HuBERTopic: Enhancing Semantic Representation of HuBERT through Self-supervision Utilizing Topic Model

TL;DR

This paper introduces HuBERTopic, a method that enhances HuBERT's semantic understanding by integrating topic modeling with self-supervised learning, improving performance across speech tasks.

Contribution

It proposes a novel approach that combines topic models with HuBERT to incorporate global semantic information in an unsupervised manner.

Findings

Achieves comparable or better performance than baseline in speech tasks.

Captures diverse semantic information like speaker and theme.

Improves understanding of global context in speech representations.

Abstract

Recently, the usefulness of self-supervised representation learning (SSRL) methods has been confirmed in various downstream tasks. Many of these models, as exemplified by HuBERT and WavLM, use pseudo-labels generated from spectral features or the model's own representation features. From previous studies, it is known that the pseudo-labels contain semantic information. However, the masked prediction task, the learning criterion of HuBERT, focuses on local contextual information and may not make effective use of global semantic information such as speaker, theme of speech, and so on. In this paper, we propose a new approach to enrich the semantic representation of HuBERT. We apply topic model to pseudo-labels to generate a topic label for each utterance. An auxiliary topic classification task is added to HuBERT by using topic labels as teachers. This allows additional global semantic information to be incorporated in an unsupervised manner. Experimental results demonstrate that our method achieves comparable or better performance than the baseline in most tasks, including automatic speech recognition and five out of the eight SUPERB tasks. Moreover, we find that topic labels include various information about utterance, such as gender, speaker, and its theme. This highlights the effectiveness of our approach in capturing multifaceted semantic nuances.