---
_id: '56004'
author:
- first_name: Thilo
full_name: von Neumann, Thilo
id: '49870'
last_name: von Neumann
orcid: https://orcid.org/0000-0002-7717-8670
- first_name: Christoph
full_name: Boeddeker, Christoph
id: '40767'
last_name: Boeddeker
- first_name: Tobias
full_name: Cord-Landwehr, Tobias
id: '44393'
last_name: Cord-Landwehr
- first_name: Marc
full_name: Delcroix, Marc
last_name: Delcroix
- first_name: Reinhold
full_name: Haeb-Umbach, Reinhold
id: '242'
last_name: Haeb-Umbach
citation:
ama: 'von Neumann T, Boeddeker C, Cord-Landwehr T, Delcroix M, Haeb-Umbach R. Meeting
Recognition with Continuous Speech Separation and Transcription-Supported Diarization.
In: 2024 IEEE International Conference on Acoustics, Speech, and Signal Processing
Workshops (ICASSPW). IEEE; 2024. doi:10.1109/icasspw62465.2024.10625894'
apa: von Neumann, T., Boeddeker, C., Cord-Landwehr, T., Delcroix, M., & Haeb-Umbach,
R. (2024). Meeting Recognition with Continuous Speech Separation and Transcription-Supported
Diarization. 2024 IEEE International Conference on Acoustics, Speech, and Signal
Processing Workshops (ICASSPW). https://doi.org/10.1109/icasspw62465.2024.10625894
bibtex: '@inproceedings{von Neumann_Boeddeker_Cord-Landwehr_Delcroix_Haeb-Umbach_2024,
title={Meeting Recognition with Continuous Speech Separation and Transcription-Supported
Diarization}, DOI={10.1109/icasspw62465.2024.10625894},
booktitle={2024 IEEE International Conference on Acoustics, Speech, and Signal
Processing Workshops (ICASSPW)}, publisher={IEEE}, author={von Neumann, Thilo
and Boeddeker, Christoph and Cord-Landwehr, Tobias and Delcroix, Marc and Haeb-Umbach,
Reinhold}, year={2024} }'
chicago: Neumann, Thilo von, Christoph Boeddeker, Tobias Cord-Landwehr, Marc Delcroix,
and Reinhold Haeb-Umbach. “Meeting Recognition with Continuous Speech Separation
and Transcription-Supported Diarization.” In 2024 IEEE International Conference
on Acoustics, Speech, and Signal Processing Workshops (ICASSPW). IEEE, 2024.
https://doi.org/10.1109/icasspw62465.2024.10625894.
ieee: 'T. von Neumann, C. Boeddeker, T. Cord-Landwehr, M. Delcroix, and R. Haeb-Umbach,
“Meeting Recognition with Continuous Speech Separation and Transcription-Supported
Diarization,” 2024, doi: 10.1109/icasspw62465.2024.10625894.'
mla: von Neumann, Thilo, et al. “Meeting Recognition with Continuous Speech Separation
and Transcription-Supported Diarization.” 2024 IEEE International Conference
on Acoustics, Speech, and Signal Processing Workshops (ICASSPW), IEEE, 2024,
doi:10.1109/icasspw62465.2024.10625894.
short: 'T. von Neumann, C. Boeddeker, T. Cord-Landwehr, M. Delcroix, R. Haeb-Umbach,
in: 2024 IEEE International Conference on Acoustics, Speech, and Signal Processing
Workshops (ICASSPW), IEEE, 2024.'
date_created: 2024-09-04T07:26:02Z
date_updated: 2025-02-12T09:20:07Z
ddc:
- '000'
department:
- _id: '54'
doi: 10.1109/icasspw62465.2024.10625894
file:
- access_level: open_access
content_type: application/pdf
creator: tvn
date_created: 2024-09-04T07:34:30Z
date_updated: 2024-09-04T07:34:30Z
file_id: '56005'
file_name: main.pdf
file_size: 150432
relation: main_file
file_date_updated: 2024-09-04T07:34:30Z
has_accepted_license: '1'
language:
- iso: eng
oa: '1'
project:
- _id: '52'
name: 'PC2: Computing Resources Provided by the Paderborn Center for Parallel Computing'
- _id: '508'
grant_number: '448568305'
name: Automatische Transkription von Gesprächssituationen
publication: 2024 IEEE International Conference on Acoustics, Speech, and Signal Processing
Workshops (ICASSPW)
publication_status: published
publisher: IEEE
status: public
title: Meeting Recognition with Continuous Speech Separation and Transcription-Supported
Diarization
type: conference
user_id: '40767'
year: '2024'
...
---
_id: '57659'
author:
- first_name: Peter
full_name: Vieting, Peter
last_name: Vieting
- first_name: Simon
full_name: Berger, Simon
last_name: Berger
- first_name: Thilo
full_name: von Neumann, Thilo
id: '49870'
last_name: von Neumann
orcid: https://orcid.org/0000-0002-7717-8670
- first_name: Christoph
full_name: Boeddeker, Christoph
id: '40767'
last_name: Boeddeker
- first_name: Ralf
full_name: Schlüter, Ralf
last_name: Schlüter
- first_name: Reinhold
full_name: Haeb-Umbach, Reinhold
id: '242'
last_name: Haeb-Umbach
citation:
ama: 'Vieting P, Berger S, von Neumann T, Boeddeker C, Schlüter R, Haeb-Umbach R.
Combining TF-GridNet and Mixture Encoder for Continuous Speech Separation for
Meeting Transcription. In: 2024 IEEE Spoken Language Technology Workshop (SLT).
; 2024.'
apa: Vieting, P., Berger, S., von Neumann, T., Boeddeker, C., Schlüter, R., &
Haeb-Umbach, R. (2024). Combining TF-GridNet and Mixture Encoder for Continuous
Speech Separation for Meeting Transcription. 2024 IEEE Spoken Language Technology
Workshop (SLT).
bibtex: '@inproceedings{Vieting_Berger_von Neumann_Boeddeker_Schlüter_Haeb-Umbach_2024,
title={Combining TF-GridNet and Mixture Encoder for Continuous Speech Separation
for Meeting Transcription}, booktitle={2024 IEEE Spoken Language Technology Workshop
(SLT)}, author={Vieting, Peter and Berger, Simon and von Neumann, Thilo and Boeddeker,
Christoph and Schlüter, Ralf and Haeb-Umbach, Reinhold}, year={2024} }'
chicago: Vieting, Peter, Simon Berger, Thilo von Neumann, Christoph Boeddeker, Ralf
Schlüter, and Reinhold Haeb-Umbach. “Combining TF-GridNet and Mixture Encoder
for Continuous Speech Separation for Meeting Transcription.” In 2024 IEEE Spoken
Language Technology Workshop (SLT), 2024.
ieee: P. Vieting, S. Berger, T. von Neumann, C. Boeddeker, R. Schlüter, and R. Haeb-Umbach,
“Combining TF-GridNet and Mixture Encoder for Continuous Speech Separation for
Meeting Transcription,” 2024.
mla: Vieting, Peter, et al. “Combining TF-GridNet and Mixture Encoder for Continuous
Speech Separation for Meeting Transcription.” 2024 IEEE Spoken Language Technology
Workshop (SLT), 2024.
short: 'P. Vieting, S. Berger, T. von Neumann, C. Boeddeker, R. Schlüter, R. Haeb-Umbach,
in: 2024 IEEE Spoken Language Technology Workshop (SLT), 2024.'
date_created: 2024-12-09T11:46:18Z
date_updated: 2025-02-12T09:20:59Z
department:
- _id: '54'
language:
- iso: eng
main_file_link:
- open_access: '1'
url: https://www-i6.informatik.rwth-aachen.de/publications/download/1259/VietingPeterBergerSimonNeumannThilovonBoeddekerChristophSchl%FCterRalfHaeb-UmbachReinhold--CombiningTF-GridNetMixtureEncoderforContinuousSpeechSeparationforMeetingTranscription--2024.pdf
oa: '1'
project:
- _id: '52'
name: 'PC2: Computing Resources Provided by the Paderborn Center for Parallel Computing'
- _id: '508'
grant_number: '448568305'
name: Automatische Transkription von Gesprächssituationen
publication: 2024 IEEE Spoken Language Technology Workshop (SLT)
status: public
title: Combining TF-GridNet and Mixture Encoder for Continuous Speech Separation for
Meeting Transcription
type: conference
user_id: '40767'
year: '2024'
...
---
_id: '35602'
abstract:
- lang: eng
text: "Continuous Speech Separation (CSS) has been proposed to address speech overlaps
during the analysis of realistic meeting-like conversations by eliminating any
overlaps before further processing.\r\nCSS separates a recording of arbitrarily
many speakers into a small number of overlap-free output channels, where each
output channel may contain speech of multiple speakers.\r\nThis is often done
by applying a conventional separation model trained with Utterance-level Permutation
Invariant Training (uPIT), which exclusively maps a speaker to an output channel,
in sliding window approach called stitching.\r\nRecently, we introduced an alternative
training scheme called Graph-PIT that teaches the separation network to directly
produce output streams in the required format without stitching.\r\nIt can handle
an arbitrary number of speakers as long as never more of them overlap at the same
time than the separator has output channels.\r\nIn this contribution, we further
investigate the Graph-PIT training scheme.\r\nWe show in extended experiments
that models trained with Graph-PIT also work in challenging reverberant conditions.\r\nModels
trained in this way are able to perform segment-less CSS, i.e., without stitching,
and achieve comparable and often better separation quality than the conventional
CSS with uPIT and stitching.\r\nWe simplify the training schedule for Graph-PIT
with the recently proposed Source Aggregated Signal-to-Distortion Ratio (SA-SDR)
loss.\r\nIt eliminates unfavorable properties of the previously used A-SDR loss
and thus enables training with Graph-PIT from scratch.\r\nGraph-PIT training relaxes
the constraints w.r.t. the allowed numbers of speakers and speaking patterns which
allows using a larger variety of training data.\r\nFurthermore, we introduce novel
signal-level evaluation metrics for meeting scenarios, namely the source-aggregated
scale- and convolution-invariant Signal-to-Distortion Ratio (SA-SI-SDR and SA-CI-SDR),
which are generalizations of the commonly used SDR-based metrics for the CSS case."
