English

Attention based on-device streaming speech recognition with large speech corpus

Audio and Speech Processing 2020-01-06 v1 Machine Learning Sound

Abstract

In this paper, we present a new on-device automatic speech recognition (ASR) system based on monotonic chunk-wise attention (MoChA) models trained with large (> 10K hours) corpus. We attained around 90% of a word recognition rate for general domain mainly by using joint training of connectionist temporal classifier (CTC) and cross entropy (CE) losses, minimum word error rate (MWER) training, layer-wise pre-training and data augmentation methods. In addition, we compressed our models by more than 3.4 times smaller using an iterative hyper low-rank approximation (LRA) method while minimizing the degradation in recognition accuracy. The memory footprint was further reduced with 8-bit quantization to bring down the final model size to lower than 39 MB. For on-demand adaptation, we fused the MoChA models with statistical n-gram models, and we could achieve a relatively 36% improvement on average in word error rate (WER) for target domains including the general domain.

Keywords

Cite

@article{arxiv.2001.00577,
  title  = {Attention based on-device streaming speech recognition with large speech corpus},
  author = {Kwangyoun Kim and Kyungmin Lee and Dhananjaya Gowda and Junmo Park and Sungsoo Kim and Sichen Jin and Young-Yoon Lee and Jinsu Yeo and Daehyun Kim and Seokyeong Jung and Jungin Lee and Myoungji Han and Chanwoo Kim},
  journal= {arXiv preprint arXiv:2001.00577},
  year   = {2020}
}

Comments

Accepted and presented at the ASRU 2019 conference

R2 v1 2026-06-23T13:01:41.690Z