Detail publikace

Language Model Integration Based on Memory Control for Sequence to Sequence Speech Recognition

CHO, J.; WATANABE, S.; HORI, T.; BASKAR, M.; INAGUMA, H.; VILLALBA LOPEZ, J.; DEHAK, N. Language Model Integration Based on Memory Control for Sequence to Sequence Speech Recognition. In Proceedings of 2019 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH AND SIGNAL PROCESSING (ICASSP). Brighton: IEEE Signal Processing Society, 2019. p. 6191-6195. ISBN: 978-1-5386-4658-8.
Název česky
Integrace jazykového modelu v sequence-to-sequence rozpoznávání řeči založená na řízení paměťových buněk
Typ
článek ve sborníku konference
Jazyk
anglicky
Autoři
CHO, J.
Watanabe Shinji (FIT)
HORI, T.
Baskar Murali Karthick, Ing., Ph.D.
INAGUMA, H.
VILLALBA LOPEZ, J.
Dehak Najim
URL
Klíčová slova

Automatic speech recognition (ASR), sequence to sequence, language model, shallow fusion, deep fusion, cold fusion

Abstrakt

Článek pojednává o integraci jazykového modelu v sequence-to-sequence rozpoznávání řeči založené na řízení paměťových buněk.

Rok
2019
Strany
6191–6195
Sborník
Proceedings of 2019 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH AND SIGNAL PROCESSING (ICASSP)
ISBN
978-1-5386-4658-8
Vydavatel
IEEE Signal Processing Society
Místo
Brighton
DOI
10.1109/ICASSP.2019.8683380
UT WoS
000482554006084
EID Scopus
2-s2.0-85069000387
BibTeX 
@inproceedings{BUT163488,
  author="CHO, J. and WATANABE, S. and HORI, T. and BASKAR, M. and INAGUMA, H. and VILLALBA LOPEZ, J. and DEHAK, N.",
  title="Language Model Integration Based on Memory Control for Sequence to Sequence Speech Recognition",
  booktitle="Proceedings of 2019 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH AND SIGNAL PROCESSING (ICASSP)",
  year="2019",
  pages="6191--6195",
  publisher="IEEE Signal Processing Society",
  address="Brighton",
  doi="10.1109/ICASSP.2019.8683380",
  isbn="978-1-5386-4658-8",
  url="https://ieeexplore.ieee.org/document/8683380"
}
Nahoru