Summary on the ICASSP 2022 Multi-Channel Multi-Party Meeting Transcription Grand Challenge

Fan Yu; Shiliang Zhang; Pengcheng Guo; Yihui Fu; Zhihao Du; Siqi Zheng; Weilong Huang; Lei Xie; Zheng Hua Tan; De Liang Wang; Yanmin Qian; Kong Aik Lee; Zhijie Yan; Bin Ma; Xin Xu; Hui Bu

doi:10.1109/ICASSP43922.2022.9746270

Summary on the ICASSP 2022 Multi-Channel Multi-Party Meeting Transcription Grand Challenge

Fan Yu, Shiliang Zhang, Pengcheng Guo, Yihui Fu, Zhihao Du, Siqi Zheng, Weilong Huang, Lei Xie^*, Zheng Hua Tan, De Liang Wang, Yanmin Qian, Kong Aik Lee, Zhijie Yan, Bin Ma, Xin Xu, Hui Bu

^*Kontaktforfatter

Publikation: Bidrag til bog/antologi/rapport/konference proceeding › Konferenceartikel i proceeding › Forskning › peer review

17 Citationer (Scopus)

Abstract

The ICASSP 2022 Multi-channel Multi-party Meeting Transcription Grand Challenge (M2MeT) focuses on one of the most valuable and the most challenging scenarios of speech technologies. The M2MeT challenge has particularly set up two tracks, speaker diarization (track 1) and multi-speaker automatic speech recognition (ASR) (track 2). Along with the challenge, we released 120 hours of real-recorded Mandarin meeting speech data with manual annotation, including far-field data collected by 8-channel microphone array as well as near-field data collected by each participants' headset microphone. We briefly describe the released dataset, track setups, baselines and summarize the challenge results and major techniques used in the submissions.

Originalsprog	Engelsk
Titel	2022 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2022 - Proceedings
Antal sider	5
Forlag	IEEE Signal Processing Society
Publikationsdato	2022
Sider	9156-9160
Artikelnummer	9746270
ISBN (Trykt)	978-1-6654-0541-6
ISBN (Elektronisk)	978-1-6654-0540-9
DOI	https://doi.org/10.1109/ICASSP43922.2022.9746270
Status	Udgivet - 2022
Begivenhed	47th IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2022 - Virtual, Online, Singapore Varighed: 23 maj 2022 → 27 maj 2022

Konference

Konference	47th IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2022
Land/Område	Singapore
By	Virtual, Online
Periode	23/05/2022 → 27/05/2022
Sponsor	Chinese and Oriental Languages Information Processing Society (COLPIS), Singapore Exhibition and Convention Bureau, The Chinese University of Hong Kong, Shenzhen (CUHK-Shenzhen), The Institute of Electrical and Electronics Engineers Signal Processing Society

Navn	ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings
Vol/bind	2022-May
ISSN	1520-6149

Bibliografisk note

Publisher Copyright:
© 2022 IEEE

Adgang til dokumentet

10.1109/ICASSP43922.2022.9746270

https://arxiv.org/pdf/2202.03647.pdf

AUB Link

Søg efter materialet i Aalborg Universitetsbiblioteks søgemaskine

Andre filer og links

Link to publication in Scopus

Citationsformater

Yu, F., Zhang, S., Guo, P., Fu, Y., Du, Z., Zheng, S., Huang, W., Xie, L., Tan, Z. H., Wang, D. L., Qian, Y., Lee, K. A., Yan, Z., Ma, B., Xu, X., & Bu, H. (2022). Summary on the ICASSP 2022 Multi-Channel Multi-Party Meeting Transcription Grand Challenge. I 2022 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2022 - Proceedings (s. 9156-9160). Artikel 9746270 IEEE Signal Processing Society. https://doi.org/10.1109/ICASSP43922.2022.9746270

Yu, Fan ; Zhang, Shiliang ; Guo, Pengcheng et al. / Summary on the ICASSP 2022 Multi-Channel Multi-Party Meeting Transcription Grand Challenge. 2022 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2022 - Proceedings. IEEE Signal Processing Society, 2022. s. 9156-9160 (ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings, Bind 2022-May).

@inproceedings{4362f891188640c689d29a68120df2cf,

title = "Summary on the ICASSP 2022 Multi-Channel Multi-Party Meeting Transcription Grand Challenge",

abstract = "The ICASSP 2022 Multi-channel Multi-party Meeting Transcription Grand Challenge (M2MeT) focuses on one of the most valuable and the most challenging scenarios of speech technologies. The M2MeT challenge has particularly set up two tracks, speaker diarization (track 1) and multi-speaker automatic speech recognition (ASR) (track 2). Along with the challenge, we released 120 hours of real-recorded Mandarin meeting speech data with manual annotation, including far-field data collected by 8-channel microphone array as well as near-field data collected by each participants' headset microphone. We briefly describe the released dataset, track setups, baselines and summarize the challenge results and major techniques used in the submissions.",

keywords = "Alimeeting, M2MeT, Meeting Transcription, Multi-speaker ASR, Speaker Diarization",

