Emotional voice conversion using neural networks with arbitrary scales F0 based on wavelet transform

Emotional voice conversion using neural networks with arbitrary scales F0 based on wavelet transform

Abstract An artificial neural network is an important model for training features of voice conversion (VC) tasks. Typically, neural networks (NNs) are very effective in processing nonlinear features, such as Mel Cepstral Coefficients (MCC), which represent the spectrum features. However, a simple re...

Full description

Bibliographic Details
Main Authors: Zhaojie Luo, Jinhui Chen, Tetsuya Takiguchi, Yasuo Ariki
Format: Article
Language:English
Published: SpringerOpen 2017-08-01
Series:EURASIP Journal on Audio, Speech, and Music Processing
Subjects:
F0 features
Continuous wavelet transform
Neural networks
Deep belief networks
Emotional voice conversion
Online Access:http://link.springer.com/article/10.1186/s13636-017-0116-2

Internet

http://link.springer.com/article/10.1186/s13636-017-0116-2

Similar Items