure for Positioning
Cellular Phones by a Comparison With a Database of Signal Power Levels,” IEEE
Transactions on Vehicular Technology, vol. 56, no. 1, pp. 368–372, 2007.
mla: Haeb-Umbach, Reinhold, and Sven Peschke. “A Novel Similarity Measure for Positioning
Cellular Phones by a Comparison With a Database of Signal Power Levels.” IEEE
Transactions on Vehicular Technology, vol. 56, no. 1, 2007, pp. 368–72, doi:10.1109/TVT.2006.889563.
short: R. Haeb-Umbach, S. Peschke, IEEE Transactions on Vehicular Technology 56
(2007) 368–372.
date_created: 2019-07-12T05:28:29Z
date_updated: 2022-01-06T06:51:08Z
department:
- _id: '54'
doi: 10.1109/TVT.2006.889563
intvolume: ' 56'
issue: '1'
keyword:
- cellular phone positioning
- cellular radio
- measured signal power levels
- mobile handsets
- mobility management (mobile radio)
language:
- iso: eng
main_file_link:
- open_access: '1'
url: https://groups.uni-paderborn.de/nt/pubs/2007/HaPe07.pdf
oa: '1'
page: 368-372
publication: IEEE Transactions on Vehicular Technology
status: public
title: A Novel Similarity Measure for Positioning Cellular Phones by a Comparison
With a Database of Signal Power Levels
type: journal_article
user_id: '44006'
volume: 56
year: '2007'
...
---
_id: '11822'
author:
- first_name: Valentin
full_name: Ion, Valentin
last_name: Ion
- first_name: Reinhold
full_name: Haeb-Umbach, Reinhold
id: '242'
last_name: Haeb-Umbach
citation:
ama: 'Ion V, Haeb-Umbach R. Multi-Resolution Soft Features for Channel-Robust Distributed
Speech Recognition. In: Interspeech 2007. ; 2007.'
apa: Ion, V., & Haeb-Umbach, R. (2007). Multi-Resolution Soft Features for Channel-Robust
Distributed Speech Recognition. In Interspeech 2007.
bibtex: '@inproceedings{Ion_Haeb-Umbach_2007, title={Multi-Resolution Soft Features
for Channel-Robust Distributed Speech Recognition}, booktitle={Interspeech 2007},
author={Ion, Valentin and Haeb-Umbach, Reinhold}, year={2007} }'
chicago: Ion, Valentin, and Reinhold Haeb-Umbach. “Multi-Resolution Soft Features
for Channel-Robust Distributed Speech Recognition.” In Interspeech 2007,
2007.
ieee: V. Ion and R. Haeb-Umbach, “Multi-Resolution Soft Features for Channel-Robust
Distributed Speech Recognition,” in Interspeech 2007, 2007.
mla: Ion, Valentin, and Reinhold Haeb-Umbach. “Multi-Resolution Soft Features for
Channel-Robust Distributed Speech Recognition.” Interspeech 2007, 2007.
short: 'V. Ion, R. Haeb-Umbach, in: Interspeech 2007, 2007.'
date_created: 2019-07-12T05:28:55Z
date_updated: 2022-01-06T06:51:10Z
department:
- _id: '54'
language:
- iso: eng
main_file_link:
- open_access: '1'
url: https://groups.uni-paderborn.de/nt/pubs/2007/IoHa07.pdf
oa: '1'
publication: Interspeech 2007
status: public
title: Multi-Resolution Soft Features for Channel-Robust Distributed Speech Recognition
type: conference
user_id: '44006'
year: '2007'
...
---
_id: '11883'
abstract:
- lang: eng
text: In this paper, we experimentally evaluate algorithms for velocity estimation
of a GSM 900 mobile terminal which are based on the analysis of the statistical
properties of the fast fading process. It is shown how theses statistics can be
obtained from the training sequences present in downlink transmission bursts without
establishing an active connection. Realistic simulations of a GSM channel according
to the COST 207 channel models have been conducted. These models incorporate effects
like multipath propagation, fading, cochannel interference and additive noise.