author = "Fan Yu and Shiliang Zhang and Pengcheng Guo and Yihui Fu and Zhihao Du and Siqi Zheng and Weilong Huang and Lei Xie and Tan, {Zheng Hua} and Wang, {De Liang} and Yanmin Qian and Lee, {Kong Aik} and Zhijie Yan and Bin Ma and Xin Xu and Hui Bu",

note = "Publisher Copyright: {\textcopyright} 2022 IEEE; 47th IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2022 ; Conference date: 23-05-2022 Through 27-05-2022",

year = "2022",

doi = "10.1109/ICASSP43922.2022.9746270",

language = "English",

isbn = "978-1-6654-0541-6",

series = "ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings",

publisher = "IEEE Signal Processing Society",

pages = "9156--9160",

booktitle = "2022 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2022 - Proceedings",

address = "United States",

}

Yu, F, Zhang, S, Guo, P, Fu, Y, Du, Z, Zheng, S, Huang, W, Xie, L, Tan, ZH, Wang, DL, Qian, Y, Lee, KA, Yan, Z, Ma, B, Xu, X & Bu, H 2022, Summary on the ICASSP 2022 Multi-Channel Multi-Party Meeting Transcription Grand Challenge. i 2022 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2022 - Proceedings., 9746270, IEEE Signal Processing Society, ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings, bind 2022-May, s. 9156-9160, 47th IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2022, Virtual, Online, Singapore, 23/05/2022. https://doi.org/10.1109/ICASSP43922.2022.9746270

Summary on the ICASSP 2022 Multi-Channel Multi-Party Meeting Transcription Grand Challenge. / Yu, Fan; Zhang, Shiliang; Guo, Pengcheng et al.
2022 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2022 - Proceedings. IEEE Signal Processing Society, 2022. s. 9156-9160 9746270 (ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings, Bind 2022-May).

Publikation: Bidrag til bog/antologi/rapport/konference proceeding › Konferenceartikel i proceeding › Forskning › peer review

TY - GEN

T1 - Summary on the ICASSP 2022 Multi-Channel Multi-Party Meeting Transcription Grand Challenge

AU - Yu, Fan

AU - Zhang, Shiliang

AU - Guo, Pengcheng

AU - Fu, Yihui

AU - Du, Zhihao

AU - Zheng, Siqi

AU - Huang, Weilong

AU - Xie, Lei

AU - Tan, Zheng Hua

AU - Wang, De Liang

AU - Qian, Yanmin

AU - Lee, Kong Aik

AU - Yan, Zhijie

AU - Ma, Bin

AU - Xu, Xin

AU - Bu, Hui

PY - 2022

Y1 - 2022

N2 - The ICASSP 2022 Multi-channel Multi-party Meeting Transcription Grand Challenge (M2MeT) focuses on one of the most valuable and the most challenging scenarios of speech technologies. The M2MeT challenge has particularly set up two tracks, speaker diarization (track 1) and multi-speaker automatic speech recognition (ASR) (track 2). Along with the challenge, we released 120 hours of real-recorded Mandarin meeting speech data with manual annotation, including far-field data collected by 8-channel microphone array as well as near-field data collected by each participants' headset microphone. We briefly describe the released dataset, track setups, baselines and summarize the challenge results and major techniques used in the submissions.

AB - The ICASSP 2022 Multi-channel Multi-party Meeting Transcription Grand Challenge (M2MeT) focuses on one of the most valuable and the most challenging scenarios of speech technologies. The M2MeT challenge has particularly set up two tracks, speaker diarization (track 1) and multi-speaker automatic speech recognition (ASR) (track 2). Along with the challenge, we released 120 hours of real-recorded Mandarin meeting speech data with manual annotation, including far-field data collected by 8-channel microphone array as well as near-field data collected by each participants' headset microphone. We briefly describe the released dataset, track setups, baselines and summarize the challenge results and major techniques used in the submissions.

KW - Alimeeting

KW - M2MeT

KW - Meeting Transcription

KW - Multi-speaker ASR

KW - Speaker Diarization

UR - http://www.scopus.com/inward/record.url?scp=85128574620&partnerID=8YFLogxK

U2 - 10.1109/ICASSP43922.2022.9746270

DO - 10.1109/ICASSP43922.2022.9746270

M3 - Article in proceeding

AN - SCOPUS:85128574620

SN - 978-1-6654-0541-6

T3 - ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings

SP - 9156

EP - 9160

BT - 2022 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2022 - Proceedings

PB - IEEE Signal Processing Society

T2 - 47th IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2022

Y2 - 23 May 2022 through 27 May 2022

ER -

Yu F, Zhang S, Guo P, Fu Y, Du Z, Zheng S et al. Summary on the ICASSP 2022 Multi-Channel Multi-Party Meeting Transcription Grand Challenge. I 2022 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2022 - Proceedings. IEEE Signal Processing Society. 2022. s. 9156-9160. 9746270. (ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings, Bind 2022-May). doi: 10.1109/ICASSP43922.2022.9746270

Summary on the ICASSP 2022 Multi-Channel Multi-Party Meeting Transcription Grand Challenge

Abstract

Konference

Bibliografisk note

Adgang til dokumentet

AUB Link

Andre filer og links

Fingeraftryk

Citationsformater