发明名称 |
METHOD FOR CREATING A SPEECH DATABASE FOR A TARGET VOCABULARY IN ORDER TO TRAIN A SPEECH RECOGNITION SYSTEM |
摘要 |
According to the invention, the words of the target vocabulary are composed of segments, which consist of one or more phonemes, whereby the segments are derived from a training text that is independent from the target vocabulary. The training text can be an arbitrary generic text.
|
申请公布号 |
WO0186634(A1) |
申请公布日期 |
2001.11.15 |
申请号 |
WO2001DE01546 |
申请日期 |
2001.04.24 |
申请人 |
SIEMENS AKTIENGESELLSCHAFT;BUDDE, MARK;SCHNEIDER, TOBIAS |
发明人 |
BUDDE, MARK;SCHNEIDER, TOBIAS |
分类号 |
G10L15/06;(IPC1-7):G10L15/06 |
主分类号 |
G10L15/06 |
代理机构 |
|
代理人 |
|
主权项 |
|
地址 |
|