TY - GEN
T1 - A Study of Transducer Based End-to-End ASR with ESPnet
T2 - 2021 IEEE Automatic Speech Recognition and Understanding Workshop, ASRU 2021
AU - Boyer, Florian
AU - Shinohara, Yusuke
AU - Ishii, Takaaki
AU - Inaguma, Hirofumi
AU - Watanabe, Shinji
N1 - Publisher Copyright:
© 2021 IEEE.
PY - 2021
Y1 - 2021
N2 - In this study, we present recent developments of models trained with the RNN-T loss in ESPnet. It involves the use of various archi-tectures such as recently proposed Conformer, multi-task learning with different auxiliary criteria and multiple decoding strategies, in-cluding our own proposition. Through experiments and benchmarks, we show that our proposed systems can be competitive against other state-of-art systems on well-known datasets such as LibriSpeech and AISHELL-1. Additionally, we demonstrate that these models are promising against other already implemented systems in ESPnet in regards to both performance and decoding speed, enabling the pos-sibility to have powerful systems for a streaming task. With these additions, we hope to expand the usefulness of the ESPnet toolkit for the research community and also give tools for the ASR industry to deploy our systems in realistic and production environments.
AB - In this study, we present recent developments of models trained with the RNN-T loss in ESPnet. It involves the use of various archi-tectures such as recently proposed Conformer, multi-task learning with different auxiliary criteria and multiple decoding strategies, in-cluding our own proposition. Through experiments and benchmarks, we show that our proposed systems can be competitive against other state-of-art systems on well-known datasets such as LibriSpeech and AISHELL-1. Additionally, we demonstrate that these models are promising against other already implemented systems in ESPnet in regards to both performance and decoding speed, enabling the pos-sibility to have powerful systems for a streaming task. With these additions, we hope to expand the usefulness of the ESPnet toolkit for the research community and also give tools for the ASR industry to deploy our systems in realistic and production environments.
KW - RNN-T loss
KW - auxiliary task
KW - decoding strategies
KW - end-to-end speech recognition
UR - http://www.scopus.com/inward/record.url?scp=85119110208&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85119110208&partnerID=8YFLogxK
U2 - 10.1109/ASRU51503.2021.9688251
DO - 10.1109/ASRU51503.2021.9688251
M3 - Conference contribution
AN - SCOPUS:85119110208
T3 - 2021 IEEE Automatic Speech Recognition and Understanding Workshop, ASRU 2021 - Proceedings
SP - 16
EP - 23
BT - 2021 IEEE Automatic Speech Recognition and Understanding Workshop, ASRU 2021 - Proceedings
PB - Institute of Electrical and Electronics Engineers Inc.
Y2 - 13 December 2021 through 17 December 2021
ER -