---
_id: '10765'
author:
- first_name: Philip
full_name: H.W. Leong, Philip
last_name: H.W. Leong
- first_name: Hideharu
full_name: Amano, Hideharu
last_name: Amano
- first_name: Jason
full_name: Anderson, Jason
last_name: Anderson
- first_name: Koen
full_name: Bertels, Koen
last_name: Bertels
- first_name: Jo\~ao
full_name: M.P. Cardoso, Jo\~ao
last_name: M.P. Cardoso
- first_name: Oliver
full_name: Diessel, Oliver
last_name: Diessel
- first_name: Guy
full_name: Gogniat, Guy
last_name: Gogniat
- first_name: Mike
full_name: Hutton, Mike
last_name: Hutton
- first_name: JunKyu
full_name: Lee, JunKyu
last_name: Lee
- first_name: Wayne
full_name: Luk, Wayne
last_name: Luk
- first_name: Patrick
full_name: Lysaght, Patrick
last_name: Lysaght
- first_name: Marco
full_name: Platzner, Marco
id: '398'
last_name: Platzner
- first_name: Viktor
full_name: K. Prasanna, Viktor
last_name: K. Prasanna
- first_name: Tero
full_name: Rissa, Tero
last_name: Rissa
- first_name: Cristina
full_name: Silvano, Cristina
last_name: Silvano
- first_name: Hayden
full_name: So, Hayden
last_name: So
- first_name: Yu
full_name: Wang, Yu
last_name: Wang
citation:
ama: 'H.W. Leong P, Amano H, Anderson J, et al. Significant papers from the first
25 years of the FPL conference. In: Proceedings of the 25th International Conference
on Field Programmable Logic and Applications (FPL). Imperial College; 2015:1-3.
doi:10.1109/FPL.2015.7293747'
apa: H.W. Leong, P., Amano, H., Anderson, J., Bertels, K., M.P. Cardoso, J., Diessel,
O., … Wang, Y. (2015). Significant papers from the first 25 years of the FPL conference.
In Proceedings of the 25th International Conference on Field Programmable Logic
and Applications (FPL) (pp. 1–3). Imperial College. https://doi.org/10.1109/FPL.2015.7293747
bibtex: '@inproceedings{H.W. Leong_Amano_Anderson_Bertels_M.P. Cardoso_Diessel_Gogniat_Hutton_Lee_Luk_et
al._2015, title={Significant papers from the first 25 years of the FPL conference},
DOI={10.1109/FPL.2015.7293747},
booktitle={Proceedings of the 25th International Conference on Field Programmable
Logic and Applications (FPL)}, publisher={Imperial College}, author={H.W. Leong,
Philip and Amano, Hideharu and Anderson, Jason and Bertels, Koen and M.P. Cardoso,
Jo\~ao and Diessel, Oliver and Gogniat, Guy and Hutton, Mike and Lee, JunKyu and
Luk, Wayne and et al.}, year={2015}, pages={1–3} }'
chicago: H.W. Leong, Philip, Hideharu Amano, Jason Anderson, Koen Bertels, Jo\~ao
M.P. Cardoso, Oliver Diessel, Guy Gogniat, et al. “Significant Papers from the
First 25 Years of the FPL Conference.” In Proceedings of the 25th International
Conference on Field Programmable Logic and Applications (FPL), 1–3. Imperial
College, 2015. https://doi.org/10.1109/FPL.2015.7293747.
ieee: P. H.W. Leong et al., “Significant papers from the first 25 years of
the FPL conference,” in Proceedings of the 25th International Conference on
Field Programmable Logic and Applications (FPL), 2015, pp. 1–3.
mla: H.W. Leong, Philip, et al. “Significant Papers from the First 25 Years of the
FPL Conference.” Proceedings of the 25th International Conference on Field
Programmable Logic and Applications (FPL), Imperial College, 2015, pp. 1–3,
doi:10.1109/FPL.2015.7293747.
short: 'P. H.W. Leong, H. Amano, J. Anderson, K. Bertels, J. M.P. Cardoso, O. Diessel,
G. Gogniat, M. Hutton, J. Lee, W. Luk, P. Lysaght, M. Platzner, V. K. Prasanna,
T. Rissa, C. Silvano, H. So, Y. Wang, in: Proceedings of the 25th International
Conference on Field Programmable Logic and Applications (FPL), Imperial College,
2015, pp. 1–3.'
date_created: 2019-07-10T12:07:53Z
date_updated: 2022-01-06T06:50:50Z
department:
- _id: '78'
doi: 10.1109/FPL.2015.7293747
language:
- iso: eng
page: 1-3
publication: Proceedings of the 25th International Conference on Field Programmable
Logic and Applications (FPL)
publisher: Imperial College
status: public
title: Significant papers from the first 25 years of the FPL conference
type: conference
user_id: '3118'
year: '2015'
...
---
_id: '10767'
author:
- first_name: Ines
full_name: Ghribi, Ines
last_name: Ghribi
- first_name: Riadh
full_name: Ben Abdallah, Riadh
last_name: Ben Abdallah
- first_name: Mohamed
full_name: Khalgui, Mohamed
last_name: Khalgui
- first_name: Marco
full_name: Platzner, Marco
id: '398'
last_name: Platzner
citation:
ama: 'Ghribi I, Ben Abdallah R, Khalgui M, Platzner M. New Codesign Solutions for
Modelling and Partitioning of Probabilistic Reconfigurable Embedded Software.
In: Proceedings of the 29th European Simulation and Modelling Conference (ESM).
; 2015.'
apa: Ghribi, I., Ben Abdallah, R., Khalgui, M., & Platzner, M. (2015). New Codesign
Solutions for Modelling and Partitioning of Probabilistic Reconfigurable Embedded
Software. In Proceedings of the 29th European Simulation and Modelling Conference
(ESM).
bibtex: '@inproceedings{Ghribi_Ben Abdallah_Khalgui_Platzner_2015, title={New Codesign
Solutions for Modelling and Partitioning of Probabilistic Reconfigurable Embedded
Software}, booktitle={Proceedings of the 29th European Simulation and Modelling
Conference (ESM)}, author={Ghribi, Ines and Ben Abdallah, Riadh and Khalgui, Mohamed
and Platzner, Marco}, year={2015} }'
chicago: Ghribi, Ines, Riadh Ben Abdallah, Mohamed Khalgui, and Marco Platzner.
“New Codesign Solutions for Modelling and Partitioning of Probabilistic Reconfigurable
Embedded Software.” In Proceedings of the 29th European Simulation and Modelling
Conference (ESM), 2015.
ieee: I. Ghribi, R. Ben Abdallah, M. Khalgui, and M. Platzner, “New Codesign Solutions
for Modelling and Partitioning of Probabilistic Reconfigurable Embedded Software,”
in Proceedings of the 29th European Simulation and Modelling Conference (ESM),
2015.
mla: Ghribi, Ines, et al. “New Codesign Solutions for Modelling and Partitioning
of Probabilistic Reconfigurable Embedded Software.” Proceedings of the 29th
European Simulation and Modelling Conference (ESM), 2015.
short: 'I. Ghribi, R. Ben Abdallah, M. Khalgui, M. Platzner, in: Proceedings of
the 29th European Simulation and Modelling Conference (ESM), 2015.'
date_created: 2019-07-10T12:07:55Z
date_updated: 2022-01-06T06:50:50Z
department:
- _id: '78'
language:
- iso: eng
publication: Proceedings of the 29th European Simulation and Modelling Conference
(ESM)
status: public
title: New Codesign Solutions for Modelling and Partitioning of Probabilistic Reconfigurable
Embedded Software
type: conference
user_id: '3118'
year: '2015'
...
---
_id: '10770'
author:
- first_name: Hassan
full_name: Ghasemzadeh Mohammadi, Hassan
id: '61186'
last_name: Ghasemzadeh Mohammadi
- first_name: Pierre-Emmanuel
full_name: Gaillardon, Pierre-Emmanuel
last_name: Gaillardon
- first_name: Giovanni
full_name: De Micheli, Giovanni
last_name: De Micheli
citation:
ama: Ghasemzadeh Mohammadi H, Gaillardon P-E, De Micheli G. From Defect Analysis
to Gate-Level Fault Modeling of Controllable-Polarity Silicon Nanowires. IEEE
Transactions on Nanotechnology. 2015;14(6):1117-1126. doi:10.1109/TNANO.2015.2482359
apa: Ghasemzadeh Mohammadi, H., Gaillardon, P.-E., & De Micheli, G. (2015).
