DiaCorrect: End-to-end error correction for speaker diarization

TL;DR

DiaCorrect introduces an end-to-end neural framework that refines speaker diarization results by leveraging acoustic interactions, significantly reducing diarization errors in a simple and efficient manner.

Contribution

This paper presents the novel DiaCorrect framework, an end-to-end error correction method that improves diarization accuracy by automatically adapting initial speaker activity estimates.

Findings

Reduces diarization error rate by over 62.4%.

Achieves a DER reduction from 12.31% to 4.63%.

Demonstrates effectiveness on LibriSpeech 2-speaker data.

Abstract

In recent years, speaker diarization has attracted widespread attention. To achieve better performance, some studies propose to diarize speech in multiple stages. Although these methods might bring additional benefits, most of them are quite complex. Motivated by spelling correction in automatic speech recognition (ASR), in this paper, we propose an end-to-end error correction framework, termed DiaCorrect, to refine the initial diarization results in a simple but efficient way. By exploiting the acoustic interactions between input mixture and its corresponding speaker activity, DiaCorrect could automatically adapt the initial speaker activity to minimize the diarization errors. Without bells and whistles, experiments on LibriSpeech based 2-speaker meeting-like data show that, the self-attentitive end-to-end neural diarization (SA-EEND) baseline with DiaCorrect could reduce its diarization error rate (DER) by over 62.4% from 12.31% to 4.63%. Our source code is available online at https://github.com/jyhan03/diacorrect.