| 发明名称 |
A method of and a device for speech recognition employing neural network and Markov model recognition techniques |
| 摘要 |
<p>A method and a device for recognition of isolated words in large vocabularies are described, wherein recognition is performed through two sequential steps (NE, MA) using neural networks and Markov models techniques, respectively, and the results of both techniques are adequately combined so as to improve recognition accuracy. The means (EL) performing the combination also provide an evaluation of recognition reliability. <IMAGE></p> |
| 申请公布号 |
EP0955628(A2) |
申请公布日期 |
1999.11.10 |
| 申请号 |
EP19990108530 |
申请日期 |
1999.05.04 |
| 申请人 |
CSELT |
发明人 |
FISSORE, LUCIANO;GEMELLO, ROBERTO;RAVERA, FRANCO |
| 分类号 |
G10L15/14;G10L15/28;G06F15/18;G06N3/00;G10L15/16;G10L15/26;(IPC1-7):G10L5/06;G10L9/00 |
主分类号 |
G10L15/14 |
| 代理机构 |
|
代理人 |
|
| 主权项 |
|
| 地址 |
|
