Dual supervised learning for non-native speech recognition

Dual supervised learning for non-native speech recognition

Abstract Current automatic speech recognition (ASR) systems achieve over 90–95% accuracy, depending on the methodology applied and datasets used. However, the level of accuracy decreases significantly when the same ASR system is used by a non-native speaker of the language to be recognized. At the s...

Full description

Bibliographic Details
Main Authors: Kacper Radzikowski, Robert Nowak, Le Wang, Osamu Yoshie
Format: Article
Language:English
Published: SpringerOpen 2019-01-01
Series:EURASIP Journal on Audio, Speech, and Music Processing
Subjects:
Speech recognition
Dual supervised learning
Reinforcement learning
Policy gradients
Non-native speaker
Machine learning
Online Access:http://link.springer.com/article/10.1186/s13636-018-0146-4

Internet

http://link.springer.com/article/10.1186/s13636-018-0146-4

Similar Items