Accented Speech Recognition Based on End-to-End Domain Adversarial Training of Neural Networks
The performance of automatic speech recognition (ASR) may be degraded when accented speech is recognized because the speech has some linguistic differences from standard speech. Conventional accented speech recognition studies have utilized the accent embedding method, in which the accent embedding...
Main Authors: | Hyeong-Ju Na, Jeong-Sik Park |
---|---|
Format: | Article |
Language: | English |
Published: |
MDPI AG
2021-09-01
|
Series: | Applied Sciences |
Subjects: | |
Online Access: | https://www.mdpi.com/2076-3417/11/18/8412 |
Similar Items
-
End-to-End Mandarin Speech Recognition Combining CNN and BLSTM
by: Dong Wang, et al.
Published: (2019-05-01) -
Adversarial joint training with self-attention mechanism for robust end-to-end speech recognition
by: Lujun Li, et al.
Published: (2021-07-01) -
Unsupervised Domain Adversarial Self-Calibration for Electromyography-Based Gesture Recognition
by: Ulysse Cote-Allard, et al.
Published: (2020-01-01) -
Targeted Speech Adversarial Example Generation With Generative Adversarial Network
by: Donghua Wang, et al.
Published: (2020-01-01) -
Towards end-to-end speech recognition with transfer learning
by: Chu-Xiong Qin, et al.
Published: (2018-11-01)