From Defect Analysis to Gate-Level Fault Modeling of Controllable-Polarity Silicon
Nanowires. IEEE Transactions on Nanotechnology, 14(6), 1117–1126.
https://doi.org/10.1109/TNANO.2015.2482359
bibtex: '@article{Ghasemzadeh Mohammadi_Gaillardon_De Micheli_2015, title={From
Defect Analysis to Gate-Level Fault Modeling of Controllable-Polarity Silicon
Nanowires}, volume={14}, DOI={10.1109/TNANO.2015.2482359},
number={6}, journal={IEEE Transactions on Nanotechnology}, publisher={IEEE}, author={Ghasemzadeh
Mohammadi, Hassan and Gaillardon, Pierre-Emmanuel and De Micheli, Giovanni}, year={2015},
pages={1117–1126} }'
chicago: 'Ghasemzadeh Mohammadi, Hassan, Pierre-Emmanuel Gaillardon, and Giovanni
De Micheli. “From Defect Analysis to Gate-Level Fault Modeling of Controllable-Polarity
Silicon Nanowires.” IEEE Transactions on Nanotechnology 14, no. 6 (2015):
1117–26. https://doi.org/10.1109/TNANO.2015.2482359.'
ieee: H. Ghasemzadeh Mohammadi, P.-E. Gaillardon, and G. De Micheli, “From Defect
Analysis to Gate-Level Fault Modeling of Controllable-Polarity Silicon Nanowires,”
IEEE Transactions on Nanotechnology, vol. 14, no. 6, pp. 1117–1126, 2015.
mla: Ghasemzadeh Mohammadi, Hassan, et al. “From Defect Analysis to Gate-Level Fault
Modeling of Controllable-Polarity Silicon Nanowires.” IEEE Transactions on
Nanotechnology, vol. 14, no. 6, IEEE, 2015, pp. 1117–26, doi:10.1109/TNANO.2015.2482359.
short: H. Ghasemzadeh Mohammadi, P.-E. Gaillardon, G. De Micheli, IEEE Transactions
on Nanotechnology 14 (2015) 1117–1126.
date_created: 2019-07-10T12:08:15Z
date_updated: 2022-01-06T06:50:50Z
department:
- _id: '78'
doi: 10.1109/TNANO.2015.2482359
extern: '1'
intvolume: ' 14'
issue: '6'
language:
- iso: eng
page: 1117-1126
publication: IEEE Transactions on Nanotechnology
publisher: IEEE
status: public
title: From Defect Analysis to Gate-Level Fault Modeling of Controllable-Polarity
Silicon Nanowires
type: journal_article
user_id: '3118'
volume: 14
year: '2015'
...
---
_id: '10771'
author:
- first_name: Hassan
full_name: Ghasemzadeh Mohammadi, Hassan
id: '61186'
last_name: Ghasemzadeh Mohammadi
- first_name: Pierre-Emmanuel
full_name: Gaillardon, Pierre-Emmanuel
last_name: Gaillardon
- first_name: Jian
full_name: Zhang, Jian
last_name: Zhang
- first_name: Giovanni
full_name: De Micheli, Giovanni
last_name: De Micheli
- first_name: Eduardo
full_name: Sanchez, Eduardo
last_name: Sanchez
- first_name: Matteo Sonza
full_name: Reorda, Matteo Sonza
last_name: Reorda
citation:
ama: 'Ghasemzadeh Mohammadi H, Gaillardon P-E, Zhang J, De Micheli G, Sanchez E,
Reorda MS. On the design of a fault tolerant ripple-carry adder with controllable-polarity
transistors. In: 2015 IEEE Computer Society Annual Symposium on VLSI. IEEE;
2015:491-496. doi:10.1109/ISVLSI.2015.13'
apa: Ghasemzadeh Mohammadi, H., Gaillardon, P.-E., Zhang, J., De Micheli, G., Sanchez,
E., & Reorda, M. S. (2015). On the design of a fault tolerant ripple-carry
adder with controllable-polarity transistors. In 2015 IEEE Computer Society
Annual Symposium on VLSI (pp. 491–496). IEEE. https://doi.org/10.1109/ISVLSI.2015.13
bibtex: '@inproceedings{Ghasemzadeh Mohammadi_Gaillardon_Zhang_De Micheli_Sanchez_Reorda_2015,
title={On the design of a fault tolerant ripple-carry adder with controllable-polarity
transistors}, DOI={10.1109/ISVLSI.2015.13},
booktitle={2015 IEEE Computer Society Annual Symposium on VLSI}, publisher={IEEE},
author={Ghasemzadeh Mohammadi, Hassan and Gaillardon, Pierre-Emmanuel and Zhang,
Jian and De Micheli, Giovanni and Sanchez, Eduardo and Reorda, Matteo Sonza},
year={2015}, pages={491–496} }'
chicago: Ghasemzadeh Mohammadi, Hassan, Pierre-Emmanuel Gaillardon, Jian Zhang,
Giovanni De Micheli, Eduardo Sanchez, and Matteo Sonza Reorda. “On the Design
of a Fault Tolerant Ripple-Carry Adder with Controllable-Polarity Transistors.”
In 2015 IEEE Computer Society Annual Symposium on VLSI, 491–96. IEEE, 2015.
https://doi.org/10.1109/ISVLSI.2015.13.
ieee: H. Ghasemzadeh Mohammadi, P.-E. Gaillardon, J. Zhang, G. De Micheli, E. Sanchez,
and M. S. Reorda, “On the design of a fault tolerant ripple-carry adder with controllable-polarity
transistors,” in 2015 IEEE Computer Society Annual Symposium on VLSI, 2015,
pp. 491–496.
mla: Ghasemzadeh Mohammadi, Hassan, et al. “On the Design of a Fault Tolerant Ripple-Carry
Adder with Controllable-Polarity Transistors.” 2015 IEEE Computer Society Annual
Symposium on VLSI, IEEE, 2015, pp. 491–96, doi:10.1109/ISVLSI.2015.13.
short: 'H. Ghasemzadeh Mohammadi, P.-E. Gaillardon, J. Zhang, G. De Micheli, E.
Sanchez, M.S. Reorda, in: 2015 IEEE Computer Society Annual Symposium on VLSI,
IEEE, 2015, pp. 491–496.'
date_created: 2019-07-10T12:08:16Z
date_updated: 2022-01-06T06:50:50Z
department:
- _id: '78'
doi: 10.1109/ISVLSI.2015.13
extern: '1'
language:
- iso: eng
page: 491-496
publication: 2015 IEEE Computer Society Annual Symposium on VLSI
publisher: IEEE
status: public
title: On the design of a fault tolerant ripple-carry adder with controllable-polarity
transistors
type: conference
user_id: '3118'
year: '2015'
...
---
_id: '10772'
author:
- first_name: Hassan
full_name: Ghasemzadeh Mohammadi, Hassan
id: '61186'
last_name: Ghasemzadeh Mohammadi
- first_name: Pierre-Emmanuel
full_name: Gaillardon, Pierre-Emmanuel
last_name: Gaillardon
- first_name: Giovanni
full_name: De Micheli, Giovanni
last_name: De Micheli
citation:
ama: 'Ghasemzadeh Mohammadi H, Gaillardon P-E, De Micheli G. Fault modeling in controllable
polarity silicon nanowire circuits. In: Proceedings of the 2015 Design, Automation
& Test in Europe Conference \& Exhibition. EDA Consortium; 2015:453-458.
doi:10.7873/DATE.2015.0428'
apa: Ghasemzadeh Mohammadi, H., Gaillardon, P.-E., & De Micheli, G. (2015).
Fault modeling in controllable polarity silicon nanowire circuits. In Proceedings
of the 2015 Design, Automation & Test in Europe Conference \& Exhibition
(pp. 453–458). EDA Consortium. https://doi.org/10.7873/DATE.2015.0428
bibtex: '@inproceedings{Ghasemzadeh Mohammadi_Gaillardon_De Micheli_2015, title={Fault
modeling in controllable polarity silicon nanowire circuits}, DOI={10.7873/DATE.2015.0428},
booktitle={Proceedings of the 2015 Design, Automation & Test in Europe Conference
\& Exhibition}, publisher={EDA Consortium}, author={Ghasemzadeh Mohammadi,
Hassan and Gaillardon, Pierre-Emmanuel and De Micheli, Giovanni}, year={2015},
pages={453–458} }'
chicago: Ghasemzadeh Mohammadi, Hassan, Pierre-Emmanuel Gaillardon, and Giovanni
De Micheli. “Fault Modeling in Controllable Polarity Silicon Nanowire Circuits.”
