CHiME-6 Challenge:Tackling Multispeaker Speech Recognition for Unsegmented Recordings

Abstract

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.

Cited by in corpus (28)

• Target-Speaker Voice Activity Detection: a Novel Approach for Multi-Speaker Diarization in a Dinner Party Scenario
• BigSSL: Exploring the Frontier of Large-Scale Semi-Supervised Learning for Automatic Speech Recognition
• SpeechStew: Simply Mix All Available Speech Recognition Data to Train One Large Neural Network
• VoxSRC 2020: The Second VoxCeleb Speaker Recognition Challenge
• Earnings-21: A Practical Benchmark for ASR in the Wild
• End-to-End Far-Field Speech Recognition with Unified Dereverberation and Beamforming
• EasyCom: An Augmented Reality Dataset to Support Algorithms for Easy Communication in Noisy Environments
• USTC-NELSLIP System Description for DIHARD-III Challenge
• Towards a Competitive End-to-End Speech Recognition for CHiME-6 Dinner Party Transcription
• Continuous Speech Separation with Conformer
• Lhotse: a speech data representation library for the modern deep learning ecosystem
• Libri-adhoc40: A dataset collected from synchronized ad-hoc microphone arrays
• Integrating Emotion Recognition with Speech Recognition and Speaker Diarisation for Conversations
• INTERSPEECH 2021 ConferencingSpeech Challenge: Towards Far-field Multi-Channel Speech Enhancement for Video Conferencing
• Speeding Up Permutation Invariant Training for Source Separation
• Microsoft Speaker Diarization System for the VoxCeleb Speaker Recognition Challenge 2020
• Sequential Multi-Frame Neural Beamforming for Speech Separation and Enhancement
• Speaker activity driven neural speech extraction
• Probing Acoustic Representations for Phonetic Properties
• Efficient Integration of Multi-channel Information for Speaker-independent Speech Separation
• Scaling sparsemax based channel selection for speech recognition with ad-hoc microphone arrays
• Target-speaker Voice Activity Detection with Improved I-Vector Estimation for Unknown Number of Speaker
• CrowdSpeech and VoxDIY: Benchmark Datasets for Crowdsourced Audio Transcription
• Quaternion Neural Networks for Multi-channel Distant Speech Recognition
• Mixture of Speaker-type PLDAs for Children's Speech Diarization
• End-to-End Speaker Diarization Conditioned on Speech Activity and Overlap Detection
• WPD++: An Improved Neural Beamformer for Simultaneous Speech Separation and Dereverberation
• Exploring End-to-End Multi-channel ASR with Bias Information for Meeting Transcription