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

Title: MS-HuBERT: Mitigating Pre-training and Inference Mismatch in Masked Language Modelling methods for learning Speech Representations
Authors: Hemant Yadav, Sunayana Sitaram, Rajiv Ratn Shah
Published: 9th June 2024 (Sunday) @ 06:30:28
Link: http://arxiv.org/abs/2406.05661v2

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.

---