In Proceedings of the 2015 Design, Automation & Test in Europe Conference
\& Exhibition, 453–58. EDA Consortium, 2015. https://doi.org/10.7873/DATE.2015.0428.
ieee: H. Ghasemzadeh Mohammadi, P.-E. Gaillardon, and G. De Micheli, “Fault modeling
in controllable polarity silicon nanowire circuits,” in Proceedings of the
2015 Design, Automation & Test in Europe Conference \& Exhibition,
2015, pp. 453–458.
mla: Ghasemzadeh Mohammadi, Hassan, et al. “Fault Modeling in Controllable Polarity
Silicon Nanowire Circuits.” Proceedings of the 2015 Design, Automation &
Test in Europe Conference \& Exhibition, EDA Consortium, 2015, pp. 453–58,
doi:10.7873/DATE.2015.0428.
short: 'H. Ghasemzadeh Mohammadi, P.-E. Gaillardon, G. De Micheli, in: Proceedings
of the 2015 Design, Automation & Test in Europe Conference \& Exhibition,
EDA Consortium, 2015, pp. 453–458.'
date_created: 2019-07-10T12:08:17Z
date_updated: 2022-01-06T06:50:50Z
department:
- _id: '78'
doi: 10.7873/DATE.2015.0428
extern: '1'
language:
- iso: eng
page: 453-458
publication: Proceedings of the 2015 Design, Automation & Test in Europe Conference
\& Exhibition
publisher: EDA Consortium
status: public
title: Fault modeling in controllable polarity silicon nanowire circuits
type: conference
user_id: '3118'
year: '2015'
...
---
_id: '10779'
author:
- first_name: Zakarya
full_name: Guettatfi, Zakarya
last_name: Guettatfi
- first_name: Omar
full_name: Kermia, Omar
last_name: Kermia
- first_name: Abdelhakim
full_name: Khouas, Abdelhakim
last_name: Khouas
citation:
ama: 'Guettatfi Z, Kermia O, Khouas A. Over effective hard real-time hardware tasks
scheduling and allocation. In: 25th International Conference on Field Programmable
Logic and Applications (FPL). Imperial College; 2015. doi:10.1109/FPL.2015.7293994'
apa: Guettatfi, Z., Kermia, O., & Khouas, A. (2015). Over effective hard real-time
hardware tasks scheduling and allocation. In 25th International Conference
on Field Programmable Logic and Applications (FPL). Imperial College. https://doi.org/10.1109/FPL.2015.7293994
bibtex: '@inproceedings{Guettatfi_Kermia_Khouas_2015, title={Over effective hard
real-time hardware tasks scheduling and allocation}, DOI={10.1109/FPL.2015.7293994},
booktitle={25th International Conference on Field Programmable Logic and Applications
(FPL)}, publisher={Imperial College}, author={Guettatfi, Zakarya and Kermia, Omar
and Khouas, Abdelhakim}, year={2015} }'
chicago: Guettatfi, Zakarya, Omar Kermia, and Abdelhakim Khouas. “Over Effective
Hard Real-Time Hardware Tasks Scheduling and Allocation.” In 25th International
Conference on Field Programmable Logic and Applications (FPL). Imperial College,
2015. https://doi.org/10.1109/FPL.2015.7293994.
ieee: Z. Guettatfi, O. Kermia, and A. Khouas, “Over effective hard real-time hardware
tasks scheduling and allocation,” in 25th International Conference on Field
Programmable Logic and Applications (FPL), 2015.
mla: Guettatfi, Zakarya, et al. “Over Effective Hard Real-Time Hardware Tasks Scheduling
and Allocation.” 25th International Conference on Field Programmable Logic
and Applications (FPL), Imperial College, 2015, doi:10.1109/FPL.2015.7293994.
short: 'Z. Guettatfi, O. Kermia, A. Khouas, in: 25th International Conference on
Field Programmable Logic and Applications (FPL), Imperial College, 2015.'
date_created: 2019-07-10T12:11:36Z
date_updated: 2022-01-06T06:50:50Z
department:
- _id: '78'
doi: 10.1109/FPL.2015.7293994
extern: '1'
keyword:
- embedded systems
- field programmable gate arrays
- operating systems (computers)
- scheduling
- μC/OS-II
- FPGAs
- OS foundation
- SafeRTOS
- Xenomai
- chip utilization ration
- complex time constraints
- embedded systems
- hard real-time hardware task allocation
- hard real-time hardware task scheduling
- hardware-software real-time operating systems
- partially reconfigurable field-programmable gate arrays
- resource constraints
- safety-critical RTOS
- Field programmable gate arrays
- Hardware
- Job shop scheduling
- Real-time systems
- Shape
- Software
language:
- iso: eng
publication: 25th International Conference on Field Programmable Logic and Applications
(FPL)
publication_identifier:
issn:
- 1946-147X
publisher: Imperial College
status: public
title: Over effective hard real-time hardware tasks scheduling and allocation
type: conference
user_id: '398'
year: '2015'
...
---
_id: '11739'
abstract:
- lang: eng
text: Noise tracking is an important component of speech enhancement algorithms.
Of the many noise trackers proposed, Minimum Statistics (MS) is a particularly
popular one due to its simple parameterization and at the same time excellent
performance. In this paper we propose to further reduce the number of MS parameters
by giving an alternative derivation of an optimal smoothing constant. At the same
time the noise tracking performance is improved as is demonstrated by experiments
employing speech degraded by various noise types and at different SNR values.
author:
- first_name: Aleksej
full_name: Chinaev, Aleksej
last_name: Chinaev
- first_name: Reinhold
full_name: Haeb-Umbach, Reinhold
id: '242'
last_name: Haeb-Umbach
citation:
ama: 'Chinaev A, Haeb-Umbach R. On Optimal Smoothing in Minimum Statistics Based
Noise Tracking. In: Interspeech 2015. ; 2015:1785-1789.'
apa: Chinaev, A., & Haeb-Umbach, R. (2015). On Optimal Smoothing in Minimum
Statistics Based Noise Tracking. In Interspeech 2015 (pp. 1785–1789).
bibtex: '@inproceedings{Chinaev_Haeb-Umbach_2015, title={On Optimal Smoothing in
Minimum Statistics Based Noise Tracking}, booktitle={Interspeech 2015}, author={Chinaev,
Aleksej and Haeb-Umbach, Reinhold}, year={2015}, pages={1785–1789} }'
chicago: Chinaev, Aleksej, and Reinhold Haeb-Umbach. “On Optimal Smoothing in Minimum
Statistics Based Noise Tracking.” In Interspeech 2015, 1785–89, 2015.
ieee: A. Chinaev and R. Haeb-Umbach, “On Optimal Smoothing in Minimum Statistics
Based Noise Tracking,” in Interspeech 2015, 2015, pp. 1785–1789.
mla: Chinaev, Aleksej, and Reinhold Haeb-Umbach. “On Optimal Smoothing in Minimum
Statistics Based Noise Tracking.” Interspeech 2015, 2015, pp. 1785–89.
short: 'A. Chinaev, R. Haeb-Umbach, in: Interspeech 2015, 2015, pp. 1785–1789.'
date_created: 2019-07-12T05:27:19Z
date_updated: 2022-01-06T06:51:08Z
department:
- _id: '54'
keyword:
- speech enhancement
- noise tracking
- optimal smoothing
language:
- iso: eng
main_file_link:
- open_access: '1'
url: https://groups.uni-paderborn.de/nt/pubs/2015/ChHa15.pdf
oa: '1'
page: 1785-1789
publication: Interspeech 2015
related_material:
link:
- description: Poster
relation: supplementary_material
url: https://groups.uni-paderborn.de/nt/pubs/2015/ChHa15_Poster.pdf
status: public
title: On Optimal Smoothing in Minimum Statistics Based Noise Tracking
type: conference
user_id: '44006'
year: '2015'
...
