Detail výsledku

Eat: Enhanced ASR-TTS for Self-Supervised Speech Recognition

BASKAR, M.; BURGET, L.; WATANABE, S.; ASTUDILLO, R.; ČERNOCKÝ, J. Eat: Enhanced ASR-TTS for Self-Supervised Speech Recognition. In ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). Toronto, Ontario: IEEE Signal Processing Society, 2021. p. 6753-6757. ISBN: 978-1-7281-7605-5.
Typ
článek ve sborníku konference
Jazyk
anglicky
Autoři
Baskar Murali Karthick, Ing., Ph.D., UPGM (FIT)
Burget Lukáš, doc. Ing., Ph.D., UPGM (FIT)
Watanabe Shinji, FIT (FIT)
ASTUDILLO, R.
Černocký Jan, prof. Dr. Ing., UPGM (FIT)
Abstrakt

Self-supervised ASR-TTS models suffer in out-of-domain data conditions.Here we propose an enhanced ASR-TTS (EAT) model thatincorporates two main features: 1) The ASR!TTS direction isequipped with a language model reward to penalize the ASR hypothesesbefore forwarding it to TTS. 2) In the TTS!ASR direction,a hyper-parameter is introduced to scale the attention contextfrom synthesized speech before sending it to ASR to handle out-ofdomaindata. Training strategies and the effectiveness of the EATmodel are explored under out-of-domain data conditions. The resultsshow that EAT reduces the performance gap between supervised andself-supervised training significantly by absolute 2.6% and 2.7% onLibrispeech and BABEL respectively.

Klíčová slova

cycle-consistency, self-supervision, sequence-tosequence,speech recognition

URL
Rok
2021
Strany
6753–6757
Sborník
ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)
Konference
2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)
ISBN
978-1-7281-7605-5
Vydavatel
IEEE Signal Processing Society
Místo
Toronto, Ontario
DOI
10.1109/ICASSP39728.2021.9413375
UT WoS
000704288407006
EID Scopus
2-s2.0-85112201924
BibTeX 
@inproceedings{BUT175793,
  author="BASKAR, M. and BURGET, L. and WATANABE, S. and ASTUDILLO, R. and ČERNOCKÝ, J.",
  title="Eat: Enhanced ASR-TTS for Self-Supervised Speech Recognition",
  booktitle="ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)",
  year="2021",
  pages="6753--6757",
  publisher="IEEE Signal Processing Society",
  address="Toronto, Ontario",
  doi="10.1109/ICASSP39728.2021.9413375",
  isbn="978-1-7281-7605-5",
  url="https://ieeexplore.ieee.org/document/9413375"
}
Soubory
Projekty
Multi-lingualita v řečových technologiích, MŠMT, INTER-EXCELLENCE - Podprogram INTER-ACTION, LTAIN19087, zahájení: 2020-01-01, ukončení: 2023-08-31, ukončen
Neuronové reprezentace v multimodálním a mnohojazyčném modelování, GAČR, Grantové projekty exelence v základním výzkumu EXPRO - 2019, GX19-26934X, zahájení: 2019-01-01, ukončení: 2023-12-31, ukončen
Výzkumné skupiny
Výzkumná skupina dolování dat z řeči BUT Speech@FIT (VZ SPEECH)
Pracoviště
Ústav počítačové grafiky a multimédií (UPGM)
Nahoru