THE FIRST MULTIMODAL INFORMATION BASED SPEECH PROCESSING (MISP) CHALLENGE: DATA, TASKS, BASELINES AND RESULTS

Hang Chen, Hengshun Zhou, Jun Du, Chin Hui Lee, Jingdong Chen, Shinji Watanabe, Sabato Marco Siniscalchi, Odette Scharenborg, Di Yuan Liu, Bao Cai Yin, Jia Pan, Jian Qing Gao, Cong Liu

科研成果: 书/报告/会议事项章节会议稿件同行评审

46 引用 (Scopus)

摘要

In this paper we discuss the rational of the Multi-model Information based Speech Processing (MISP) Challenge, and provide a detailed description of the data recorded, the two evaluation tasks and the corresponding baselines, followed by a summary of submitted systems and evaluation results. The MISP Challenge aims at tackling speech processing tasks in different scenarios by introducing information about an additional modality (e.g., video, or text), which will hopefully lead to better environmental and speaker robustness in realistic applications. In the first MISP challenge, two benchmark datasets recorded in a real-home TV room with two reproducible open-source baseline systems have been released to promote research in audio-visual wake word spotting (AVWWS) and audio-visual speech recognition (AVSR). To our knowledge, MISP is the first open evaluation challenge to tackle real-world issues of AVWWS and AVSR in the home TV scenario.

源语言英语
主期刊名2022 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2022 - Proceedings
出版商Institute of Electrical and Electronics Engineers Inc.
9266-9270
页数5
ISBN(电子版)9781665405409
DOI
出版状态已出版 - 2022
活动2022 IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP 2022 - Hybrid, 新加坡
期限: 22 5月 202227 5月 2022

出版系列

姓名ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings
2022-May
ISSN(印刷版)1520-6149

会议

会议2022 IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP 2022
国家/地区新加坡
Hybrid
时期22/05/2227/05/22

指纹

探究 'THE FIRST MULTIMODAL INFORMATION BASED SPEECH PROCESSING (MISP) CHALLENGE: DATA, TASKS, BASELINES AND RESULTS' 的科研主题。它们共同构成独一无二的指纹。

引用此