---
_id: '11748'
abstract:
- lang: eng
text: We present a semantic analysis technique for spoken input using Markov Logic
Networks (MLNs). MLNs combine graphical models with first-order logic. They areparticularly
suitable for providing inference in the presence of inconsistent and incomplete
data, which are typical of an automatic speech recognizer's (ASR) output in the
presence of degraded speech. The target application is a speech interface to a
home automation system to be operated by people with speech impairments, where
the ASR output is particularly noisy. In order to cater for dysarthric speech
with non-canonical phoneme realizations, acoustic representations of the input
speech are learned in an unsupervised fashion. While training data transcripts
are not required for the acoustic model training, the MLN training requires supervision,
however, at a rather loose and abstract level. Results on two databases, one of
them for dysarthric speech, show that MLN-based semantic analysis clearly outperforms
baseline approaches employing non-negative matrix factorization, multinomial naive
Bayes models, or support vector machines.
author:
- first_name: Vladimir
full_name: Despotovic, Vladimir
last_name: Despotovic
- first_name: Oliver
full_name: Walter, Oliver
last_name: Walter
- first_name: Reinhold
full_name: Haeb-Umbach, Reinhold
id: '242'
last_name: Haeb-Umbach
citation:
ama: 'Despotovic V, Walter O, Haeb-Umbach R. Semantic Analysis of Spoken Input using
Markov Logic Networks. In: INTERSPEECH 2015. ; 2015.'
apa: Despotovic, V., Walter, O., & Haeb-Umbach, R. (2015). Semantic Analysis
of Spoken Input using Markov Logic Networks. In INTERSPEECH 2015.
bibtex: '@inproceedings{Despotovic_Walter_Haeb-Umbach_2015, title={Semantic Analysis
of Spoken Input using Markov Logic Networks}, booktitle={INTERSPEECH 2015}, author={Despotovic,
Vladimir and Walter, Oliver and Haeb-Umbach, Reinhold}, year={2015} }'
chicago: Despotovic, Vladimir, Oliver Walter, and Reinhold Haeb-Umbach. “Semantic
Analysis of Spoken Input Using Markov Logic Networks.” In INTERSPEECH 2015,
2015.
ieee: V. Despotovic, O. Walter, and R. Haeb-Umbach, “Semantic Analysis of Spoken
Input using Markov Logic Networks,” in INTERSPEECH 2015, 2015.
mla: Despotovic, Vladimir, et al. “Semantic Analysis of Spoken Input Using Markov
Logic Networks.” INTERSPEECH 2015, 2015.
short: 'V. Despotovic, O. Walter, R. Haeb-Umbach, in: INTERSPEECH 2015, 2015.'
date_created: 2019-07-12T05:27:30Z
date_updated: 2022-01-06T06:51:08Z
department:
- _id: '54'
language:
- iso: eng
main_file_link:
- open_access: '1'
url: https://groups.uni-paderborn.de/nt/pubs/2015/DeWaHa.pdf
oa: '1'
publication: INTERSPEECH 2015
related_material:
link:
- description: Poster
relation: supplementary_material
url: https://groups.uni-paderborn.de/nt/pubs/2015/DeWaHa_Poster.pdf
status: public
title: Semantic Analysis of Spoken Input using Markov Logic Networks
type: conference
user_id: '44006'
year: '2015'
...
---
_id: '11755'
abstract:
- lang: eng
text: This contribution presents a Direction of Arrival (DoA) estimation algorithm
based on the complex Watson distribution to incorporate both phase and level differences
of captured micro- phone array signals. The derived algorithm is reviewed in the
context of the Generalized State Coherence Transform (GSCT) on the one hand and
a kernel density estimation method on the other hand. A thorough simulative evaluation
yields insight into parameter selection and provides details on the performance
for both directional and omni-directional microphones. A comparison to the well
known Steered Response Power with Phase Transform (SRP-PHAT) algorithm and a state
of the art DoA estimator which explicitly accounts for aliasing, shows in particular
the advantages of presented algorithm if inter-sensor level differences are indicative
of the DoA, as with directional microphones.
author:
- first_name: Lukas
full_name: Drude, Lukas
id: '11213'
last_name: Drude
- first_name: Florian
full_name: Jacob, Florian
last_name: Jacob
- first_name: Reinhold
full_name: Haeb-Umbach, Reinhold
id: '242'
last_name: Haeb-Umbach
citation:
ama: 'Drude L, Jacob F, Haeb-Umbach R. DOA-Estimation based on a Complex Watson
Kernel Method. In: 23th European Signal Processing Conference (EUSIPCO 2015).
; 2015.'
apa: Drude, L., Jacob, F., & Haeb-Umbach, R. (2015). DOA-Estimation based on
a Complex Watson Kernel Method. In 23th European Signal Processing Conference
(EUSIPCO 2015).
bibtex: '@inproceedings{Drude_Jacob_Haeb-Umbach_2015, title={DOA-Estimation based
on a Complex Watson Kernel Method}, booktitle={23th European Signal Processing
Conference (EUSIPCO 2015)}, author={Drude, Lukas and Jacob, Florian and Haeb-Umbach,
Reinhold}, year={2015} }'
chicago: Drude, Lukas, Florian Jacob, and Reinhold Haeb-Umbach. “DOA-Estimation
Based on a Complex Watson Kernel Method.” In 23th European Signal Processing
Conference (EUSIPCO 2015), 2015.
ieee: L. Drude, F. Jacob, and R. Haeb-Umbach, “DOA-Estimation based on a Complex
Watson Kernel Method,” in 23th European Signal Processing Conference (EUSIPCO
2015), 2015.
mla: Drude, Lukas, et al. “DOA-Estimation Based on a Complex Watson Kernel Method.”
23th European Signal Processing Conference (EUSIPCO 2015), 2015.
short: 'L. Drude, F. Jacob, R. Haeb-Umbach, in: 23th European Signal Processing
Conference (EUSIPCO 2015), 2015.'
date_created: 2019-07-12T05:27:38Z
date_updated: 2022-01-06T06:51:08Z
department:
- _id: '54'
language:
- iso: eng
main_file_link:
- open_access: '1'
url: https://groups.uni-paderborn.de/nt/pubs/2015/DrJaHa15.pdf
oa: '1'
publication: 23th European Signal Processing Conference (EUSIPCO 2015)
related_material:
link:
- description: Presentation
relation: supplementary_material
url: https://groups.uni-paderborn.de/nt/pubs/2015/DrJaHa15_Presentation.pdf
status: public
title: DOA-Estimation based on a Complex Watson Kernel Method
type: conference
user_id: '44006'
year: '2015'
...
---
_id: '11810'
author:
- first_name: Jahn
full_name: Heymann, Jahn
id: '9168'
last_name: Heymann
- first_name: Lukas
full_name: Drude, Lukas
id: '11213'
last_name: Drude
- first_name: Aleksej
full_name: Chinaev, Aleksej
last_name: Chinaev
- first_name: Reinhold
full_name: Haeb-Umbach, Reinhold
id: '242'
last_name: Haeb-Umbach
citation:
ama: 'Heymann J, Drude L, Chinaev A, Haeb-Umbach R. BLSTM supported GEV Beamformer
Front-End for the 3RD CHiME Challenge. In: Automatic Speech Recognition and
Understanding Workshop (ASRU 2015). ; 2015.'
apa: Heymann, J., Drude, L., Chinaev, A., & Haeb-Umbach, R. (2015). BLSTM supported
GEV Beamformer Front-End for the 3RD CHiME Challenge. In Automatic Speech Recognition
and Understanding Workshop (ASRU 2015).
bibtex: '@inproceedings{Heymann_Drude_Chinaev_Haeb-Umbach_2015, title={BLSTM supported
GEV Beamformer Front-End for the 3RD CHiME Challenge}, booktitle={Automatic Speech
Recognition and Understanding Workshop (ASRU 2015)}, author={Heymann, Jahn and
Drude, Lukas and Chinaev, Aleksej and Haeb-Umbach, Reinhold}, year={2015} }'
chicago: Heymann, Jahn, Lukas Drude, Aleksej Chinaev, and Reinhold Haeb-Umbach.
“BLSTM Supported GEV Beamformer Front-End for the 3RD CHiME Challenge.” In Automatic
Speech Recognition and Understanding Workshop (ASRU 2015), 2015.
ieee: J. Heymann, L. Drude, A. Chinaev, and R. Haeb-Umbach, “BLSTM supported GEV
Beamformer Front-End for the 3RD CHiME Challenge,” in Automatic Speech Recognition
and Understanding Workshop (ASRU 2015), 2015.
mla: Heymann, Jahn, et al. “BLSTM Supported GEV Beamformer Front-End for the 3RD
CHiME Challenge.” Automatic Speech Recognition and Understanding Workshop (ASRU
2015), 2015.
short: 'J. Heymann, L. Drude, A. Chinaev, R. Haeb-Umbach, in: Automatic Speech Recognition
and Understanding Workshop (ASRU 2015), 2015.'
date_created: 2019-07-12T05:28:41Z
date_updated: 2022-01-06T06:51:09Z
department:
- _id: '54'
language:
- iso: eng
publication: Automatic Speech Recognition and Understanding Workshop (ASRU 2015)
status: public
title: BLSTM supported GEV Beamformer Front-End for the 3RD CHiME Challenge
type: conference
user_id: '44006'
year: '2015'
...
