The Second Multi-Channel Multi-Party Meeting Transcription Challenge (M2MeT 2.0): A Benchmark for Speaker-Attributed ASR

Yuhao Liang; Mohan Shi; Fan Yu; Yangze Li; Shiliang Zhang; Zhihao Du; Qian Chen; Lei Xie; Yanmin Qian; Jian Wu; Zhuo Chen; Kong Aik Lee; Zhijie Yan; Hui Bu

doi:10.1109/ASRU57964.2023.10389625

The Second Multi-Channel Multi-Party Meeting Transcription Challenge (M2MeT 2.0): A Benchmark for Speaker-Attributed ASR

Yuhao Liang
, Mohan Shi
, Fan Yu
, Yangze Li
, Shiliang Zhang
, Zhihao Du
, Qian Chen
, Lei Xie
, Yanmin Qian
, Jian Wu
, Zhuo Chen
, Kong Aik Lee
, Zhijie Yan
, Hui Bu

School of Computer Science

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

7 Scopus citations

Abstract

With the success of the first Multi-channel Multi-party Meeting Transcription challenge (M2MeT), the second M2MeT challenge (M2MeT 2.0) held in ASRU2023 particularly aims to tackle the complex task of speaker-attributed ASR (SAASR), which directly addresses the practical and challenging problem of 'who spoke what at when' at typical meeting scenario. We particularly established two sub-tracks. The fixed training condition sub-track, where the training data is constrained to predetermined datasets, but participants can use any open-source pre-trained model. The open training condition sub-track, which allows for the use of all available data and models without limitation. In addition, we release a new 10-hour test set for challenge ranking. This paper provides an overview of the dataset, track settings, results, and analysis of submitted systems, as a benchmark to show the current state of speaker-attributed ASR.

Original language	English
Title of host publication	2023 IEEE Automatic Speech Recognition and Understanding Workshop, ASRU 2023
Publisher	Institute of Electrical and Electronics Engineers Inc.
ISBN (Electronic)	9798350306897
DOIs	https://doi.org/10.1109/ASRU57964.2023.10389625
State	Published - 2023
Event	2023 IEEE Automatic Speech Recognition and Understanding Workshop, ASRU 2023 - Taipei, Taiwan, Province of China Duration: 16 Dec 2023 → 20 Dec 2023

Publication series

Name	2023 IEEE Automatic Speech Recognition and Understanding Workshop, ASRU 2023

Conference

Conference	2023 IEEE Automatic Speech Recognition and Understanding Workshop, ASRU 2023
Country/Territory	Taiwan, Province of China
City	Taipei
Period	16/12/23 → 20/12/23

Keywords

Alimeeting
M2MeT 2.0
Meeting Transcription
Multi-speaker ASR
Speaker-attributed ASR

Access to Document

10.1109/ASRU57964.2023.10389625

Cite this

Liang, Y., Shi, M., Yu, F., Li, Y., Zhang, S., Du, Z., Chen, Q., Xie, L., Qian, Y., Wu, J., Chen, Z., Lee, K. A., Yan, Z., & Bu, H. (2023). The Second Multi-Channel Multi-Party Meeting Transcription Challenge (M2MeT 2.0): A Benchmark for Speaker-Attributed ASR. In 2023 IEEE Automatic Speech Recognition and Understanding Workshop, ASRU 2023 (2023 IEEE Automatic Speech Recognition and Understanding Workshop, ASRU 2023). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/ASRU57964.2023.10389625

Liang, Yuhao ; Shi, Mohan ; Yu, Fan et al. / The Second Multi-Channel Multi-Party Meeting Transcription Challenge (M2MeT 2.0) : A Benchmark for Speaker-Attributed ASR. 2023 IEEE Automatic Speech Recognition and Understanding Workshop, ASRU 2023. Institute of Electrical and Electronics Engineers Inc., 2023. (2023 IEEE Automatic Speech Recognition and Understanding Workshop, ASRU 2023).

@inproceedings{e4671271b8ed46bd9a4f20f407f27277,

title = "The Second Multi-Channel Multi-Party Meeting Transcription Challenge (M2MeT 2.0): A Benchmark for Speaker-Attributed ASR",

abstract = "With the success of the first Multi-channel Multi-party Meeting Transcription challenge (M2MeT), the second M2MeT challenge (M2MeT 2.0) held in ASRU2023 particularly aims to tackle the complex task of speaker-attributed ASR (SAASR), which directly addresses the practical and challenging problem of 'who spoke what at when' at typical meeting scenario. We particularly established two sub-tracks. The fixed training condition sub-track, where the training data is constrained to predetermined datasets, but participants can use any open-source pre-trained model. The open training condition sub-track, which allows for the use of all available data and models without limitation. In addition, we release a new 10-hour test set for challenge ranking. This paper provides an overview of the dataset, track settings, results, and analysis of submitted systems, as a benchmark to show the current state of speaker-attributed ASR.",

keywords = "Alimeeting, M2MeT 2.0, Meeting Transcription, Multi-speaker ASR, Speaker-attributed ASR",

author = "Yuhao Liang and Mohan Shi and Fan Yu and Yangze Li and Shiliang Zhang and Zhihao Du and Qian Chen and Lei Xie and Yanmin Qian and Jian Wu and Zhuo Chen and Lee, \{Kong Aik\} and Zhijie Yan and Hui Bu",

note = "Publisher Copyright: {\textcopyright} 2023 IEEE.; 2023 IEEE Automatic Speech Recognition and Understanding Workshop, ASRU 2023 ; Conference date: 16-12-2023 Through 20-12-2023",

year = "2023",

doi = "10.1109/ASRU57964.2023.10389625",

language = "英语",

series = "2023 IEEE Automatic Speech Recognition and Understanding Workshop, ASRU 2023",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

booktitle = "2023 IEEE Automatic Speech Recognition and Understanding Workshop, ASRU 2023",

