Efficient minimum word error rate training of RNN-Transducer for end-to-end speech recognition

TL;DR

This paper introduces an efficient MWER training method for RNN-Transducer in end-to-end speech recognition, significantly speeding up training while maintaining or improving WER performance.

Contribution

It proposes a semi-on-the-fly MWER training approach that decouples decoding and training, enabling faster training and improved accuracy over baseline models.

Findings

Speeds up MWER training by 6 times compared to previous methods.

Achieves 3.6% WER reduction on a speech recognition benchmark.

Reduces high-deletion errors and improves recognition in various domains.

Abstract

In this work, we propose a novel and efficient minimum word error rate (MWER) training method for RNN-Transducer (RNN-T). Unlike previous work on this topic, which performs on-the-fly limited-size beam-search decoding and generates alignment scores for expected edit-distance computation, in our proposed method, we re-calculate and sum scores of all the possible alignments for each hypothesis in N-best lists. The hypothesis probability scores and back-propagated gradients are calculated efficiently using the forward-backward algorithm. Moreover, the proposed method allows us to decouple the decoding and training processes, and thus we can perform offline parallel-decoding and MWER training for each subset iteratively. Experimental results show that this proposed semi-on-the-fly method can speed up the on-the-fly method by 6 times and result in a similar WER improvement (3.6%) over a baseline RNN-T model. The proposed MWER training can also effectively reduce high-deletion errors (9.2% WER-reduction) introduced by RNN-T models when EOS is added for endpointer. Further improvement can be achieved if we use a proposed RNN-T rescoring method to re-rank hypotheses and use external RNN-LM to perform additional rescoring. The best system achieves a 5% relative improvement on an English test-set of real far-field recordings and a 11.6% WER reduction on music-domain utterances.