It is shown that velocity estimation by searching for the maximum slope of the
power density spectrum of the fast fading performs best.
author:
- first_name: Sven
full_name: Peschke, Sven
last_name: Peschke
- first_name: Reinhold
full_name: Haeb-Umbach, Reinhold
id: '242'
last_name: Haeb-Umbach
citation:
ama: 'Peschke S, Haeb-Umbach R. Velocity Estimation of Mobile Terminals by Exploiting
GSM Downlink Signalling. In: 4th Workshop on Positioning Navigation and Communication
(WPNC 2007). ; 2007:217-222. doi:10.1109/WPNC.2007.353637'
apa: Peschke, S., & Haeb-Umbach, R. (2007). Velocity Estimation of Mobile Terminals
by Exploiting GSM Downlink Signalling. In 4th Workshop on Positioning Navigation
and Communication (WPNC 2007) (pp. 217–222). https://doi.org/10.1109/WPNC.2007.353637
bibtex: '@inproceedings{Peschke_Haeb-Umbach_2007, title={Velocity Estimation of
Mobile Terminals by Exploiting GSM Downlink Signalling}, DOI={10.1109/WPNC.2007.353637},
booktitle={4th Workshop on Positioning Navigation and Communication (WPNC 2007)},
author={Peschke, Sven and Haeb-Umbach, Reinhold}, year={2007}, pages={217–222}
}'
chicago: Peschke, Sven, and Reinhold Haeb-Umbach. “Velocity Estimation of Mobile
Terminals by Exploiting GSM Downlink Signalling.” In 4th Workshop on Positioning
Navigation and Communication (WPNC 2007), 217–22, 2007. https://doi.org/10.1109/WPNC.2007.353637.
ieee: S. Peschke and R. Haeb-Umbach, “Velocity Estimation of Mobile Terminals by
Exploiting GSM Downlink Signalling,” in 4th Workshop on Positioning Navigation
and Communication (WPNC 2007), 2007, pp. 217–222.
mla: Peschke, Sven, and Reinhold Haeb-Umbach. “Velocity Estimation of Mobile Terminals
by Exploiting GSM Downlink Signalling.” 4th Workshop on Positioning Navigation
and Communication (WPNC 2007), 2007, pp. 217–22, doi:10.1109/WPNC.2007.353637.
short: 'S. Peschke, R. Haeb-Umbach, in: 4th Workshop on Positioning Navigation and
Communication (WPNC 2007), 2007, pp. 217–222.'
date_created: 2019-07-12T05:30:06Z
date_updated: 2022-01-06T06:51:11Z
department:
- _id: '54'
doi: 10.1109/WPNC.2007.353637
keyword:
- additive noise
- cellular radio
- channel estimation
- cochannel interference
- COST 207 channel models
- downlink transmission bursts
- fading channels
- fading process
- GSM downlink signalling
- mobile terminals
- multipath channels
- multipath propagation
- power density spectrum
- statistical analysis
- statistical properties
- telecommunication links
- telecommunication terminals
- velocity estimation
language:
- iso: eng
main_file_link:
- open_access: '1'
url: https://groups.uni-paderborn.de/nt/pubs/2007/PeHa07.pdf
oa: '1'
page: 217-222
publication: 4th Workshop on Positioning Navigation and Communication (WPNC 2007)
status: public
title: Velocity Estimation of Mobile Terminals by Exploiting GSM Downlink Signalling
type: conference
user_id: '44006'
year: '2007'
...
---
_id: '11927'
abstract:
- lang: eng
text: Maximizing the output signal-to-noise ratio (SNR) of a sensor array in the
presence of spatially colored noise leads to a generalized eigenvalue problem.
While this approach has extensively been employed in narrowband (antenna) array
beamforming, it is typically not used for broadband (microphone) array beamforming
due to the uncontrolled amount of speech distortion introduced by a narrowband
SNR criterion. In this paper, we show how the distortion of the desired signal
can be controlled by a single-channel post-filter, resulting in a performance
comparable to the generalized minimum variance distortionless response beamformer,
where arbitrary transfer functions relate the source and the microphones. Results
are given both for directional and diffuse noise. A novel gradient ascent adaptation
algorithm is presented, and its good convergence properties are experimentally
revealed by comparison with alternatives from the literature. A key feature of
the proposed beamformer is that it operates blindly, i.e., it neither requires
knowledge about the array geometry nor an explicit estimation of the transfer
functions from source to sensors or the direction-of-arrival.
author:
- 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: Warsitz E, Haeb-Umbach R. Blind Acoustic Beamforming Based on Generalized Eigenvalue
Decomposition. IEEE Transactions on Audio, Speech, and Language Processing.
