Prosodic Parameter Generation Using Small-Corpus Trained Neural Network for Mandarin Speech Synthesis
碩士 === 國立臺灣科技大學 === 電機工程系 === 91 === In this thesis, a neural network based method is studied to solve the problem of prosodic parameter generation for Mandarin speech synthesis. The focus is placed at the restricted situation that only a small corpus of speech data is available for model training....
Main Authors: | Yi-Tsen Tsao, 曹亦岑 |
---|---|
Other Authors: | Hung-Yan Gu |
Format: | Others |
Language: | zh-TW |
Published: |
2003
|
Online Access: | http://ndltd.ncl.edu.tw/handle/43580283176890738993 |
Similar Items
-
Prosodic Modeling for Mandarin Text-To-Speech
by: Wen-Li Shih, et al.
Published: (2006) -
= A study on prosodic information generator for mandarin text-to-speech
by: 黃紹華
Published: (1996) -
A study on the prosodic rules for Mandarin speech synthesis
by: 夏邦娥
Published: (1991) -
A Study on The Prosodic Model of Mandarin Speech
by: Khans Su, et al.
Published: (1994) -
A synthesis of prosodic information in mandarin text-to-speech system
by: HUANG,SHAO-HUA, et al.
Published: (1991)