article_type: original
author:
- first_name: Thilo
full_name: von Neumann, Thilo
id: '49870'
last_name: von Neumann
orcid: https://orcid.org/0000-0002-7717-8670
- first_name: Keisuke
full_name: Kinoshita, Keisuke
last_name: Kinoshita
- first_name: Christoph
full_name: Boeddeker, Christoph
id: '40767'
last_name: Boeddeker
- first_name: Marc
full_name: Delcroix, Marc
last_name: Delcroix
- first_name: Reinhold
full_name: Haeb-Umbach, Reinhold
id: '242'
last_name: Haeb-Umbach
citation:
ama: 'von Neumann T, Kinoshita K, Boeddeker C, Delcroix M, Haeb-Umbach R. Segment-Less
Continuous Speech Separation of Meetings: Training and Evaluation Criteria. IEEE/ACM
Transactions on Audio, Speech, and Language Processing. 2023;31:576-589. doi:10.1109/taslp.2022.3228629'
apa: 'von Neumann, T., Kinoshita, K., Boeddeker, C., Delcroix, M., & Haeb-Umbach,
R. (2023). Segment-Less Continuous Speech Separation of Meetings: Training and
Evaluation Criteria. IEEE/ACM Transactions on Audio, Speech, and Language Processing,
31, 576–589. https://doi.org/10.1109/taslp.2022.3228629'
bibtex: '@article{von Neumann_Kinoshita_Boeddeker_Delcroix_Haeb-Umbach_2023, title={Segment-Less
Continuous Speech Separation of Meetings: Training and Evaluation Criteria}, volume={31},
DOI={10.1109/taslp.2022.3228629},
journal={IEEE/ACM Transactions on Audio, Speech, and Language Processing}, publisher={Institute
of Electrical and Electronics Engineers (IEEE)}, author={von Neumann, Thilo and
Kinoshita, Keisuke and Boeddeker, Christoph and Delcroix, Marc and Haeb-Umbach,
Reinhold}, year={2023}, pages={576–589} }'
chicago: 'Neumann, Thilo von, Keisuke Kinoshita, Christoph Boeddeker, Marc Delcroix,
and Reinhold Haeb-Umbach. “Segment-Less Continuous Speech Separation of Meetings:
Training and Evaluation Criteria.” IEEE/ACM Transactions on Audio, Speech,
and Language Processing 31 (2023): 576–89. https://doi.org/10.1109/taslp.2022.3228629.'
ieee: 'T. von Neumann, K. Kinoshita, C. Boeddeker, M. Delcroix, and R. Haeb-Umbach,
“Segment-Less Continuous Speech Separation of Meetings: Training and Evaluation
Criteria,” IEEE/ACM Transactions on Audio, Speech, and Language Processing,
vol. 31, pp. 576–589, 2023, doi: 10.1109/taslp.2022.3228629.'
mla: 'von Neumann, Thilo, et al. “Segment-Less Continuous Speech Separation of Meetings:
Training and Evaluation Criteria.” IEEE/ACM Transactions on Audio, Speech,
and Language Processing, vol. 31, Institute of Electrical and Electronics
Engineers (IEEE), 2023, pp. 576–89, doi:10.1109/taslp.2022.3228629.'
short: T. von Neumann, K. Kinoshita, C. Boeddeker, M. Delcroix, R. Haeb-Umbach,
IEEE/ACM Transactions on Audio, Speech, and Language Processing 31 (2023) 576–589.
date_created: 2023-01-09T17:24:17Z
date_updated: 2023-11-15T12:16:11Z
ddc:
- '000'
department:
- _id: '54'
doi: 10.1109/taslp.2022.3228629
file:
- access_level: open_access
content_type: application/pdf
creator: haebumb
date_created: 2023-01-09T17:46:05Z
date_updated: 2023-01-11T08:50:19Z
file_id: '35607'
file_name: main.pdf
file_size: 7185077
relation: main_file
file_date_updated: 2023-01-11T08:50:19Z
has_accepted_license: '1'
intvolume: ' 31'
keyword:
- Continuous Speech Separation
- Source Separation
- Graph-PIT
- Dynamic Programming
- Permutation Invariant Training
language:
- iso: eng
oa: '1'
page: 576-589
project:
- _id: '52'
name: 'PC2: Computing Resources Provided by the Paderborn Center for Parallel Computing'
publication: IEEE/ACM Transactions on Audio, Speech, and Language Processing
publication_identifier:
issn:
- 2329-9290
- 2329-9304
publication_status: published
publisher: Institute of Electrical and Electronics Engineers (IEEE)
quality_controlled: '1'
status: public
title: 'Segment-Less Continuous Speech Separation of Meetings: Training and Evaluation
Criteria'
type: journal_article
user_id: '49870'
volume: 31
year: '2023'
...
---
_id: '48281'
abstract:
- lang: eng
text: "\tWe propose a general framework to compute the word error rate (WER) of
ASR systems that process recordings containing multiple speakers at their input
and that produce multiple output word sequences (MIMO).\r\n\tSuch ASR systems
are typically required, e.g., for meeting transcription.\r\n\tWe provide an efficient
implementation based on a dynamic programming search in a multi-dimensional Levenshtein
distance tensor under the constraint that a reference utterance must be matched
consistently with one hypothesis output. \r\n\tThis also results in an efficient
implementation of the ORC WER which previously suffered from exponential complexity.\r\n\tWe
give an overview of commonly used WER definitions for multi-speaker scenarios
and show that they are specializations of the above MIMO WER tuned to particular
application scenarios. \r\n\tWe conclude with a discussion of the pros and cons
of the various WER definitions and a recommendation when to use which."
author:
- first_name: Thilo
full_name: von Neumann, Thilo
id: '49870'
last_name: von Neumann
orcid: https://orcid.org/0000-0002-7717-8670
- first_name: Christoph
full_name: Boeddeker, Christoph
id: '40767'
last_name: Boeddeker
- first_name: Keisuke
full_name: Kinoshita, Keisuke
last_name: Kinoshita
- first_name: Marc
full_name: Delcroix, Marc
last_name: Delcroix
- first_name: Reinhold
full_name: Haeb-Umbach, Reinhold
id: '242'
last_name: Haeb-Umbach
citation:
ama: 'von Neumann T, Boeddeker C, Kinoshita K, Delcroix M, Haeb-Umbach R. On Word
Error Rate Definitions and Their Efficient Computation for Multi-Speaker Speech
Recognition Systems. In: ICASSP 2023 - 2023 IEEE International Conference on
Acoustics, Speech and Signal Processing (ICASSP). IEEE; 2023. doi:10.1109/icassp49357.2023.10094784'
apa: von Neumann, T., Boeddeker, C., Kinoshita, K., Delcroix, M., & Haeb-Umbach,
R. (2023). On Word Error Rate Definitions and Their Efficient Computation for
Multi-Speaker Speech Recognition Systems. ICASSP 2023 - 2023 IEEE International
Conference on Acoustics, Speech and Signal Processing (ICASSP). https://doi.org/10.1109/icassp49357.2023.10094784
bibtex: '@inproceedings{von Neumann_Boeddeker_Kinoshita_Delcroix_Haeb-Umbach_2023,
title={On Word Error Rate Definitions and Their Efficient Computation for Multi-Speaker
Speech Recognition Systems}, DOI={10.1109/icassp49357.2023.10094784},
booktitle={ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech
and Signal Processing (ICASSP)}, publisher={IEEE}, author={von Neumann, Thilo
and Boeddeker, Christoph and Kinoshita, Keisuke and Delcroix, Marc and Haeb-Umbach,
Reinhold}, year={2023} }'
chicago: Neumann, Thilo von, Christoph Boeddeker, Keisuke Kinoshita, Marc Delcroix,
and Reinhold Haeb-Umbach. “On Word Error Rate Definitions and Their Efficient
Computation for Multi-Speaker Speech Recognition Systems.” In ICASSP 2023 -
2023 IEEE International Conference on Acoustics, Speech and Signal Processing
(ICASSP). IEEE, 2023. https://doi.org/10.1109/icassp49357.2023.10094784.
ieee: 'T. von Neumann, C. Boeddeker, K. Kinoshita, M. Delcroix, and R. Haeb-Umbach,
“On Word Error Rate Definitions and Their Efficient Computation for Multi-Speaker
Speech Recognition Systems,” 2023, doi: 10.1109/icassp49357.2023.10094784.'
mla: von Neumann, Thilo, et al. “On Word Error Rate Definitions and Their Efficient
Computation for Multi-Speaker Speech Recognition Systems.” ICASSP 2023 - 2023
IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP),
IEEE, 2023, doi:10.1109/icassp49357.2023.10094784.
short: 'T. von Neumann, C. Boeddeker, K. Kinoshita, M. Delcroix, R. Haeb-Umbach,
in: ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and
Signal Processing (ICASSP), IEEE, 2023.'
date_created: 2023-10-19T07:38:31Z
date_updated: 2025-02-12T09:16:34Z
ddc:
- '000'
department:
- _id: '54'
doi: 10.1109/icassp49357.2023.10094784
file:
- access_level: open_access
content_type: application/pdf
creator: tvn
date_created: 2023-10-19T07:39:57Z
date_updated: 2023-10-19T07:41:56Z
file_id: '48282'
file_name: ICASSP_2023_Meeting_Evaluation.pdf
file_size: 204994
relation: main_file
file_date_updated: 2023-10-19T07:41:56Z
has_accepted_license: '1'
keyword:
- Word Error Rate
- Meeting Recognition
- Levenshtein Distance
language:
- iso: eng
main_file_link:
- url: https://ieeexplore.ieee.org/document/10094784
oa: '1'
project:
- _id: '52'
name: 'PC2: Computing Resources Provided by the Paderborn Center for Parallel Computing'
- _id: '508'
grant_number: '448568305'
name: Automatische Transkription von Gesprächssituationen
publication: ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech
and Signal Processing (ICASSP)
publication_status: published
publisher: IEEE
quality_controlled: '1'
related_material:
link:
- relation: software
url: https://github.com/fgnt/meeteval
status: public
title: On Word Error Rate Definitions and Their Efficient Computation for Multi-Speaker
Speech Recognition Systems
type: conference
user_id: '40767'
year: '2023'
...
