The reviewed record of science sign in
Pith

arxiv: 2106.04078 · v1 · pith:2W7Y63M4 · submitted 2021-06-08 · eess.AS · cs.SD

End-to-End Speaker Diarization Conditioned on Speech Activity and Overlap Detection

Reviewed by Pith T0 review T1 audit T2 compute T3 formal T4 kernel pith:2W7Y63M4record.jsonopen to challenge →

classification eess.AS cs.SD
keywords diarizationspeakereendspeechactivityconditioneddetectionend-to-end
0
0 comments X
read the original abstract

In this paper, we present a conditional multitask learning method for end-to-end neural speaker diarization (EEND). The EEND system has shown promising performance compared with traditional clustering-based methods, especially in the case of overlapping speech. In this paper, to further improve the performance of the EEND system, we propose a novel multitask learning framework that solves speaker diarization and a desired subtask while explicitly considering the task dependency. We optimize speaker diarization conditioned on speech activity and overlap detection that are subtasks of speaker diarization, based on the probabilistic chain rule. Experimental results show that our proposed method can leverage a subtask to effectively model speaker diarization, and outperforms conventional EEND systems in terms of diarization error rate.

This paper has not been read by Pith yet.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.