---
_id: '11932'
abstract:
- lang: eng
text: While the main objective of adaptive Filter-and-Sum beamforming is to obtain
an enhanced speech signal for subsequent processing like speech recognition, we
show how speaker localization information can be derived from the filter coefficients.
To increase localization accuracy, speaker tracking is performed by non-linear
Bayesian state estimation, which is realized by sequential Monte Carlo methods.
Improved acquisition and tracking performance was achieved even in highly reverberant
environments, in comparison with both a Kalman Filter and a recently proposed
Particle Filter operating on the output of a nonadaptive Delay-and-Sum beamformer.
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: Sven
full_name: Peschke, Sven
last_name: Peschke
citation:
ama: 'Warsitz E, Haeb-Umbach R, Peschke S. Adaptive Beamforming Combined with Particle
Filtering for Acoustic Source Localization. In: International Conference on
Spoken Language Processing (ICSLP 2004). ; 2004.'
apa: Warsitz, E., Haeb-Umbach, R., & Peschke, S. (2004). Adaptive Beamforming
Combined with Particle Filtering for Acoustic Source Localization. In International
Conference on Spoken Language Processing (ICSLP 2004).
bibtex: '@inproceedings{Warsitz_Haeb-Umbach_Peschke_2004, title={Adaptive Beamforming
Combined with Particle Filtering for Acoustic Source Localization}, booktitle={International
Conference on Spoken Language Processing (ICSLP 2004)}, author={Warsitz, Ernst
and Haeb-Umbach, Reinhold and Peschke, Sven}, year={2004} }'
chicago: Warsitz, Ernst, Reinhold Haeb-Umbach, and Sven Peschke. “Adaptive Beamforming
Combined with Particle Filtering for Acoustic Source Localization.” In International
Conference on Spoken Language Processing (ICSLP 2004), 2004.
ieee: E. Warsitz, R. Haeb-Umbach, and S. Peschke, “Adaptive Beamforming Combined
with Particle Filtering for Acoustic Source Localization,” in International
Conference on Spoken Language Processing (ICSLP 2004), 2004.
mla: Warsitz, Ernst, et al. “Adaptive Beamforming Combined with Particle Filtering
for Acoustic Source Localization.” International Conference on Spoken Language
Processing (ICSLP 2004), 2004.
short: 'E. Warsitz, R. Haeb-Umbach, S. Peschke, in: International Conference on
Spoken Language Processing (ICSLP 2004), 2004.'
date_created: 2019-07-12T05:31:02Z
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/2004/WaHaPe04.pdf
oa: '1'
publication: International Conference on Spoken Language Processing (ICSLP 2004)
status: public
title: Adaptive Beamforming Combined with Particle Filtering for Acoustic Source Localization
type: conference
user_id: '44006'
year: '2004'
...
---
_id: '11777'
author:
- first_name: Reinhold
full_name: Haeb-Umbach, Reinhold
id: '242'
last_name: Haeb-Umbach
citation:
ama: Haeb-Umbach R. Auf ein Wort - Moeglichkeiten und Grenzen der automatischen
Spracherkennung. Forschungsforum Paderborn. 2003:68-71.
apa: Haeb-Umbach, R. (2003). Auf ein Wort - Moeglichkeiten und Grenzen der automatischen
Spracherkennung. Forschungsforum Paderborn, 68–71.
bibtex: '@article{Haeb-Umbach_2003, title={Auf ein Wort - Moeglichkeiten und Grenzen
der automatischen Spracherkennung}, journal={Forschungsforum Paderborn}, author={Haeb-Umbach,
Reinhold}, year={2003}, pages={68–71} }'
chicago: Haeb-Umbach, Reinhold. “Auf Ein Wort - Moeglichkeiten Und Grenzen Der Automatischen
Spracherkennung.” Forschungsforum Paderborn, 2003, 68–71.
ieee: R. Haeb-Umbach, “Auf ein Wort - Moeglichkeiten und Grenzen der automatischen
Spracherkennung,” Forschungsforum Paderborn, pp. 68–71, 2003.
mla: Haeb-Umbach, Reinhold. “Auf Ein Wort - Moeglichkeiten Und Grenzen Der Automatischen
Spracherkennung.” Forschungsforum Paderborn, 2003, pp. 68–71.
short: R. Haeb-Umbach, Forschungsforum Paderborn (2003) 68–71.
date_created: 2019-07-12T05:28:03Z
date_updated: 2022-01-06T06:51:08Z
department:
- _id: '54'
language:
- iso: eng
main_file_link:
- open_access: '1'
url: https://groups.uni-paderborn.de/nt/pubs/2003/Ha03.pdf
oa: '1'
page: 68-71
publication: Forschungsforum Paderborn
status: public
title: Auf ein Wort - Moeglichkeiten und Grenzen der automatischen Spracherkennung
type: journal_article
user_id: '44006'
year: '2003'
...
---
_id: '11727'
abstract:
- lang: eng
text: 'Automatic speech recognition of real-live broadcast news (BN) data (Hub-4)
has become a challenging research topic in recent years. This paper summarizes
our key efforts to build a large vocabulary continuous speech recognition system
for the heterogenous BN task without inducing undesired complexity and computational
resources. These key efforts included: - automatic segmentation of the audio signal
into speech utterances; - efficient one-pass trigram decoding using look-ahead
techniques; - optimal log-linear interpolation of a variety of acoustic and language
models using discriminative model combination (DMC); - handling short-range and
weak longer-range correlations in natural speech and language by the use of phrases
and of distance-language models; - improving the acoustic modeling by a robust
feature extraction, channel normalization, adaptation techniques as well as automatic
script selection and verification. The starting point of the system development
was the Philips 64k-NAB word-internal triphone trigram system. On the speaker-independent
but microphone-dependent NAB-task (transcription of read newspaper texts) we obtained
a word error rate of about 10\%. Now, at the conclusion of the system development,
we have arrived at Philips at an DMC-interpolated phrase-based crossword-pentaphone
4-gram system. This system transcribes BN data with an overall word error rate
of about 17\%.'
author:
- first_name: P.
full_name: Beyerlein, P.
last_name: Beyerlein
- first_name: X.
full_name: Aubert, X.
last_name: Aubert
- first_name: Reinhold
full_name: Haeb-Umbach, Reinhold
id: '242'
last_name: Haeb-Umbach
- first_name: M.
full_name: Harris, M.
last_name: Harris
- first_name: D.
full_name: Klakow, D.
last_name: Klakow
- first_name: A.
full_name: Wendemuth, A.
last_name: Wendemuth
- first_name: S.
full_name: Molau, S.
last_name: Molau
- first_name: N.
full_name: Ney, N.
last_name: Ney
- first_name: Michael
full_name: Pitz, Michael
last_name: Pitz
- first_name: A.
full_name: Sixtus, A.
last_name: Sixtus
citation:
ama: Beyerlein P, Aubert X, Haeb-Umbach R, et al. Large Vocabulary Continuous Speech
Recognition of Broadcast News - The Philips/RWTH Approach. Speech Communication.
2002;(37):109-131.
apa: Beyerlein, P., Aubert, X., Haeb-Umbach, R., Harris, M., Klakow, D., Wendemuth,
A., … Sixtus, A. (2002). Large Vocabulary Continuous Speech Recognition of Broadcast
News - The Philips/RWTH Approach. Speech Communication, (37), 109–131.
bibtex: '@article{Beyerlein_Aubert_Haeb-Umbach_Harris_Klakow_Wendemuth_Molau_Ney_Pitz_Sixtus_2002,
title={Large Vocabulary Continuous Speech Recognition of Broadcast News - The
Philips/RWTH Approach}, number={37}, journal={Speech Communication}, author={Beyerlein,
P. and Aubert, X. and Haeb-Umbach, Reinhold and Harris, M. and Klakow, D. and
Wendemuth, A. and Molau, S. and Ney, N. and Pitz, Michael and Sixtus, A.}, year={2002},
pages={109–131} }'
chicago: 'Beyerlein, P., X. Aubert, Reinhold Haeb-Umbach, M. Harris, D. Klakow,
A. Wendemuth, S. Molau, N. Ney, Michael Pitz, and A. Sixtus. “Large Vocabulary
Continuous Speech Recognition of Broadcast News - The Philips/RWTH Approach.”
Speech Communication, no. 37 (2002): 109–31.'
ieee: P. Beyerlein et al., “Large Vocabulary Continuous Speech Recognition
of Broadcast News - The Philips/RWTH Approach,” Speech Communication, no.
