Neural Speaker Diarization Using Memory-Aware Multi-Speaker Embedding with Sequence-to-Sequence Architecture
This work addresses speaker diarization for audio processing, showing incremental improvements in efficiency and performance for a specific challenge.
The paper tackles speaker diarization by proposing a neural system that integrates memory-aware multi-speaker embedding with a sequence-to-sequence architecture, achieving a diarization error rate of 15.9% on the CHiME-7 EVAL set, which is a 49% relative improvement over the baseline.
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 will be available at https://github.com/liyunlongaaa/NSD-MS2S.