Unsupervised Speech Segmentation: A General Approach Using Speech Language Models

TL;DR

This paper presents a novel unsupervised speech segmentation method leveraging speech language models to identify multiple acoustic-semantic style changes in speech, outperforming traditional spectral change-based methods.

Contribution

It introduces a general unsupervised approach for speech segmentation that captures diverse acoustic-semantic distinctions using speech language models, extending beyond single-style change detection.

Findings

Superior boundary detection compared to baselines

Higher segment purity achieved

Reduced over-segmentation

Abstract

In this paper, we introduce an unsupervised approach for Speech Segmentation, which builds on previously researched approaches, e.g., Speaker Diarization, while being applicable to an inclusive set of acoustic-semantic distinctions, paving a path towards a general Unsupervised Speech Segmentation approach. Unlike traditional speech and audio segmentation, which mainly focuses on spectral changes in the input signal, e.g., phone segmentation, our approach tries to segment the spoken utterance into chunks with differing acoustic-semantic styles, focusing on acoustic-semantic information that does not translate well into text, e.g., emotion or speaker. While most Speech Segmentation tasks only handle one style change, e.g., emotion diarization, our approach tries to handle multiple acoustic-semantic style changes. Leveraging recent advances in Speech Language Models (SLMs), we propose a simple unsupervised method to segment a given speech utterance. We empirically demonstrate the effectiveness of the proposed approach by considering several setups. Results suggest that the proposed method is superior to the evaluated baselines on boundary detection, segment purity, and over-segmentation. Code is available at https://github.com/avishaiElmakies/unsupervised_speech_segmentation_using_slm.