Online End-to-End Neural Diarization with Speaker-Tracing Buffer
Abstract
This paper proposes a novel online speaker diarization algorithm based on a fully supervised self-attention mechanism (SA-EEND). Online diarization inherently presents a speaker's permutation problem due to the possibility to assign speaker regions incorrectly across the recording. To circumvent this inconsistency, we proposed a speaker-tracing buffer mechanism that selects several input frames representing the speaker permutation information from previous chunks and stores them in a buffer. These buffered frames are stacked with the input frames in the current chunk and fed into a self-attention network. Our method ensures consistent diarization outputs across the buffer and the current chunk by checking the correlation between their corresponding outputs. Additionally, we trained SA-EEND with variable chunk-sizes to mitigate the mismatch between training and inference introduced by the speaker-tracing buffer mechanism. Experimental results, including online SA-EEND and variable chunk-size, achieved DERs of 12.54% for CALLHOME and 20.77% for CSJ with 1.4s actual latency.
Cite
@article{arxiv.2006.02616,
title = {Online End-to-End Neural Diarization with Speaker-Tracing Buffer},
author = {Yawen Xue and Shota Horiguchi and Yusuke Fujita and Shinji Watanabe and Kenji Nagamatsu},
journal= {arXiv preprint arXiv:2006.02616},
year = {2021}
}
Comments
Accepted to SLT 2021