Detail publikačního výsledku

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

Anglický název

Promising Accurate Prefix Boosting For Sequence-to-sequence ASR

Druh

Stať ve sborníku v databázi WoS či Scopus

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 andtesting scheme effectively. The training procedure involves maximizingthe score of each partial correct sequence obtained duringbeam search compared to other hypotheses. The training objectivealso includes minimization of token (character) error rate. PAPBshows its efficacy by achieving 10.8% and 3.8% WER with and withoutexternal RNNLM respectively on Wall Street Journal dataset.

Anglický 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 andtesting scheme effectively. The training procedure involves maximizingthe score of each partial correct sequence obtained duringbeam search compared to other hypotheses. The training objectivealso includes minimization of token (character) error rate. PAPBshows its efficacy by achieving 10.8% and 3.8% WER with and withoutexternal RNNLM respectively on Wall Street Journal dataset.

Klíčová slova

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

Klíčová slova v angličtině

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

Autoři

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

Rok RIV

2020

Vydáno

12.05.2019

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

https://ieeexplore.ieee.org/document/8682782

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"
}

Dokumenty

baskar_icassp2019_0005646