Voice conversion using deep Bidirectional Long Short-Term Memory based Recurrent Neural Networks

This paper investigates the use of Deep Bidirectional Long Short-Term Memory based Recurrent Neural Networks (DBLSTM-RNNs) for voice conversion. Temporal correlations across speech frames are not directly modeled in frame-based methods using conventional Deep Neural Networks (DNNs), which results in...

Full description

Saved in:
Bibliographic Details
Published in2015 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) pp. 4869 - 4873
Main Authors Lifa Sun, Shiyin Kang, Kun Li, Meng, Helen
Format Conference Proceeding
LanguageEnglish
Published IEEE 01.04.2015
Subjects
Acoustics
bidirectional long short-term memory
Context
dynamic features
Logic gates
Recurrent neural networks
Speech
Training
voice conversion
Online AccessGet full text

Cover

More Information
Summary:This paper investigates the use of Deep Bidirectional Long Short-Term Memory based Recurrent Neural Networks (DBLSTM-RNNs) for voice conversion. Temporal correlations across speech frames are not directly modeled in frame-based methods using conventional Deep Neural Networks (DNNs), which results in a limited quality of the converted speech. To improve the naturalness and continuity of the speech output in voice conversion, we propose a sequence-based conversion method using DBLSTM-RNNs to model not only the frame-wised relationship between the source and the target voice, but also the long-range context-dependencies in the acoustic trajectory. Experiments show that DBLSTM-RNNs outperform DNNs where Mean Opinion Scores are 3.2 and 2.3 respectively. Also, DBLSTM-RNNs without dynamic features have better performance than DNNs with dynamic features.
ISSN:1520-6149
DOI:10.1109/ICASSP.2015.7178896