TY - JOUR
T1 - The Multimodal Information Based Speech Processing (MISP) 2025 Challenge
T2 - 26th Interspeech Conference 2025
AU - Gao, Ming
AU - Wu, Shilong
AU - Chen, Hang
AU - Du, Jun
AU - Lee, Chin Hui
AU - Watanabe, Shinji
AU - Chen, Jingdong
AU - Marco, Siniscalchi Sabato
AU - Scharenborg, Odette
N1 - Publisher Copyright:
© 2025 International Speech Communication Association. All rights reserved.
PY - 2025
Y1 - 2025
N2 - Meetings are a valuable yet challenging scenario for speech applications due to complex acoustic conditions. This paper summarizes the outcomes of the MISP 2025 Challenge, hosted at Interspeech 2025, which focuses on multi-modal, multi-device meeting transcription by incorporating video modality alongside audio. The tasks include Audio-Visual Speaker Diarization (AVSD), Audio-Visual Speech Recognition (AVSR), and Audio-Visual Diarization and Recognition (AVDR). We present the challenge's objectives, tasks, dataset, baseline systems, and solutions proposed by participants. The best-performing systems achieved significant improvements over the baseline: the top AVSD model achieved a Diarization Error Rate (DER) of 8.09%, improving by 7.43%; the top AVSR system achieved a Character Error Rate (CER) of 9.48%, improving by 10.62%; and the best AVDR system achieved a concatenated minimum-permutation Character Error Rate (cpCER) of 11.56%, improving by 72.49%.
AB - Meetings are a valuable yet challenging scenario for speech applications due to complex acoustic conditions. This paper summarizes the outcomes of the MISP 2025 Challenge, hosted at Interspeech 2025, which focuses on multi-modal, multi-device meeting transcription by incorporating video modality alongside audio. The tasks include Audio-Visual Speaker Diarization (AVSD), Audio-Visual Speech Recognition (AVSR), and Audio-Visual Diarization and Recognition (AVDR). We present the challenge's objectives, tasks, dataset, baseline systems, and solutions proposed by participants. The best-performing systems achieved significant improvements over the baseline: the top AVSD model achieved a Diarization Error Rate (DER) of 8.09%, improving by 7.43%; the top AVSR system achieved a Character Error Rate (CER) of 9.48%, improving by 10.62%; and the best AVDR system achieved a concatenated minimum-permutation Character Error Rate (cpCER) of 11.56%, improving by 72.49%.
KW - audio-visual fusion
KW - multimodal speech processing
KW - speaker diarization
KW - speech recognition
UR - https://www.scopus.com/pages/publications/105020092259
U2 - 10.21437/Interspeech.2025-2017
DO - 10.21437/Interspeech.2025-2017
M3 - 会议文章
AN - SCOPUS:105020092259
SN - 2308-457X
SP - 1888
EP - 1892
JO - Proceedings of the Annual Conference of the International Speech Communication Association, INTERSPEECH
JF - Proceedings of the Annual Conference of the International Speech Communication Association, INTERSPEECH
Y2 - 17 August 2025 through 21 August 2025
ER -