Speaker-adaptive-trainable Boltzmann machine and its application to non-parallel voice conversion

Speaker-adaptive-trainable Boltzmann machine and its application to non-parallel voice conversion

Abstract In this paper, we present a voice conversion (VC) method that does not use any parallel data while training the model. Voice conversion is a technique where only speaker-specific information in the source speech is converted while keeping the phonological information unchanged. Most of the...

Full description

Bibliographic Details
Main Authors: Toru Nakashika, Yasuhiro Minami
Format: Article
Language:English
Published: SpringerOpen 2017-06-01
Series:EURASIP Journal on Audio, Speech, and Music Processing
Subjects:
Voice conversion
Boltzmann machine
Unsupervised training
Energy-based model
Speaker adaptation
Non-parallel training
Online Access:http://link.springer.com/article/10.1186/s13636-017-0112-6

Internet

http://link.springer.com/article/10.1186/s13636-017-0112-6

Similar Items