English

QuartzNet: Deep Automatic Speech Recognition with 1D Time-Channel Separable Convolutions

Audio and Speech Processing 2019-10-24 v1

Abstract

We propose a new end-to-end neural acoustic model for automatic speech recognition. The model is composed of multiple blocks with residual connections between them. Each block consists of one or more modules with 1D time-channel separable convolutional layers, batch normalization, and ReLU layers. It is trained with CTC loss. The proposed network achieves near state-of-the-art accuracy on LibriSpeech and Wall Street Journal, while having fewer parameters than all competing models. We also demonstrate that this model can be effectively fine-tuned on new datasets.

Keywords

Cite

@article{arxiv.1910.10261,
  title  = {QuartzNet: Deep Automatic Speech Recognition with 1D Time-Channel Separable Convolutions},
  author = {Samuel Kriman and Stanislav Beliaev and Boris Ginsburg and Jocelyn Huang and Oleksii Kuchaiev and Vitaly Lavrukhin and Ryan Leary and Jason Li and Yang Zhang},
  journal= {arXiv preprint arXiv:1910.10261},
  year   = {2019}
}

Comments

Submitted to ICASSP 2020

R2 v1 2026-06-23T11:51:57.138Z