English

3M: Multi-loss, Multi-path and Multi-level Neural Networks for speech recognition

Sound 2022-04-15 v2 Computation and Language Audio and Speech Processing

Abstract

Recently, Conformer based CTC/AED model has become a mainstream architecture for ASR. In this paper, based on our prior work, we identify and integrate several approaches to achieve further improvements for ASR tasks, which we denote as multi-loss, multi-path and multi-level, summarized as "3M" model. Specifically, multi-loss refers to the joint CTC/AED loss and multi-path denotes the Mixture-of-Experts(MoE) architecture which can effectively increase the model capacity without remarkably increasing computation cost. Multi-level means that we introduce auxiliary loss at multiple level of a deep model to help training. We evaluate our proposed method on the public WenetSpeech dataset and experimental results show that the proposed method provides 12.2%-17.6% relative CER improvement over the baseline model trained by Wenet toolkit. On our large scale dataset of 150k hours corpus, the 3M model has also shown obvious superiority over the baseline Conformer model. Code is publicly available at https://github.com/tencent-ailab/3m-asr.

Keywords

Cite

@article{arxiv.2204.03178,
  title  = {3M: Multi-loss, Multi-path and Multi-level Neural Networks for speech recognition},
  author = {Zhao You and Shulin Feng and Dan Su and Dong Yu},
  journal= {arXiv preprint arXiv:2204.03178},
  year   = {2022}
}

Comments

5 pages, 1 figure. Submitted to INTERSPEECH 2022

R2 v1 2026-06-24T10:40:39.104Z