Neural Multichannel Distant Speaker Diarization with Heavy-tailed Source Separation Model

2026-09-10

AI Summary

本文针对远场说话人日志难题，提出了一种结合重尾模型的神经多通道方法，改进了原有基于高斯分布的模型，提高了日志错误率和Jaccard错误率。

Abstract

Distant speaker diarization remains challenging due to difficult acoustic environments, varying numbers of speakers and overlapping speech. Model-driven methods are proposed to exploit the speech source features in multi-channel recordings that help diarization. This paper generalizes a neural model that jointly learns to perform blind source separation and diarization over speech mixtures (neural FCASA) with heavy-tailed models. The popular Gaussian distribution has been applied for variance modeling in the original source separation model, which we replace with two families of heavy-tailed models (Leptokurtic Generalized Gaussian distribution and Student's t distribution) to better capture the heavy-tailedness in speech signals. Thanks to the Gaussian scale mixture model, we are able to unify the proposed method and the original one under the same form of learning objective. Our experiments show consistent large improvements in Diarization Error Rate (DER) and Jaccard Error Rate (JER) compared to the baseline on various corpora.

Problem

• Distant speaker diarization
• Acoustic environments
• Overlapping speech

Innovation

• Neural FCASA
• Heavy-tailed models
• Diarization Error Rate (DER)
• Jaccard Error Rate (JER)
• Gaussian scale mixture model