Publication detail

Promising Accurate Prefix Boosting For Sequence-to-sequence ASR

BASKAR, M. BURGET, L. WATANABE, S. KARAFIÁT, M. HORI, T. ČERNOCKÝ, J.

Original Title

Promising Accurate Prefix Boosting For Sequence-to-sequence ASR

Type

conference paper

Language

English

Original Abstract

In this paper, we present promising accurate prefix boosting (PAPB), a discriminative training technique for attention based sequence-tosequence (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.

Keywords

Beam search training, sequence learning, discriminative training, Attention models, softmax-margin

Authors

BASKAR, M.; BURGET, L.; WATANABE, S.; KARAFIÁT, M.; HORI, T.; ČERNOCKÝ, J.

Released

12. 5. 2019

Publisher

IEEE Signal Processing Society

Location

Brighton

ISBN

978-1-5386-4658-8

Book

Proceedings of ICASSP

Pages from

5646

Pages to

5650

Pages count

5

URL

BibTex

@inproceedings{BUT160001,
  author="BASKAR, M. and BURGET, L. and WATANABE, S. and KARAFIÁT, M. and HORI, T. and ČERNOCKÝ, J.",
  title="Promising Accurate Prefix Boosting For Sequence-to-sequence ASR",
  booktitle="Proceedings of ICASSP",
  year="2019",
  pages="5646--5650",
  publisher="IEEE Signal Processing Society",
  address="Brighton",
  doi="10.1109/ICASSP.2019.8682782",
  isbn="978-1-5386-4658-8",
  url="https://ieeexplore.ieee.org/document/8682782"
}

Documents