End-to-End Speech Recognition Sequence Training With Reinforcement Learning

End-to-End Speech Recognition Sequence Training With Reinforcement Learning

End-to-end sequence modeling has become a popular choice for automatic speech recognition (ASR) because of the simpler pipeline compared to the conventional system and its excellent performance. However, there are several drawbacks in the end-to-end ASR model training where the current time-step pre...

Full description

Bibliographic Details
Main Authors: Andros Tjandra, Sakriani Sakti, Satoshi Nakamura
Format: Article
Language:English
Published: IEEE 2019-01-01
Series:IEEE Access
Subjects:
End-to-end sequence model
speech recognition
policy gradient optimization
reinforcement learning
Online Access:https://ieeexplore.ieee.org/document/8735756/

Internet

https://ieeexplore.ieee.org/document/8735756/

Similar Items