Multimodal Voice Conversion Under Adverse Environment Using a Deep Convolutional Neural Network

Multimodal Voice Conversion Under Adverse Environment Using a Deep Convolutional Neural Network

This paper presents a voice conversion (VC) technique under noisy environments. Typically, VC methods use only audio information for conversion in a noiseless environment. However, existing conversion methods do not always achieve satisfactory results in an adverse acoustic environment. To solve thi...

Full description

Bibliographic Details
Main Authors: Jian Zhou, Yuting Hu, Hailun Lian, Huabin Wang, Liang Tao, Hon Keung Kwan
Format: Article
Language:English
Published: IEEE 2019-01-01
Series:IEEE Access
Subjects:
Audio and video feature fusion
convolutional neural network
deep learning
mel-frequency cepstral coefficients
multilayer feedforward neural networks
multimodal voice conversion
Online Access:https://ieeexplore.ieee.org/document/8913498/

Internet

https://ieeexplore.ieee.org/document/8913498/

Similar Items