2007;15(5):1529-1539. doi:10.1109/TASL.2007.898454
apa: Warsitz, E., & Haeb-Umbach, R. (2007). Blind Acoustic Beamforming Based
on Generalized Eigenvalue Decomposition. IEEE Transactions on Audio, Speech,
and Language Processing, 15(5), 1529–1539. https://doi.org/10.1109/TASL.2007.898454
bibtex: '@article{Warsitz_Haeb-Umbach_2007, title={Blind Acoustic Beamforming Based
on Generalized Eigenvalue Decomposition}, volume={15}, DOI={10.1109/TASL.2007.898454},
number={5}, journal={IEEE Transactions on Audio, Speech, and Language Processing},
author={Warsitz, Ernst and Haeb-Umbach, Reinhold}, year={2007}, pages={1529–1539}
}'
chicago: 'Warsitz, Ernst, and Reinhold Haeb-Umbach. “Blind Acoustic Beamforming
Based on Generalized Eigenvalue Decomposition.” IEEE Transactions on Audio,
Speech, and Language Processing 15, no. 5 (2007): 1529–39. https://doi.org/10.1109/TASL.2007.898454.'
ieee: E. Warsitz and R. Haeb-Umbach, “Blind Acoustic Beamforming Based on Generalized
Eigenvalue Decomposition,” IEEE Transactions on Audio, Speech, and Language
Processing, vol. 15, no. 5, pp. 1529–1539, 2007.
mla: Warsitz, Ernst, and Reinhold Haeb-Umbach. “Blind Acoustic Beamforming Based
on Generalized Eigenvalue Decomposition.” IEEE Transactions on Audio, Speech,
and Language Processing, vol. 15, no. 5, 2007, pp. 1529–39, doi:10.1109/TASL.2007.898454.
short: E. Warsitz, R. Haeb-Umbach, IEEE Transactions on Audio, Speech, and Language
Processing 15 (2007) 1529–1539.
date_created: 2019-07-12T05:30:57Z
date_updated: 2022-01-06T06:51:12Z
department:
- _id: '54'
doi: 10.1109/TASL.2007.898454
intvolume: ' 15'
issue: '5'
keyword:
- acoustic signal processing
- arbitrary transfer function
- array signal processing
- blind acoustic beamforming
- direction-of-arrival
- direction-of-arrival estimation
- eigenvalues and eigenfunctions
- generalized eigenvalue decomposition
- gradient ascent adaptation algorithm
- microphone arrays
- microphones
- narrowband array beamforming
- sensor array
- single-channel post-filter
- spatially colored noise
- transfer functions
language:
- iso: eng
main_file_link:
- open_access: '1'
url: https://groups.uni-paderborn.de/nt/pubs/2007/WaHa07.pdf
oa: '1'
page: 1529-1539
publication: IEEE Transactions on Audio, Speech, and Language Processing
status: public
title: Blind Acoustic Beamforming Based on Generalized Eigenvalue Decomposition
type: journal_article
user_id: '44006'
volume: 15
year: '2007'
...
