Promising Accurate Prefix Boosting for Sequence-to-sequence ASR

Murali Karthick Baskar; Lukás Burget; Shinji Watanabe; Martin Karafiát; Takaaki Hori; Jan Honza Cernocký

ICASSP 2019accepted0 citations

Promising Accurate Prefix Boosting for Sequence-to-sequence ASR

Murali Karthick Baskar, Lukás Burget, Shinji Watanabe, Martin Karafiát, Takaaki Hori, Jan Honza Cernocký

Abstract

In this paper, we present promising accurate prefix boosting (PAPB), a discriminative training technique for attention based sequence-to-sequence (seq2seq) ASR. PAPB is devised to unify the training and testing scheme effectively. The training procedure involves maximizing the score of each partial correct sequence obtained during beam search compared to other hypotheses. The training objective also includes minimization of token (character) error rate. PAPB shows its efficacy by achieving 10.8% and 3.8% WER with and without external RNNLM respectively on Wall Street Journal dataset.

BibTeX

@inproceedings{icassp2019_promisingaccurat,
  title = {Promising Accurate Prefix Boosting for Sequence-to-sequence ASR},
  author = {Murali Karthick Baskar and Lukás Burget and Shinji Watanabe and Martin Karafiát and Takaaki Hori and Jan Honza Cernocký},
  booktitle = {ICASSP 2019},
  year = {2019}
}