CHiME-6 Challenge: Tackling multispeaker speech recognition for unsegmented recordings

Shinji Watanabe (1) , Michael Mandel (2) , Jon Barker (3) , Emmanuel Vincent (4) , Ashish Arora (1) , Xuankai Chang (1) , Sanjeev Khudanpur (1) , Vimal Manohar (1) , Daniel Povey (1) , Desh Raj (1) , David Snyder (1) , Aswin Shanmugam Subramanian (1) , Jan Trmal (1) , Bar Ben Yair (1) , Christoph Boeddeker (5) , Zhaoheng Ni (2) , Yusuke Fujita (6) , Shota Horiguchi (6) , Naoyuki Kanda (7) , Takuya Yoshioka (7) , Neville Ryant (8)

1 CLSP - Center for Language and Speech Processing [Baltimore]
2 Brooklyn College [CUNY, New York]
3 Department of Computer Science [Sheffield]
4 MULTISPEECH - Speech Modeling for Facilitating Oral-Based Communication
5 UPB - Universität Paderborn
6 Hitachi, Ltd
7 Microsoft Research [Redmond]
8 LDC - Linguistic Data Consortium

Following the success of the 1st, 2nd, 3rd, 4th and 5th CHiME challenges we organize the 6th CHiME Speech Separation and Recognition Challenge (CHiME-6). The new challenge revisits the previous CHiME-5 challenge and further considers the problem of distant multi-microphone conversational speech diarization and recognition in everyday home environments. Speech material is the same as the previous CHiME-5 recordings except for accurate array synchronization. The material was elicited using a dinner party scenario with efforts taken to capture data that is representative of natural conversational speech. This paper provides a baseline description of the CHiME-6 challenge for both segmented multispeaker speech recognition (Track 1) and unsegmented multispeaker speech recognition (Track 2). Of note, Track 2 is the first challenge activity in the community to tackle an unsegmented multispeaker speech recognition scenario with a complete set of reproducible open source baselines providing speech enhancement, speaker diarization, and speech recognition modules.

Mots clés: CHiME challenge; speech recognition; speech enhancement; speech separation; speaker diarization; computational paralinguistics

Domaines: Traitement du signal et de l'image [eess.SP]

Shinji Watanabe, Michael Mandel, Jon Barker, Emmanuel Vincent, Ashish Arora, et al.. CHiME-6 Challenge: Tackling multispeaker speech recognition for unsegmented recordings. CHiME 2020 - 6th International Workshop on Speech Processing in Everyday Environments, May 2020, Barcelona / Virtual, Spain. ⟨hal-02546993v2⟩