---
_id: '11934'
author:
- first_name: Ernst
full_name: Warsitz, Ernst
last_name: Warsitz
- first_name: Reinhold
full_name: Haeb-Umbach, Reinhold
id: '242'
last_name: Haeb-Umbach
- first_name: Dang Hai
full_name: Tran Vu, Dang Hai
last_name: Tran Vu
citation:
ama: 'Warsitz E, Haeb-Umbach R, Tran Vu DH. Blind Adaptive Principal Eigenvector
Beamforming for Acoustical Source Separation. In: Interspeech 2007. ; 2007.'
apa: Warsitz, E., Haeb-Umbach, R., & Tran Vu, D. H. (2007). Blind Adaptive Principal
Eigenvector Beamforming for Acoustical Source Separation. In Interspeech 2007.
bibtex: '@inproceedings{Warsitz_Haeb-Umbach_Tran Vu_2007, title={Blind Adaptive
Principal Eigenvector Beamforming for Acoustical Source Separation}, booktitle={Interspeech
2007}, author={Warsitz, Ernst and Haeb-Umbach, Reinhold and Tran Vu, Dang Hai},
year={2007} }'
chicago: Warsitz, Ernst, Reinhold Haeb-Umbach, and Dang Hai Tran Vu. “Blind Adaptive
Principal Eigenvector Beamforming for Acoustical Source Separation.” In Interspeech
2007, 2007.
ieee: E. Warsitz, R. Haeb-Umbach, and D. H. Tran Vu, “Blind Adaptive Principal Eigenvector
Beamforming for Acoustical Source Separation,” in Interspeech 2007, 2007.
mla: Warsitz, Ernst, et al. “Blind Adaptive Principal Eigenvector Beamforming for
Acoustical Source Separation.” Interspeech 2007, 2007.
short: 'E. Warsitz, R. Haeb-Umbach, D.H. Tran Vu, in: Interspeech 2007, 2007.'
date_created: 2019-07-12T05:31:05Z
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/2007/WaHaDa07.pdf
oa: '1'
publication: Interspeech 2007
status: public
title: Blind Adaptive Principal Eigenvector Beamforming for Acoustical Source Separation
type: conference
user_id: '44006'
year: '2007'
...
---
_id: '11941'
author:
- first_name: Stefan
full_name: Windmann, Stefan
last_name: Windmann
- first_name: Reinhold
full_name: Haeb-Umbach, Reinhold
id: '242'
last_name: Haeb-Umbach
citation:
ama: 'Windmann S, Haeb-Umbach R. An Approach to Iterative Speech Feature Enhancement
and Recognition. In: Interspeech 2007. ; 2007.'
apa: Windmann, S., & Haeb-Umbach, R. (2007). An Approach to Iterative Speech
Feature Enhancement and Recognition. In Interspeech 2007.
bibtex: '@inproceedings{Windmann_Haeb-Umbach_2007, title={An Approach to Iterative
Speech Feature Enhancement and Recognition}, booktitle={Interspeech 2007}, author={Windmann,
Stefan and Haeb-Umbach, Reinhold}, year={2007} }'
chicago: Windmann, Stefan, and Reinhold Haeb-Umbach. “An Approach to Iterative Speech
Feature Enhancement and Recognition.” In Interspeech 2007, 2007.
ieee: S. Windmann and R. Haeb-Umbach, “An Approach to Iterative Speech Feature Enhancement
and Recognition,” in Interspeech 2007, 2007.
mla: Windmann, Stefan, and Reinhold Haeb-Umbach. “An Approach to Iterative Speech
Feature Enhancement and Recognition.” Interspeech 2007, 2007.
short: 'S. Windmann, R. Haeb-Umbach, in: Interspeech 2007, 2007.'
date_created: 2019-07-12T05:31:13Z
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/2007/WiHa07.pdf
oa: '1'
publication: Interspeech 2007
status: public
title: An Approach to Iterative Speech Feature Enhancement and Recognition
type: conference
user_id: '44006'
year: '2007'
...
---
_id: '11893'
author:
- 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: 'Schmalenstroeer J, Haeb-Umbach R. Joint Speaker Segmentation, Localization
and Identification for Streaming Audio. In: Interspeech 2007. ; 2007.'
apa: Schmalenstroeer, J., & Haeb-Umbach, R. (2007). Joint Speaker Segmentation,
Localization and Identification for Streaming Audio. Interspeech 2007.
bibtex: '@inproceedings{Schmalenstroeer_Haeb-Umbach_2007, title={Joint Speaker Segmentation,
Localization and Identification for Streaming Audio}, booktitle={Interspeech 2007},
author={Schmalenstroeer, Joerg and Haeb-Umbach, Reinhold}, year={2007} }'
chicago: Schmalenstroeer, Joerg, and Reinhold Haeb-Umbach. “Joint Speaker Segmentation,
Localization and Identification for Streaming Audio.” In Interspeech 2007,
2007.