---
_id: '48275'
abstract:
- lang: eng
text: "MeetEval is an open-source toolkit to evaluate all kinds of meeting transcription
systems.\r\nIt provides a unified interface for the computation of commonly used
Word Error Rates (WERs), specifically cpWER, ORC WER and MIMO WER along other
WER definitions.\r\nWe extend the cpWER computation by a temporal constraint to
ensure that only words are identified as correct when the temporal alignment is
plausible.\r\nThis leads to a better quality of the matching of the hypothesis
string to the reference string that more closely resembles the actual transcription
quality, and a system is penalized if it provides poor time annotations.\r\nSince
word-level timing information is often not available, we present a way to approximate
exact word-level timings from segment-level timings (e.g., a sentence) and show
that the approximation leads to a similar WER as a matching with exact word-level
annotations.\r\nAt the same time, the time constraint leads to a speedup of the
matching algorithm, which outweighs the additional overhead caused by processing
the time stamps."
author:
- first_name: Thilo
full_name: von Neumann, Thilo
id: '49870'
last_name: von Neumann
orcid: https://orcid.org/0000-0002-7717-8670
- first_name: Christoph
full_name: Boeddeker, Christoph
id: '40767'
last_name: Boeddeker
- first_name: Marc
full_name: Delcroix, Marc
last_name: Delcroix
- first_name: Reinhold
full_name: Haeb-Umbach, Reinhold
id: '242'
last_name: Haeb-Umbach
citation:
ama: 'von Neumann T, Boeddeker C, Delcroix M, Haeb-Umbach R. MeetEval: A Toolkit
for Computation of Word Error Rates for Meeting Transcription Systems. In: Proc.
CHiME 2023 Workshop on Speech Processing in Everyday Environments. ; 2023.'
apa: 'von Neumann, T., Boeddeker, C., Delcroix, M., & Haeb-Umbach, R. (2023).
MeetEval: A Toolkit for Computation of Word Error Rates for Meeting Transcription
Systems. Proc. CHiME 2023 Workshop on Speech Processing in Everyday Environments.
CHiME 2023 Workshop on Speech Processing in Everyday Environments, Dublin.'
bibtex: '@inproceedings{von Neumann_Boeddeker_Delcroix_Haeb-Umbach_2023, title={MeetEval:
A Toolkit for Computation of Word Error Rates for Meeting Transcription Systems},
booktitle={Proc. CHiME 2023 Workshop on Speech Processing in Everyday Environments},
author={von Neumann, Thilo and Boeddeker, Christoph and Delcroix, Marc and Haeb-Umbach,
Reinhold}, year={2023} }'
chicago: 'Neumann, Thilo von, Christoph Boeddeker, Marc Delcroix, and Reinhold Haeb-Umbach.
“MeetEval: A Toolkit for Computation of Word Error Rates for Meeting Transcription
Systems.” In Proc. CHiME 2023 Workshop on Speech Processing in Everyday Environments,
2023.'
ieee: 'T. von Neumann, C. Boeddeker, M. Delcroix, and R. Haeb-Umbach, “MeetEval:
A Toolkit for Computation of Word Error Rates for Meeting Transcription Systems,”
presented at the CHiME 2023 Workshop on Speech Processing in Everyday Environments,
Dublin, 2023.'
mla: 'von Neumann, Thilo, et al. “MeetEval: A Toolkit for Computation of Word Error
Rates for Meeting Transcription Systems.” Proc. CHiME 2023 Workshop on Speech
Processing in Everyday Environments, 2023.'
short: 'T. von Neumann, C. Boeddeker, M. Delcroix, R. Haeb-Umbach, in: Proc. CHiME
2023 Workshop on Speech Processing in Everyday Environments, 2023.'
conference:
location: Dublin
name: CHiME 2023 Workshop on Speech Processing in Everyday Environments
date_created: 2023-10-19T07:24:51Z
date_updated: 2025-02-12T09:12:05Z
ddc:
- '000'
department:
- _id: '54'
file:
- access_level: open_access
content_type: application/pdf
creator: tvn
date_created: 2023-10-19T07:19:59Z
date_updated: 2023-10-19T07:19:59Z
file_id: '48276'
file_name: Chime_7__MeetEval.pdf
file_size: 263744
relation: main_file
file_date_updated: 2023-10-19T07:19:59Z
has_accepted_license: '1'
keyword:
- Speech Recognition
- Word Error Rate
- Meeting Transcription
language:
- iso: eng
main_file_link:
- open_access: '1'
url: https://arxiv.org/abs/2307.11394
oa: '1'
project:
- _id: '52'
name: 'PC2: Computing Resources Provided by the Paderborn Center for Parallel Computing'
- _id: '508'
grant_number: '448568305'
name: Automatische Transkription von Gesprächssituationen
publication: Proc. CHiME 2023 Workshop on Speech Processing in Everyday Environments
quality_controlled: '1'
related_material:
link:
- relation: software
url: https://github.com/fgnt/meeteval
status: public
title: 'MeetEval: A Toolkit for Computation of Word Error Rates for Meeting Transcription
Systems'
type: conference
user_id: '40767'
year: '2023'
...
---
_id: '54439'
author:
- first_name: Christoph
full_name: Boeddeker, Christoph
id: '40767'
last_name: Boeddeker
- first_name: Tobias
full_name: Cord-Landwehr, Tobias
id: '44393'
last_name: Cord-Landwehr
- first_name: Thilo
full_name: von Neumann, Thilo
id: '49870'
last_name: von Neumann
orcid: https://orcid.org/0000-0002-7717-8670
- first_name: Reinhold
full_name: Haeb-Umbach, Reinhold
id: '242'
last_name: Haeb-Umbach
citation:
ama: 'Boeddeker C, Cord-Landwehr T, von Neumann T, Haeb-Umbach R. Multi-stage diarization
refinement for the CHiME-7 DASR scenario. In: 7th International Workshop on
Speech Processing in Everyday Environments (CHiME 2023). ISCA; 2023. doi:10.21437/chime.2023-10'
apa: Boeddeker, C., Cord-Landwehr, T., von Neumann, T., & Haeb-Umbach, R. (2023).
Multi-stage diarization refinement for the CHiME-7 DASR scenario. 7th International
Workshop on Speech Processing in Everyday Environments (CHiME 2023). https://doi.org/10.21437/chime.2023-10
bibtex: '@inproceedings{Boeddeker_Cord-Landwehr_von Neumann_Haeb-Umbach_2023, title={Multi-stage
diarization refinement for the CHiME-7 DASR scenario}, DOI={10.21437/chime.2023-10},
booktitle={7th International Workshop on Speech Processing in Everyday Environments
(CHiME 2023)}, publisher={ISCA}, author={Boeddeker, Christoph and Cord-Landwehr,
Tobias and von Neumann, Thilo and Haeb-Umbach, Reinhold}, year={2023} }'
chicago: Boeddeker, Christoph, Tobias Cord-Landwehr, Thilo von Neumann, and Reinhold
Haeb-Umbach. “Multi-Stage Diarization Refinement for the CHiME-7 DASR Scenario.”
In 7th International Workshop on Speech Processing in Everyday Environments
(CHiME 2023). ISCA, 2023. https://doi.org/10.21437/chime.2023-10.
ieee: 'C. Boeddeker, T. Cord-Landwehr, T. von Neumann, and R. Haeb-Umbach, “Multi-stage
diarization refinement for the CHiME-7 DASR scenario,” 2023, doi: 10.21437/chime.2023-10.'
mla: Boeddeker, Christoph, et al. “Multi-Stage Diarization Refinement for the CHiME-7
DASR Scenario.” 7th International Workshop on Speech Processing in Everyday
Environments (CHiME 2023), ISCA, 2023, doi:10.21437/chime.2023-10.
short: 'C. Boeddeker, T. Cord-Landwehr, T. von Neumann, R. Haeb-Umbach, in: 7th
International Workshop on Speech Processing in Everyday Environments (CHiME 2023),
ISCA, 2023.'
date_created: 2024-05-23T15:16:15Z
date_updated: 2025-02-12T09:16:13Z
department:
- _id: '54'
doi: 10.21437/chime.2023-10
language:
- iso: eng
main_file_link:
- open_access: '1'
url: https://www.isca-archive.org/chime_2023/boeddeker23_chime.pdf
oa: '1'
project:
- _id: '52'
name: 'PC2: Computing Resources Provided by the Paderborn Center for Parallel Computing'
- _id: '508'
grant_number: '448568305'
name: Automatische Transkription von Gesprächssituationen
publication: 7th International Workshop on Speech Processing in Everyday Environments
(CHiME 2023)
publication_status: published
publisher: ISCA
status: public
title: Multi-stage diarization refinement for the CHiME-7 DASR scenario
type: conference
user_id: '40767'
year: '2023'
...
---
_id: '33847'
abstract:
- lang: eng
text: "The scope of speech enhancement has changed from a monolithic view of single,\r\nindependent
tasks, to a joint processing of complex conversational speech\r\nrecordings. Training
and evaluation of these single tasks requires synthetic\r\ndata with access to
intermediate signals that is as close as possible to the\r\nevaluation scenario.
As such data often is not available, many works instead\r\nuse specialized databases
for the training of each system component, e.g\r\nWSJ0-mix for source separation.
We present a Multi-purpose Multi-Speaker\r\nMixture Signal Generator (MMS-MSG)
for generating a variety of speech mixture\r\nsignals based on any speech corpus,
ranging from classical anechoic mixtures\r\n(e.g., WSJ0-mix) over reverberant
mixtures (e.g., SMS-WSJ) to meeting-style\r\ndata. Its highly modular and flexible
structure allows for the simulation of\r\ndiverse environments and dynamic mixing,
while simultaneously enabling an easy\r\nextension and modification to generate
new scenarios and mixture types. These\r\nmeetings can be used for prototyping,
evaluation, or training purposes. We\r\nprovide example evaluation data and baseline
results for meetings based on the\r\nWSJ corpus. Further, we demonstrate the usefulness
for realistic scenarios by\r\nusing MMS-MSG to provide training data for the LibriCSS
database."
author:
- first_name: Tobias
full_name: Cord-Landwehr, Tobias
id: '44393'
last_name: Cord-Landwehr
- first_name: Thilo
full_name: von Neumann, Thilo
id: '49870'
last_name: von Neumann
orcid: https://orcid.org/0000-0002-7717-8670
- first_name: Christoph
full_name: Boeddeker, Christoph
id: '40767'
last_name: Boeddeker
- first_name: Reinhold
full_name: Haeb-Umbach, Reinhold
id: '242'
last_name: Haeb-Umbach
citation:
ama: 'Cord-Landwehr T, von Neumann T, Boeddeker C, Haeb-Umbach R. MMS-MSG: A Multi-purpose
Multi-Speaker Mixture Signal Generator. In: 2022 International Workshop on
Acoustic Signal Enhancement (IWAENC). ; 2022.'
apa: 'Cord-Landwehr, T., von Neumann, T., Boeddeker, C., & Haeb-Umbach, R. (2022).
