Subword Regularization and Beam Search Decoding for End-to-end Automatic Speech Recognition

Jennifer Drexler; James R. Glass

ICASSP 2019accepted0 citations

Subword Regularization and Beam Search Decoding for End-to-end Automatic Speech Recognition

Abstract

In this paper, we experiment with the recently introduced subword regularization technique [1] in the context of end-to-end automatic speech recognition (ASR). We present results from both attention-based and CTC-based ASR systems on two common benchmark datasets, the 80 hour Wall Street Journal corpus and 1,000 hour Librispeech corpus. We also introduce a novel subword beam search decoding algorithm that significantly improves the final performance of the CTC-based systems. Overall, we find that subword regularization improves the performance of both types of ASR systems, with the regularized attention-based model performing best overall.

BibTeX

@inproceedings{icassp2019_subwordregulariz,
  title = {Subword Regularization and Beam Search Decoding for End-to-end Automatic Speech Recognition},
  author = {Jennifer Drexler and James R. Glass},
  booktitle = {ICASSP 2019},
  year = {2019}
}