下載電子全文宣告This thesis is authorized to indicate in-campus access only
You can not download at the moment.
Your IP address is 220.127.116.11
The defense date of the thesis is 2008-01-04
The current date is 2019-03-22
This thesis will be accessible at off-campus not accessible
URN etd-0104108-100045 Statistics This thesis had been viewed 2298 times. Download 18 times. Author Yu-liang Hsueh Author's Email Address No Public. Department Computer Science and Enginerring Year 2007 Semester 1 Degree Master Type of Document Master's Thesis Language zh-TW.Big5 Chinese Page Count 41 Title The Research and Application of Chinese Speech Synthesis Based on Hidden Markov Model Keyword Text-to-Speech synthesis system speech reconstruction Hidden Markov model Hidden Markov model speech reconstruction Text-to-Speech synthesis system Abstract This thesis describes a novel approach to text-to-speech synthesis (TTS)
based on hidden Markov model (HMM). There have been several attempts
proposed to utilize HMM for constructing TTS systems.
However, most of such systems are based on waveform concatenation techniques.
In the proposed approach, we constructs this TTS system based on the speech parameter to complete the goal of the map navigation.
We get the speech parameter sequences that generated from HMM directly based on maximum likelihood criterion.
By considering relationship between static and dynamic parameters, smooth spectral sequences are generated according to the statistics of static and dynamic parameters
modeled by HMMs.
As a result, natural sounding speech can be synthesized throught speech reconstruction technique.
Advisor Committee Tai-wen Yue - advisor
Chen-Chiung Hsieh - co-chair
none - co-chair
Files Date of Defense 2008-01-02 Date of Submission 2008-01-04