Detail publikace

Promising Accurate Prefix Boosting For Sequence-to-sequence ASR

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

Originální název

Promising Accurate Prefix Boosting For Sequence-to-sequence ASR

Typ

článek ve sborníku ve WoS nebo Scopus

Jazyk

angličtina

Originální abstrakt

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.

Klíčová slova

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

Autoři

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

Vydáno

12. 5. 2019

Nakladatel

IEEE Signal Processing Society

Místo

Brighton

ISBN

978-1-5386-4658-8

Kniha

Proceedings of ICASSP

Strany od

5646

Strany do

5650

Strany počet

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"
}