Online Streaming End-to-End Neural Diarization Handling Overlapping Speech and Flexible Numbers of Speakers
This addresses the need for real-time diarization in applications like teleconferencing, but it is incremental as it builds on existing EEND and STB approaches.
The paper tackles the problem of online streaming speaker diarization with overlapping speech and flexible speaker counts, proposing FLEX-STB to extend a previous method to handle multiple speakers, achieving performance comparable to offline methods with 1-second latency on datasets like CALLHOME and DIHARD II.
We propose a streaming diarization method based on an end-to-end neural diarization (EEND) model, which handles flexible numbers of speakers and overlapping speech. In our previous study, the speaker-tracing buffer (STB) mechanism was proposed to achieve a chunk-wise streaming diarization using a pre-trained EEND model. STB traces the speaker information in previous chunks to map the speakers in a new chunk. However, it only worked with two-speaker recordings. In this paper, we propose an extended STB for flexible numbers of speakers, FLEX-STB. The proposed method uses a zero-padding followed by speaker-tracing, which alleviates the difference in the number of speakers between a buffer and a current chunk. We also examine buffer update strategies to select important frames for tracing multiple speakers. Experiments on CALLHOME and DIHARD II datasets show that the proposed method achieves comparable performance to the offline EEND method with 1-second latency. The results also show that our proposed method outperforms recently proposed chunk-wise diarization methods based on EEND (BW-EDA-EEND).