37, pp. 109–131, 2002.
mla: Beyerlein, P., et al. “Large Vocabulary Continuous Speech Recognition of Broadcast
News - The Philips/RWTH Approach.” Speech Communication, no. 37, 2002,
pp. 109–31.
short: P. Beyerlein, X. Aubert, R. Haeb-Umbach, M. Harris, D. Klakow, A. Wendemuth,
S. Molau, N. Ney, M. Pitz, A. Sixtus, Speech Communication (2002) 109–131.
date_created: 2019-07-12T05:27:05Z
date_updated: 2022-01-06T06:51:07Z
department:
- _id: '54'
issue: '37'
language:
- iso: eng
main_file_link:
- open_access: '1'
url: https://groups.uni-paderborn.de/nt/pubs/2002/BeAuHaHaKlWeMoNePiSi02.pdf
oa: '1'
page: 109-131
publication: Speech Communication
status: public
title: Large Vocabulary Continuous Speech Recognition of Broadcast News - The Philips/RWTH
Approach
type: journal_article
user_id: '44006'
year: '2002'
...
---
_id: '11731'
abstract:
- lang: eng
text: Currently the future satellite navigation system Galileo and the third generation
mobile communications system UMTS are on their way to the market in Europe. cdma2000
is under development in the USA and, furthermore, a new civil GPS signal in L2
band and the new frequency band L5 are added. In a hybrid receiver for satellite
navigation and mobile radio communications, the possibility of an additional usage
of the mobile radio signals for navigation purposes could also be a remedy to
one problem of satellite navigation systems, which is the reduced location accuracy
inside of buildings and urban canyons. A hybrid receiver with two fully separated
receiver branches would lead to an increased bill of material and to increased
power consumption in the receiver. This paper, therefore, introduces a hybrid
receiver capable of evaluating Galileo/GPS as well as UMTS/cdma2000 signals with
reduced computational efforts. Furthermore, the proposed structure performs a
constructive superposition of the incoming paths to improve location accuracy.
author:
- first_name: Renke
full_name: Bischoff, Renke
last_name: Bischoff
- first_name: Reinhold
full_name: Haeb-Umbach, Reinhold
id: '242'
last_name: Haeb-Umbach
- first_name: Guenther
full_name: Heinrichs, Guenther
last_name: Heinrichs
citation:
ama: 'Bischoff R, Haeb-Umbach R, Heinrichs G. A Joint Time Multiplex Receiver for
UMTS and Galileo. In: ION-GPS 2002. ; 2002.'
apa: Bischoff, R., Haeb-Umbach, R., & Heinrichs, G. (2002). A Joint Time Multiplex
Receiver for UMTS and Galileo. In ION-GPS 2002.
bibtex: '@inproceedings{Bischoff_Haeb-Umbach_Heinrichs_2002, title={A Joint Time
Multiplex Receiver for UMTS and Galileo}, booktitle={ION-GPS 2002}, author={Bischoff,
Renke and Haeb-Umbach, Reinhold and Heinrichs, Guenther}, year={2002} }'
chicago: Bischoff, Renke, Reinhold Haeb-Umbach, and Guenther Heinrichs. “A Joint
Time Multiplex Receiver for UMTS and Galileo.” In ION-GPS 2002, 2002.
ieee: R. Bischoff, R. Haeb-Umbach, and G. Heinrichs, “A Joint Time Multiplex Receiver
for UMTS and Galileo,” in ION-GPS 2002, 2002.
mla: Bischoff, Renke, et al. “A Joint Time Multiplex Receiver for UMTS and Galileo.”
ION-GPS 2002, 2002.
short: 'R. Bischoff, R. Haeb-Umbach, G. Heinrichs, in: ION-GPS 2002, 2002.'
date_created: 2019-07-12T05:27:10Z
date_updated: 2022-01-06T06:51:08Z
department:
- _id: '54'
language:
- iso: eng
main_file_link:
- open_access: '1'
url: https://groups.uni-paderborn.de/nt/pubs/2002/BiHaHe02.pdf
oa: '1'
publication: ION-GPS 2002
status: public
title: A Joint Time Multiplex Receiver for UMTS and Galileo
type: conference
user_id: '44006'
year: '2002'
...
---
_id: '11733'
abstract:
- lang: eng
text: Current navigation systems like GPS (Global Positioning System) and its Russian
counterpart GLONASS (Global Navigation Satellite System) only evaluate the direct
signal path. The receivers treat the reflected paths also reaching the receiver
antenna as disturbance which has to be suppressed. Multipath affects the tracking
accuracy by resulting in a degeneration of the S-curve of the DLL (delay locked
loop). Nowadays the future European systems GALILEO and GPSIIF/III with two new
signals are on the way to the market and it is time to think about new receiver
structures. Therefore we investigated if it is possible to use multipath for navigation
constructively.
author:
- first_name: Renke
full_name: Bischoff, Renke
last_name: Bischoff
- first_name: Reinhold
full_name: Haeb-Umbach, Reinhold
id: '242'
last_name: Haeb-Umbach
- first_name: Wolfgang
full_name: Schulz, Wolfgang
last_name: Schulz
- first_name: Guenther
full_name: Heinrichs, Guenther
last_name: Heinrichs
citation:
ama: 'Bischoff R, Haeb-Umbach R, Schulz W, Heinrichs G. Employment of a multipath
receiver structure in a combined GALILEO/UMTS receiver. In: IEEE 55th Vehicular
Technology Conference (VTC 2002 Spring). Vol 4. ; 2002:1844-1848 vol.4. doi:10.1109/VTC.2002.1002940'
apa: Bischoff, R., Haeb-Umbach, R., Schulz, W., & Heinrichs, G. (2002). Employment
of a multipath receiver structure in a combined GALILEO/UMTS receiver. In IEEE
55th Vehicular Technology Conference (VTC 2002 Spring) (Vol. 4, pp. 1844–1848
vol.4). https://doi.org/10.1109/VTC.2002.1002940
bibtex: '@inproceedings{Bischoff_Haeb-Umbach_Schulz_Heinrichs_2002, title={Employment
of a multipath receiver structure in a combined GALILEO/UMTS receiver}, volume={4},
DOI={10.1109/VTC.2002.1002940},
booktitle={IEEE 55th Vehicular Technology Conference (VTC 2002 Spring)}, author={Bischoff,
Renke and Haeb-Umbach, Reinhold and Schulz, Wolfgang and Heinrichs, Guenther},
year={2002}, pages={1844–1848 vol.4} }'
chicago: Bischoff, Renke, Reinhold Haeb-Umbach, Wolfgang Schulz, and Guenther Heinrichs.
“Employment of a Multipath Receiver Structure in a Combined GALILEO/UMTS Receiver.”
In IEEE 55th Vehicular Technology Conference (VTC 2002 Spring), 4:1844–48
vol.4, 2002. https://doi.org/10.1109/VTC.2002.1002940.
ieee: R. Bischoff, R. Haeb-Umbach, W. Schulz, and G. Heinrichs, “Employment of a
multipath receiver structure in a combined GALILEO/UMTS receiver,” in IEEE
55th Vehicular Technology Conference (VTC 2002 Spring), 2002, vol. 4, pp.
1844–1848 vol.4.
mla: Bischoff, Renke, et al. “Employment of a Multipath Receiver Structure in a
Combined GALILEO/UMTS Receiver.” IEEE 55th Vehicular Technology Conference
(VTC 2002 Spring), vol. 4, 2002, pp. 1844–48 vol.4, doi:10.1109/VTC.2002.1002940.
short: 'R. Bischoff, R. Haeb-Umbach, W. Schulz, G. Heinrichs, in: IEEE 55th Vehicular
Technology Conference (VTC 2002 Spring), 2002, pp. 1844–1848 vol.4.'
date_created: 2019-07-12T05:27:12Z
date_updated: 2022-01-06T06:51:08Z
department:
- _id: '54'
doi: 10.1109/VTC.2002.1002940
intvolume: ' 4'
keyword:
- combined GALILEO/UMTS receiver
- delay locked loop
- delay lock loops
- DLL
- Global Positioning System
- GLONASS
- GPS
- GPSIIF/III
- mobile satellite communication
- multipath channels
- multipath receiver structure
- radio receivers
- RAKE receiver
- S-curve
language:
- iso: eng
main_file_link:
- open_access: '1'
url: https://groups.uni-paderborn.de/nt/pubs/2002/BiHaScHe02.pdf
oa: '1'
page: 1844-1848 vol.4
publication: IEEE 55th Vehicular Technology Conference (VTC 2002 Spring)
status: public
title: Employment of a multipath receiver structure in a combined GALILEO/UMTS receiver
type: conference
user_id: '44006'
volume: 4
year: '2002'
...
