Publication Details

Promising Accurate Prefix Boosting For Sequence-to-sequence ASR

BASKAR Murali K., BURGET Lukáš, WATANABE Shinji, KARAFIÁT Martin, HORI Takaaki and ČERNOCKÝ Jan. Promising Accurate Prefix Boosting For Sequence-to-sequence ASR. In: Proceedings of ICASSP. Brighton: IEEE Signal Processing Society, 2019, pp. 5646-5650. ISBN 978-1-5386-4658-8. Available from: https://ieeexplore.ieee.org/document/8682782
Czech title
Slibná technika pro přesné zdůrazňování prexixů pro ASR založené na převodu sekvencí na sekvence
Type
conference paper
Language
english
Authors
Baskar Murali K. (DCGM FIT BUT)
Burget Lukáš, doc. Ing., Ph.D. (DCGM FIT BUT)
Watanabe Shinji, Dr. (JHU)
Karafiát Martin, Ing., Ph.D. (DCGM FIT BUT)
Hori Takaaki (MERL)
Černocký Jan, prof. Dr. Ing. (DCGM FIT BUT)
URL
Keywords

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

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.

Published
2019
Pages
5646-5650
Proceedings
Proceedings of ICASSP
Conference
2019 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH AND SIGNAL PROCESSING (ICASSP), Brighton, GB
ISBN
978-1-5386-4658-8
Publisher
IEEE Signal Processing Society
Place
Brighton, GB
DOI
UT WoS
000482554005176
EID Scopus
BibTeX
@INPROCEEDINGS{FITPUB12094,
   author = "K. Murali Baskar and Luk\'{a}\v{s} Burget and Shinji Watanabe and Martin Karafi\'{a}t and Takaaki Hori and Jan \v{C}ernock\'{y}",
   title = "Promising Accurate Prefix Boosting For Sequence-to-sequence ASR",
   pages = "5646--5650",
   booktitle = "Proceedings of ICASSP",
   year = 2019,
   location = "Brighton, GB",
   publisher = "IEEE Signal Processing Society",
   ISBN = "978-1-5386-4658-8",
   doi = "10.1109/ICASSP.2019.8682782",
   language = "english",
   url = "https://www.fit.vut.cz/research/publication/12094"
}
Back to top