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

• Published in: 2015 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
• Language: English
• Published: IEEE 01.04.2015
• Subjects: Acoustics; bidirectional long short-term memory; Context; dynamic features; Logic gates; Recurrent neural networks; Speech; Training; voice conversion

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...