---
_id: '11808'
abstract:
- lang: eng
text: Current location methods for cellular communication systems TOA and E-OTD
exploit time delays and time differences of various base station signals measured
in a mobile phone to determine its location. These methods assume line-of-sight
(LOS) connections to all utilized base stations. Since mobile radio channels are
mainly characterized by scattered propagation paths and non-line-of-sight (NLOS)
propagation, bias errors occur when measured time delays and time differences
are utilized in position calculation algorithms. In this paper, the distribution
of the time error due to NLOS propagation is estimated based on the channel model
proposed in [1]. In combination with actual channel measurements in [2] the NLOS
time error and its probability distribution function is estimated. With this information
being determined for each received signal, position calculation algorithms can
utilize the reliability information to enhance positioning accuracy. [1] L. J.
Greenstein, V. Erceg, Y. S. Yeh, M. V. Clark, {grqq}A new path-gain/delay-spread
propagation model for digital cellular channels'', IEEE Transactions on Vehicular
Technology, Vol. 46, No. 2, May 1997 [2] H. Asplund, {grqq}Wideband Channel Measurements
in Central Stockholm'', T1P1.5/98-242r1
author:
- first_name: Thomas
full_name: Hesse, Thomas
last_name: Hesse
- first_name: Renke
full_name: Bischoff, Renke
last_name: Bischoff
- first_name: Wolfgang
full_name: Schulz, Wolfgang
last_name: Schulz
- first_name: Reinhold
full_name: Haeb-Umbach, Reinhold
id: '242'
last_name: Haeb-Umbach
citation:
ama: 'Hesse T, Bischoff R, Schulz W, Haeb-Umbach R. Estimation of Bias Location
Error due to Absence of the LOS-Signal in a UMTS-System. In: International
Symposium on Location Based Services for Cellular Users (LOCELLUS 2002). ;
2002.'
apa: Hesse, T., Bischoff, R., Schulz, W., & Haeb-Umbach, R. (2002). Estimation
of Bias Location Error due to Absence of the LOS-Signal in a UMTS-System. In International
Symposium on Location Based Services for Cellular Users (LOCELLUS 2002).
bibtex: '@inproceedings{Hesse_Bischoff_Schulz_Haeb-Umbach_2002, title={Estimation
of Bias Location Error due to Absence of the LOS-Signal in a UMTS-System}, booktitle={International
Symposium on Location Based Services for Cellular Users (LOCELLUS 2002)}, author={Hesse,
Thomas and Bischoff, Renke and Schulz, Wolfgang and Haeb-Umbach, Reinhold}, year={2002}
}'
chicago: Hesse, Thomas, Renke Bischoff, Wolfgang Schulz, and Reinhold Haeb-Umbach.
“Estimation of Bias Location Error Due to Absence of the LOS-Signal in a UMTS-System.”
In International Symposium on Location Based Services for Cellular Users (LOCELLUS
2002), 2002.
ieee: T. Hesse, R. Bischoff, W. Schulz, and R. Haeb-Umbach, “Estimation of Bias
Location Error due to Absence of the LOS-Signal in a UMTS-System,” in International
Symposium on Location Based Services for Cellular Users (LOCELLUS 2002), 2002.
mla: Hesse, Thomas, et al. “Estimation of Bias Location Error Due to Absence of
the LOS-Signal in a UMTS-System.” International Symposium on Location Based
Services for Cellular Users (LOCELLUS 2002), 2002.
short: 'T. Hesse, R. Bischoff, W. Schulz, R. Haeb-Umbach, in: International Symposium
on Location Based Services for Cellular Users (LOCELLUS 2002), 2002.'
date_created: 2019-07-12T05:28:39Z
date_updated: 2022-01-06T06:51:09Z
department:
- _id: '54'
language:
- iso: eng
main_file_link:
- open_access: '1'
url: https://groups.uni-paderborn.de/nt/pubs/2002/HeBiScHa02.pdf
oa: '1'
publication: International Symposium on Location Based Services for Cellular Users
(LOCELLUS 2002)
status: public
title: Estimation of Bias Location Error due to Absence of the LOS-Signal in a UMTS-System
type: conference
user_id: '44006'
year: '2002'
...
---
_id: '11734'
author:
- first_name: R.
full_name: Bischoff, R.
last_name: Bischoff
- first_name: Reinhold
full_name: Haeb-Umbach, Reinhold
id: '242'
last_name: Haeb-Umbach
- first_name: W.
full_name: Schulz, W.
last_name: Schulz
- first_name: G.
full_name: Heinrichs, G.
last_name: Heinrichs
citation:
ama: 'Bischoff R, Haeb-Umbach R, Schulz W, Heinrichs G. Implementation of a Rake
Receiver Architecture into a Galileo Receiver. In: 1st ESA Workshop on Satellite
Navigation User Equipment Technology (Navitec 2001). ; 2001.'
apa: Bischoff, R., Haeb-Umbach, R., Schulz, W., & Heinrichs, G. (2001). Implementation
of a Rake Receiver Architecture into a Galileo Receiver. In 1st ESA Workshop
on Satellite Navigation User Equipment Technology (Navitec 2001).
bibtex: '@inproceedings{Bischoff_Haeb-Umbach_Schulz_Heinrichs_2001, title={Implementation
of a Rake Receiver Architecture into a Galileo Receiver}, booktitle={1st ESA Workshop
on Satellite Navigation User Equipment Technology (Navitec 2001)}, author={Bischoff,
R. and Haeb-Umbach, Reinhold and Schulz, W. and Heinrichs, G.}, year={2001} }'
chicago: Bischoff, R., Reinhold Haeb-Umbach, W. Schulz, and G. Heinrichs. “Implementation
of a Rake Receiver Architecture into a Galileo Receiver.” In 1st ESA Workshop
on Satellite Navigation User Equipment Technology (Navitec 2001), 2001.
ieee: R. Bischoff, R. Haeb-Umbach, W. Schulz, and G. Heinrichs, “Implementation
of a Rake Receiver Architecture into a Galileo Receiver,” in 1st ESA Workshop
on Satellite Navigation User Equipment Technology (Navitec 2001), 2001.
mla: Bischoff, R., et al. “Implementation of a Rake Receiver Architecture into a
Galileo Receiver.” 1st ESA Workshop on Satellite Navigation User Equipment
Technology (Navitec 2001), 2001.
short: 'R. Bischoff, R. Haeb-Umbach, W. Schulz, G. Heinrichs, in: 1st ESA Workshop
on Satellite Navigation User Equipment Technology (Navitec 2001), 2001.'
date_created: 2019-07-12T05:27:14Z
date_updated: 2022-01-06T06:51:08Z
department:
- _id: '54'
language:
- iso: eng
main_file_link:
- open_access: '1'
url: https://groups.uni-paderborn.de/nt/pubs/2001/BiHaScHe01.pdf
oa: '1'
publication: 1st ESA Workshop on Satellite Navigation User Equipment Technology (Navitec
2001)
status: public
title: Implementation of a Rake Receiver Architecture into a Galileo Receiver
type: conference
user_id: '44006'
year: '2001'
...
---
_id: '11778'
abstract:
- lang: eng
text: In this paper, it is shown that a correlation criterion is the appropriate
criterion for bottom-up clustering to obtain broad phonetic class regression trees
for maximum likelihood linear regression (MLLR)-based speaker adaptation. The
correlation structure among speech units is estimated on the speaker-independent
training data. In adaptation experiments the tree outperformed a regression tree
obtained from clustering according to closeness in acoustic space and achieved
results comparable with those of a manually designed broad phonetic class tree
author:
- first_name: Reinhold
full_name: Haeb-Umbach, Reinhold
id: '242'
last_name: Haeb-Umbach
citation:
ama: Haeb-Umbach R. Automatic generation of phonetic regression class trees for
MLLR adaptation. IEEE Transactions on Speech and Audio Processing. 2001;9(3):299-302.
doi:10.1109/89.906003
apa: Haeb-Umbach, R. (2001). Automatic generation of phonetic regression class trees
for MLLR adaptation. IEEE Transactions on Speech and Audio Processing,
9(3), 299–302. https://doi.org/10.1109/89.906003
bibtex: '@article{Haeb-Umbach_2001, title={Automatic generation of phonetic regression
class trees for MLLR adaptation}, volume={9}, DOI={10.1109/89.906003},
number={3}, journal={IEEE Transactions on Speech and Audio Processing}, author={Haeb-Umbach,
Reinhold}, year={2001}, pages={299–302} }'
chicago: 'Haeb-Umbach, Reinhold. “Automatic Generation of Phonetic Regression Class
Trees for MLLR Adaptation.” IEEE Transactions on Speech and Audio Processing
9, no. 3 (2001): 299–302. https://doi.org/10.1109/89.906003.'
ieee: R. Haeb-Umbach, “Automatic generation of phonetic regression class trees for
MLLR adaptation,” IEEE Transactions on Speech and Audio Processing, vol.
