Objective-driven discriminative training and adaptation based on an MCE criterion for speech recognition and detection

Objective-driven discriminative training and adaptation based on an MCE criterion for speech recognition and detection

Acoustic modeling in state-of-the-art speech recognition systems is commonly based on discriminative criteria. Different from the paradigm of the conventional distribution estimation such as maximum a posteriori (MAP) and maximum likelihood (ML), the most popular discriminative criteria such as MCE...

Full description

Bibliographic Details
Main Author: Shin, Sung-Hwan
Other Authors: Juang, Biing-Hwang
Format: Others
Language:en_US
Published: Georgia Institute of Technology 2014
Subjects:
Speech recognition
Acoustic modeling
Discriminative training
Discriminative adaptation
Utterance verification
Constrained optimization
Minimum classification error
Minimum verification error
Speech perception
Pattern recognition systems
Automatic speech recognition
Online Access:http://hdl.handle.net/1853/50255

Internet

http://hdl.handle.net/1853/50255

Similar Items