ieee: J. Schmalenstroeer and R. Haeb-Umbach, “Joint Speaker Segmentation, Localization
and Identification for Streaming Audio,” 2007.
mla: Schmalenstroeer, Joerg, and Reinhold Haeb-Umbach. “Joint Speaker Segmentation,
Localization and Identification for Streaming Audio.” Interspeech 2007,
2007.
short: 'J. Schmalenstroeer, R. Haeb-Umbach, in: Interspeech 2007, 2007.'
date_created: 2019-07-12T05:30:17Z
date_updated: 2023-10-26T08:10:02Z
department:
- _id: '54'
language:
- iso: eng
main_file_link:
- open_access: '1'
url: https://groups.uni-paderborn.de/nt/pubs/2007/ScHa07.pdf
oa: '1'
publication: Interspeech 2007
quality_controlled: '1'
status: public
title: Joint Speaker Segmentation, Localization and Identification for Streaming Audio
type: conference
user_id: '460'
year: '2007'
...
---
_id: '11901'
author:
- first_name: Joerg
full_name: Schmalenstroeer, Joerg
id: '460'
last_name: Schmalenstroeer
- 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: 'Schmalenstroeer J, Leutnant V, Haeb-Umbach R. Amigo Context Management Service
with Applications in Ambient Communication Scenarios. In: AMI-07 - European
Conference on Ambient Intelligence. ; 2007.'
apa: Schmalenstroeer, J., Leutnant, V., & Haeb-Umbach, R. (2007). Amigo Context
Management Service with Applications in Ambient Communication Scenarios. AMI-07
- European Conference on Ambient Intelligence.
bibtex: '@inproceedings{Schmalenstroeer_Leutnant_Haeb-Umbach_2007, title={Amigo
Context Management Service with Applications in Ambient Communication Scenarios},
booktitle={AMI-07 - European Conference on Ambient Intelligence}, author={Schmalenstroeer,
Joerg and Leutnant, Volker and Haeb-Umbach, Reinhold}, year={2007} }'
chicago: Schmalenstroeer, Joerg, Volker Leutnant, and Reinhold Haeb-Umbach. “Amigo
Context Management Service with Applications in Ambient Communication Scenarios.”
In AMI-07 - European Conference on Ambient Intelligence, 2007.
ieee: J. Schmalenstroeer, V. Leutnant, and R. Haeb-Umbach, “Amigo Context Management
Service with Applications in Ambient Communication Scenarios,” 2007.
mla: Schmalenstroeer, Joerg, et al. “Amigo Context Management Service with Applications
in Ambient Communication Scenarios.” AMI-07 - European Conference on Ambient
Intelligence, 2007.
short: 'J. Schmalenstroeer, V. Leutnant, R. Haeb-Umbach, in: AMI-07 - European Conference
on Ambient Intelligence, 2007.'
date_created: 2019-07-12T05:30:27Z
date_updated: 2023-10-26T08:13:09Z
department:
- _id: '54'
language:
- iso: eng
main_file_link:
- open_access: '1'
url: https://groups.uni-paderborn.de/nt/pubs/2007/ScLeHa07.pdf
oa: '1'
publication: AMI-07 - European Conference on Ambient Intelligence
quality_controlled: '1'
status: public
title: Amigo Context Management Service with Applications in Ambient Communication
Scenarios
type: conference
user_id: '460'
year: '2007'
...