9, no. 3, pp. 299–302, 2001.
mla: Haeb-Umbach, Reinhold. “Automatic Generation of Phonetic Regression Class Trees
for MLLR Adaptation.” IEEE Transactions on Speech and Audio Processing,
vol. 9, no. 3, 2001, pp. 299–302, doi:10.1109/89.906003.
short: R. Haeb-Umbach, IEEE Transactions on Speech and Audio Processing 9 (2001)
299–302.
date_created: 2019-07-12T05:28:04Z
date_updated: 2022-01-06T06:51:08Z
department:
- _id: '54'
doi: 10.1109/89.906003
intvolume: ' 9'
issue: '3'
keyword:
- acoustic space
- adaptation experiments
- automatic generation
- bottom-up clustering
- broad phonetic class regression trees
- correlation criterion
- correlation methods
- maximum likelihood estimation
- maximum likelihood linear regression based speaker adaptation
- MLLR adaptation
- pattern clustering
- phonetic regression class trees
- speaker-independent training data
- speech recognition
- speech units
- statistical analysis
- trees (mathematics)
language:
- iso: eng
main_file_link:
- open_access: '1'
url: https://groups.uni-paderborn.de/nt/pubs/2001/Ha01.pdf
oa: '1'
page: 299-302
publication: IEEE Transactions on Speech and Audio Processing
status: public
title: Automatic generation of phonetic regression class trees for MLLR adaptation
type: journal_article
user_id: '44006'
volume: 9
year: '2001'
...
---
_id: '11870'
abstract:
- lang: eng
text: We derive a class of computationally inexpensive linear dimension reduction
criteria by introducing a weighted variant of the well-known K-class Fisher criterion
associated with linear discriminant analysis (LDA). It can be seen that LDA weights
contributions of individual class pairs according to the Euclidean distance of
the respective class means. We generalize upon LDA by introducing a different
weighting function
author:
- first_name: M.
full_name: Loog, M.
last_name: Loog
- first_name: R.P.W.
full_name: Duin, R.P.W.
last_name: Duin
- first_name: Reinhold
full_name: Haeb-Umbach, Reinhold
id: '242'
last_name: Haeb-Umbach
citation:
ama: Loog M, Duin RPW, Haeb-Umbach R. Multiclass linear dimension reduction by weighted
pairwise Fisher criteria. IEEE Transactions on Pattern Analysis and Machine
Intelligence. 2001;23(7):762-766. doi:10.1109/34.935849
apa: Loog, M., Duin, R. P. W., & Haeb-Umbach, R. (2001). Multiclass linear dimension
reduction by weighted pairwise Fisher criteria. IEEE Transactions on Pattern
Analysis and Machine Intelligence, 23(7), 762–766. https://doi.org/10.1109/34.935849
bibtex: '@article{Loog_Duin_Haeb-Umbach_2001, title={Multiclass linear dimension
reduction by weighted pairwise Fisher criteria}, volume={23}, DOI={10.1109/34.935849},
number={7}, journal={IEEE Transactions on Pattern Analysis and Machine Intelligence},
author={Loog, M. and Duin, R.P.W. and Haeb-Umbach, Reinhold}, year={2001}, pages={762–766}
}'
chicago: 'Loog, M., R.P.W. Duin, and Reinhold Haeb-Umbach. “Multiclass Linear Dimension
Reduction by Weighted Pairwise Fisher Criteria.” IEEE Transactions on Pattern
Analysis and Machine Intelligence 23, no. 7 (2001): 762–66. https://doi.org/10.1109/34.935849.'
ieee: M. Loog, R. P. W. Duin, and R. Haeb-Umbach, “Multiclass linear dimension reduction
by weighted pairwise Fisher criteria,” IEEE Transactions on Pattern Analysis
and Machine Intelligence, vol. 23, no. 7, pp. 762–766, 2001.
mla: Loog, M., et al. “Multiclass Linear Dimension Reduction by Weighted Pairwise
Fisher Criteria.” IEEE Transactions on Pattern Analysis and Machine Intelligence,
vol. 23, no. 7, 2001, pp. 762–66, doi:10.1109/34.935849.
short: M. Loog, R.P.W. Duin, R. Haeb-Umbach, IEEE Transactions on Pattern Analysis
and Machine Intelligence 23 (2001) 762–766.
date_created: 2019-07-12T05:29:51Z
date_updated: 2022-01-06T06:51:11Z
department:
- _id: '54'
doi: 10.1109/34.935849
intvolume: ' 23'
issue: '7'
keyword:
- approximate pairwise accuracy
- Bayes error
- Bayes methods
- error statistics
- Euclidean distance
- Fisher criterion
- linear dimension reduction
- linear discriminant analysis
- pattern classification
- statistical analysis
- statistical pattern classification
- weighting function
language:
- iso: eng
main_file_link:
- open_access: '1'
url: https://groups.uni-paderborn.de/nt/pubs/2001/LoDuHa01.pdf
oa: '1'
page: 762-766
publication: IEEE Transactions on Pattern Analysis and Machine Intelligence
status: public
title: Multiclass linear dimension reduction by weighted pairwise Fisher criteria
type: journal_article
user_id: '44006'
volume: 23
year: '2001'
...
---
_id: '11758'
abstract:
- lang: eng
text: The traditional way to find a linear solution to the feature extraction problem
is based on the maximization of the class-between scatter over the class-within
scatter (Fisher mapping). For the multi-class problem this is, however, sub-optimal
due to class conjunctions, even for the simple situation of normal distributed
classes with identical covariance matrices. We propose a novel, equally fast method,
based on nonlinear PCA. Although still sub-optimal, it may avoid the class conjunction.
The proposed method is experimentally compared with Fisher mapping and with a
neural network based approach to nonlinear PCA. It appears to outperform both
methods, the first one even in a dramatic way.
author:
- first_name: Robert P.W.
full_name: Duin, Robert P.W.
last_name: Duin
- first_name: Marco
full_name: Loog, Marco
last_name: Loog
- first_name: Reinhold
full_name: Haeb-Umbach, Reinhold
id: '242'
last_name: Haeb-Umbach
citation:
ama: 'Duin RPW, Loog M, Haeb-Umbach R. Multi-class Linear Feature Extraction by
Nonlinear PCA. In: International Conference on Pattern Recognition (ICPR 2000).
; 2000.'
apa: Duin, R. P. W., Loog, M., & Haeb-Umbach, R. (2000). Multi-class Linear
Feature Extraction by Nonlinear PCA. In International Conference on Pattern
Recognition (ICPR 2000).
bibtex: '@inproceedings{Duin_Loog_Haeb-Umbach_2000, title={Multi-class Linear Feature
Extraction by Nonlinear PCA}, booktitle={International Conference on Pattern Recognition
(ICPR 2000)}, author={Duin, Robert P.W. and Loog, Marco and Haeb-Umbach, Reinhold},
year={2000} }'
chicago: Duin, Robert P.W., Marco Loog, and Reinhold Haeb-Umbach. “Multi-Class Linear
Feature Extraction by Nonlinear PCA.” In International Conference on Pattern
Recognition (ICPR 2000), 2000.
ieee: R. P. W. Duin, M. Loog, and R. Haeb-Umbach, “Multi-class Linear Feature Extraction
by Nonlinear PCA,” in International Conference on Pattern Recognition (ICPR
2000), 2000.
mla: Duin, Robert P. W., et al. “Multi-Class Linear Feature Extraction by Nonlinear
PCA.” International Conference on Pattern Recognition (ICPR 2000), 2000.
short: 'R.P.W. Duin, M. Loog, R. Haeb-Umbach, in: International Conference on Pattern
Recognition (ICPR 2000), 2000.'
date_created: 2019-07-12T05:27:41Z
date_updated: 2022-01-06T06:51:08Z
department:
- _id: '54'
language:
- iso: eng
main_file_link:
- open_access: '1'
url: https://groups.uni-paderborn.de/nt/pubs/2000/DuLoHa2000paper.pdf
oa: '1'
publication: International Conference on Pattern Recognition (ICPR 2000)
status: public
title: Multi-class Linear Feature Extraction by Nonlinear PCA
type: conference
user_id: '44006'
year: '2000'
...
