End-to-end automatic speech recognition (ASR) models with a single neural network have recently demonstrated state-of-the-art results compared to conventional hybrid speech recognizers. Specifically, recurrent neural network transducer (RNN-T) has shown competitive ASR performance on various benchmarks. In this work, we examine ways in which RNN-T can achieve better ASR accuracy via performing auxiliary tasks. We propose (i) using the same auxiliary task as primary RNN-T ASR task, and (ii) performing context-dependent graphemic state prediction as in conventional hybrid modeling. In transcribing social media videos with varying training data size, we first evaluate the streaming ASR performance on three languages: Romanian, Turkish and German. We find that both proposed methods provide consistent improvements. Next, we observe that both auxiliary tasks demonstrate efficacy in learning deep transformer encoders for RNN-T criterion, thus achieving competitive results - 2.0%/4.2% WER on LibriSpeech test-clean/other - as compared to prior top performing models.
@article{arxiv.2011.03109,
title = {Improving RNN Transducer Based ASR with Auxiliary Tasks},
author = {Chunxi Liu and Frank Zhang and Duc Le and Suyoun Kim and Yatharth Saraf and Geoffrey Zweig},
journal= {arXiv preprint arXiv:2011.03109},
year = {2020}
}
Comments
Accepted for publication at IEEE Spoken Language Technology Workshop (SLT), 2021