|
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/10119/18114
|
| Title: | Quality improvement of HMM-based synthesized speech based on decomposition of naturalness and intelligibility using non-negative matrix factorization |
| Authors: | Dinh, Anh-Tuan
Akagi, Masato |
| Keywords: | Hidden Markov model (HMM)
Non-negative
matrix factorization (NMF)
Singular value decomposition (SVD) |
| Issue Date: | 2016-10 |
| Publisher: | Institute of Electrical and Electronics Engineers (IEEE) |
| Magazine name: | 2016 Conference of The Oriental Chapter of International Committee for Coordination and Standardization of Speech Databases and Assessment Techniques (O-COCOSDA) |
| Start page: | 62 |
| End page: | 67 |
| DOI: | 10.1109/ICSDA.2016.7918985 |
| Abstract: | Hidden Markov model based synthesized speech is intelligible but not natural because of over-smoothing of the speech spectra. The purpose of this study is improving naturalness without violating acceptable intelligibility by decomposing the naturalness and intelligibility of synthesized speech using a novel asymmetric bilinear model involving non-negative matrix factorization. Subjective evaluations carried out on English data confirm that the proposed method outperforms original asymmetric bilinear model involving singular value decomposition in factorizing naturalness and intelligibility. Moreover, the performance of the proposed method is comparable with other methods. |
| Rights: | This is the author's version of the work. Copyright (C) 2016 IEEE. 2016 Conference of The Oriental Chapter of International Committee for Coordination and Standardization of Speech Databases and Assessment Techniques (O-COCOSDA), 2016, pp.62-67.DOI:10.1109/ICSDA.2016.7918985. 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/10119/18114 |
| 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 |
|---|
| Dinh_ococosda-3.pdf | | 461Kb | Adobe PDF | View/Open |
|
All items in DSpace are protected by copyright, with all rights reserved.
|