---
_id: '11933'
author:
- first_name: Ernst
full_name: Warsitz, Ernst
last_name: Warsitz
- first_name: Reinhold
full_name: Haeb-Umbach, Reinhold
id: '242'
last_name: Haeb-Umbach
- first_name: Joerg
full_name: Schmalenstroeer, Joerg
id: '460'
last_name: Schmalenstroeer
citation:
ama: 'Warsitz E, Haeb-Umbach R, Schmalenstroeer J. Zweistufige Sprache/Pause-Detektion
in stark gestoerter Umgebung. In: 33. Deutsche Jahrestagung Fuer Akustik (DAGA
2007). ; 2007.'
apa: Warsitz, E., Haeb-Umbach, R., & Schmalenstroeer, J. (2007). Zweistufige
Sprache/Pause-Detektion in stark gestoerter Umgebung. 33. Deutsche Jahrestagung
Fuer Akustik (DAGA 2007).
bibtex: '@inproceedings{Warsitz_Haeb-Umbach_Schmalenstroeer_2007, title={Zweistufige
Sprache/Pause-Detektion in stark gestoerter Umgebung}, booktitle={33. Deutsche
Jahrestagung fuer Akustik (DAGA 2007)}, author={Warsitz, Ernst and Haeb-Umbach,
Reinhold and Schmalenstroeer, Joerg}, year={2007} }'
chicago: Warsitz, Ernst, Reinhold Haeb-Umbach, and Joerg Schmalenstroeer. “Zweistufige
Sprache/Pause-Detektion in Stark Gestoerter Umgebung.” In 33. Deutsche Jahrestagung
Fuer Akustik (DAGA 2007), 2007.
ieee: E. Warsitz, R. Haeb-Umbach, and J. Schmalenstroeer, “Zweistufige Sprache/Pause-Detektion
in stark gestoerter Umgebung,” 2007.
mla: Warsitz, Ernst, et al. “Zweistufige Sprache/Pause-Detektion in Stark Gestoerter
Umgebung.” 33. Deutsche Jahrestagung Fuer Akustik (DAGA 2007), 2007.
short: 'E. Warsitz, R. Haeb-Umbach, J. Schmalenstroeer, in: 33. Deutsche Jahrestagung
Fuer Akustik (DAGA 2007), 2007.'
date_created: 2019-07-12T05:31:04Z
date_updated: 2023-10-26T08:12:49Z
department:
- _id: '54'
language:
- iso: eng
main_file_link:
- open_access: '1'
url: https://groups.uni-paderborn.de/nt/pubs/2007/WaHaSc07.pdf
oa: '1'
publication: 33. Deutsche Jahrestagung fuer Akustik (DAGA 2007)
quality_controlled: '1'
status: public
title: Zweistufige Sprache/Pause-Detektion in stark gestoerter Umgebung
type: conference
user_id: '460'
year: '2007'
...
---
_id: '11902'
author:
- first_name: Joerg
full_name: Schmalenstroeer, Joerg
id: '460'
last_name: Schmalenstroeer
- 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: 'Schmalenstroeer J, Warsitz E, Haeb-Umbach R. Projekt Amigo - Sprachsignalverarbeitung
im vernetzten Haus. In: 33. Deutsche Jahrestagung Fuer Akustik (DAGA 2007).
; 2007.'
apa: Schmalenstroeer, J., Warsitz, E., & Haeb-Umbach, R. (2007). Projekt Amigo
- Sprachsignalverarbeitung im vernetzten Haus. 33. Deutsche Jahrestagung Fuer
Akustik (DAGA 2007).
bibtex: '@inproceedings{Schmalenstroeer_Warsitz_Haeb-Umbach_2007, title={Projekt
Amigo - Sprachsignalverarbeitung im vernetzten Haus}, booktitle={33. Deutsche
Jahrestagung fuer Akustik (DAGA 2007)}, author={Schmalenstroeer, Joerg and Warsitz,
Ernst and Haeb-Umbach, Reinhold}, year={2007} }'
chicago: Schmalenstroeer, Joerg, Ernst Warsitz, and Reinhold Haeb-Umbach. “Projekt
Amigo - Sprachsignalverarbeitung Im Vernetzten Haus.” In 33. Deutsche Jahrestagung
Fuer Akustik (DAGA 2007), 2007.
ieee: J. Schmalenstroeer, E. Warsitz, and R. Haeb-Umbach, “Projekt Amigo - Sprachsignalverarbeitung
im vernetzten Haus,” 2007.
mla: Schmalenstroeer, Joerg, et al. “Projekt Amigo - Sprachsignalverarbeitung Im
Vernetzten Haus.” 33. Deutsche Jahrestagung Fuer Akustik (DAGA 2007), 2007.