---
_id: '11779'
author:
- first_name: Reinhold
full_name: Haeb-Umbach, Reinhold
id: '242'
last_name: Haeb-Umbach
citation:
ama: 'Haeb-Umbach R. Data-driven Phonetic Regression Class Tree Estimation for MLLR
Adaptation. In: International Conference on Spoken Language Processing (ICSLP
2000). ; 2000.'
apa: Haeb-Umbach, R. (2000). Data-driven Phonetic Regression Class Tree Estimation
for MLLR Adaptation. In International Conference on Spoken Language Processing
(ICSLP 2000).
bibtex: '@inproceedings{Haeb-Umbach_2000, title={Data-driven Phonetic Regression
Class Tree Estimation for MLLR Adaptation}, booktitle={International Conference
on Spoken Language Processing (ICSLP 2000)}, author={Haeb-Umbach, Reinhold}, year={2000}
}'
chicago: Haeb-Umbach, Reinhold. “Data-Driven Phonetic Regression Class Tree Estimation
for MLLR Adaptation.” In International Conference on Spoken Language Processing
(ICSLP 2000), 2000.
ieee: R. Haeb-Umbach, “Data-driven Phonetic Regression Class Tree Estimation for
MLLR Adaptation,” in International Conference on Spoken Language Processing
(ICSLP 2000), 2000.
mla: Haeb-Umbach, Reinhold. “Data-Driven Phonetic Regression Class Tree Estimation
for MLLR Adaptation.” International Conference on Spoken Language Processing
(ICSLP 2000), 2000.
short: 'R. Haeb-Umbach, in: International Conference on Spoken Language Processing
(ICSLP 2000), 2000.'
date_created: 2019-07-12T05:28:05Z
date_updated: 2022-01-06T06:51:08Z
department:
- _id: '54'
language:
- iso: eng
main_file_link:
- open_access: '1'
url: https://groups.uni-paderborn.de/nt/pubs/2000/Ha00.pdf
oa: '1'
publication: International Conference on Spoken Language Processing (ICSLP 2000)
status: public
title: Data-driven Phonetic Regression Class Tree Estimation for MLLR Adaptation
type: conference
user_id: '44006'
year: '2000'
...
---
_id: '11869'
abstract:
- lang: eng
text: Amongst several data driven approaches for designing filters for the time
sequence of spectral parameters, the linear discriminant analysis (LDA) based
method has been proposed for automatic speech recognition. Here we apply LDA-based
filter design to cepstral features, which better match the inherent assumption
of this method that feature vector components are uncorrelated. Extensive recognition
experiments have been conducted both on the standard TIMIT phone recognition task
and on a proprietary 130-words command word task under various adverse environmental
conditions, including reverberant data with real-life room impulse responses and
data processed by acoustic echo cancellation algorithms. Significant error rate
reductions have been achieved when applying the novel long-range feature filters
compared to standard approaches employing cepstral mean normalization and delta
and delta-delta features, in particular when facing acoustic echo cancellation
scenarios and room reverberation. For example, the phone accuracy on reverberated
TIMIT data could be increased from 50.7\% to 56.0\%
author:
- first_name: M.
full_name: Lieb, M.
last_name: Lieb
- first_name: Reinhold
full_name: Haeb-Umbach, Reinhold
id: '242'
last_name: Haeb-Umbach
citation:
ama: 'Lieb M, Haeb-Umbach R. LDA derived cepstral trajectory filters in adverse
environmental conditions. In: IEEE International Conference on Acoustics, Speech,
and Signal Processing (ICASSP 2000). Vol 2. ; 2000:II1105-II1108 vol.2. doi:10.1109/ICASSP.2000.859157'
apa: Lieb, M., & Haeb-Umbach, R. (2000). LDA derived cepstral trajectory filters
in adverse environmental conditions. In IEEE International Conference on Acoustics,
Speech, and Signal Processing (ICASSP 2000) (Vol. 2, pp. II1105-II1108 vol.2).
https://doi.org/10.1109/ICASSP.2000.859157
bibtex: '@inproceedings{Lieb_Haeb-Umbach_2000, title={LDA derived cepstral trajectory
filters in adverse environmental conditions}, volume={2}, DOI={10.1109/ICASSP.2000.859157},
booktitle={IEEE International Conference on Acoustics, Speech, and Signal Processing
(ICASSP 2000)}, author={Lieb, M. and Haeb-Umbach, Reinhold}, year={2000}, pages={II1105-II1108
vol.2} }'
chicago: Lieb, M., and Reinhold Haeb-Umbach. “LDA Derived Cepstral Trajectory Filters
in Adverse Environmental Conditions.” In IEEE International Conference on Acoustics,
Speech, and Signal Processing (ICASSP 2000), 2:II1105-II1108 vol.2, 2000.
https://doi.org/10.1109/ICASSP.2000.859157.
ieee: M. Lieb and R. Haeb-Umbach, “LDA derived cepstral trajectory filters in adverse
environmental conditions,” in IEEE International Conference on Acoustics, Speech,
and Signal Processing (ICASSP 2000), 2000, vol. 2, pp. II1105-II1108 vol.2.
mla: Lieb, M., and Reinhold Haeb-Umbach. “LDA Derived Cepstral Trajectory Filters
in Adverse Environmental Conditions.” IEEE International Conference on Acoustics,
Speech, and Signal Processing (ICASSP 2000), vol. 2, 2000, pp. II1105-II1108
vol.2, doi:10.1109/ICASSP.2000.859157.
short: 'M. Lieb, R. Haeb-Umbach, in: IEEE International Conference on Acoustics,
Speech, and Signal Processing (ICASSP 2000), 2000, pp. II1105-II1108 vol.2.'
date_created: 2019-07-12T05:29:50Z
date_updated: 2022-01-06T06:51:11Z
department:
- _id: '54'
doi: 10.1109/ICASSP.2000.859157
intvolume: ' 2'
keyword:
- acoustic echo cancellation algorithms
- adverse environmental conditions
- automatic speech recognition
- cepstral analysis
- cepstral features
- cepstral mean normalization
- command word task
- delta-delta features
- delta features
- echo suppression
- error rate reductions
- feature vector components
- FIR filters
- LDA derived cepstral trajectory filters
- linear discriminant analysis
- long-range feature filters
- phone accuracy
- real-life room impulse responses
- reverberant data
- spectral parameters
- speech recognition
- standard TIMIT phone recognition task
language:
- iso: eng
main_file_link:
- open_access: '1'
url: https://groups.uni-paderborn.de/nt/pubs/2000/LiHa00.pdf
oa: '1'
page: II1105-II1108 vol.2
publication: IEEE International Conference on Acoustics, Speech, and Signal Processing
(ICASSP 2000)
status: public
title: LDA derived cepstral trajectory filters in adverse environmental conditions
type: conference
user_id: '44006'
volume: 2
year: '2000'
...
---
_id: '11871'
author:
- first_name: M.
full_name: Loog, M.
last_name: Loog
- first_name: Reinhold
full_name: Haeb-Umbach, Reinhold
id: '242'
last_name: Haeb-Umbach
citation:
ama: 'Loog M, Haeb-Umbach R. Multi-class Linear Dimension Reduction by Generalized
Fisher Criteria. In: International Conference on Spoken Language Processing
(ICSLP 2000). ; 2000.'
apa: Loog, M., & Haeb-Umbach, R. (2000). Multi-class Linear Dimension Reduction
by Generalized Fisher Criteria. In International Conference on Spoken Language
Processing (ICSLP 2000).
bibtex: '@inproceedings{Loog_Haeb-Umbach_2000, title={Multi-class Linear Dimension
Reduction by Generalized Fisher Criteria}, booktitle={International Conference
on Spoken Language Processing (ICSLP 2000)}, author={Loog, M. and Haeb-Umbach,
Reinhold}, year={2000} }'
chicago: Loog, M., and Reinhold Haeb-Umbach. “Multi-Class Linear Dimension Reduction
by Generalized Fisher Criteria.” In International Conference on Spoken Language
Processing (ICSLP 2000), 2000.
ieee: M. Loog and R. Haeb-Umbach, “Multi-class Linear Dimension Reduction by Generalized
Fisher Criteria,” in International Conference on Spoken Language Processing
(ICSLP 2000), 2000.
mla: Loog, M., and Reinhold Haeb-Umbach. “Multi-Class Linear Dimension Reduction
by Generalized Fisher Criteria.” International Conference on Spoken Language
Processing (ICSLP 2000), 2000.
short: 'M. Loog, R. Haeb-Umbach, in: International Conference on Spoken Language
Processing (ICSLP 2000), 2000.'
date_created: 2019-07-12T05:29:52Z
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/2000/LoHa00.pdf
oa: '1'
publication: International Conference on Spoken Language Processing (ICSLP 2000)
status: public
title: Multi-class Linear Dimension Reduction by Generalized Fisher Criteria
type: conference
user_id: '44006'
year: '2000'
...
