The Xmuspeech System For Multi-channel Multi-party Meeting Transcription Challenge

Abstract

This paper describes the system developed by the XMUSPEECH team for the Multi-channel Multi-party Meeting Transcription Challenge (M2MeT). For the speaker diarization task, we propose a multi-channel speaker diarization system that obtains spatial information of speaker by Difference of Arrival (DOA) technology. Speaker-spatial embedding is generated by x-vector and s-vector derived from Filter-and-Sum Beamforming (FSB) which makes the embedding more robust. Specifically, we propose a novel multi-channel sequence-to-sequence neural network architecture named Discriminative Multi-stream Neural Network (DMSNet) which consists of Attention Filter-and-Sum block (AFSB) and Conformer encoder. We explore DMSNet to address overlapped speech problem on multi-channel audio. Compared with LSTM based OSD module, we achieve a decreases of 10.1% in Detection Error Rate(DetER). By performing DMSNet based OSD module, the DER of cluster-based diarization system decrease significantly form 13.44% to 7.6

Stats

• citations0
• S2 citations—
• github stars0
• HF likes0
• heat score0.00
• arxiv keywang2022the

Related papers

• Royalflush Speaker Diarization System For ICASSP 2022 Multi-channel Multi-party Meeting Transcription Challenge (2022)0.00
• The Volcspeech System For The ICASSP 2022 Multi-channel Multi-party Meeting Transcription Challenge (2022)5.84
• The CUHK-TENCENT Speaker Diarization System For The ICASSP 2022 Multi-channel Multi-party Meeting Transcription Challenge (2022)7.81
• The Ustc-ximalaya System For The ICASSP 2022 Multi-channel Multi-party Meeting Transcription (m2met) Challenge (2022)6.34
• Cross-channel Attention-based Target Speaker Voice Activity Detection: Experimental Results For M2met Challenge (2022)10.07
• Microsoft Speaker Diarization System For The Voxceleb Speaker Recognition Challenge 2020 (2020)11.93
• Neural Speaker Diarization Using Memory-aware Multi-speaker Embedding With Sequence-to-sequence Architecture (2023)3.87
• Summary On The ICASSP 2022 Multi-channel Multi-party Meeting Transcription Grand Challenge (2022)10.35