2024 INTERSPEECH INTERSPEECH 2024

MS-HuBERT: Mitigating Pre-training and Inference Mismatch in Masked Language Modelling methods for learning Speech Representations

Abstract

In recent years, self-supervised pre-training methods have gained significant traction in learning high-level information from raw speech. Among these methods, HuBERT has demonstrated SOTA performance in automatic speech recognition (ASR). However, HuBERT's performance lags behind data2vec due to disparities in pre-training strategies. In this paper, we propose (i) a Swap method to address pre-training and inference mismatch observed in HuBERT and (ii) incorporates Multicluster masked prediction loss for more effective utilization of the models capacity. The resulting method is, MS-HuBERT, an end-to-end self-supervised pre-training method for learning robust speech representations. It beats vanilla HuBERT on the ASR Librispeech benchmark on average by a 5% margin when evaluated on different finetuning splits. Additionally, we demonstrate that the learned embeddings obtained during pre-training encode essential information for improving performance of content based tasks such as ASR.

🌉 Interdisciplinary Bridge — Deep Learning and Machine Learning and Speech & Audio
🧭 Keyword Pioneer — masked language modelling
🐝 Cross-Pollinator — Artificial Intelligence, Computer Science, Computer Vision, Deep Learning, Interdisciplinary, Machine Learning, Natural Language Processing, Speech & Audio