Large-Scale Semi-Supervised Training in Deep Learning Acoustic Model for ASR

Large-Scale Semi-Supervised Training in Deep Learning Acoustic Model for ASR

This study investigated large-scale semi-supervised training (SST) to improve acoustic models for automatic speech recognition. The conventional self-training, the recently proposed committee-based SST using heterogeneous neural networks and the lattice-based SST were examined and compared. The larg...

Full description

Bibliographic Details
Main Authors: Yanhua Long, Yijie Li, Shuang Wei, Qiaozheng Zhang, Chunxia Yang
Format: Article
Language:English
Published: IEEE 2019-01-01
Series:IEEE Access
Subjects:
Semi-supervised learning
data preprocessing
acoustic modeling
speech recognition
Online Access:https://ieeexplore.ieee.org/document/8835895/

Internet

https://ieeexplore.ieee.org/document/8835895/

Similar Items