Voice conversion with parallel/non-parallel data and synthetic speech detection
The objective of voice conversion techniques is to convert a source speaker's voice so that it sounds like that of a target speaker. Voice conversion belongs to a popular area of personalized speech generation. On one hand, it can be applied to solve problems, e.g. emotion conversion, improving...
Saved in:
Main Author: | Tian, Xiaohai |
---|---|
Other Authors: | Chng Eng Siong |
Format: | Theses and Dissertations |
Language: | English |
Published: |
2019
|
Subjects: | |
Online Access: | https://hdl.handle.net/10356/89880 http://hdl.handle.net/10220/47729 |
Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
Institution: | Nanyang Technological University |
Language: | English |
Similar Items
-
Mixture of factor analyzers using priors from non-parallel speech for voice conversion
by: Wu, Zhizheng, et al.
Published: (2013) -
Transfer Learning From Speech Synthesis to Voice Conversion With Non-Parallel Training Data
by: Li, Haizhou
Published: (2021) -
Detecting synthetic speech using long term magnitude and phase information
by: Tian, Xiaohai, et al.
Published: (2018) -
Correlation-based frequency warping for voice conversion
by: Tian, Xiaohai, et al.
Published: (2018) -
An exemplar-based approach to frequency warping for voice conversion
by: Tian, Xiaohai, et al.
Published: (2018)