Context-adaptive Phoneme Segmentation for a TTS Database
![]() |
이기승
(건국대학교 정보통신대학 전자공학과)
김정수 (삼성전자㈜ 종합기술원 휴먼-컴퓨터 인터엑티브 연구실) |
1 |
A bootstaping training technique for obtaining demisyllable reference patterns
/
ScienceOn |
2 |
Nonlinear predictive vector quantization with recurrent neural nets
/
|
3 |
Reducing audible spectral discontinuities
/
ScienceOn |
4 |
Diphone concatenation using a harmonic plus noise model of speech
/
|
5 |
Concatenative speech synthesis using units selected from a large speech database
/
|
6 |
Automatic segmentation of speech
/
ScienceOn |
7 |
Speech synthesis from text
/
ScienceOn |
8 |
The AT\&T Next-Gen TTS system
/
|
9 |
Unit selection in a concatenative speech synthesis system using a large speech database
/
|
10 |
Explicit segmentation of speech using gaussian models
/
|
11 |
An introduction to computing with neural nets
/
|
12 |
Neural network boundary refining for automatic speech segmentation
/
|
13 |
Spectral stability based event localizing temporal decomposition
/
|
14 |
Automatic speech synthesis unit generation with MLP based postprocessor against auto-segemented phoneme errors
/
|
![]() |