|
JAIST Repository >
School of Information Science >
Conference Papers >
Conference Papers >
Please use this identifier to cite or link to this item:
http://hdl.handle.net/10119/16656
|
| Title: | Non-parallel Voice Conversion with Controllable Speaker Individuality using Variational Autoencoder |
| Authors: | Ho, Tuan Vu
Akagi, Masato |
| Keywords: | Voice conversion
speaker embedding
voice characteristics control
variational autoencoder
non-parallel data |
| Issue Date: | 2019-11-19 |
| Publisher: | Institute of Electrical and Electronics Engineers (IEEE) |
| Magazine name: | 2019 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC) |
| Start page: | 106 |
| End page: | 111 |
| DOI: | 10.1109/APSIPAASC47483.2019.9023264 |
| Abstract: | We propose a flexible non-parallel voice conversion (VC) system that is capable of both performing speaker adaptation and controlling speaker individuality. The proposed VC framework aims to tackle the inability to arbitrarily modify voice characteristics in the converted waveform of conventional VC model. To achieve this goal, we use the speaker embedding realized by a Variational Autoencoder (VAE) instead of one-hot encoded vectors to represent and modify the target voice's characteristics. Neither parallel training data, linguistic label nor time alignment procedure is required to train our system. After training on a multi-speaker speech database, the proposed VC system can adapt an arbitrary source speaker to any target speaker using only one sample from a target speaker. The speaker individuality of converted speech can be controlled by modifying the speaker embedding vectors; resulting in a fictitious speaker individuality. The experimental results showed that our proposed system is similar to conventional non-parallel VAE-based VC and better than the parallel Gaussian Mixture Model (GMM) in both perceived speech naturalness and speaker similarity; even when our system only uses one sample from target speaker. Moreover, our proposed system can convert a source voice to a fictitious target voice with well perceived speech naturalness of 3.1 MOS. |
| Rights: | This is the author's version of the work. Copyright (C) 2019 IEEE. 2019 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC), 2019, pp.106-111. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works. |
| URI: | http://hdl.handle.net/10119/16656 |
| Material Type: | author |
| Appears in Collections: | b11-1. 会議発表論文・発表資料 (Conference Papers)
|
Files in This Item:
| File |
Description |
Size | Format |
|---|
| APSIPA_2019_106.pdf | | 1162Kb | Adobe PDF | View/Open |
|
All items in DSpace are protected by copyright, with all rights reserved.
|