---
_id: '11728'
abstract:
- lang: eng
text: This paper contains a description of the Philips/RWTH 1998 HUB4 system which
has been build in a joint e ort of Philips Research Laboratories Aachen and Aachen
University of Technology. We will focus our discussion on recent improvements
compared to the original 1997 HUB4 system and evaluate them on the HUB4'97 evaluation
data. The paper will deal with 1. a rough system overview including feature extraction,
acoustic training, audio stream segmentation, and decoding 2. log-linear interpolation
of distance-language models, 3. and the integration of various acoustic and language
models via Discriminative Model Combination (DMC). The performance of the described
system is 23% (relative) better than the performance of the 1997 Philips HUB4
system. A word error rate of 17.9% was achieved on the 1997 HUB4 evaluation set,
compared to 23.5% using the original 1997 system.
author:
- first_name: Peter
full_name: Beyerlein, Peter
last_name: Beyerlein
- first_name: Xavier L.
full_name: Aubert, Xavier L.
last_name: Aubert
- first_name: Reinhold
full_name: Haeb-Umbach, Reinhold
id: '242'
last_name: Haeb-Umbach
- first_name: Matthew J.
full_name: Harris, Matthew J.
last_name: Harris
- first_name: Dietrich
full_name: Klakow, Dietrich
last_name: Klakow
- first_name: Andreas
full_name: Wendemuth, Andreas
last_name: Wendemuth
- first_name: Sirko
full_name: Molau, Sirko
last_name: Molau
- first_name: Michael
full_name: Pitz, Michael
last_name: Pitz
- first_name: Achim
full_name: Sixtus, Achim
last_name: Sixtus
citation:
ama: 'Beyerlein P, Aubert XL, Haeb-Umbach R, et al. The Philips/RWTH system for
transcription of broadcast news. In: Eurospeech. ; 1999.'
apa: Beyerlein, P., Aubert, X. L., Haeb-Umbach, R., Harris, M. J., Klakow, D., Wendemuth,
A., … Sixtus, A. (1999). The Philips/RWTH system for transcription of broadcast
news. In Eurospeech.
bibtex: '@inproceedings{Beyerlein_Aubert_Haeb-Umbach_Harris_Klakow_Wendemuth_Molau_Pitz_Sixtus_1999,
title={The Philips/RWTH system for transcription of broadcast news}, booktitle={Eurospeech},
author={Beyerlein, Peter and Aubert, Xavier L. and Haeb-Umbach, Reinhold and Harris,
Matthew J. and Klakow, Dietrich and Wendemuth, Andreas and Molau, Sirko and Pitz,
Michael and Sixtus, Achim}, year={1999} }'
chicago: Beyerlein, Peter, Xavier L. Aubert, Reinhold Haeb-Umbach, Matthew J. Harris,
Dietrich Klakow, Andreas Wendemuth, Sirko Molau, Michael Pitz, and Achim Sixtus.
“The Philips/RWTH System for Transcription of Broadcast News.” In Eurospeech,
1999.
ieee: P. Beyerlein et al., “The Philips/RWTH system for transcription of
broadcast news,” in Eurospeech, 1999.
mla: Beyerlein, Peter, et al. “The Philips/RWTH System for Transcription of Broadcast
News.” Eurospeech, 1999.
short: 'P. Beyerlein, X.L. Aubert, R. Haeb-Umbach, M.J. Harris, D. Klakow, A. Wendemuth,
S. Molau, M. Pitz, A. Sixtus, in: Eurospeech, 1999.'
date_created: 2019-07-12T05:27:07Z
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/1999/Eurospeech_2_1999_Haeb_paper.pdf
oa: '1'
publication: Eurospeech
status: public
title: The Philips/RWTH system for transcription of broadcast news
type: conference
user_id: '44006'
year: '1999'
...
---
_id: '11729'
abstract:
- lang: eng
text: This paper contains a description of the Philips/RWTH 1998 HUB4 system which
has been build in a joint e ort of Philips Research Laboratories Aachen and Aachen
University of Technology. We will focus our discussion on recent improvements
compared to the original 1997 HUB4 system and evaluate them on the HUB4'97 evaluation
data. The paper will deal with 1. a rough system overview including feature extraction,
acoustic training, audio stream segmentation, and decoding 2. log-linear interpolation
of distance-language models, 3. and the integration of various acoustic and language
models via Discriminative Model Combination (DMC). The performance of the described
system is 23% (relative) better than the performance of the 1997 Philips HUB4
system. A word error rate of 17.9% was achieved on the 1997 HUB4 evaluation set,
compared to 23.5% using the original 1997 system.
author:
- first_name: Peter
full_name: Beyerlein, Peter
last_name: Beyerlein
- first_name: Xavier L.
full_name: Aubert, Xavier L.
last_name: Aubert
- first_name: Reinhold
full_name: Haeb-Umbach, Reinhold
id: '242'
last_name: Haeb-Umbach
- first_name: Matthew J.
full_name: Harris, Matthew J.
last_name: Harris
- first_name: Dietrich
full_name: Klakow, Dietrich
last_name: Klakow
- first_name: Andreas
full_name: Wendemuth, Andreas
last_name: Wendemuth
- first_name: Sirko
full_name: Molau, Sirko
last_name: Molau
- first_name: Michael
full_name: Pitz, Michael
last_name: Pitz
- first_name: Achim
full_name: Sixtus, Achim
last_name: Sixtus
citation:
ama: 'Beyerlein P, Aubert XL, Haeb-Umbach R, et al. The Philips/RWTH System for
Transcription of Broadcast News. In: Broadcast News Transcription and Understanding
Workshop, Washington. ; 1999.'
apa: Beyerlein, P., Aubert, X. L., Haeb-Umbach, R., Harris, M. J., Klakow, D., Wendemuth,
A., … Sixtus, A. (1999). The Philips/RWTH System for Transcription of Broadcast
News. In Broadcast News Transcription and Understanding Workshop, Washington.
bibtex: '@inproceedings{Beyerlein_Aubert_Haeb-Umbach_Harris_Klakow_Wendemuth_Molau_Pitz_Sixtus_1999,
title={The Philips/RWTH System for Transcription of Broadcast News}, booktitle={Broadcast
News Transcription and Understanding Workshop, Washington}, author={Beyerlein,
Peter and Aubert, Xavier L. and Haeb-Umbach, Reinhold and Harris, Matthew J. and
Klakow, Dietrich and Wendemuth, Andreas and Molau, Sirko and Pitz, Michael and
Sixtus, Achim}, year={1999} }'
chicago: Beyerlein, Peter, Xavier L. Aubert, Reinhold Haeb-Umbach, Matthew J. Harris,
Dietrich Klakow, Andreas Wendemuth, Sirko Molau, Michael Pitz, and Achim Sixtus.
“The Philips/RWTH System for Transcription of Broadcast News.” In Broadcast
News Transcription and Understanding Workshop, Washington, 1999.
ieee: P. Beyerlein et al., “The Philips/RWTH System for Transcription of
Broadcast News,” in Broadcast News Transcription and Understanding Workshop,
Washington, 1999.
mla: Beyerlein, Peter, et al. “The Philips/RWTH System for Transcription of Broadcast
News.” Broadcast News Transcription and Understanding Workshop, Washington,
1999.
short: 'P. Beyerlein, X.L. Aubert, R. Haeb-Umbach, M.J. Harris, D. Klakow, A. Wendemuth,
S. Molau, M. Pitz, A. Sixtus, in: Broadcast News Transcription and Understanding
Workshop, Washington, 1999.'
date_created: 2019-07-12T05:27:08Z
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/1999/Workshop_Washington_1999_Haeb_paper.pdf
oa: '1'
publication: Broadcast News Transcription and Understanding Workshop, Washington
status: public
title: The Philips/RWTH System for Transcription of Broadcast News
type: conference
user_id: '44006'
year: '1999'
...
