Voice conversion using Gaussian Mixture Models

Author

D´souza, Kevin ; Talele, K.T.V.

Author_Institution

Dept. of Electron. & Telecommun. Eng., Sardar Patel Inst. of Technol., Mumbai, India

fYear

2015

Firstpage

1

Lastpage

5

Abstract

Voice conversion is an emergent problem in voice and speech processing with increasing commercial interest. The main aim of the voice conversion system is to modify the speaker specific characteristics with respect to target specific characteristics. The vocal tract transfer function,shape of the glottal pulse and the prosodic features uniquely characterize a particular speaker. This work present a method of extracting features of vocal tract level i.e. Line Spectrum Frequencies (LSFs) using Regressions Model and the source characteristics level feature i.e. LP Residual is mapped using Gaussian Mixture Models for improving the performance of voice conversion system. The Performance of Gaussian Based Models based voice conversion system is conducted using objective measures and subjective measures.

Keywords

Gaussian processes; feature extraction; regression analysis; speech processing; Gaussian based models; Gaussian mixture models; LSF; feature extraction; glottal pulse; line spectrum frequencies; prosodic features; regressions model; speech processing; vocal tract transfer function; voice conversion system; voice processing; Feature extraction; Gaussian mixture model; Speech; Speech processing; Training; Vectors; Gaussian Mixture Models (GMMs); LP Residual; Line spectrum frequencies; Regression Model;

fLanguage

English

Publisher

ieee

Conference_Titel

Communication, Information & Computing Technology (ICCICT), 2015 International Conference on

Conference_Location

Mumbai

Print_ISBN

978-1-4799-5521-3

Type

conf

DOI

10.1109/ICCICT.2015.7045743

Filename

7045743