发明名称 |
Method of adapting a neural network of an automatic speech recognition device |
摘要 |
A method of adapting a neural network of an automatic speech recognition device, includes the steps of: providing a neural network including an input stage, an intermediate stage and an output stage, the output stage outputting phoneme probabilities; providing a linear stage in the neural network; and training the linear stage by means of an adaptation set; wherein the step of providing the linear stage includes the step of providing the linear stage after the intermediate stage.
|
申请公布号 |
US2009216528(A1) |
申请公布日期 |
2009.08.27 |
申请号 |
US20050921303 |
申请日期 |
2005.06.01 |
申请人 |
GEMELLO ROBERTO;MANA FRANCO |
发明人 |
GEMELLO ROBERTO;MANA FRANCO |
分类号 |
G10L15/16;G10L15/06;G10L15/065 |
主分类号 |
G10L15/16 |
代理机构 |
|
代理人 |
|
主权项 |
|
地址 |
|