English

Joint Unsupervised and Supervised Training for Multilingual ASR

Computation and Language 2021-11-17 v1 Machine Learning Sound Audio and Speech Processing

Abstract

Self-supervised training has shown promising gains in pretraining models and facilitating the downstream finetuning for speech recognition, like multilingual ASR. Most existing methods adopt a 2-stage scheme where the self-supervised loss is optimized in the first pretraining stage, and the standard supervised finetuning resumes in the second stage. In this paper, we propose an end-to-end (E2E) Joint Unsupervised and Supervised Training (JUST) method to combine the supervised RNN-T loss and the self-supervised contrastive and masked language modeling (MLM) losses. We validate its performance on the public dataset Multilingual LibriSpeech (MLS), which includes 8 languages and is extremely imbalanced. On MLS, we explore (1) JUST trained from scratch, and (2) JUST finetuned from a pretrained checkpoint. Experiments show that JUST can consistently outperform other existing state-of-the-art methods, and beat the monolingual baseline by a significant margin, demonstrating JUST's capability of handling low-resource languages in multilingual ASR. Our average WER of all languages outperforms average monolingual baseline by 33.3%, and the state-of-the-art 2-stage XLSR by 32%. On low-resource languages like Polish, our WER is less than half of the monolingual baseline and even beats the supervised transfer learning method which uses external supervision.

Keywords

Cite

@article{arxiv.2111.08137,
  title  = {Joint Unsupervised and Supervised Training for Multilingual ASR},
  author = {Junwen Bai and Bo Li and Yu Zhang and Ankur Bapna and Nikhil Siddhartha and Khe Chai Sim and Tara N. Sainath},
  journal= {arXiv preprint arXiv:2111.08137},
  year   = {2021}
}
R2 v1 2026-06-24T07:39:46.056Z