发明名称 |
Determining prosodic markings for text-to-speech systems - using neural network to determine prosodic markings based on linguistic categories such as number, verb, verb particle, pronoun, preposition etc. |
摘要 |
The method involves using a neural network (1) to determine prosodic markings e.g. phrase boundaries based on linguistic categories. The markings are evaluated. The linguistic categories of at least three words of a text to be synthesised are applied to the input of the neural network. The characteristics of each prosodic marking are detected by neuronal auto-associators (7) which are trained respectively for a certain prosodic marking. The output information from each auto-associator is evaluated in a neural classifier.
|
申请公布号 |
DE10018134(A1) |
申请公布日期 |
2001.10.18 |
申请号 |
DE2000118134 |
申请日期 |
2000.04.12 |
申请人 |
SIEMENS AG |
发明人 |
MUELLER, ACHIM DIPL.-ING.;HOLZAPFEL, MARTIN DIPL.-ING. |
分类号 |
G10L13/08;(IPC1-7):G10L13/08 |
主分类号 |
G10L13/08 |
代理机构 |
|
代理人 |
|
主权项 |
|
地址 |
|