MMS-MSG: A Multi-purpose Multi-Speaker Mixture Signal Generator. 2022 International
Workshop on Acoustic Signal Enhancement (IWAENC). 2022 International Workshop
on Acoustic Signal Enhancement (IWAENC), Bamberg.'
bibtex: '@inproceedings{Cord-Landwehr_von Neumann_Boeddeker_Haeb-Umbach_2022, title={MMS-MSG:
A Multi-purpose Multi-Speaker Mixture Signal Generator}, booktitle={2022 International
Workshop on Acoustic Signal Enhancement (IWAENC)}, author={Cord-Landwehr, Tobias
and von Neumann, Thilo and Boeddeker, Christoph and Haeb-Umbach, Reinhold}, year={2022}
}'
chicago: 'Cord-Landwehr, Tobias, Thilo von Neumann, Christoph Boeddeker, and Reinhold
Haeb-Umbach. “MMS-MSG: A Multi-Purpose Multi-Speaker Mixture Signal Generator.”
In 2022 International Workshop on Acoustic Signal Enhancement (IWAENC),
2022.'
ieee: 'T. Cord-Landwehr, T. von Neumann, C. Boeddeker, and R. Haeb-Umbach, “MMS-MSG:
A Multi-purpose Multi-Speaker Mixture Signal Generator,” presented at the 2022
International Workshop on Acoustic Signal Enhancement (IWAENC), Bamberg, 2022.'
mla: 'Cord-Landwehr, Tobias, et al. “MMS-MSG: A Multi-Purpose Multi-Speaker Mixture
Signal Generator.” 2022 International Workshop on Acoustic Signal Enhancement
(IWAENC), 2022.'
short: 'T. Cord-Landwehr, T. von Neumann, C. Boeddeker, R. Haeb-Umbach, in: 2022
International Workshop on Acoustic Signal Enhancement (IWAENC), 2022.'
conference:
location: Bamberg
name: 2022 International Workshop on Acoustic Signal Enhancement (IWAENC)
date_created: 2022-10-20T14:02:14Z
date_updated: 2023-11-15T14:55:14Z
ddc:
- '000'
department:
- _id: '54'
external_id:
arxiv:
- '2209.11494'
file:
- access_level: open_access
content_type: application/pdf
creator: cord
date_created: 2023-11-15T14:54:56Z
date_updated: 2023-11-15T14:54:56Z
file_id: '48931'
file_name: mms_msg_camera_ready.pdf
file_size: 177975
relation: main_file
file_date_updated: 2023-11-15T14:54:56Z
has_accepted_license: '1'
language:
- iso: eng
oa: '1'
project:
- _id: '52'
name: 'PC2: Computing Resources Provided by the Paderborn Center for Parallel Computing'
publication: 2022 International Workshop on Acoustic Signal Enhancement (IWAENC)
quality_controlled: '1'
status: public
title: 'MMS-MSG: A Multi-purpose Multi-Speaker Mixture Signal Generator'
type: conference
user_id: '44393'
year: '2022'
...
---
_id: '33848'
abstract:
- lang: eng
text: "Impressive progress in neural network-based single-channel speech source\r\nseparation
has been made in recent years. But those improvements have been\r\nmostly reported
on anechoic data, a situation that is hardly met in practice.\r\nTaking the SepFormer
as a starting point, which achieves state-of-the-art\r\nperformance on anechoic
mixtures, we gradually modify it to optimize its\r\nperformance on reverberant
mixtures. Although this leads to a word error rate\r\nimprovement by 7 percentage
points compared to the standard SepFormer\r\nimplementation, the system ends up
with only marginally better performance than\r\na PIT-BLSTM separation system,
that is optimized with rather straightforward\r\nmeans. This is surprising and
at the same time sobering, challenging the\r\npractical usefulness of many improvements
reported in recent years for monaural\r\nsource separation on nonreverberant data."
author:
- first_name: Tobias
full_name: Cord-Landwehr, Tobias
id: '44393'
last_name: Cord-Landwehr
- first_name: Christoph
full_name: Boeddeker, Christoph
id: '40767'
last_name: Boeddeker
- first_name: Thilo
full_name: von Neumann, Thilo
id: '49870'
last_name: von Neumann
orcid: https://orcid.org/0000-0002-7717-8670
- first_name: Catalin
full_name: Zorila, Catalin
last_name: Zorila
- first_name: Rama
full_name: Doddipatla, Rama
last_name: Doddipatla
- first_name: Reinhold
full_name: Haeb-Umbach, Reinhold
id: '242'
last_name: Haeb-Umbach
citation:
ama: 'Cord-Landwehr T, Boeddeker C, von Neumann T, Zorila C, Doddipatla R, Haeb-Umbach
R. Monaural source separation: From anechoic to reverberant environments. In:
2022 International Workshop on Acoustic Signal Enhancement (IWAENC). IEEE;
2022.'
apa: 'Cord-Landwehr, T., Boeddeker, C., von Neumann, T., Zorila, C., Doddipatla,
R., & Haeb-Umbach, R. (2022). Monaural source separation: From anechoic to
reverberant environments. 2022 International Workshop on Acoustic Signal Enhancement
(IWAENC). 2022 International Workshop on Acoustic Signal Enhancement (IWAENC).'
bibtex: '@inproceedings{Cord-Landwehr_Boeddeker_von Neumann_Zorila_Doddipatla_Haeb-Umbach_2022,
place={Bamberg}, title={Monaural source separation: From anechoic to reverberant
environments}, booktitle={2022 International Workshop on Acoustic Signal Enhancement
(IWAENC)}, publisher={IEEE}, author={Cord-Landwehr, Tobias and Boeddeker, Christoph
and von Neumann, Thilo and Zorila, Catalin and Doddipatla, Rama and Haeb-Umbach,
Reinhold}, year={2022} }'
chicago: 'Cord-Landwehr, Tobias, Christoph Boeddeker, Thilo von Neumann, Catalin
Zorila, Rama Doddipatla, and Reinhold Haeb-Umbach. “Monaural Source Separation:
From Anechoic to Reverberant Environments.” In 2022 International Workshop
on Acoustic Signal Enhancement (IWAENC). Bamberg: IEEE, 2022.'
ieee: 'T. Cord-Landwehr, C. Boeddeker, T. von Neumann, C. Zorila, R. Doddipatla,
and R. Haeb-Umbach, “Monaural source separation: From anechoic to reverberant
environments,” presented at the 2022 International Workshop on Acoustic Signal
Enhancement (IWAENC), 2022.'
mla: 'Cord-Landwehr, Tobias, et al. “Monaural Source Separation: From Anechoic to
Reverberant Environments.” 2022 International Workshop on Acoustic Signal Enhancement
(IWAENC), IEEE, 2022.'
short: 'T. Cord-Landwehr, C. Boeddeker, T. von Neumann, C. Zorila, R. Doddipatla,
R. Haeb-Umbach, in: 2022 International Workshop on Acoustic Signal Enhancement
(IWAENC), IEEE, Bamberg, 2022.'
conference:
name: 2022 International Workshop on Acoustic Signal Enhancement (IWAENC)
date_created: 2022-10-20T14:07:28Z
date_updated: 2025-02-12T09:05:25Z
ddc:
- '000'
department:
- _id: '54'
external_id:
arxiv:
- '2111.07578'
file:
- access_level: open_access
content_type: application/pdf
creator: cord
date_created: 2023-11-15T14:52:16Z
date_updated: 2023-11-15T14:52:16Z
file_id: '48930'
file_name: monaural_source_separation.pdf
file_size: 212890
relation: main_file
file_date_updated: 2023-11-15T14:52:16Z
has_accepted_license: '1'
language:
- iso: eng
oa: '1'
place: Bamberg
project:
- _id: '52'
name: 'PC2: Computing Resources Provided by the Paderborn Center for Parallel Computing'
- _id: '508'
grant_number: '448568305'
name: Automatische Transkription von Gesprächssituationen
publication: 2022 International Workshop on Acoustic Signal Enhancement (IWAENC)
publisher: IEEE
status: public
title: 'Monaural source separation: From anechoic to reverberant environments'
type: conference
user_id: '40767'
year: '2022'
...