---
_id: '11780'
abstract:
- lang: eng
text: We apply Fisher variate analysis to measure the effectiveness of speaker normalization
techniques. A trace criterion, which measures the ratio of the variations due
to different phonemes compared to variations due to different speakers, serves
as a first assessment of a feature set without the need for recognition experiments.
By using this measure and by recognition experiments we demonstrate that cepstral
mean normalization also has a speaker normalization effect, in addition to the
well-known channel normalization effect. Similarly vocal tract normalization (VTN)
is shown to remove inter-speaker variability. For VTN we show that normalization
on a per sentence basis performs better than normalization on a per speaker basis.
Recognition results are given on Wall Street Journal and Hub-4 databases
author:
- first_name: Reinhold
full_name: Haeb-Umbach, Reinhold
id: '242'
last_name: Haeb-Umbach
citation:
ama: 'Haeb-Umbach R. Investigations on inter-speaker variability in the feature
space. In: ICASSP99 Phoenix, AZ. ; 1999.'
apa: Haeb-Umbach, R. (1999). Investigations on inter-speaker variability in the
feature space. In ICASSP99 Phoenix, AZ.
bibtex: '@inproceedings{Haeb-Umbach_1999, title={Investigations on inter-speaker
variability in the feature space}, booktitle={ICASSP99 Phoenix, AZ}, author={Haeb-Umbach,
Reinhold}, year={1999} }'
chicago: Haeb-Umbach, Reinhold. “Investigations on Inter-Speaker Variability in
the Feature Space.” In ICASSP99 Phoenix, AZ, 1999.
ieee: R. Haeb-Umbach, “Investigations on inter-speaker variability in the feature
space,” in ICASSP99 Phoenix, AZ, 1999.
mla: Haeb-Umbach, Reinhold. “Investigations on Inter-Speaker Variability in the
Feature Space.” ICASSP99 Phoenix, AZ, 1999.
short: 'R. Haeb-Umbach, in: ICASSP99 Phoenix, AZ, 1999.'
date_created: 2019-07-12T05:28:07Z
date_updated: 2022-01-06T06:51:08Z
department:
- _id: '54'
language:
- iso: eng
main_file_link:
- open_access: '1'
url: https://groups.uni-paderborn.de/nt/pubs/1999/ICASSP_1999_Haeb_paper.pdf
oa: '1'
publication: ICASSP99 Phoenix, AZ
status: public
title: Investigations on inter-speaker variability in the feature space
type: conference
user_id: '44006'
year: '1999'
...
---
_id: '11791'
abstract:
- lang: eng
text: 'We examined variants of MFCC and PLP cepstral parameterisations in the context
of large vocabulary continuous speech recognition under different acous-tical
environmental conditions: Compared to MFCC, mel-frequency PLP uses a cubic root
intensity-to-loudness law, and an LPC analysis is applied to the mel-warped spectrum.
In LPC-smoothed MFCC, the only difference to MFCC is the additional LPC smoothing
of the warped spectrum. While neither technique was able to significantly outperform
the MFCC parameterisation in our setup which includes an LDA feature transformation,
feature set combination via DMC at the acoustic likelihood level and via ROVER
at the recognized word level delivered small but consistent improvements.'
author:
- first_name: Reinhold
full_name: Haeb-Umbach, Reinhold
id: '242'
last_name: Haeb-Umbach
- first_name: Marco
full_name: Loog, Marco
last_name: Loog
citation:
ama: 'Haeb-Umbach R, Loog M. An Investigation of Cepstral Parameterisations for
Large Vocabulary Speech Recognition. In: Eurospeech. ; 1999.'
apa: Haeb-Umbach, R., & Loog, M. (1999). An Investigation of Cepstral Parameterisations
for Large Vocabulary Speech Recognition. In Eurospeech.
bibtex: '@inproceedings{Haeb-Umbach_Loog_1999, title={An Investigation of Cepstral
Parameterisations for Large Vocabulary Speech Recognition}, booktitle={Eurospeech},
author={Haeb-Umbach, Reinhold and Loog, Marco}, year={1999} }'
chicago: Haeb-Umbach, Reinhold, and Marco Loog. “An Investigation of Cepstral Parameterisations
for Large Vocabulary Speech Recognition.” In Eurospeech, 1999.
ieee: R. Haeb-Umbach and M. Loog, “An Investigation of Cepstral Parameterisations
for Large Vocabulary Speech Recognition,” in Eurospeech, 1999.
mla: Haeb-Umbach, Reinhold, and Marco Loog. “An Investigation of Cepstral Parameterisations
for Large Vocabulary Speech Recognition.” Eurospeech, 1999.
short: 'R. Haeb-Umbach, M. Loog, in: Eurospeech, 1999.'
date_created: 2019-07-12T05:28:19Z
date_updated: 2022-01-06T06:51:08Z
department:
- _id: '54'
language:
- iso: eng
main_file_link:
- open_access: '1'
url: https://groups.uni-paderborn.de/nt/pubs/1999/Eurospeech_1999_Haeb_paper.pdf
oa: '1'
publication: Eurospeech
status: public
title: An Investigation of Cepstral Parameterisations for Large Vocabulary Speech
Recognition
type: conference
user_id: '44006'
year: '1999'
...
---
_id: '11805'
abstract:
- lang: eng
text: In transcription of broadcast news, dividing the signal into homogeneous segments,
and clustering together similar segments is important. Decoding a complete broadcast
news program in one chunk is technically di cult. Also, through creation of homogeneous
clusters of segments, improvement from adaptation can be increased. Two systems
of segmentation and clustering are compared. The best system used the BIC algorithm
to produce long, homogeneous segments, and a nearest neighbour bottom-up agglomerative
clustering algorithm to produce homogeneous clusters. Adaptation brought a word
error rate (WER) improvement from 23:4% to 21:0% using the automatic segmentation
and clustering, compared to an improvement from 21:8% to 20:0% using a handmade
\correct" segmentation and clustering.
author:
- first_name: Matthew J.
full_name: Harris, Matthew J.
last_name: Harris
- first_name: Xavier L.
full_name: Aubert, Xavier L.
last_name: Aubert
- first_name: Reinhold
full_name: Haeb-Umbach, Reinhold
id: '242'
last_name: Haeb-Umbach
- first_name: Peter
full_name: Beyerlein, Peter
last_name: Beyerlein
citation:
ama: 'Harris MJ, Aubert XL, Haeb-Umbach R, Beyerlein P. A study of broadcast news
audio stream segmentation and segment clustering. In: Eurospeech. ; 1999.'
apa: Harris, M. J., Aubert, X. L., Haeb-Umbach, R., & Beyerlein, P. (1999).
A study of broadcast news audio stream segmentation and segment clustering. In
Eurospeech.
bibtex: '@inproceedings{Harris_Aubert_Haeb-Umbach_Beyerlein_1999, title={A study
of broadcast news audio stream segmentation and segment clustering}, booktitle={Eurospeech},
author={Harris, Matthew J. and Aubert, Xavier L. and Haeb-Umbach, Reinhold and
Beyerlein, Peter}, year={1999} }'
chicago: Harris, Matthew J., Xavier L. Aubert, Reinhold Haeb-Umbach, and Peter Beyerlein.
“A Study of Broadcast News Audio Stream Segmentation and Segment Clustering.”
In Eurospeech, 1999.
ieee: M. J. Harris, X. L. Aubert, R. Haeb-Umbach, and P. Beyerlein, “A study of
broadcast news audio stream segmentation and segment clustering,” in Eurospeech,
1999.
mla: Harris, Matthew J., et al. “A Study of Broadcast News Audio Stream Segmentation
and Segment Clustering.” Eurospeech, 1999.
short: 'M.J. Harris, X.L. Aubert, R. Haeb-Umbach, P. Beyerlein, in: Eurospeech,
1999.'
date_created: 2019-07-12T05:28:36Z
date_updated: 2022-01-06T06:51:09Z
department:
- _id: '54'
language:
- iso: eng
main_file_link:
- open_access: '1'
url: https://groups.uni-paderborn.de/nt/pubs/1999/Eurospeech_1_1999_Haeb_paper.pdf
oa: '1'
publication: Eurospeech
status: public
title: A study of broadcast news audio stream segmentation and segment clustering
type: conference
user_id: '44006'
year: '1999'
...
---
_id: '11730'
abstract:
- lang: eng
text: In this paper the Philips Broadcast News transcription system is described.