---
_id: '11813'
abstract:
- lang: eng
text: 'The parametric Bayesian Feature Enhancement (BFE) and a datadriven Denoising
Autoencoder (DA) both bring performance gains in severe single-channel speech
recognition conditions. The first can be adjusted to different conditions by an
appropriate parameter setting, while the latter needs to be trained on conditions
similar to the ones expected at decoding time, making it vulnerable to a mismatch
between training and test conditions. We use a DNN backend and study reverberant
ASR under three types of mismatch conditions: different room reverberation times,
different speaker to microphone distances and the difference between artificially
reverberated data and the recordings in a reverberant environment. We show that
for these mismatch conditions BFE can provide the targets for a DA. This unsupervised
adaptation provides a performance gain over the direct use of BFE and even enables
to compensate for the mismatch of real and simulated reverberant data.'
author:
- first_name: Jahn
full_name: Heymann, Jahn
id: '9168'
last_name: Heymann
- first_name: Reinhold
full_name: Haeb-Umbach, Reinhold
id: '242'
last_name: Haeb-Umbach
- first_name: P.
full_name: Golik, P.
last_name: Golik
- first_name: R.
full_name: Schlueter, R.
last_name: Schlueter
citation:
ama: 'Heymann J, Haeb-Umbach R, Golik P, Schlueter R. Unsupervised adaptation of
a denoising autoencoder by Bayesian Feature Enhancement for reverberant asr under
mismatch conditions. In: Acoustics, Speech and Signal Processing (ICASSP),
2015 IEEE International Conference On. ; 2015:5053-5057. doi:10.1109/ICASSP.2015.7178933'
apa: Heymann, J., Haeb-Umbach, R., Golik, P., & Schlueter, R. (2015). Unsupervised
adaptation of a denoising autoencoder by Bayesian Feature Enhancement for reverberant
asr under mismatch conditions. In Acoustics, Speech and Signal Processing (ICASSP),
2015 IEEE International Conference on (pp. 5053–5057). https://doi.org/10.1109/ICASSP.2015.7178933
bibtex: '@inproceedings{Heymann_Haeb-Umbach_Golik_Schlueter_2015, title={Unsupervised
adaptation of a denoising autoencoder by Bayesian Feature Enhancement for reverberant
asr under mismatch conditions}, DOI={10.1109/ICASSP.2015.7178933},
booktitle={Acoustics, Speech and Signal Processing (ICASSP), 2015 IEEE International
Conference on}, author={Heymann, Jahn and Haeb-Umbach, Reinhold and Golik, P.
and Schlueter, R.}, year={2015}, pages={5053–5057} }'
chicago: Heymann, Jahn, Reinhold Haeb-Umbach, P. Golik, and R. Schlueter. “Unsupervised
Adaptation of a Denoising Autoencoder by Bayesian Feature Enhancement for Reverberant
Asr under Mismatch Conditions.” In Acoustics, Speech and Signal Processing
(ICASSP), 2015 IEEE International Conference On, 5053–57, 2015. https://doi.org/10.1109/ICASSP.2015.7178933.
ieee: J. Heymann, R. Haeb-Umbach, P. Golik, and R. Schlueter, “Unsupervised adaptation
of a denoising autoencoder by Bayesian Feature Enhancement for reverberant asr
under mismatch conditions,” in Acoustics, Speech and Signal Processing (ICASSP),
2015 IEEE International Conference on, 2015, pp. 5053–5057.
mla: Heymann, Jahn, et al. “Unsupervised Adaptation of a Denoising Autoencoder by
Bayesian Feature Enhancement for Reverberant Asr under Mismatch Conditions.” Acoustics,
Speech and Signal Processing (ICASSP), 2015 IEEE International Conference On,
2015, pp. 5053–57, doi:10.1109/ICASSP.2015.7178933.
short: 'J. Heymann, R. Haeb-Umbach, P. Golik, R. Schlueter, in: Acoustics, Speech
and Signal Processing (ICASSP), 2015 IEEE International Conference On, 2015, pp.
5053–5057.'
date_created: 2019-07-12T05:28:45Z
date_updated: 2022-01-06T06:51:09Z
department:
- _id: '54'
doi: 10.1109/ICASSP.2015.7178933
keyword:
- codecs
- signal denoising
- speech recognition
- Bayesian feature enhancement
- denoising autoencoder
- reverberant ASR
- single-channel speech recognition
- speaker to microphone distances
- unsupervised adaptation
- Adaptation models
- Noise reduction
- Reverberation
- Speech
- Speech recognition
- Training
- deep neuronal networks
- denoising autoencoder
- feature enhancement
- robust speech recognition
language:
- iso: eng
main_file_link:
- open_access: '1'
url: https://groups.uni-paderborn.de/nt/pubs/2015/hey_icassp_2015.pdf
oa: '1'
page: 5053-5057
publication: Acoustics, Speech and Signal Processing (ICASSP), 2015 IEEE International
Conference on
status: public
title: Unsupervised adaptation of a denoising autoencoder by Bayesian Feature Enhancement
for reverberant asr under mismatch conditions
type: conference
user_id: '44006'
year: '2015'
...
---
_id: '11830'
abstract:
- lang: eng
text: Joint audio-visual speaker tracking requires that the locations of microphones
and cameras are known and that they are given in a common coordinate system. Sensor
self-localization algorithms, however, are usually separately developed for either
the acoustic or the visual modality and return their positions in a modality specific
coordinate system, often with an unknown rotation, scaling and translation between
the two. In this paper we propose two techniques to determine the positions of
acoustic sensors in a common coordinate system, based on audio-visual correlates,
i.e., events that are localized by both, microphones and cameras separately. The
first approach maps the output of an acoustic self-calibration algorithm by estimating
rotation, scale and translation to the visual coordinate system, while the second
solves a joint system of equations with acoustic and visual directions of arrival
as input. The evaluation of the two strategies reveals that joint calibration
outperforms the mapping approach and achieves an overall calibration error of
0.20m even in reverberant environments.
author:
- first_name: Florian
full_name: Jacob, Florian
last_name: Jacob
- first_name: Reinhold
full_name: Haeb-Umbach, Reinhold
id: '242'
last_name: Haeb-Umbach
citation:
ama: Jacob F, Haeb-Umbach R. Absolute Geometry Calibration of Distributed Microphone
Arrays in an Audio-Visual Sensor Network. ArXiv e-prints. 2015.
apa: Jacob, F., & Haeb-Umbach, R. (2015). Absolute Geometry Calibration of Distributed
Microphone Arrays in an Audio-Visual Sensor Network. ArXiv E-Prints.
bibtex: '@article{Jacob_Haeb-Umbach_2015, title={Absolute Geometry Calibration of
Distributed Microphone Arrays in an Audio-Visual Sensor Network}, journal={ArXiv
e-prints}, author={Jacob, Florian and Haeb-Umbach, Reinhold}, year={2015} }'
chicago: Jacob, Florian, and Reinhold Haeb-Umbach. “Absolute Geometry Calibration
of Distributed Microphone Arrays in an Audio-Visual Sensor Network.” ArXiv
E-Prints, 2015.
ieee: F. Jacob and R. Haeb-Umbach, “Absolute Geometry Calibration of Distributed
Microphone Arrays in an Audio-Visual Sensor Network,” ArXiv e-prints, 2015.
mla: Jacob, Florian, and Reinhold Haeb-Umbach. “Absolute Geometry Calibration of
Distributed Microphone Arrays in an Audio-Visual Sensor Network.” ArXiv E-Prints,
2015.
short: F. Jacob, R. Haeb-Umbach, ArXiv E-Prints (2015).
date_created: 2019-07-12T05:29:05Z
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/2015/JaHa2015.pdf
oa: '1'
publication: ArXiv e-prints
status: public
title: Absolute Geometry Calibration of Distributed Microphone Arrays in an Audio-Visual
Sensor Network
type: journal_article
user_id: '44006'
year: '2015'
...
---
_id: '11868'
author:
- first_name: Jinyu
full_name: Li, Jinyu
last_name: Li
- first_name: Li
full_name: Deng, Li
last_name: Deng
- first_name: Reinhold
full_name: Haeb-Umbach, Reinhold
id: '242'
last_name: Haeb-Umbach
- first_name: Y.
full_name: Gong, Y.
last_name: Gong
citation:
ama: Li J, Deng L, Haeb-Umbach R, Gong Y. Robust Automatic Speech Recognition.
