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

Lifa Sun; Shiyin Kang; Kun Li; Helen M. Meng

ICASSP 2015accepted0 citations

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

Lifa Sun, Shiyin Kang, Kun Li, Helen M. Meng

Abstract

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.

BibTeX

@inproceedings{icassp2015_voiceconversionu,
  title = {Voice conversion using deep Bidirectional Long Short-Term Memory based Recurrent Neural Networks},
  author = {Lifa Sun and Shiyin Kang and Kun Li and Helen M. Meng},
  booktitle = {ICASSP 2015},
  year = {2015}
}