Comparison of Cepstral Normalization Techniques in Whispered Speech Recognition

Comparison of Cepstral Normalization Techniques in Whispered Speech Recognition

This article presents an analysis of different cepstral normalization techniques in automatic recognition of whispered and bimodal speech (speech+whisper). In these experiments, conventional GMM-HMM speech recognizer was used as speaker-dependant automatic speech recognition system with special Wh...

Full description

Bibliographic Details
Main Authors: GROZDIC, D., JOVICIC, S., SUMARAC PAVLOVIC, D., GALIC, J., MARKOVIC, B.
Format: Article
Language:English
Published: Stefan cel Mare University of Suceava 2017-02-01
Series:Advances in Electrical and Computer Engineering
Subjects:
automatic speech recognition
cepstral analysis
hidden Markov models
speech analysis
whisper
Online Access:http://dx.doi.org/10.4316/AECE.2017.01004

Internet

http://dx.doi.org/10.4316/AECE.2017.01004

Similar Items