Eat: Enhanced ASR-TTS for Self-Supervised Speech Recognition
The result's identifiers
Result code in IS VaVaI
<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F00216305%3A26230%2F21%3APU142916" target="_blank" >RIV/00216305:26230/21:PU142916 - isvavai.cz</a>
Result on the web
<a href="https://ieeexplore.ieee.org/document/9413375" target="_blank" >https://ieeexplore.ieee.org/document/9413375</a>
DOI - Digital Object Identifier
<a href="http://dx.doi.org/10.1109/ICASSP39728.2021.9413375" target="_blank" >10.1109/ICASSP39728.2021.9413375</a>
Alternative languages
Result language
angličtina
Original language name
Eat: Enhanced ASR-TTS for Self-Supervised Speech Recognition
Original language description
Self-supervised ASR-TTS models suffer in out-of-domain data conditions. Here we propose an enhanced ASR-TTS (EAT) model that incorporates two main features: 1) The ASR!TTS direction is equipped with a language model reward to penalize the ASR hypotheses before forwarding it to TTS. 2) In the TTS!ASR direction, a hyper-parameter is introduced to scale the attention context from synthesized speech before sending it to ASR to handle out-ofdomain data. Training strategies and the effectiveness of the EAT model are explored under out-of-domain data conditions. The results show that EAT reduces the performance gap between supervised and self-supervised training significantly by absolute 2.6% and 2.7% on Librispeech and BABEL respectively.
Czech name
—
Czech description
—
Classification
Type
D - Article in proceedings
CEP classification
—
OECD FORD branch
10201 - Computer sciences, information science, bioinformathics (hardware development to be 2.2, social aspect to be 5.8)
Result continuities
Project
Result was created during the realization of more than one project. More information in the Projects tab.
Continuities
P - Projekt vyzkumu a vyvoje financovany z verejnych zdroju (s odkazem do CEP)
Others
Publication year
2021
Confidentiality
S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů
Data specific for result type
Article name in the collection
ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)
ISBN
978-1-7281-7605-5
ISSN
—
e-ISSN
—
Number of pages
5
Pages from-to
6753-6757
Publisher name
IEEE Signal Processing Society
Place of publication
Toronto, Ontario
Event location
Toronto, Canada
Event date
Jun 6, 2021
Type of event by nationality
WRD - Celosvětová akce
UT code for WoS article
000704288407006