The Broadcast News task aims at the recognition of "found" speech in radio and
television broadcasts without any additional side information (e.g. speaking style,
background conditions). The system was derived from the Philips continuous mixture
density crossword HMM system, using MFCC features and Laplacian densities. A segmentation
was performed to obtain sentence-like partitions of the broadcasts. Using data-driven
clustering, the obtained segments were grouped into clusters with similar acoustic
conditions for adaptation purposes. Gender independent word-internal and crossword
triphone models were trained on 70 hours of the HUB4 training data. No focus condition
specific training was applied. Channel and speaker normalization was done by mean
and variance normalization as well as VTN and MLLR. The transcription was produced
by an adaptive multiple pass decoder starting with phrase-bigram decoding using
word-internal triphones and finishing with a phrase-trigram decoding using MLLR-adapted
crossword models.
author:
- first_name: Peter
full_name: Beyerlein, Peter
last_name: Beyerlein
- first_name: Xavier L.
full_name: Aubert, Xavier L.
last_name: Aubert
- first_name: Reinhold
full_name: Haeb-Umbach, Reinhold
id: '242'
last_name: Haeb-Umbach
- first_name: Dietrich
full_name: Klakow, Dietrich
last_name: Klakow
- first_name: Meinhard
full_name: Ullrich, Meinhard
last_name: Ullrich
- first_name: Andreas
full_name: Wendemuth, Andreas
last_name: Wendemuth
- first_name: Patricia
full_name: Wilcox, Patricia
last_name: Wilcox
citation:
ama: 'Beyerlein P, Aubert XL, Haeb-Umbach R, et al. Automatic Transcription of English
Broadcast News. In: DARPA Broadcast News Transcription and Understanding Workshop,
Landsdowne. ; 1998.'
apa: Beyerlein, P., Aubert, X. L., Haeb-Umbach, R., Klakow, D., Ullrich, M., Wendemuth,
A., & Wilcox, P. (1998). Automatic Transcription of English Broadcast News.
In DARPA Broadcast News Transcription and Understanding Workshop, Landsdowne.
bibtex: '@inproceedings{Beyerlein_Aubert_Haeb-Umbach_Klakow_Ullrich_Wendemuth_Wilcox_1998,
title={Automatic Transcription of English Broadcast News}, booktitle={DARPA Broadcast
News Transcription and Understanding Workshop, Landsdowne}, author={Beyerlein,
Peter and Aubert, Xavier L. and Haeb-Umbach, Reinhold and Klakow, Dietrich and
Ullrich, Meinhard and Wendemuth, Andreas and Wilcox, Patricia}, year={1998} }'
chicago: Beyerlein, Peter, Xavier L. Aubert, Reinhold Haeb-Umbach, Dietrich Klakow,
Meinhard Ullrich, Andreas Wendemuth, and Patricia Wilcox. “Automatic Transcription
of English Broadcast News.” In DARPA Broadcast News Transcription and Understanding
Workshop, Landsdowne, 1998.
ieee: P. Beyerlein et al., “Automatic Transcription of English Broadcast
News,” in DARPA Broadcast News Transcription and Understanding Workshop, Landsdowne,
1998.
mla: Beyerlein, Peter, et al. “Automatic Transcription of English Broadcast News.”
DARPA Broadcast News Transcription and Understanding Workshop, Landsdowne,
1998.
short: 'P. Beyerlein, X.L. Aubert, R. Haeb-Umbach, D. Klakow, M. Ullrich, A. Wendemuth,
P. Wilcox, in: DARPA Broadcast News Transcription and Understanding Workshop,
Landsdowne, 1998.'
date_created: 2019-07-12T05:27:09Z
date_updated: 2022-01-06T06:51:08Z
department:
- _id: '54'
language:
- iso: eng
main_file_link:
- open_access: '1'
url: https://groups.uni-paderborn.de/nt/pubs/1998/Workshop_Lansdowne_1998_Haeb_paper.pdf
oa: '1'
publication: DARPA Broadcast News Transcription and Understanding Workshop, Landsdowne
status: public
title: Automatic Transcription of English Broadcast News
type: conference
user_id: '44006'
year: '1998'
...
---
_id: '11784'
abstract:
- lang: eng
text: 'In this paper we describe some characteristics of the acoustic modeling used
in the Philips continuous-speech recognition system for the DARPA Hub-4 1997 evaluation,
which are related to robustness issues. We aimed at a conceptually simple system:
We trained two model sets on 70 hours of the Hub-4 training data, one for within-word
and one for cross-word decoding. These model sets were used for both genders and
all environmental conditions. In order to be able to do so, channel normalization
(mean, variance normalization) and speaker normalization (vocal tract length normalization,
realized by an appropriate shift of the center frequencies of the mel filter bank)
have been applied, as well as adaptation techniques. MLLR-based unsupervised batch
adaptation on clusters of segments was conducted both after a first within-word
decoding and a cross-word decoding pass. The training strategy and the effects
of the various normalization and adaptation techniques will be discussed in the
paper.'
author:
- first_name: Reinhold
full_name: Haeb-Umbach, Reinhold
id: '242'
last_name: Haeb-Umbach
- first_name: Xavier L.
full_name: Aubert, Xavier L.
last_name: Aubert
- first_name: Peter
full_name: Beyerlein, Peter
last_name: Beyerlein
- first_name: Dietrich
full_name: Klakow, Dietrich
last_name: Klakow
- first_name: Meinhard
full_name: Ullrich, Meinhard
last_name: Ullrich
- first_name: Andreas
full_name: Wendemuth, Andreas
last_name: Wendemuth
- first_name: Patricia
full_name: Wilcox, Patricia
last_name: Wilcox
citation:
ama: 'Haeb-Umbach R, Aubert XL, Beyerlein P, et al. Acoustic Modeling in the Philips
Hub-4 Continuous-Speech Recognition System. In: DARPA Broadcast News Transcription
and Understanding Workshop, Landsdowne. ; 1998.'
apa: Haeb-Umbach, R., Aubert, X. L., Beyerlein, P., Klakow, D., Ullrich, M., Wendemuth,
A., & Wilcox, P. (1998). Acoustic Modeling in the Philips Hub-4 Continuous-Speech
Recognition System. In DARPA Broadcast News Transcription and Understanding
Workshop, Landsdowne.
bibtex: '@inproceedings{Haeb-Umbach_Aubert_Beyerlein_Klakow_Ullrich_Wendemuth_Wilcox_1998,
title={Acoustic Modeling in the Philips Hub-4 Continuous-Speech Recognition System},
booktitle={DARPA Broadcast News Transcription and Understanding Workshop, Landsdowne},
author={Haeb-Umbach, Reinhold and Aubert, Xavier L. and Beyerlein, Peter and Klakow,
Dietrich and Ullrich, Meinhard and Wendemuth, Andreas and Wilcox, Patricia}, year={1998}
}'
chicago: Haeb-Umbach, Reinhold, Xavier L. Aubert, Peter Beyerlein, Dietrich Klakow,
Meinhard Ullrich, Andreas Wendemuth, and Patricia Wilcox. “Acoustic Modeling in
the Philips Hub-4 Continuous-Speech Recognition System.” In DARPA Broadcast
News Transcription and Understanding Workshop, Landsdowne, 1998.
ieee: R. Haeb-Umbach et al., “Acoustic Modeling in the Philips Hub-4 Continuous-Speech
Recognition System,” in DARPA Broadcast News Transcription and Understanding
Workshop, Landsdowne, 1998.
mla: Haeb-Umbach, Reinhold, et al. “Acoustic Modeling in the Philips Hub-4 Continuous-Speech
Recognition System.” DARPA Broadcast News Transcription and Understanding Workshop,
Landsdowne, 1998.
short: 'R. Haeb-Umbach, X.L. Aubert, P. Beyerlein, D. Klakow, M. Ullrich, A. Wendemuth,
P. Wilcox, in: DARPA Broadcast News Transcription and Understanding Workshop,
Landsdowne, 1998.'
date_created: 2019-07-12T05:28:11Z
date_updated: 2022-01-06T06:51:08Z
department:
- _id: '54'
language:
- iso: eng
main_file_link:
- open_access: '1'
url: https://groups.uni-paderborn.de/nt/pubs/1998/Workshop_Landsdowne_1998_Haeb2_paper.pdf
oa: '1'
publication: DARPA Broadcast News Transcription and Understanding Workshop, Landsdowne
status: public
title: Acoustic Modeling in the Philips Hub-4 Continuous-Speech Recognition System
type: conference
user_id: '44006'
year: '1998'
...