| Presentation | 2014-12-16 Many-to-one Voice Conversion using Multiple Non-negative Matrix Factorization Ryo AIHARA, Tetsuya TAKIGUCHI, Yasuo ARIKI, |
|---|---|
| PDF Download Page |  PDF download Page Link |
| Abstract(in Japanese) | (See Japanese page) |
| Abstract(in English) | Voice conversion (VC) is being widely researched in the field of speech processing because of increased interest in using such processing in applications such as personalized Text-To-Speech systems. Statistical approach using Gaussian Mixture Model (GMM) is widely researched in VC and eigen-voice GMM enables one-to-many and many-to-one VC from multiple training data sets. We present in this paper an exemplar-based VC method using Non-negative Matrix Factorization (NMF), which is different from conventional statistical VC. NMF-based VC has advantages of noise robustness and naturalness of converted voice compared to GMM-based VC. However, because NMF-based VC is based on parallel training data of source and target speaker, we cannot covert voice of arbitrary speakers in this framework. In this paper, we propose a many-to-one VC using Multiple Non-negative Matrix Factorization (Multi-NMF). By using Multi-NMF, arbitrary speaker's voice is converted to target speaker's voice without any training data of input speaker's. We assume that this method is flexible because we can adopt it to many-to-many VC or voice quality control. |
| Keyword(in Japanese) | (See Japanese page) |
| Keyword(in English) | Voice Conversion / Speech synthesis / Non-negative Matrix Factorization / Exemplar-based / Many-to-one |
| Paper # | SP2014-114 |
| Date of Issue |
| Conference Information | |
| Committee | SP |
|---|---|
| Conference Date | 2014/12/8(1days) |
| Place (in Japanese) | (See Japanese page) |
| Place (in English) | |
| Topics (in Japanese) | (See Japanese page) |
| Topics (in English) | |
| Chair | |
| Vice Chair | |
| Secretary | |
| Assistant | |
| Paper Information | |
| Registration To | Speech (SP) |
|---|---|
| Language | JPN |
| Title (in Japanese) | (See Japanese page) |
| Sub Title (in Japanese) | (See Japanese page) |
| Title (in English) | Many-to-one Voice Conversion using Multiple Non-negative Matrix Factorization |
| Sub Title (in English) | |
| Keyword(1) | Voice Conversion |
| Keyword(2) | Speech synthesis |
| Keyword(3) | Non-negative Matrix Factorization |
| Keyword(4) | Exemplar-based |
| Keyword(5) | Many-to-one |
| 1st Author's Name | Ryo AIHARA |
| 1st Author's Affiliation | Graduate School of System Informatics, Kobe University() |
| 2nd Author's Name | Tetsuya TAKIGUCHI |
| 2nd Author's Affiliation | Organization of Advanced Science and Technology, Kobe University |
| 3rd Author's Name | Yasuo ARIKI |
| 3rd Author's Affiliation | Organization of Advanced Science and Technology, Kobe University |
| Date | 2014-12-16 |
| Paper # | SP2014-114 |
| Volume (vol) | vol.114 |
| Number (no) | 365 |
| Page | pp.pp.- |
| #Pages | 6 |
| Date of Issue | |