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