Neural Speaker Diarization Using Memory-Aware Multi-Speaker Embedding with Sequence-to-Sequence Architecture

• Main Authors: Yang, Gaobin, He, Maokui, Niu, Shutong, Wang, Ruoyu, Yue, Yanyan, Qian, Shuangqing, Wu, Shilong, Du, Jun, Lee, Chin-Hui
• Format: Conference Proceeding
• Language: English
• Subjects: Acoustics; CHiME challenge; Codes; Error analysis; Graphics processing units; Memory management; memory-aware speaker embedding; Oral communication; sequence-to-sequence architecture; Signal processing; speaker diarization
• ISSN: 2379-190X
• DOI: 10.1109/ICASSP48485.2024.10446661

We propose a novel neural speaker diarization system using memory-aware multi-speaker embedding with sequence-to-sequence architecture (NSD-MS2S), which integrates the strengths of memory-aware multi-speaker embedding (MA-MSE) and sequence-to-sequence (Seq2Seq) architecture, leading to improvement in both efficiency and performance. Next, we further decrease the memory occupation of decoding by incorporating input features fusion and then employ a multi-head attention mechanism to capture features at different levels. NSD-MS2S achieved a macro diarization error rate (DER) of 15.9% on the CHiME-7 EVAL set, which signifies a relative improvement of 49% over the official baseline system, and is the key technique for us to achieve the best performance for the main track of CHiME-7 DASR Challenge. Additionally, we introduce a deep interactive module (DIM) in MA-MSE module to better retrieve a cleaner and more discriminative multi-speaker embedding, enabling the current model to outperform the system we used in the CHiME-7 DASR Challenge. Our code is available at https://github.com/liyunlongaaa/NSD-MS2S.