Elsevier; 2015.
apa: Li, J., Deng, L., Haeb-Umbach, R., & Gong, Y. (2015). Robust Automatic
Speech Recognition. Elsevier.
bibtex: '@book{Li_Deng_Haeb-Umbach_Gong_2015, title={Robust Automatic Speech Recognition},
publisher={Elsevier}, author={Li, Jinyu and Deng, Li and Haeb-Umbach, Reinhold
and Gong, Y.}, year={2015} }'
chicago: Li, Jinyu, Li Deng, Reinhold Haeb-Umbach, and Y. Gong. Robust Automatic
Speech Recognition. Elsevier, 2015.
ieee: J. Li, L. Deng, R. Haeb-Umbach, and Y. Gong, Robust Automatic Speech Recognition.
Elsevier, 2015.
mla: Li, Jinyu, et al. Robust Automatic Speech Recognition. Elsevier, 2015.
short: J. Li, L. Deng, R. Haeb-Umbach, Y. Gong, Robust Automatic Speech Recognition,
Elsevier, 2015.
date_created: 2019-07-12T05:29:49Z
date_updated: 2022-01-06T06:51:11Z
department:
- _id: '54'
language:
- iso: eng
main_file_link:
- open_access: '1'
url: http://store.elsevier.com/Robust-Automatic-Speech-Recognition/Jinyu-Li/isbn-9780128023983/
oa: '1'
publisher: Elsevier
related_material:
link:
- description: Sample-Chapter
relation: supplementary_material
url: https://groups.uni-paderborn.de/nt/pubs/2015/RASR_Chap5.pdf
- description: Store
relation: supplementary_material
url: http://store.elsevier.com/9780128023983
status: public
title: Robust Automatic Speech Recognition
type: book
user_id: '44006'
year: '2015'
...
---
_id: '11875'
abstract:
- lang: eng
text: Only a few studies exist on automatic emotion analysis of speech from children
with Autism Spectrum Conditions (ASC). Out of these, some preliminary studies
have recently focused on comparing the relevance of selected prosodic features
against large sets of acoustic, spectral, and cepstral features; however, no study
so far provided a comparison of performances across different languages. The present
contribution aims to fill this white spot in the literature and provide insight
by extensive evaluations carried out on three databases of prompted phrases collected
in English, Swedish, and Hebrew, inducing nine emotion categories embedded in
short-stories. The datasets contain speech of children with ASC and typically
developing children under the same conditions. We evaluate automatic diagnosis
and recognition of emotions in atypical childrens voice over the nine categories
including binary valence/arousal discrimination.
author:
- first_name: Erik
full_name: Marchi, Erik
last_name: Marchi
- first_name: Bjoern
full_name: Schuller, Bjoern
last_name: Schuller
- first_name: Simon
full_name: Baron-Cohen, Simon
last_name: Baron-Cohen
- first_name: Ofer
full_name: Golan, Ofer
last_name: Golan
- first_name: Sven
full_name: Boelte, Sven
last_name: Boelte
- first_name: Prerna
full_name: Arora, Prerna
last_name: Arora
- first_name: Reinhold
full_name: Haeb-Umbach, Reinhold
id: '242'
last_name: Haeb-Umbach
citation:
ama: 'Marchi E, Schuller B, Baron-Cohen S, et al. Typicality and Emotion in the
Voice of Children with Autism Spectrum Condition: Evidence Across Three Languages.
In: INTERSPEECH 2015. ; 2015.'
apa: 'Marchi, E., Schuller, B., Baron-Cohen, S., Golan, O., Boelte, S., Arora, P.,
& Haeb-Umbach, R. (2015). Typicality and Emotion in the Voice of Children
with Autism Spectrum Condition: Evidence Across Three Languages. In INTERSPEECH
2015.'
bibtex: '@inproceedings{Marchi_Schuller_Baron-Cohen_Golan_Boelte_Arora_Haeb-Umbach_2015,
title={Typicality and Emotion in the Voice of Children with Autism Spectrum Condition:
Evidence Across Three Languages}, booktitle={INTERSPEECH 2015}, author={Marchi,
Erik and Schuller, Bjoern and Baron-Cohen, Simon and Golan, Ofer and Boelte, Sven
and Arora, Prerna and Haeb-Umbach, Reinhold}, year={2015} }'
chicago: 'Marchi, Erik, Bjoern Schuller, Simon Baron-Cohen, Ofer Golan, Sven Boelte,
Prerna Arora, and Reinhold Haeb-Umbach. “Typicality and Emotion in the Voice of
Children with Autism Spectrum Condition: Evidence Across Three Languages.” In
INTERSPEECH 2015, 2015.'
ieee: 'E. Marchi et al., “Typicality and Emotion in the Voice of Children
with Autism Spectrum Condition: Evidence Across Three Languages,” in INTERSPEECH
2015, 2015.'
mla: 'Marchi, Erik, et al. “Typicality and Emotion in the Voice of Children with
Autism Spectrum Condition: Evidence Across Three Languages.” INTERSPEECH 2015,
2015.'
short: 'E. Marchi, B. Schuller, S. Baron-Cohen, O. Golan, S. Boelte, P. Arora, R.
Haeb-Umbach, in: INTERSPEECH 2015, 2015.'
date_created: 2019-07-12T05:29:57Z
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/2015/MaScBaOfSvPrHa.pdf
oa: '1'
publication: INTERSPEECH 2015
status: public
title: 'Typicality and Emotion in the Voice of Children with Autism Spectrum Condition:
Evidence Across Three Languages'
type: conference
user_id: '44006'
year: '2015'
...
---
_id: '11919'
abstract:
- lang: eng
text: In this paper we present a source counting algorithm to determine the number
of speakers in a speech mixture. In our proposed method, we model the histogram
of estimated directions of arrival with a nonparametric Bayesian infinite Gaussian
mixture model. As an alternative to classical model selection criteria and to
avoid specifying the maximum number of mixture components in advance, a Dirichlet
process prior is employed over the mixture components. This allows to automatically
determine the optimal number of mixture components that most probably model the
observations. We demonstrate by experiments that this model outperforms a parametric
approach using a finite Gaussian mixture model with a Dirichlet distribution prior
over the mixture weights.
author:
- first_name: Oliver
full_name: Walter, Oliver
last_name: Walter
- first_name: Lukas
full_name: Drude, Lukas
id: '11213'
last_name: Drude
- first_name: Reinhold
full_name: Haeb-Umbach, Reinhold
id: '242'
last_name: Haeb-Umbach
citation:
ama: 'Walter O, Drude L, Haeb-Umbach R. Source Counting in Speech Mixtures by Nonparametric
Bayesian Estimation of an infinite Gaussian Mixture Model. In: 40th International
Conference on Acoustics, Speech and Signal Processing (ICASSP 2015). ; 2015.'
apa: Walter, O., Drude, L., & Haeb-Umbach, R. (2015). Source Counting in Speech
Mixtures by Nonparametric Bayesian Estimation of an infinite Gaussian Mixture
Model. In 40th International Conference on Acoustics, Speech and Signal Processing
(ICASSP 2015).
bibtex: '@inproceedings{Walter_Drude_Haeb-Umbach_2015, title={Source Counting in
Speech Mixtures by Nonparametric Bayesian Estimation of an infinite Gaussian Mixture
Model}, booktitle={40th International Conference on Acoustics, Speech and Signal
Processing (ICASSP 2015)}, author={Walter, Oliver and Drude, Lukas and Haeb-Umbach,
Reinhold}, year={2015} }'
chicago: Walter, Oliver, Lukas Drude, and Reinhold Haeb-Umbach. “Source Counting
in Speech Mixtures by Nonparametric Bayesian Estimation of an Infinite Gaussian
Mixture Model.” In 40th International Conference on Acoustics, Speech and Signal
Processing (ICASSP 2015), 2015.
ieee: O. Walter, L. Drude, and R. Haeb-Umbach, “Source Counting in Speech Mixtures
by Nonparametric Bayesian Estimation of an infinite Gaussian Mixture Model,” in
40th International Conference on Acoustics, Speech and Signal Processing (ICASSP
2015), 2015.
mla: Walter, Oliver, et al. “Source Counting in Speech Mixtures by Nonparametric
Bayesian Estimation of an Infinite Gaussian Mixture Model.” 40th International
Conference on Acoustics, Speech and Signal Processing (ICASSP 2015), 2015.
short: 'O. Walter, L. Drude, R. Haeb-Umbach, in: 40th International Conference on
Acoustics, Speech and Signal Processing (ICASSP 2015), 2015.'
date_created: 2019-07-12T05:30:47Z
date_updated: 2022-01-06T06:51:12Z
department:
- _id: '54'
language:
- iso: eng
main_file_link:
- open_access: '1'
url: https://groups.uni-paderborn.de/nt/pubs/2015/WaDrHa15.pdf
oa: '1'
publication: 40th International Conference on Acoustics, Speech and Signal Processing
(ICASSP 2015)
related_material:
link:
- description: Poster
relation: supplementary_material
url: https://groups.uni-paderborn.de/nt/pubs/2015/WaDrHa15_Poster.pdf
status: public
title: Source Counting in Speech Mixtures by Nonparametric Bayesian Estimation of
an infinite Gaussian Mixture Model
type: conference
user_id: '44006'
year: '2015'
...
