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

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.

@article{yadav2025_2406.05661,
  title={ MS-HuBERT: Mitigating Pre-training and Inference Mismatch in Masked Language Modelling methods for learning Speech Representations },
  author={ Hemant Yadav and Sunayana Sitaram and Rajiv Ratn Shah },
  journal={arXiv preprint arXiv:2406.05661},
  year={ 2025 }
}