}

Liang, Y, Shi, M, Yu, F, Li, Y, Zhang, S, Du, Z, Chen, Q, Xie, L, Qian, Y, Wu, J, Chen, Z, Lee, KA, Yan, Z & Bu, H 2023, The Second Multi-Channel Multi-Party Meeting Transcription Challenge (M2MeT 2.0): A Benchmark for Speaker-Attributed ASR. in 2023 IEEE Automatic Speech Recognition and Understanding Workshop, ASRU 2023. 2023 IEEE Automatic Speech Recognition and Understanding Workshop, ASRU 2023, Institute of Electrical and Electronics Engineers Inc., 2023 IEEE Automatic Speech Recognition and Understanding Workshop, ASRU 2023, Taipei, Taiwan, Province of China, 16/12/23. https://doi.org/10.1109/ASRU57964.2023.10389625

The Second Multi-Channel Multi-Party Meeting Transcription Challenge (M2MeT 2.0): A Benchmark for Speaker-Attributed ASR. / Liang, Yuhao; Shi, Mohan; Yu, Fan et al.
2023 IEEE Automatic Speech Recognition and Understanding Workshop, ASRU 2023. Institute of Electrical and Electronics Engineers Inc., 2023. (2023 IEEE Automatic Speech Recognition and Understanding Workshop, ASRU 2023).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

TY - GEN

T1 - The Second Multi-Channel Multi-Party Meeting Transcription Challenge (M2MeT 2.0)

T2 - 2023 IEEE Automatic Speech Recognition and Understanding Workshop, ASRU 2023

AU - Liang, Yuhao

AU - Shi, Mohan

AU - Yu, Fan

AU - Li, Yangze

AU - Zhang, Shiliang

AU - Du, Zhihao

AU - Chen, Qian

AU - Xie, Lei

AU - Qian, Yanmin

AU - Wu, Jian

AU - Chen, Zhuo

AU - Lee, Kong Aik

AU - Yan, Zhijie

AU - Bu, Hui

PY - 2023

Y1 - 2023

N2 - With the success of the first Multi-channel Multi-party Meeting Transcription challenge (M2MeT), the second M2MeT challenge (M2MeT 2.0) held in ASRU2023 particularly aims to tackle the complex task of speaker-attributed ASR (SAASR), which directly addresses the practical and challenging problem of 'who spoke what at when' at typical meeting scenario. We particularly established two sub-tracks. The fixed training condition sub-track, where the training data is constrained to predetermined datasets, but participants can use any open-source pre-trained model. The open training condition sub-track, which allows for the use of all available data and models without limitation. In addition, we release a new 10-hour test set for challenge ranking. This paper provides an overview of the dataset, track settings, results, and analysis of submitted systems, as a benchmark to show the current state of speaker-attributed ASR.

AB - With the success of the first Multi-channel Multi-party Meeting Transcription challenge (M2MeT), the second M2MeT challenge (M2MeT 2.0) held in ASRU2023 particularly aims to tackle the complex task of speaker-attributed ASR (SAASR), which directly addresses the practical and challenging problem of 'who spoke what at when' at typical meeting scenario. We particularly established two sub-tracks. The fixed training condition sub-track, where the training data is constrained to predetermined datasets, but participants can use any open-source pre-trained model. The open training condition sub-track, which allows for the use of all available data and models without limitation. In addition, we release a new 10-hour test set for challenge ranking. This paper provides an overview of the dataset, track settings, results, and analysis of submitted systems, as a benchmark to show the current state of speaker-attributed ASR.

KW - Alimeeting

KW - M2MeT 2.0

KW - Meeting Transcription

KW - Multi-speaker ASR

KW - Speaker-attributed ASR

UR - https://www.scopus.com/pages/publications/85184667150

U2 - 10.1109/ASRU57964.2023.10389625

DO - 10.1109/ASRU57964.2023.10389625

M3 - 会议稿件

AN - SCOPUS:85184667150

T3 - 2023 IEEE Automatic Speech Recognition and Understanding Workshop, ASRU 2023

BT - 2023 IEEE Automatic Speech Recognition and Understanding Workshop, ASRU 2023

PB - Institute of Electrical and Electronics Engineers Inc.

Y2 - 16 December 2023 through 20 December 2023

ER -

Liang Y, Shi M, Yu F, Li Y, Zhang S, Du Z et al. The Second Multi-Channel Multi-Party Meeting Transcription Challenge (M2MeT 2.0): A Benchmark for Speaker-Attributed ASR. In 2023 IEEE Automatic Speech Recognition and Understanding Workshop, ASRU 2023. Institute of Electrical and Electronics Engineers Inc. 2023. (2023 IEEE Automatic Speech Recognition and Understanding Workshop, ASRU 2023). doi: 10.1109/ASRU57964.2023.10389625

The Second Multi-Channel Multi-Party Meeting Transcription Challenge (M2MeT 2.0): A Benchmark for Speaker-Attributed ASR

Abstract

Publication series

Conference

Keywords

Access to Document

Other files and links

Fingerprint

Cite this