@inproceedings{5b05d0d2ae2049fda75382afa7950c42,
title = "The Multimodal Information Based Speech Processing (Misp) 2022 Challenge: Audio-Visual Diarization And Recognition",
abstract = "The Multi-modal Information based Speech Processing (MISP) challenge aims to extend the application of signal processing technology in specific scenarios by promoting the research into wake-up words, speaker diarization, speech recognition, and other technologies. The MISP2022 challenge has two tracks: 1) audio-visual speaker diarization (AVSD), aiming to solve {"}who spoken when{"}using both audio and visual data; 2) a novel audio-visual diarization and recognition (AVDR) task that focuses on addressing {"}who spoken what when{"}with audio-visual speaker diarization results. Both tracks focus on the Chinese language, and use far-field audio and video in real home-tv scenarios: 2-6 people communicating each other with TV noise in the background. This paper introduces the dataset, track settings, and baselines of the MISP2022 challenge. Our analyses of experiments and examples indicate the good performance of AVDR baseline system, and the potential difficulties in this challenge due to, e.g., the far-field video quality, the presence of TV noise in the background, and the indistinguishable speakers.",
keywords = "MISP challenge, multimodality, speaker diarization, speech recognition",
author = "Zhe Wang and Shilong Wu and Hang Chen and He, \{Mao Kui\} and Jun Du and Lee, \{Chin Hui\} and Jingdong Chen and Shinji Watanabe and Sabato Siniscalchi and Odette Scharenborg and Diyuan Liu and Baocai Yin and Jia Pan and Jianqing Gao and Cong Liu",
note = "Publisher Copyright: {\textcopyright} 2023 IEEE.; 48th IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP 2023 ; Conference date: 04-06-2023 Through 10-06-2023",
year = "2023",
doi = "10.1109/ICASSP49357.2023.10094836",
language = "英语",
series = "ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
booktitle = "ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing, Proceedings",
}