|
naistar (NAIST Academic Repository) >
学術リポジトリ naistar / NAIST Academic Repository naistar >
国際会議発表論文 / Proceedings >
情報科学研究科 / Graduate School of Information Science >
Please use this identifier to cite or link to this item:
http://hdl.handle.net/10061/8071
|
| Title: | On the State Definition for a Trainable Excitation Model in HMM-based Speech Synthesis |
| Authors: | Ranniery Maia
Tomoki Toda
Keiichi Tokuda
Shinsuke Sakai
Satoshi Nakamura |
| Keywords: | Speech processing
speech synthesis
hidden Markov models
digital filters |
| Issue Date: | Mar-2008 |
| Publisher: | IEEE |
| Start page: | 3965 |
| End page: | 3968 |
| Abstract: | One of the issues of speech synthesizers based on hidden Markov models concerns the vocoded quality of the synthesized speech. From the principle of analysis-by-synthesis speech coders a trainable excitation model has been proposed to improve naturalness, where the method consists in the design of a set of state-dependent filters in a way to minimize the distortion between residual and synthetic excitation. Although this approach seems successful, state definition still represents an open issue. This paper describes a method for state definition wherein bottom-up clustering is performed on full context decision trees, using the likelihood of the residual database as merging criterion. Experiments have shown that improvement on residual modeling through better filter design can be achieved. |
| Description: | ICASSP2008: IEEE International Conference on Acoustics, Speech, and Signal Processing, March 30 - April 4, 2008, Las Vegas, Nevada, USA. |
| URI: | http://hdl.handle.net/10061/8071 |
| ISBN: | 9781424414833 |
| ISSN: | 1520-6149 |
| Rights: | Copyright 2008 IEEE |
| Text Version: | Publisher |
| Publisher DOI: | 10.1109/ICASSP.2008.4518522 |
| Appears in Collections: | 情報科学研究科 / Graduate School of Information Science
|
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.
|
