English

A Conformer Based Acoustic Model for Robust Automatic Speech Recognition

Sound 2022-10-21 v3 Artificial Intelligence Computation and Language Audio and Speech Processing

Abstract

This study addresses robust automatic speech recognition (ASR) by introducing a Conformer-based acoustic model. The proposed model builds on the wide residual bi-directional long short-term memory network (WRBN) with utterance-wise dropout and iterative speaker adaptation, but employs a Conformer encoder instead of the recurrent network. The Conformer encoder uses a convolution-augmented attention mechanism for acoustic modeling. The proposed system is evaluated on the monaural ASR task of the CHiME-4 corpus. Coupled with utterance-wise normalization and speaker adaptation, our model achieves 6.25%6.25\% word error rate, which outperforms WRBN by 8.4%8.4\% relatively. In addition, the proposed Conformer-based model is 18.3%18.3\% smaller in model size and reduces total training time by 79.6%79.6\%.

Keywords

Cite

@article{arxiv.2203.00725,
  title  = {A Conformer Based Acoustic Model for Robust Automatic Speech Recognition},
  author = {Yufeng Yang and Peidong Wang and DeLiang Wang},
  journal= {arXiv preprint arXiv:2203.00725},
  year   = {2022}
}

Comments

5 pages, 2 figures

R2 v1 2026-06-24T09:58:29.588Z