---
_id: '33819'
author:
- first_name: Thilo
full_name: von Neumann, Thilo
id: '49870'
last_name: von Neumann
orcid: https://orcid.org/0000-0002-7717-8670
- first_name: Keisuke
full_name: Kinoshita, Keisuke
last_name: Kinoshita
- first_name: Christoph
full_name: Boeddeker, Christoph
id: '40767'
last_name: Boeddeker
- first_name: Marc
full_name: Delcroix, Marc
last_name: Delcroix
- first_name: Reinhold
full_name: Haeb-Umbach, Reinhold
id: '242'
last_name: Haeb-Umbach
citation:
ama: 'von Neumann T, Kinoshita K, Boeddeker C, Delcroix M, Haeb-Umbach R. SA-SDR:
A Novel Loss Function for Separation of Meeting Style Data. In: ICASSP 2022
- 2022 IEEE International Conference on Acoustics, Speech and Signal Processing
(ICASSP). IEEE; 2022. doi:10.1109/icassp43922.2022.9746757'
apa: 'von Neumann, T., Kinoshita, K., Boeddeker, C., Delcroix, M., & Haeb-Umbach,
R. (2022). SA-SDR: A Novel Loss Function for Separation of Meeting Style Data.
ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal
Processing (ICASSP). https://doi.org/10.1109/icassp43922.2022.9746757'
bibtex: '@inproceedings{von Neumann_Kinoshita_Boeddeker_Delcroix_Haeb-Umbach_2022,
title={SA-SDR: A Novel Loss Function for Separation of Meeting Style Data}, DOI={10.1109/icassp43922.2022.9746757},
booktitle={ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech
and Signal Processing (ICASSP)}, publisher={IEEE}, author={von Neumann, Thilo
and Kinoshita, Keisuke and Boeddeker, Christoph and Delcroix, Marc and Haeb-Umbach,
Reinhold}, year={2022} }'
chicago: 'Neumann, Thilo von, Keisuke Kinoshita, Christoph Boeddeker, Marc Delcroix,
and Reinhold Haeb-Umbach. “SA-SDR: A Novel Loss Function for Separation of Meeting
Style Data.” In ICASSP 2022 - 2022 IEEE International Conference on Acoustics,
Speech and Signal Processing (ICASSP). IEEE, 2022. https://doi.org/10.1109/icassp43922.2022.9746757.'
ieee: 'T. von Neumann, K. Kinoshita, C. Boeddeker, M. Delcroix, and R. Haeb-Umbach,
“SA-SDR: A Novel Loss Function for Separation of Meeting Style Data,” 2022, doi:
10.1109/icassp43922.2022.9746757.'
mla: 'von Neumann, Thilo, et al. “SA-SDR: A Novel Loss Function for Separation of
Meeting Style Data.” ICASSP 2022 - 2022 IEEE International Conference on Acoustics,
Speech and Signal Processing (ICASSP), IEEE, 2022, doi:10.1109/icassp43922.2022.9746757.'
short: 'T. von Neumann, K. Kinoshita, C. Boeddeker, M. Delcroix, R. Haeb-Umbach,
in: ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and
Signal Processing (ICASSP), IEEE, 2022.'
date_created: 2022-10-20T05:29:12Z
date_updated: 2025-02-12T09:08:14Z
ddc:
- '000'
department:
- _id: '54'
doi: 10.1109/icassp43922.2022.9746757
file:
- access_level: open_access
content_type: application/pdf
creator: tvn
date_created: 2022-10-20T05:33:10Z
date_updated: 2022-10-20T05:33:10Z
file_id: '33820'
file_name: main.pdf
file_size: 228069
relation: main_file
- access_level: open_access
content_type: application/pdf
creator: tvn
date_created: 2022-10-20T05:35:32Z
date_updated: 2022-10-20T05:35:32Z
file_id: '33821'
file_name: poster.pdf
file_size: 229166
relation: poster
file_date_updated: 2022-10-20T05:35:32Z
has_accepted_license: '1'
language:
- iso: eng
oa: '1'
project:
- _id: '52'
name: 'PC2: Computing Resources Provided by the Paderborn Center for Parallel Computing'
- _id: '508'
grant_number: '448568305'
name: Automatische Transkription von Gesprächssituationen
publication: ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech
and Signal Processing (ICASSP)
publication_status: published
publisher: IEEE
quality_controlled: '1'
related_material:
link:
- relation: supplementary_material
url: https://github.com/fgnt/graph_pit
status: public
title: 'SA-SDR: A Novel Loss Function for Separation of Meeting Style Data'
type: conference
user_id: '40767'
year: '2022'
...
---
_id: '33816'
author:
- first_name: Tobias
full_name: Gburrek, Tobias
id: '44006'
last_name: Gburrek
- first_name: Christoph
full_name: Boeddeker, Christoph
id: '40767'
last_name: Boeddeker
- first_name: Thilo
full_name: von Neumann, Thilo
id: '49870'
last_name: von Neumann
orcid: https://orcid.org/0000-0002-7717-8670
- first_name: Tobias
full_name: Cord-Landwehr, Tobias
id: '44393'
last_name: Cord-Landwehr
- first_name: Joerg
full_name: Schmalenstroeer, Joerg
id: '460'
last_name: Schmalenstroeer
- first_name: Reinhold
full_name: Haeb-Umbach, Reinhold
id: '242'
last_name: Haeb-Umbach
citation:
ama: Gburrek T, Boeddeker C, von Neumann T, Cord-Landwehr T, Schmalenstroeer J,
Haeb-Umbach R. A Meeting Transcription System for an Ad-Hoc Acoustic Sensor
Network. arXiv; 2022. doi:10.48550/ARXIV.2205.00944
apa: Gburrek, T., Boeddeker, C., von Neumann, T., Cord-Landwehr, T., Schmalenstroeer,
J., & Haeb-Umbach, R. (2022). A Meeting Transcription System for an Ad-Hoc
Acoustic Sensor Network. arXiv. https://doi.org/10.48550/ARXIV.2205.00944
bibtex: '@book{Gburrek_Boeddeker_von Neumann_Cord-Landwehr_Schmalenstroeer_Haeb-Umbach_2022,
title={A Meeting Transcription System for an Ad-Hoc Acoustic Sensor Network},
DOI={10.48550/ARXIV.2205.00944},
publisher={arXiv}, author={Gburrek, Tobias and Boeddeker, Christoph and von Neumann,
Thilo and Cord-Landwehr, Tobias and Schmalenstroeer, Joerg and Haeb-Umbach, Reinhold},
year={2022} }'
chicago: Gburrek, Tobias, Christoph Boeddeker, Thilo von Neumann, Tobias Cord-Landwehr,
Joerg Schmalenstroeer, and Reinhold Haeb-Umbach. A Meeting Transcription System
for an Ad-Hoc Acoustic Sensor Network. arXiv, 2022. https://doi.org/10.48550/ARXIV.2205.00944.
ieee: T. Gburrek, C. Boeddeker, T. von Neumann, T. Cord-Landwehr, J. Schmalenstroeer,
and R. Haeb-Umbach, A Meeting Transcription System for an Ad-Hoc Acoustic Sensor
Network. arXiv, 2022.
mla: Gburrek, Tobias, et al. A Meeting Transcription System for an Ad-Hoc Acoustic
Sensor Network. arXiv, 2022, doi:10.48550/ARXIV.2205.00944.
short: T. Gburrek, C. Boeddeker, T. von Neumann, T. Cord-Landwehr, J. Schmalenstroeer,
R. Haeb-Umbach, A Meeting Transcription System for an Ad-Hoc Acoustic Sensor Network,
arXiv, 2022.
date_created: 2022-10-18T11:10:58Z
date_updated: 2025-02-12T09:03:42Z
ddc:
- '004'
department:
- _id: '54'
doi: 10.48550/ARXIV.2205.00944
file:
- access_level: open_access
content_type: application/pdf
creator: tgburrek
date_created: 2023-11-17T06:42:04Z
date_updated: 2023-11-17T06:42:04Z
file_id: '48992'
file_name: meeting_transcription_22.pdf
file_size: 199006
relation: main_file
file_date_updated: 2023-11-17T06:42:04Z
has_accepted_license: '1'
language:
- iso: eng
oa: '1'
project:
- _id: '52'
name: 'PC2: Computing Resources Provided by the Paderborn Center for Parallel Computing'
- _id: '508'
grant_number: '448568305'
name: Automatische Transkription von Gesprächssituationen
publisher: arXiv
status: public
title: A Meeting Transcription System for an Ad-Hoc Acoustic Sensor Network
type: misc
user_id: '40767'
year: '2022'
...
---
_id: '33954'
author:
- first_name: Christoph
full_name: Boeddeker, Christoph
id: '40767'
last_name: Boeddeker
- first_name: Tobias
full_name: Cord-Landwehr, Tobias
id: '44393'
last_name: Cord-Landwehr
- first_name: Thilo
full_name: von Neumann, Thilo
id: '49870'
last_name: von Neumann
orcid: https://orcid.org/0000-0002-7717-8670
- first_name: Reinhold
full_name: Haeb-Umbach, Reinhold
id: '242'
last_name: Haeb-Umbach
citation:
ama: 'Boeddeker C, Cord-Landwehr T, von Neumann T, Haeb-Umbach R. An Initialization
Scheme for Meeting Separation with Spatial Mixture Models. In: Interspeech
2022. ISCA; 2022. doi:10.21437/interspeech.2022-10929'
apa: Boeddeker, C., Cord-Landwehr, T., von Neumann, T., & Haeb-Umbach, R. (2022).
An Initialization Scheme for Meeting Separation with Spatial Mixture Models. Interspeech
2022. https://doi.org/10.21437/interspeech.2022-10929
bibtex: '@inproceedings{Boeddeker_Cord-Landwehr_von Neumann_Haeb-Umbach_2022, title={An
Initialization Scheme for Meeting Separation with Spatial Mixture Models}, DOI={10.21437/interspeech.2022-10929},
booktitle={Interspeech 2022}, publisher={ISCA}, author={Boeddeker, Christoph and
Cord-Landwehr, Tobias and von Neumann, Thilo and Haeb-Umbach, Reinhold}, year={2022}
}'
chicago: Boeddeker, Christoph, Tobias Cord-Landwehr, Thilo von Neumann, and Reinhold
Haeb-Umbach. “An Initialization Scheme for Meeting Separation with Spatial Mixture
Models.” In Interspeech 2022. ISCA, 2022. https://doi.org/10.21437/interspeech.2022-10929.
ieee: 'C. Boeddeker, T. Cord-Landwehr, T. von Neumann, and R. Haeb-Umbach, “An Initialization
Scheme for Meeting Separation with Spatial Mixture Models,” 2022, doi: 10.21437/interspeech.2022-10929.'
mla: Boeddeker, Christoph, et al. “An Initialization Scheme for Meeting Separation
with Spatial Mixture Models.” Interspeech 2022, ISCA, 2022, doi:10.21437/interspeech.2022-10929.
short: 'C. Boeddeker, T. Cord-Landwehr, T. von Neumann, R. Haeb-Umbach, in: Interspeech
2022, ISCA, 2022.'
date_created: 2022-10-28T10:53:56Z
date_updated: 2025-02-12T09:06:56Z
department:
- _id: '54'
doi: 10.21437/interspeech.2022-10929
language:
- iso: eng
main_file_link:
- open_access: '1'
url: https://www.isca-archive.org/interspeech_2022/boeddeker22_interspeech.pdf
oa: '1'
project:
- _id: '52'
name: 'PC2: Computing Resources Provided by the Paderborn Center for Parallel Computing'
- _id: '508'
grant_number: '448568305'
name: Automatische Transkription von Gesprächssituationen
publication: Interspeech 2022
publication_status: published
publisher: ISCA
status: public
title: An Initialization Scheme for Meeting Separation with Spatial Mixture Models
type: conference
user_id: '40767'
year: '2022'
...