short: 'J. Schmalenstroeer, E. Warsitz, R. Haeb-Umbach, in: 33. Deutsche Jahrestagung
Fuer Akustik (DAGA 2007), 2007.'
date_created: 2019-07-12T05:30:28Z
date_updated: 2023-10-26T08:13:01Z
department:
- _id: '54'
language:
- iso: eng
main_file_link:
- open_access: '1'
url: https://groups.uni-paderborn.de/nt/pubs/2007/ScWaHa07.pdf
oa: '1'
publication: 33. Deutsche Jahrestagung fuer Akustik (DAGA 2007)
quality_controlled: '1'
status: public
title: Projekt Amigo - Sprachsignalverarbeitung im vernetzten Haus
type: conference
user_id: '460'
year: '2007'
...
---
_id: '11823'
abstract:
- lang: eng
text: In this study we evaluate transmission error compensation techniques for distributed
speech recognition systems based on modification of the speech decoder. The candidates
are marginalization, weighted Viterbi and our recently proposed soft-feature uncertainty
decoding. For the latter, it is shown how the Bayesian speech recognition approach
must be reformulated for recognition at the server side. The resulting predictive
classifier is able to take account of the transmission errors by changing the
contribution of the affected speech features to the acoustic score. The comparison
of the experimental results has proven the superiority of our approach.
author:
- first_name: Valentin
full_name: Ion, Valentin
last_name: Ion
- first_name: Reinhold
full_name: Haeb-Umbach, Reinhold
id: '242'
last_name: Haeb-Umbach
citation:
ama: 'Ion V, Haeb-Umbach R. Comparison of Decoder-based Transmission Error Compensation
Techniques for Distributed Speech Recognition. In: 7. ITG-Fachtagung Sprachkommunikation.
; 2006.'
apa: Ion, V., & Haeb-Umbach, R. (2006). Comparison of Decoder-based Transmission
Error Compensation Techniques for Distributed Speech Recognition. In 7. ITG-Fachtagung
Sprachkommunikation.
bibtex: '@inproceedings{Ion_Haeb-Umbach_2006, title={Comparison of Decoder-based
Transmission Error Compensation Techniques for Distributed Speech Recognition},
booktitle={7. ITG-Fachtagung Sprachkommunikation}, author={Ion, Valentin and Haeb-Umbach,
Reinhold}, year={2006} }'
chicago: Ion, Valentin, and Reinhold Haeb-Umbach. “Comparison of Decoder-Based Transmission
Error Compensation Techniques for Distributed Speech Recognition.” In 7. ITG-Fachtagung
Sprachkommunikation, 2006.
ieee: V. Ion and R. Haeb-Umbach, “Comparison of Decoder-based Transmission Error
Compensation Techniques for Distributed Speech Recognition,” in 7. ITG-Fachtagung
Sprachkommunikation, 2006.
mla: Ion, Valentin, and Reinhold Haeb-Umbach. “Comparison of Decoder-Based Transmission
Error Compensation Techniques for Distributed Speech Recognition.” 7. ITG-Fachtagung
Sprachkommunikation, 2006.
short: 'V. Ion, R. Haeb-Umbach, in: 7. ITG-Fachtagung Sprachkommunikation, 2006.'
date_created: 2019-07-12T05:28:56Z
date_updated: 2022-01-06T06:51:10Z
department:
- _id: '54'
language:
- iso: eng
main_file_link:
- open_access: '1'
url: https://groups.uni-paderborn.de/nt/pubs/2006/IoHa06-1.pdf
oa: '1'
publication: 7. ITG-Fachtagung Sprachkommunikation
status: public
title: Comparison of Decoder-based Transmission Error Compensation Techniques for
Distributed Speech Recognition
type: conference
user_id: '44006'
year: '2006'
...
