講演抄録/キーワード |
講演名 |
2008-03-20 15:15
[ポスター講演]A Context Clustering Technique for Improvement of Tone Intelligibility of Average-voice-based Thai Speech Synthesis ○Suphattharachai Chomphan・Takao Kobayashi(Tokyo Inst. of Tech.) SP2007-194 |
抄録 |
(和) |
This paper describes a novel approach to the context clustering process in a speaker independent HMM-based Thai speech synthesis for improvement of the tone intelligibility of the average voice and also the speaker adapted voice. In our previous work, phrase intonation features extracted from a generative model were proposed to improve the tone intelligibility. In the present work, we propose a number of tonal features including tone-geometrical features and phrase intonation features to be exploited in the context clustering process of HMM training stage. In experiments, subjective evaluations of both average voice and adapted voice in terms of the intelligibility of tone are conducted. Effects on decision trees of the extracted features are also evaluated. By considering gender in training speech, two core experiments were conducted. The first experiment shows that the proposed tonal features can improve the tone intelligibility for female speech model above that of male speech model, while the second experiment shows that the proposed tonal features give the better improvement of the tone intelligibility for gender dependent model than for gender independent model. Both experimental results confirm that the tone correctness of the synthesized speech is significantly improved when using most of the extracted features. |
(英) |
This paper describes a novel approach to the context clustering process in a speaker independent HMM-based Thai speech synthesis for improvement of the tone intelligibility of the average voice and also the speaker adapted voice. In our previous work, phrase intonation features extracted from a generative model were proposed to improve the tone intelligibility. In the present work, we propose a number of tonal features including tone-geometrical features and phrase intonation features to be exploited in the context clustering process of HMM training stage. In experiments, subjective evaluations of both average voice and adapted voice in terms of the intelligibility of tone are conducted. Effects on decision trees of the extracted features are also evaluated. By considering gender in training speech, two core experiments were conducted. The first experiment shows that the proposed tonal features can improve the tone intelligibility for female speech model above that of male speech model, while the second experiment shows that the proposed tonal features give the better improvement of the tone intelligibility for gender dependent model than for gender independent model. Both experimental results confirm that the tone correctness of the synthesized speech is significantly improved when using most of the extracted features. |
キーワード |
(和) |
tone intelligibility / generative model / average voice / hidden Markov models / speech synthesis / / / |
(英) |
tone intelligibility / generative model / average voice / hidden Markov models / speech synthesis / / / |
文献情報 |
信学技報, vol. 107, no. 551, SP2007-194, pp. 45-50, 2008年3月. |
資料番号 |
SP2007-194 |
発行日 |
2008-03-13 (SP) |
ISSN |
Print edition: ISSN 0913-5685 Online edition: ISSN 2432-6380 |
著作権に ついて |
技術研究報告に掲載された論文の著作権は電子情報通信学会に帰属します.(許諾番号:10GA0019/12GB0052/13GB0056/17GB0034/18GB0034) |
PDFダウンロード |
SP2007-194 |
|