---
_id: '33958'
abstract:
- lang: eng
text: Recent speaker diarization studies showed that integration of end-to-end neural
diarization (EEND) and clustering-based diarization is a promising approach for
achieving state-of-the-art performance on various tasks. Such an approach first
divides an observed signal into fixed-length segments, then performs {\it segment-level}
local diarization based on an EEND module, and merges the segment-level results
via clustering to form a final global diarization result. The segmentation is
done to limit the number of speakers in each segment since the current EEND cannot
handle a large number of speakers. In this paper, we argue that such an approach
involving the segmentation has several issues; for example, it inevitably faces
a dilemma that larger segment sizes increase both the context available for enhancing
the performance and the number of speakers for the local EEND module to handle.
To resolve such a problem, this paper proposes a novel framework that performs
diarization without segmentation. However, it can still handle challenging data
containing many speakers and a significant amount of overlapping speech. The proposed
method can take an entire meeting for inference and perform {\it utterance-by-utterance}
diarization that clusters utterance activities in terms of speakers. To this end,
we leverage a neural network training scheme called Graph-PIT proposed recently
for neural source separation. Experiments with simulated active-meeting-like data
and CALLHOME data show the superiority of the proposed approach over the conventional
methods.
author:
- first_name: Keisuke
full_name: Kinoshita, Keisuke
last_name: Kinoshita
- first_name: Thilo
full_name: von Neumann, Thilo
id: '49870'
last_name: von Neumann
orcid: https://orcid.org/0000-0002-7717-8670
- first_name: Marc
full_name: Delcroix, Marc
last_name: Delcroix
- first_name: Christoph
full_name: Boeddeker, Christoph
id: '40767'
last_name: Boeddeker
- first_name: Reinhold
full_name: Haeb-Umbach, Reinhold
id: '242'
last_name: Haeb-Umbach
citation:
ama: 'Kinoshita K, von Neumann T, Delcroix M, Boeddeker C, Haeb-Umbach R. Utterance-by-utterance
overlap-aware neural diarization with Graph-PIT. In: Proc. Interspeech 2022.
ISCA; 2022:1486-1490. doi:10.21437/Interspeech.2022-11408'
apa: Kinoshita, K., von Neumann, T., Delcroix, M., Boeddeker, C., & Haeb-Umbach,
R. (2022). Utterance-by-utterance overlap-aware neural diarization with Graph-PIT.
Proc. Interspeech 2022, 1486–1490. https://doi.org/10.21437/Interspeech.2022-11408
bibtex: '@inproceedings{Kinoshita_von Neumann_Delcroix_Boeddeker_Haeb-Umbach_2022,
title={Utterance-by-utterance overlap-aware neural diarization with Graph-PIT},
DOI={10.21437/Interspeech.2022-11408},
booktitle={Proc. Interspeech 2022}, publisher={ISCA}, author={Kinoshita, Keisuke
and von Neumann, Thilo and Delcroix, Marc and Boeddeker, Christoph and Haeb-Umbach,
Reinhold}, year={2022}, pages={1486–1490} }'
chicago: Kinoshita, Keisuke, Thilo von Neumann, Marc Delcroix, Christoph Boeddeker,
and Reinhold Haeb-Umbach. “Utterance-by-Utterance Overlap-Aware Neural Diarization
with Graph-PIT.” In Proc. Interspeech 2022, 1486–90. ISCA, 2022. https://doi.org/10.21437/Interspeech.2022-11408.
ieee: 'K. Kinoshita, T. von Neumann, M. Delcroix, C. Boeddeker, and R. Haeb-Umbach,
“Utterance-by-utterance overlap-aware neural diarization with Graph-PIT,” in Proc.
Interspeech 2022, 2022, pp. 1486–1490, doi: 10.21437/Interspeech.2022-11408.'
mla: Kinoshita, Keisuke, et al. “Utterance-by-Utterance Overlap-Aware Neural Diarization
with Graph-PIT.” Proc. Interspeech 2022, ISCA, 2022, pp. 1486–90, doi:10.21437/Interspeech.2022-11408.
short: 'K. Kinoshita, T. von Neumann, M. Delcroix, C. Boeddeker, R. Haeb-Umbach,
in: Proc. Interspeech 2022, ISCA, 2022, pp. 1486–1490.'
conference:
name: Interspeech 2022
date_created: 2022-10-28T12:07:57Z
date_updated: 2025-02-12T09:09:05Z
department:
- _id: '54'
doi: 10.21437/Interspeech.2022-11408
language:
- iso: eng
main_file_link:
- url: https://www.isca-archive.org/interspeech_2022/kinoshita22_interspeech.pdf
page: 1486-1490
publication: Proc. Interspeech 2022
publication_status: published
publisher: ISCA
quality_controlled: '1'
status: public
title: Utterance-by-utterance overlap-aware neural diarization with Graph-PIT
type: conference
user_id: '40767'
year: '2022'
...
---
_id: '26770'
abstract:
- lang: eng
text: "Automatic transcription of meetings requires handling of overlapped speech,
which calls for continuous speech separation (CSS) systems. The uPIT criterion
was proposed for utterance-level separation with neural networks and introduces
the constraint that the total number of speakers must not exceed the number of
output channels. When processing meeting-like data in a segment-wise manner, i.e.,
by separating overlapping segments independently and stitching adjacent segments
to continuous output streams, this constraint has to be fulfilled for any segment.
In this contribution, we show that this constraint can be significantly relaxed.
We propose a novel graph-based PIT criterion, which casts the assignment of utterances
to output channels in a graph coloring problem. It only requires that the number
of concurrently active speakers must not exceed the number of output channels.
As a consequence, the system can process an arbitrary number of speakers and arbitrarily
long segments and thus can handle more diverse scenarios.\r\nFurther, the stitching
algorithm for obtaining a consistent output order in neighboring segments is of
less importance and can even be eliminated completely, not the least reducing
the computational effort. Experiments on meeting-style WSJ data show improvements
in recognition performance over using the uPIT criterion. "
author:
- first_name: Thilo
full_name: von Neumann, Thilo
id: '49870'
last_name: von Neumann
orcid: https://orcid.org/0000-0002-7717-8670
- first_name: Keisuke
full_name: Kinoshita, Keisuke
last_name: Kinoshita
- first_name: Christoph
full_name: Boeddeker, Christoph
id: '40767'
last_name: Boeddeker
- first_name: Marc
full_name: Delcroix, Marc
last_name: Delcroix
- first_name: Reinhold
full_name: Haeb-Umbach, Reinhold
id: '242'
last_name: Haeb-Umbach
citation:
ama: 'von Neumann T, Kinoshita K, Boeddeker C, Delcroix M, Haeb-Umbach R. Graph-PIT:
Generalized Permutation Invariant Training for Continuous Separation of Arbitrary
Numbers of Speakers. In: Interspeech 2021. ; 2021. doi:10.21437/interspeech.2021-1177'
apa: 'von Neumann, T., Kinoshita, K., Boeddeker, C., Delcroix, M., & Haeb-Umbach,
R. (2021). Graph-PIT: Generalized Permutation Invariant Training for Continuous
Separation of Arbitrary Numbers of Speakers. Interspeech 2021. Interspeech.
https://doi.org/10.21437/interspeech.2021-1177'
bibtex: '@inproceedings{von Neumann_Kinoshita_Boeddeker_Delcroix_Haeb-Umbach_2021,
title={Graph-PIT: Generalized Permutation Invariant Training for Continuous Separation
of Arbitrary Numbers of Speakers}, DOI={10.21437/interspeech.2021-1177},
booktitle={Interspeech 2021}, author={von Neumann, Thilo and Kinoshita, Keisuke
and Boeddeker, Christoph and Delcroix, Marc and Haeb-Umbach, Reinhold}, year={2021}
}'
chicago: 'Neumann, Thilo von, Keisuke Kinoshita, Christoph Boeddeker, Marc Delcroix,
and Reinhold Haeb-Umbach. “Graph-PIT: Generalized Permutation Invariant Training
for Continuous Separation of Arbitrary Numbers of Speakers.” In Interspeech
2021, 2021. https://doi.org/10.21437/interspeech.2021-1177.'
ieee: 'T. von Neumann, K. Kinoshita, C. Boeddeker, M. Delcroix, and R. Haeb-Umbach,
“Graph-PIT: Generalized Permutation Invariant Training for Continuous Separation
of Arbitrary Numbers of Speakers,” presented at the Interspeech, 2021, doi: 10.21437/interspeech.2021-1177.'
mla: 'von Neumann, Thilo, et al. “Graph-PIT: Generalized Permutation Invariant Training
for Continuous Separation of Arbitrary Numbers of Speakers.” Interspeech 2021,
2021, doi:10.21437/interspeech.2021-1177.'
short: 'T. von Neumann, K. Kinoshita, C. Boeddeker, M. Delcroix, R. Haeb-Umbach,
in: Interspeech 2021, 2021.'
conference:
name: Interspeech
date_created: 2021-10-25T08:50:01Z
date_updated: 2023-11-15T12:14:40Z
ddc:
- '000'
department:
- _id: '54'
doi: 10.21437/interspeech.2021-1177
file:
- access_level: open_access
content_type: video/mp4
creator: tvn
date_created: 2021-12-06T10:39:13Z
date_updated: 2021-12-06T10:48:30Z
file_id: '28327'
file_name: Interspeech 2021 voiceover-002-compressed.mp4
file_size: 9550220
relation: supplementary_material
title: Video for INTERSPEECH 2021
- access_level: open_access
content_type: application/vnd.openxmlformats-officedocument.presentationml.presentation
creator: tvn
date_created: 2021-12-06T10:47:01Z
date_updated: 2021-12-06T10:47:01Z
file_id: '28328'
file_name: Graph-PIT-poster-presentation.pptx
file_size: 1337297
relation: slides
title: Slides from INTERSPEECH 2021
- access_level: open_access
content_type: application/pdf
creator: tvn
date_created: 2021-12-06T10:48:21Z
date_updated: 2021-12-06T10:48:21Z
file_id: '28329'
file_name: INTERSPEECH2021_Graph_PIT.pdf
file_size: 226589
relation: main_file
file_date_updated: 2021-12-06T10:48:30Z
has_accepted_license: '1'
keyword:
- Continuous speech separation
- automatic speech recognition
- overlapped speech
- permutation invariant training
language:
- iso: eng
oa: '1'
project:
- _id: '52'
name: 'PC2: Computing Resources Provided by the Paderborn Center for Parallel Computing'
publication: Interspeech 2021
publication_status: published
quality_controlled: '1'
related_material:
link:
- relation: software
url: https://github.com/fgnt/graph_pit
status: public
title: 'Graph-PIT: Generalized Permutation Invariant Training for Continuous Separation
of Arbitrary Numbers of Speakers'
type: conference
user_id: '49870'
year: '2021'
...