---
_id: '11922'
abstract:
- lang: eng
text: 'Besides the core learning algorithm itself, one major question in machine
learning is how to best encode given training data such that the learning technology
can efficiently learn based thereon and generalize to novel data. While classical
approaches often rely on a hand coded data representation, the topic of autonomous
representation or feature learning plays a major role in modern learning architectures.
The goal of this contribution is to give an overview about different principles
of autonomous feature learning, and to exemplify two principles based on two recent
examples: autonomous metric learning for sequences, and autonomous learning of
a deep representation for spoken language, respectively.'
author:
- first_name: Oliver
full_name: Walter, Oliver
last_name: Walter
- first_name: Reinhold
full_name: Haeb-Umbach, Reinhold
id: '242'
last_name: Haeb-Umbach
- first_name: Bassam
full_name: Mokbel, Bassam
last_name: Mokbel
- first_name: Benjamin
full_name: Paassen, Benjamin
last_name: Paassen
- first_name: Barbara
full_name: Hammer, Barbara
last_name: Hammer
citation:
ama: Walter O, Haeb-Umbach R, Mokbel B, Paassen B, Hammer B. Autonomous Learning
of Representations. KI - Kuenstliche Intelligenz. 2015:1-13. doi:http://dx.doi.org/10.1007/s13218-015-0372-1
apa: Walter, O., Haeb-Umbach, R., Mokbel, B., Paassen, B., & Hammer, B. (2015).
Autonomous Learning of Representations. KI - Kuenstliche Intelligenz, 1–13.
http://dx.doi.org/10.1007/s13218-015-0372-1
bibtex: '@article{Walter_Haeb-Umbach_Mokbel_Paassen_Hammer_2015, title={Autonomous
Learning of Representations}, DOI={http://dx.doi.org/10.1007/s13218-015-0372-1},
journal={KI - Kuenstliche Intelligenz}, author={Walter, Oliver and Haeb-Umbach,
Reinhold and Mokbel, Bassam and Paassen, Benjamin and Hammer, Barbara}, year={2015},
pages={1–13} }'
chicago: Walter, Oliver, Reinhold Haeb-Umbach, Bassam Mokbel, Benjamin Paassen,
and Barbara Hammer. “Autonomous Learning of Representations.” KI - Kuenstliche
Intelligenz, 2015, 1–13. http://dx.doi.org/10.1007/s13218-015-0372-1.
ieee: O. Walter, R. Haeb-Umbach, B. Mokbel, B. Paassen, and B. Hammer, “Autonomous
Learning of Representations,” KI - Kuenstliche Intelligenz, pp. 1–13, 2015.
mla: Walter, Oliver, et al. “Autonomous Learning of Representations.” KI - Kuenstliche
Intelligenz, 2015, pp. 1–13, doi:http://dx.doi.org/10.1007/s13218-015-0372-1.
short: O. Walter, R. Haeb-Umbach, B. Mokbel, B. Paassen, B. Hammer, KI - Kuenstliche
Intelligenz (2015) 1–13.
date_created: 2019-07-12T05:30:51Z
date_updated: 2022-01-06T06:51:12Z
department:
- _id: '54'
doi: http://dx.doi.org/10.1007/s13218-015-0372-1
keyword:
- Representation learning
- Metric learning
- Deep representation
- Spoken language
language:
- iso: eng
main_file_link:
- open_access: '1'
url: https://groups.uni-paderborn.de/nt/pubs/2015/WaHaMoPaHa15.pdf
oa: '1'
page: 1-13
publication: KI - Kuenstliche Intelligenz
status: public
title: Autonomous Learning of Representations
type: journal_article
user_id: '44006'
year: '2015'
...
---
_id: '11923'
abstract:
- lang: eng
text: 'In this paper we show that recently developed algorithms for unsupervised
word segmentation can be a valuable tool for the documentation of endangered languages.
We applied an unsupervised word segmentation algorithm based on a nested Pitman-Yor
language model to two austronesian languages, Wooi and Waima''a. The algorithm
was then modified and parameterized to cater the needs of linguists for high precision
of lexical discovery: We obtained a lexicon precision of of 69.2\% and 67.5\%
for Wooi and Waima''a, respectively, if single-letter words and words found less
than three times were discarded. A comparison with an English word segmentation
task showed comparable performance, verifying that the assumptions underlying
the Pitman-Yor language model, the universality of Zipf''s law and the power of
n-gram structures, do also hold for languages as exotic as Wooi and Waima''a.'
author:
- first_name: Oliver
full_name: Walter, Oliver
last_name: Walter
- first_name: Reinhold
full_name: Haeb-Umbach, Reinhold
id: '242'
last_name: Haeb-Umbach
- first_name: Jan
full_name: Strunk, Jan
last_name: Strunk
- first_name: 'Nikolaus '
full_name: 'P. Himmelmann, Nikolaus '
last_name: P. Himmelmann
citation:
ama: Walter O, Haeb-Umbach R, Strunk J, P. Himmelmann N. Lexicon Discovery for
Language Preservation Using Unsupervised Word Segmentation with Pitman-Yor Language
Models (FGNT-2015-01).; 2015.
apa: Walter, O., Haeb-Umbach, R., Strunk, J., & P. Himmelmann, N. (2015). Lexicon
Discovery for Language Preservation using Unsupervised Word Segmentation with
Pitman-Yor Language Models (FGNT-2015-01).
bibtex: '@book{Walter_Haeb-Umbach_Strunk_P. Himmelmann_2015, title={Lexicon Discovery
for Language Preservation using Unsupervised Word Segmentation with Pitman-Yor
Language Models (FGNT-2015-01)}, author={Walter, Oliver and Haeb-Umbach, Reinhold
and Strunk, Jan and P. Himmelmann, Nikolaus }, year={2015} }'
chicago: Walter, Oliver, Reinhold Haeb-Umbach, Jan Strunk, and Nikolaus P. Himmelmann.
Lexicon Discovery for Language Preservation Using Unsupervised Word Segmentation
with Pitman-Yor Language Models (FGNT-2015-01), 2015.
ieee: O. Walter, R. Haeb-Umbach, J. Strunk, and N. P. Himmelmann, Lexicon Discovery
for Language Preservation using Unsupervised Word Segmentation with Pitman-Yor
Language Models (FGNT-2015-01). 2015.
mla: Walter, Oliver, et al. Lexicon Discovery for Language Preservation Using
Unsupervised Word Segmentation with Pitman-Yor Language Models (FGNT-2015-01).
2015.
short: O. Walter, R. Haeb-Umbach, J. Strunk, N. P. Himmelmann, Lexicon Discovery
for Language Preservation Using Unsupervised Word Segmentation with Pitman-Yor
Language Models (FGNT-2015-01), 2015.
date_created: 2019-07-12T05:30:52Z
date_updated: 2022-01-06T06:51:12Z
department:
- _id: '54'
language:
- iso: eng
main_file_link:
- open_access: '1'
url: https://groups.uni-paderborn.de/nt/pubs/2015/WaHaStHi.pdf
oa: '1'
status: public
title: Lexicon Discovery for Language Preservation using Unsupervised Word Segmentation
with Pitman-Yor Language Models (FGNT-2015-01)
type: report
user_id: '44006'
year: '2015'
...
