The CUHK-Tencent Speaker Diarization System for the ICASSP 2022 Multi-Channel Multi-Party Meeting Transcription Challenge
Refereed conference paper presented and published in conference proceedings
CUHK Authors
Full Text
Digital Object Identifier (DOI) DOI for CUHK Users |
Times Cited
Altmetrics Information
.
Other information
AbstractThis paper describes our speaker diarization system submitted to the Multi-channel Multi-party Meeting Transcription (M2MeT) challenge, where Mandarin meeting data were recorded in multi-channel format for diarization and automatic speech recognition (ASR) tasks. In these meeting scenarios, the uncertainty of the speaker number and the high ratio of overlapped speech present great challenges for diarization. Based on the assumption that there is valuable complementary information between acoustic features, spatial-related and speaker-related features, we propose a multi-level feature fusion mechanism based target-speaker voice activity detection (FFM-TS-VAD) system to improve the performance of the conventional TS-VAD system. Furthermore, we propose a data augmentation method during training to improve the system robustness when the angular difference between two speakers is relatively small. We provide comparisons for different sub-systems we used in M2MeT challenge. Our submission is a fusion of several sub-systems and ranks second in the diarization task.
All Author(s) ListNaijun Zheng, Na Li, Xixin Wu, Lingwei Meng, Jiawen Kang, Haibin Wu, Chao Weng, Dan Su, Helen Meng
Name of ConferenceIEEE International Conference on Acoustics, Speech and Signal Processing
Start Date of Conference07/05/2022
End Date of Conference13/05/2022
Place of ConferenceSingapore
Country/Region of ConferenceSingapore
Proceedings TitleIEEE International Conference on Acoustics, Speech and Signal Processing
Year2022
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages9161 - 9165
ISBN9781665405409
LanguagesEnglish-United Kingdom
Keywordsfeature fusion, M2MeT, multi-channel, overlapped speech, speaker diarization