---
_id: '29173'
author:
- first_name: Thilo
full_name: von Neumann, Thilo
id: '49870'
last_name: von Neumann
orcid: https://orcid.org/0000-0002-7717-8670
- first_name: Christoph
full_name: Boeddeker, Christoph
id: '40767'
last_name: Boeddeker
- first_name: Keisuke
full_name: Kinoshita, Keisuke
last_name: Kinoshita
- first_name: Marc
full_name: Delcroix, Marc
last_name: Delcroix
- first_name: Reinhold
full_name: Haeb-Umbach, Reinhold
id: '242'
last_name: Haeb-Umbach
citation:
ama: 'von Neumann T, Boeddeker C, Kinoshita K, Delcroix M, Haeb-Umbach R. Speeding
Up Permutation Invariant Training for Source Separation. In: Speech Communication;
14th ITG Conference. ; 2021.'
apa: von Neumann, T., Boeddeker, C., Kinoshita, K., Delcroix, M., & Haeb-Umbach,
R. (2021). Speeding Up Permutation Invariant Training for Source Separation. Speech
Communication; 14th ITG Conference. Speech Communication; 14th ITG Conference,
Kiel.
bibtex: '@inproceedings{von Neumann_Boeddeker_Kinoshita_Delcroix_Haeb-Umbach_2021,
title={Speeding Up Permutation Invariant Training for Source Separation}, booktitle={Speech
Communication; 14th ITG Conference}, author={von Neumann, Thilo and Boeddeker,
Christoph and Kinoshita, Keisuke and Delcroix, Marc and Haeb-Umbach, Reinhold},
year={2021} }'
chicago: Neumann, Thilo von, Christoph Boeddeker, Keisuke Kinoshita, Marc Delcroix,
and Reinhold Haeb-Umbach. “Speeding Up Permutation Invariant Training for Source
Separation.” In Speech Communication; 14th ITG Conference, 2021.
ieee: T. von Neumann, C. Boeddeker, K. Kinoshita, M. Delcroix, and R. Haeb-Umbach,
“Speeding Up Permutation Invariant Training for Source Separation,” presented
at the Speech Communication; 14th ITG Conference, Kiel, 2021.
mla: von Neumann, Thilo, et al. “Speeding Up Permutation Invariant Training for
Source Separation.” Speech Communication; 14th ITG Conference, 2021.
short: 'T. von Neumann, C. Boeddeker, K. Kinoshita, M. Delcroix, R. Haeb-Umbach,
in: Speech Communication; 14th ITG Conference, 2021.'
conference:
end_date: 2021-10-01
location: Kiel
name: Speech Communication; 14th ITG Conference
start_date: 2021-09-29
date_created: 2022-01-07T10:40:56Z
date_updated: 2023-11-15T12:16:31Z
ddc:
- '000'
department:
- _id: '54'
file:
- access_level: open_access
content_type: application/pdf
creator: tvn
date_created: 2022-01-06T13:23:27Z
date_updated: 2022-01-06T13:23:27Z
file_id: '29180'
file_name: poster.pdf
file_size: 191938
relation: poster
- access_level: open_access
content_type: application/pdf
creator: tvn
date_created: 2022-01-07T10:42:54Z
date_updated: 2022-01-07T10:42:54Z
file_id: '29181'
file_name: ITG2021_Speeding_up_Permutation_Invariant_Training.pdf
file_size: 236670
relation: main_file
file_date_updated: 2022-01-07T10:42:54Z
has_accepted_license: '1'
language:
- iso: eng
oa: '1'
project:
- _id: '52'
name: 'PC2: Computing Resources Provided by the Paderborn Center for Parallel Computing'
publication: Speech Communication; 14th ITG Conference
quality_controlled: '1'
status: public
title: Speeding Up Permutation Invariant Training for Source Separation
type: conference
user_id: '49870'
year: '2021'
...
---
_id: '20762'
abstract:
- lang: eng
text: The rising interest in single-channel multi-speaker speech separation sparked
development of End-to-End (E2E) approaches to multispeaker speech recognition.
However, up until now, state-of-theart neural network–based time domain source
separation has not yet been combined with E2E speech recognition. We here demonstrate
how to combine a separation module based on a Convolutional Time domain Audio
Separation Network (Conv-TasNet) with an E2E speech recognizer and how to train
such a model jointly by distributing it over multiple GPUs or by approximating
truncated back-propagation for the convolutional front-end. To put this work into
perspective and illustrate the complexity of the design space, we provide a compact
overview of single-channel multi-speaker recognition systems. Our experiments
show a word error rate of 11.0% on WSJ0-2mix and indicate that our joint time
domain model can yield substantial improvements over cascade DNN-HMM and monolithic
E2E frequency domain systems proposed so far.
author:
- first_name: Thilo
full_name: von Neumann, Thilo
id: '49870'
last_name: von Neumann
orcid: https://orcid.org/0000-0002-7717-8670
- first_name: Keisuke
full_name: Kinoshita, Keisuke
last_name: Kinoshita
- first_name: Lukas
full_name: Drude, Lukas
last_name: Drude
- first_name: Christoph
full_name: Boeddeker, Christoph
id: '40767'
last_name: Boeddeker
- first_name: Marc
full_name: Delcroix, Marc
last_name: Delcroix
- first_name: Tomohiro
full_name: Nakatani, Tomohiro
last_name: Nakatani
- first_name: Reinhold
full_name: Haeb-Umbach, Reinhold
id: '242'
last_name: Haeb-Umbach
citation:
ama: 'von Neumann T, Kinoshita K, Drude L, et al. End-to-End Training of Time Domain
Audio Separation and Recognition. In: ICASSP 2020 - 2020 IEEE International
Conference on Acoustics, Speech and Signal Processing (ICASSP). ; 2020:7004-7008.
doi:10.1109/ICASSP40776.2020.9053461'
apa: von Neumann, T., Kinoshita, K., Drude, L., Boeddeker, C., Delcroix, M., Nakatani,
T., & Haeb-Umbach, R. (2020). End-to-End Training of Time Domain Audio Separation
and Recognition. ICASSP 2020 - 2020 IEEE International Conference on Acoustics,
Speech and Signal Processing (ICASSP), 7004–7008. https://doi.org/10.1109/ICASSP40776.2020.9053461
bibtex: '@inproceedings{von Neumann_Kinoshita_Drude_Boeddeker_Delcroix_Nakatani_Haeb-Umbach_2020,
title={End-to-End Training of Time Domain Audio Separation and Recognition}, DOI={10.1109/ICASSP40776.2020.9053461},
booktitle={ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech
and Signal Processing (ICASSP)}, author={von Neumann, Thilo and Kinoshita, Keisuke
and Drude, Lukas and Boeddeker, Christoph and Delcroix, Marc and Nakatani, Tomohiro
and Haeb-Umbach, Reinhold}, year={2020}, pages={7004–7008} }'
chicago: Neumann, Thilo von, Keisuke Kinoshita, Lukas Drude, Christoph Boeddeker,
Marc Delcroix, Tomohiro Nakatani, and Reinhold Haeb-Umbach. “End-to-End Training
of Time Domain Audio Separation and Recognition.” In ICASSP 2020 - 2020 IEEE
International Conference on Acoustics, Speech and Signal Processing (ICASSP),
7004–8, 2020. https://doi.org/10.1109/ICASSP40776.2020.9053461.
ieee: 'T. von Neumann et al., “End-to-End Training of Time Domain Audio Separation
and Recognition,” in ICASSP 2020 - 2020 IEEE International Conference on Acoustics,
Speech and Signal Processing (ICASSP), 2020, pp. 7004–7008, doi: 10.1109/ICASSP40776.2020.9053461.'
mla: von Neumann, Thilo, et al. “End-to-End Training of Time Domain Audio Separation
and Recognition.” ICASSP 2020 - 2020 IEEE International Conference on Acoustics,
Speech and Signal Processing (ICASSP), 2020, pp. 7004–08, doi:10.1109/ICASSP40776.2020.9053461.
short: 'T. von Neumann, K. Kinoshita, L. Drude, C. Boeddeker, M. Delcroix, T. Nakatani,
R. Haeb-Umbach, in: ICASSP 2020 - 2020 IEEE International Conference on Acoustics,
Speech and Signal Processing (ICASSP), 2020, pp. 7004–7008.'
date_created: 2020-12-16T14:07:54Z
date_updated: 2023-11-15T12:17:45Z
ddc:
- '000'
department:
- _id: '54'
doi: 10.1109/ICASSP40776.2020.9053461
file:
- access_level: open_access
content_type: application/pdf
creator: huesera
date_created: 2020-12-16T14:09:48Z
date_updated: 2020-12-16T14:09:48Z
file_id: '20763'
file_name: ICASSP_2020_vonNeumann_Paper.pdf
file_size: 192529
relation: main_file
file_date_updated: 2020-12-16T14:09:48Z
has_accepted_license: '1'
language:
- iso: eng
oa: '1'
page: 7004-7008
project:
- _id: '52'
name: Computing Resources Provided by the Paderborn Center for Parallel Computing
publication: ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech
and Signal Processing (ICASSP)
quality_controlled: '1'
status: public
title: End-to-End Training of Time Domain Audio Separation and Recognition
type: conference
user_id: '49870'
year: '2020'
...