---
_id: '11969'
author:
- first_name: Onur
full_name: Altintas, Onur
last_name: Altintas
- first_name: Falko
full_name: Dressler, Falko
last_name: Dressler
- first_name: Florian
full_name: Hagenauer, Florian
last_name: Hagenauer
- first_name: Makiko
full_name: Matsumoto, Makiko
last_name: Matsumoto
- first_name: Miguel
full_name: Sepulcre, Miguel
last_name: Sepulcre
- first_name: Christoph
full_name: Sommer, Christoph
id: '49154'
last_name: Sommer
orcid: 0000-0002-4336-7350
citation:
ama: 'Altintas O, Dressler F, Hagenauer F, Matsumoto M, Sepulcre M, Sommer C. Making
cars a main ICT resource in smart cities. In: 2015 IEEE Conference on Computer
Communications Workshops (INFOCOM WKSHPS). ; 2015. doi:10.1109/infcomw.2015.7179448'
apa: Altintas, O., Dressler, F., Hagenauer, F., Matsumoto, M., Sepulcre, M., &
Sommer, C. (2015). Making cars a main ICT resource in smart cities. In 2015
IEEE Conference on Computer Communications Workshops (INFOCOM WKSHPS). https://doi.org/10.1109/infcomw.2015.7179448
bibtex: '@inproceedings{Altintas_Dressler_Hagenauer_Matsumoto_Sepulcre_Sommer_2015,
title={Making cars a main ICT resource in smart cities}, DOI={10.1109/infcomw.2015.7179448},
booktitle={2015 IEEE Conference on Computer Communications Workshops (INFOCOM
WKSHPS)}, author={Altintas, Onur and Dressler, Falko and Hagenauer, Florian and
Matsumoto, Makiko and Sepulcre, Miguel and Sommer, Christoph}, year={2015} }'
chicago: Altintas, Onur, Falko Dressler, Florian Hagenauer, Makiko Matsumoto, Miguel
Sepulcre, and Christoph Sommer. “Making Cars a Main ICT Resource in Smart Cities.”
In 2015 IEEE Conference on Computer Communications Workshops (INFOCOM WKSHPS),
2015. https://doi.org/10.1109/infcomw.2015.7179448.
ieee: O. Altintas, F. Dressler, F. Hagenauer, M. Matsumoto, M. Sepulcre, and C.
Sommer, “Making cars a main ICT resource in smart cities,” in 2015 IEEE Conference
on Computer Communications Workshops (INFOCOM WKSHPS), 2015.
mla: Altintas, Onur, et al. “Making Cars a Main ICT Resource in Smart Cities.” 2015
IEEE Conference on Computer Communications Workshops (INFOCOM WKSHPS), 2015,
doi:10.1109/infcomw.2015.7179448.
short: 'O. Altintas, F. Dressler, F. Hagenauer, M. Matsumoto, M. Sepulcre, C. Sommer,
in: 2015 IEEE Conference on Computer Communications Workshops (INFOCOM WKSHPS),
2015.'
date_created: 2019-07-18T09:46:00Z
date_updated: 2022-01-06T06:51:14Z
department:
- _id: '589'
doi: 10.1109/infcomw.2015.7179448
language:
- iso: eng
publication: 2015 IEEE Conference on Computer Communications Workshops (INFOCOM WKSHPS)
publication_identifier:
isbn:
- '9781467371315'
publication_status: published
status: public
title: Making cars a main ICT resource in smart cities
type: conference
user_id: '49154'
year: '2015'
...
---
_id: '11980'
author:
- first_name: Bastian
full_name: Bloessl, Bastian
last_name: Bloessl
- first_name: Andre
full_name: Puschmann, Andre
last_name: Puschmann
- first_name: Christoph
full_name: Sommer, Christoph
id: '49154'
last_name: Sommer
orcid: 0000-0002-4336-7350
- first_name: Falko
full_name: Dressler, Falko
last_name: Dressler
citation:
ama: Bloessl B, Puschmann A, Sommer C, Dressler F. Timings Matter. ACM SIGMOBILE
Mobile Computing and Communications Review. 2015:81-90. doi:10.1145/2721896.2721913
apa: Bloessl, B., Puschmann, A., Sommer, C., & Dressler, F. (2015). Timings
Matter. ACM SIGMOBILE Mobile Computing and Communications Review, 81–90.
https://doi.org/10.1145/2721896.2721913
bibtex: '@article{Bloessl_Puschmann_Sommer_Dressler_2015, title={Timings Matter},
DOI={10.1145/2721896.2721913},
journal={ACM SIGMOBILE Mobile Computing and Communications Review}, author={Bloessl,
Bastian and Puschmann, Andre and Sommer, Christoph and Dressler, Falko}, year={2015},
pages={81–90} }'
chicago: Bloessl, Bastian, Andre Puschmann, Christoph Sommer, and Falko Dressler.
“Timings Matter.” ACM SIGMOBILE Mobile Computing and Communications Review,
2015, 81–90. https://doi.org/10.1145/2721896.2721913.
ieee: B. Bloessl, A. Puschmann, C. Sommer, and F. Dressler, “Timings Matter,” ACM
SIGMOBILE Mobile Computing and Communications Review, pp. 81–90, 2015.
mla: Bloessl, Bastian, et al. “Timings Matter.” ACM SIGMOBILE Mobile Computing
and Communications Review, 2015, pp. 81–90, doi:10.1145/2721896.2721913.
short: B. Bloessl, A. Puschmann, C. Sommer, F. Dressler, ACM SIGMOBILE Mobile Computing
and Communications Review (2015) 81–90.
date_created: 2019-07-18T09:51:35Z
date_updated: 2022-01-06T06:51:14Z
department:
- _id: '589'
doi: 10.1145/2721896.2721913
language:
- iso: eng
page: 81-90
publication: ACM SIGMOBILE Mobile Computing and Communications Review
publication_identifier:
issn:
- 1559-1662
publication_status: published
status: public
title: Timings Matter
type: journal_article
user_id: '49154'
year: '2015'
...
---
_id: '11981'
author:
- first_name: Bastian
full_name: Bloessl, Bastian
last_name: Bloessl
- first_name: Christoph
full_name: Sommer, Christoph
id: '49154'
last_name: Sommer
orcid: 0000-0002-4336-7350
- first_name: Falko
full_name: Dressler, Falko
last_name: Dressler
citation:
ama: 'Bloessl B, Sommer C, Dressler F. Power matters: Automatic Gain Control for
a Software Defined Radio IEEE 802.11a/g/p receiver. In: 2015 IEEE Conference
on Computer Communications Workshops (INFOCOM WKSHPS). ; 2015. doi:10.1109/infcomw.2015.7179325'
apa: 'Bloessl, B., Sommer, C., & Dressler, F. (2015). Power matters: Automatic
Gain Control for a Software Defined Radio IEEE 802.11a/g/p receiver. In 2015
IEEE Conference on Computer Communications Workshops (INFOCOM WKSHPS). https://doi.org/10.1109/infcomw.2015.7179325'
bibtex: '@inproceedings{Bloessl_Sommer_Dressler_2015, title={Power matters: Automatic
Gain Control for a Software Defined Radio IEEE 802.11a/g/p receiver}, DOI={10.1109/infcomw.2015.7179325},
booktitle={2015 IEEE Conference on Computer Communications Workshops (INFOCOM
WKSHPS)}, author={Bloessl, Bastian and Sommer, Christoph and Dressler, Falko},
year={2015} }'
chicago: 'Bloessl, Bastian, Christoph Sommer, and Falko Dressler. “Power Matters:
Automatic Gain Control for a Software Defined Radio IEEE 802.11a/g/p Receiver.”
In 2015 IEEE Conference on Computer Communications Workshops (INFOCOM WKSHPS),
2015. https://doi.org/10.1109/infcomw.2015.7179325.'
ieee: 'B. Bloessl, C. Sommer, and F. Dressler, “Power matters: Automatic Gain Control
for a Software Defined Radio IEEE 802.11a/g/p receiver,” in 2015 IEEE Conference
on Computer Communications Workshops (INFOCOM WKSHPS), 2015.'
mla: 'Bloessl, Bastian, et al. “Power Matters: Automatic Gain Control for a Software
Defined Radio IEEE 802.11a/g/p Receiver.” 2015 IEEE Conference on Computer
Communications Workshops (INFOCOM WKSHPS), 2015, doi:10.1109/infcomw.2015.7179325.'
short: 'B. Bloessl, C. Sommer, F. Dressler, in: 2015 IEEE Conference on Computer
Communications Workshops (INFOCOM WKSHPS), 2015.'
date_created: 2019-07-18T09:51:38Z
date_updated: 2022-01-06T06:51:14Z
department:
- _id: '589'
doi: 10.1109/infcomw.2015.7179325
language:
- iso: eng
publication: 2015 IEEE Conference on Computer Communications Workshops (INFOCOM WKSHPS)
publication_identifier:
isbn:
- '9781467371315'
publication_status: published
status: public
title: 'Power matters: Automatic Gain Control for a Software Defined Radio IEEE 802.11a/g/p
receiver'
type: conference
user_id: '49154'
year: '2015'
...