English

Knowledge distillation from language model to acoustic model: a hierarchical multi-task learning approach

Machine Learning 2021-10-22 v1 Computation and Language Sound Audio and Speech Processing

Abstract

The remarkable performance of the pre-trained language model (LM) using self-supervised learning has led to a major paradigm shift in the study of natural language processing. In line with these changes, leveraging the performance of speech recognition systems with massive deep learning-based LMs is a major topic of speech recognition research. Among the various methods of applying LMs to speech recognition systems, in this paper, we focus on a cross-modal knowledge distillation method that transfers knowledge between two types of deep neural networks with different modalities. We propose an acoustic model structure with multiple auxiliary output layers for cross-modal distillation and demonstrate that the proposed method effectively compensates for the shortcomings of the existing label-interpolation-based distillation method. In addition, we extend the proposed method to a hierarchical distillation method using LMs trained in different units (senones, monophones, and subwords) and reveal the effectiveness of the hierarchical distillation method through an ablation study.

Keywords

Cite

@article{arxiv.2110.10429,
  title  = {Knowledge distillation from language model to acoustic model: a hierarchical multi-task learning approach},
  author = {Mun-Hak Lee and Joon-Hyuk Chang},
  journal= {arXiv preprint arXiv:2110.10429},
  year   = {2021}
}

Comments

4page + 1page for citation + 2 pages for appendix

R2 v1 2026-06-24T07:02:20.368Z