Voice conversion using Artificial Neural Networks

Author

Desai, Srinivas ; Raghavendra, E. Veera ; Yegnanarayana, B. ; Black, Alan W. ; Prahallad, Kishore

Author_Institution

Int. Inst. of Inf. Technol., Hyderabad

fYear

2009

fDate

19-24 April 2009

Firstpage

3893

Lastpage

3896

Abstract

In this paper, we propose to use artificial neural networks (ANN) for voice conversion. We have exploited the mapping abilities of ANN to perform mapping of spectral features of a source speaker to that of a target speaker. A comparative study of voice conversion using ANN and the state-of-the-art Gaussian mixture model (GMM) is conducted. The results of voice conversion evaluated using subjective and objective measures confirm that ANNs perform better transformation than GMMs and the quality of the transformed speech is intelligible and has the characteristics of the target speaker.

Keywords

Gaussian processes; neural nets; spectral analysis; speech intelligibility; speech processing; ANN; Gaussian mixture model; artificial neural networks; source speaker; spectral feature mapping; speech intelligibility; target speaker; voice conversion; Artificial neural networks; Books; Data mining; Databases; Filters; Frequency estimation; Loudspeakers; Speech synthesis; Training data; Vectors; Artificial Neural Networks; Gaussian Mixture Model; Voice conversion;

fLanguage

English

Publisher

ieee

Conference_Titel

Acoustics, Speech and Signal Processing, 2009. ICASSP 2009. IEEE International Conference on

Conference_Location

Taipei

ISSN

1520-6149

Print_ISBN

978-1-4244-2353-8

Electronic_ISBN

1520-6149

Type

conf

DOI

10.1109/ICASSP.2009.4960478

Filename

4960478