---
_id: '11824'
abstract:
- lang: eng
text: Soft-feature based speech recognition, which is an example of uncertainty
decoding, has been proven to be a robust error mitigation method for distributed
speech recognition over wireless channels exhibiting bit errors. In this paper
we extend this concept to packet-oriented transmissions. The a posteriori probability
density function of the lost feature vector, given the closest received neighbours,
is computed. In the experiments, the nearest frame repetition, which is shown
to be equivalent to the MAP estimate, outperforms the MMSE estimate for long bursts.
Taking the variance into account at the speech recognition stage results in superior
performance compared to classical schemes using point estimates. A computationally
and memory efficient implementation of the proposed packet loss compensation scheme
based on table lookup is presented
author:
- first_name: Valentin
full_name: Ion, Valentin
last_name: Ion
- first_name: Reinhold
full_name: Haeb-Umbach, Reinhold
id: '242'
last_name: Haeb-Umbach
citation:
ama: 'Ion V, Haeb-Umbach R. An Inexpensive Packet Loss Compensation Scheme for Distributed
Speech Recognition Based on Soft-Features. In: IEEE International Conference
on Acoustics, Speech and Signal Processing (ICASSP 2006). Vol 1. ; 2006:I.
doi:10.1109/ICASSP.2006.1659984'
apa: Ion, V., & Haeb-Umbach, R. (2006). An Inexpensive Packet Loss Compensation
Scheme for Distributed Speech Recognition Based on Soft-Features. In IEEE International
Conference on Acoustics, Speech and Signal Processing (ICASSP 2006) (Vol.
1, p. I). https://doi.org/10.1109/ICASSP.2006.1659984
bibtex: '@inproceedings{Ion_Haeb-Umbach_2006, title={An Inexpensive Packet Loss
Compensation Scheme for Distributed Speech Recognition Based on Soft-Features},
volume={1}, DOI={10.1109/ICASSP.2006.1659984},
booktitle={IEEE International Conference on Acoustics, Speech and Signal Processing
(ICASSP 2006)}, author={Ion, Valentin and Haeb-Umbach, Reinhold}, year={2006},
pages={I} }'
chicago: Ion, Valentin, and Reinhold Haeb-Umbach. “An Inexpensive Packet Loss Compensation
Scheme for Distributed Speech Recognition Based on Soft-Features.” In IEEE
International Conference on Acoustics, Speech and Signal Processing (ICASSP 2006),
1:I, 2006. https://doi.org/10.1109/ICASSP.2006.1659984.
ieee: V. Ion and R. Haeb-Umbach, “An Inexpensive Packet Loss Compensation Scheme
for Distributed Speech Recognition Based on Soft-Features,” in IEEE International
Conference on Acoustics, Speech and Signal Processing (ICASSP 2006), 2006,
vol. 1, p. I.
mla: Ion, Valentin, and Reinhold Haeb-Umbach. “An Inexpensive Packet Loss Compensation
Scheme for Distributed Speech Recognition Based on Soft-Features.” IEEE International
Conference on Acoustics, Speech and Signal Processing (ICASSP 2006), vol.
1, 2006, p. I, doi:10.1109/ICASSP.2006.1659984.
short: 'V. Ion, R. Haeb-Umbach, in: IEEE International Conference on Acoustics,
Speech and Signal Processing (ICASSP 2006), 2006, p. I.'
date_created: 2019-07-12T05:28:58Z
date_updated: 2022-01-06T06:51:10Z
department:
- _id: '54'
doi: 10.1109/ICASSP.2006.1659984
intvolume: ' 1'
keyword:
- distributed speech recognition
- least mean squares methods
- MAP estimate
- maximum likelihood estimation
- MMSE estimate
- packet loss compensation scheme
- packet switched communication
- posteriori probability density function
- robust error mitigation method
- soft-features
- speech recognition
- table lookup
- voice communication
- wireless channels
language:
- iso: eng
main_file_link:
- open_access: '1'
url: https://groups.uni-paderborn.de/nt/pubs/2006/IoHa06-2.pdf
oa: '1'
page: I
publication: IEEE International Conference on Acoustics, Speech and Signal Processing
(ICASSP 2006)
status: public
title: An Inexpensive Packet Loss Compensation Scheme for Distributed Speech Recognition
Based on Soft-Features
type: conference
user_id: '44006'
volume: 1
year: '2006'
...