发明名称 |
Store speech, select vocabulary to recognize word |
摘要 |
For operating a speech recognition facility, the following steps are executed: a stream of concatenated speech items is received and stored; various such received speech items are recognized; and a representation of recognized speech items is associated for operative outputting. In particular, the following further steps are executed: a. from the stored speech items, a first non-recognized speech item for recognizing vizàviz an actual limited vocabulary is selected to get a recognition representation or a failure; b. through the failure a second non-recognized speech item is selected for recognition whilst maintaining the actual limited vocabulary and returning to a); c. and through the recognition a third non-recognized speech item is selected, amending the actual limited vocabulary and returning to a); d. until attaining a sufficient amount of recognitions for operative outputting.
|
申请公布号 |
US2002103641(A1) |
申请公布日期 |
2002.08.01 |
申请号 |
US20010022392 |
申请日期 |
2001.12.13 |
申请人 |
KUO JIE YUNG;BAKKER MARTIJN ALEXANDER;MARIA CLABBERS LEONARDUS JACOBUS HENDRIKUS THEODORUS |
发明人 |
KUO JIE YUNG;BAKKER MARTIJN ALEXANDER;MARIA CLABBERS LEONARDUS JACOBUS HENDRIKUS THEODORUS |
分类号 |
G10L15/22;G10L15/00;G10L15/18;G10L15/26;(IPC1-7):G10L15/00 |
主分类号 |
G10L15/22 |
代理机构 |
|
代理人 |
|
主权项 |
|
地址 |
|