A DCT based nonlinear predictive coding for feature extraction in speech recognition systems

Author

Azar, Mahmood Yousefi ; Razzazi, Farbod

Author_Institution

Sci. & Res. Campus, Islamic Azad Univ., Tehran

fYear

2008

fDate

14-16 July 2008

Firstpage

19

Lastpage

22

Abstract

Speech representation strategies play a key role in automatic speech recognition systems. In this study, a nonlinear procedure has been proposed to overcome the complexities of speech sequence representations. The proposed method may be considered as an extension of nonlinear predictive coding representation procedure in cosine transform domain. The best results belong to classification of nonlinear behaved stop phonemes (i.e. /b/, /d/, /g/) in TIMIT database which show good performance while reducing the computational complexity in comparison to standard NPC.

Keywords

feature extraction; speech recognition; transform coding; DCT; NPC; TIMIT database; automatic speech recognition systems; discrete cosine transform; feature extraction; nonlinear predictive coding; speech representation strategies; Automatic speech recognition; Computational complexity; Discrete cosine transforms; Feature extraction; Humans; Linear predictive coding; Neural networks; Predictive coding; Speech coding; Speech recognition; automatic feature extraction; automatic speech recognition; cosine transform; neural network;

fLanguage

English

Publisher

ieee

Conference_Titel

Computational Intelligence for Measurement Systems and Applications, 2008. CIMSA 2008. 2008 IEEE International Conference on

Conference_Location

Istanbul

Print_ISBN

978-1-4244-2305-7

Electronic_ISBN

978-1-4244-2306-4

Type

conf

DOI

10.1109/CIMSA.2008.4595825

Filename

4595825