Result Details

Promising Accurate Prefix Boosting For Sequence-to-sequence ASR

BASKAR, M.; BURGET, L.; WATANABE, S.; KARAFIÁT, M.; HORI, T.; ČERNOCKÝ, J. Promising Accurate Prefix Boosting For Sequence-to-sequence ASR. In Proceedings of ICASSP. Brighton: IEEE Signal Processing Society, 2019. p. 5646-5650. ISBN: 978-1-5386-4658-8.
Type
conference paper
Language
English
Authors
Baskar Murali Karthick, Ing., Ph.D., DCGM (FIT)
Burget Lukáš, doc. Ing., Ph.D., DCGM (FIT)
Watanabe Shinji, FIT (FIT)
Karafiát Martin, Ing., Ph.D., DCGM (FIT)
HORI, T.
Černocký Jan, prof. Dr. Ing., DCGM (FIT)
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 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.

Keywords

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

URL
Published
2019
Pages
5646–5650
Proceedings
Proceedings of ICASSP
Conference
2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)
ISBN
978-1-5386-4658-8
Publisher
IEEE Signal Processing Society
Place
Brighton
DOI
10.1109/ICASSP.2019.8682782
UT WoS
000482554005176
EID Scopus
2-s2.0-85068959446
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"
}
Files
Projects
IARPA Machine Translation for English Retrieval of Information in Any Language (MATERIAL) - Foreign Language Automated Information Retrieval (FLAIR), IARPA, start: 2017-09-21, end: 2021-10-22, completed
IT4Innovations excellence in science, MŠMT, Národní program udržitelnosti II, LQ1602, start: 2016-01-01, end: 2020-12-31, completed
Research groups
Speech Data Mining Research Group BUT Speech@FIT (RG SPEECH)
Departments
Department of Computer Graphics and Multimedia (DCGM)
Back to top