---
_id: '20764'
abstract:
- lang: eng
text: 'Most approaches to multi-talker overlapped speech separation and recognition
assume that the number of simultaneously active speakers is given, but in realistic
situations, it is typically unknown. To cope with this, we extend an iterative
speech extraction system with mechanisms to count the number of sources and combine
it with a single-talker speech recognizer to form the first end-to-end multi-talker
automatic speech recognition system for an unknown number of active speakers.
Our experiments show very promising performance in counting accuracy, source separation
and speech recognition on simulated clean mixtures from WSJ0-2mix and WSJ0-3mix.
Among others, we set a new state-of-the-art word error rate on the WSJ0-2mix database.
Furthermore, our system generalizes well to a larger number of speakers than it
ever saw during training, as shown in experiments with the WSJ0-4mix database. '
author:
- first_name: Thilo
full_name: von Neumann, Thilo
id: '49870'
last_name: von Neumann
orcid: https://orcid.org/0000-0002-7717-8670
- first_name: Christoph
full_name: Boeddeker, Christoph
id: '40767'
last_name: Boeddeker
- first_name: Lukas
full_name: Drude, Lukas
last_name: Drude
- first_name: Keisuke
full_name: Kinoshita, Keisuke
last_name: Kinoshita
- first_name: Marc
full_name: Delcroix, Marc
last_name: Delcroix
- first_name: Tomohiro
full_name: Nakatani, Tomohiro
last_name: Nakatani
- first_name: Reinhold
full_name: Haeb-Umbach, Reinhold
id: '242'
last_name: Haeb-Umbach
citation:
ama: 'von Neumann T, Boeddeker C, Drude L, et al. Multi-Talker ASR for an Unknown
Number of Sources: Joint Training of Source Counting, Separation and ASR. In:
Proc. Interspeech 2020. ; 2020:3097-3101. doi:10.21437/Interspeech.2020-2519'
apa: 'von Neumann, T., Boeddeker, C., Drude, L., Kinoshita, K., Delcroix, M., Nakatani,
T., & Haeb-Umbach, R. (2020). Multi-Talker ASR for an Unknown Number of Sources:
Joint Training of Source Counting, Separation and ASR. Proc. Interspeech 2020,
3097–3101. https://doi.org/10.21437/Interspeech.2020-2519'
bibtex: '@inproceedings{von Neumann_Boeddeker_Drude_Kinoshita_Delcroix_Nakatani_Haeb-Umbach_2020,
title={Multi-Talker ASR for an Unknown Number of Sources: Joint Training of Source
Counting, Separation and ASR}, DOI={10.21437/Interspeech.2020-2519},
booktitle={Proc. Interspeech 2020}, author={von Neumann, Thilo and Boeddeker,
Christoph and Drude, Lukas and Kinoshita, Keisuke and Delcroix, Marc and Nakatani,
Tomohiro and Haeb-Umbach, Reinhold}, year={2020}, pages={3097–3101} }'
chicago: 'Neumann, Thilo von, Christoph Boeddeker, Lukas Drude, Keisuke Kinoshita,
Marc Delcroix, Tomohiro Nakatani, and Reinhold Haeb-Umbach. “Multi-Talker ASR
for an Unknown Number of Sources: Joint Training of Source Counting, Separation
and ASR.” In Proc. Interspeech 2020, 3097–3101, 2020. https://doi.org/10.21437/Interspeech.2020-2519.'
ieee: 'T. von Neumann et al., “Multi-Talker ASR for an Unknown Number of
Sources: Joint Training of Source Counting, Separation and ASR,” in Proc. Interspeech
2020, 2020, pp. 3097–3101, doi: 10.21437/Interspeech.2020-2519.'
mla: 'von Neumann, Thilo, et al. “Multi-Talker ASR for an Unknown Number of Sources:
Joint Training of Source Counting, Separation and ASR.” Proc. Interspeech 2020,
2020, pp. 3097–101, doi:10.21437/Interspeech.2020-2519.'
short: 'T. von Neumann, C. Boeddeker, L. Drude, K. Kinoshita, M. Delcroix, T. Nakatani,
R. Haeb-Umbach, in: Proc. Interspeech 2020, 2020, pp. 3097–3101.'
date_created: 2020-12-16T14:12:45Z
date_updated: 2023-11-15T12:17:57Z
ddc:
- '000'
department:
- _id: '54'
doi: 10.21437/Interspeech.2020-2519
file:
- access_level: open_access
content_type: application/pdf
creator: huesera
date_created: 2020-12-16T14:14:14Z
date_updated: 2020-12-16T14:14:14Z
file_id: '20765'
file_name: INTERSPEECH_2020_vonNeumann_Paper.pdf
file_size: 267893
relation: main_file
file_date_updated: 2020-12-16T14:14:14Z
has_accepted_license: '1'
language:
- iso: eng
oa: '1'
page: 3097-3101
project:
- _id: '52'
name: Computing Resources Provided by the Paderborn Center for Parallel Computing
publication: Proc. Interspeech 2020
quality_controlled: '1'
status: public
title: 'Multi-Talker ASR for an Unknown Number of Sources: Joint Training of Source
Counting, Separation and ASR'
type: conference
user_id: '49870'
year: '2020'
...
---
_id: '20766'
abstract:
- lang: eng
text: Recently, the source separation performance was greatly improved by time-domain
audio source separation based on dual-path recurrent neural network (DPRNN). DPRNN
is a simple but effective model for a long sequential data. While DPRNN is quite
efficient in modeling a sequential data of the length of an utterance, i.e., about
5 to 10 second data, it is harder to apply it to longer sequences such as whole
conversations consisting of multiple utterances. It is simply because, in such
a case, the number of time steps consumed by its internal module called inter-chunk
RNN becomes extremely large. To mitigate this problem, this paper proposes a multi-path
RNN (MPRNN), a generalized version of DPRNN, that models the input data in a hierarchical
manner. In the MPRNN framework, the input data is represented at several (>_ 3)
time-resolutions, each of which is modeled by a specific RNN sub-module. For example,
the RNN sub-module that deals with the finest resolution may model temporal relationship
only within a phoneme, while the RNN sub-module handling the most coarse resolution
may capture only the relationship between utterances such as speaker information.
We perform experiments using simulated dialogue-like mixtures and show that MPRNN
has greater model capacity, and it outperforms the current state-of-the-art DPRNN
framework especially in online processing scenarios.
author:
- first_name: Keisuke
full_name: Kinoshita, Keisuke
last_name: Kinoshita
- first_name: Thilo
full_name: von Neumann, Thilo
id: '49870'
last_name: von Neumann
orcid: https://orcid.org/0000-0002-7717-8670
- first_name: Marc
full_name: Delcroix, Marc
last_name: Delcroix
- first_name: Tomohiro
full_name: Nakatani, Tomohiro
last_name: Nakatani
- first_name: Reinhold
full_name: Haeb-Umbach, Reinhold
id: '242'
last_name: Haeb-Umbach
citation:
ama: 'Kinoshita K, von Neumann T, Delcroix M, Nakatani T, Haeb-Umbach R. Multi-Path
RNN for Hierarchical Modeling of Long Sequential Data and its Application to Speaker
Stream Separation. In: Proc. Interspeech 2020. ; 2020:2652-2656. doi:10.21437/Interspeech.2020-2388'
apa: Kinoshita, K., von Neumann, T., Delcroix, M., Nakatani, T., & Haeb-Umbach,
R. (2020). Multi-Path RNN for Hierarchical Modeling of Long Sequential Data and
its Application to Speaker Stream Separation. Proc. Interspeech 2020, 2652–2656.
https://doi.org/10.21437/Interspeech.2020-2388
bibtex: '@inproceedings{Kinoshita_von Neumann_Delcroix_Nakatani_Haeb-Umbach_2020,
title={Multi-Path RNN for Hierarchical Modeling of Long Sequential Data and its
Application to Speaker Stream Separation}, DOI={10.21437/Interspeech.2020-2388},
booktitle={Proc. Interspeech 2020}, author={Kinoshita, Keisuke and von Neumann,
Thilo and Delcroix, Marc and Nakatani, Tomohiro and Haeb-Umbach, Reinhold}, year={2020},
pages={2652–2656} }'
chicago: Kinoshita, Keisuke, Thilo von Neumann, Marc Delcroix, Tomohiro Nakatani,
and Reinhold Haeb-Umbach. “Multi-Path RNN for Hierarchical Modeling of Long Sequential
Data and Its Application to Speaker Stream Separation.” In Proc. Interspeech
2020, 2652–56, 2020. https://doi.org/10.21437/Interspeech.2020-2388.
ieee: 'K. Kinoshita, T. von Neumann, M. Delcroix, T. Nakatani, and R. Haeb-Umbach,
“Multi-Path RNN for Hierarchical Modeling of Long Sequential Data and its Application
to Speaker Stream Separation,” in Proc. Interspeech 2020, 2020, pp. 2652–2656,
doi: 10.21437/Interspeech.2020-2388.'
mla: Kinoshita, Keisuke, et al. “Multi-Path RNN for Hierarchical Modeling of Long
Sequential Data and Its Application to Speaker Stream Separation.” Proc. Interspeech
2020, 2020, pp. 2652–56, doi:10.21437/Interspeech.2020-2388.
short: 'K. Kinoshita, T. von Neumann, M. Delcroix, T. Nakatani, R. Haeb-Umbach,
in: Proc. Interspeech 2020, 2020, pp. 2652–2656.'
date_created: 2020-12-16T14:15:24Z
date_updated: 2023-11-15T12:14:25Z
ddc:
- '000'
department:
- _id: '54'
doi: 10.21437/Interspeech.2020-2388
file:
- access_level: open_access
content_type: application/pdf
creator: huesera
date_created: 2020-12-16T14:16:32Z
date_updated: 2020-12-16T14:16:32Z
file_id: '20767'
file_name: INTERSPEECH_2020_vonNeumann1_Paper.pdf
file_size: 1725219
relation: main_file
file_date_updated: 2020-12-16T14:16:32Z
has_accepted_license: '1'
language:
- iso: eng
oa: '1'
page: 2652-2656
publication: Proc. Interspeech 2020
quality_controlled: '1'
status: public
title: Multi-Path RNN for Hierarchical Modeling of Long Sequential Data and its Application
to Speaker Stream Separation
type: conference
user_id: '49870'
year: '2020'
...