Title :
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
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;
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
DOI :
10.1109/CIMSA.2008.4595825
