Encoder-Decoder Based Attractors for End-to-End Neural Diarization

Shota Horiguchi*, Yusuke Fujita, Shinji Watanabe, Yawen Xue, Paola Garcia

*この研究の対応する著者

研究成果: Article査読

抄録

This paper investigates an end-to-end neural diarization (EEND) method for an unknown number of speakers. In contrast to the conventional cascaded approach to speaker diarization, EEND methods are better in terms of speaker overlap handling. However, EEND still has a disadvantage in that it cannot deal with a flexible number of speakers. To remedy this problem, we introduce encoder-decoder-based attractor calculation module (EDA) to EEND. Once frame-wise embeddings are obtained, EDA sequentially generates speaker-wise attractors on the basis of a sequence-to-sequence method using an LSTM encoder-decoder. The attractor generation continues until a stopping condition is satisfied; thus, the number of attractors can be flexible. Diarization results are then estimated as dot products of the attractors and embeddings. The embeddings from speaker overlaps result in larger dot product values with multiple attractors; thus, this method can deal with speaker overlaps. Because the maximum number of output speakers is still limited by the training set, we also propose an iterative inference method to remove this restriction. Further, we propose a method that aligns the estimated diarization results with the results of an external speech activity detector, which enables fair comparison against cascaded approaches. Extensive evaluations on simulated and real datasets show that EEND-EDA outperforms the conventional cascaded approach.

本文言語English
ページ(範囲)1493-1507
ページ数15
ジャーナルIEEE/ACM Transactions on Audio Speech and Language Processing
30
DOI
出版ステータスPublished - 2022
外部発表はい

ASJC Scopus subject areas

  • コンピュータ サイエンス(その他)
  • 音響学および超音波学
  • 計算数学
  • 電子工学および電気工学

フィンガープリント

「Encoder-Decoder Based Attractors for End-to-End Neural Diarization」の研究トピックを掘り下げます。これらがまとまってユニークなフィンガープリントを構成します。

引用スタイル