| 发明名称 |
Determining word sequence constraints for low cognitive speech recognition |
| 摘要 |
A method for recognizing speech including a sequence of words determines a shape of a gesture and a location of the gesture with respect to a display device showing a set of interpretations of the speech. The method determines a type of the word sequence constraint based on the shape of the gesture and determines a value of the word sequence constraint based on the location of the gesture. Next, the speech is recognized using the word sequence constraint. |
| 申请公布号 |
US9196246(B2) |
申请公布日期 |
2015.11.24 |
| 申请号 |
US201414337472 |
申请日期 |
2014.07.22 |
| 申请人 |
Mitsubishi Electric Research Laboratories, Inc. |
发明人 |
Harsham Bret;Hershey John |
| 分类号 |
G10L15/18;G10L15/183;G10L15/22;G06F3/16;G06F3/0488;G10L15/08 |
主分类号 |
G10L15/18 |
| 代理机构 |
|
代理人 |
Brinkman Dirk;Vinokur Gene |
| 主权项 |
1. A method for recognizing speech including a sequence of words, comprising:
displaying a set of interpretations of the speech on a display device, such that elements in the set of interpretations are displayed at corresponding locations on the display device; determining a shape of a gesture and a location of the gesture with respect to the display device showing the set of interpretations of the speech; determining a type of a word sequence constraint based on the shape of the gesture and a mapping between a set of shapes of gestures and a set of types of word sequence constraint; determining a value of the word sequence constraint based on the location of the gesture relative to the locations of the elements in the set of interpretations on the display device; and recognizing the speech using the type and the value of the word sequence constraint, wherein steps of the method are performed by a processor. |
| 地址 |
Cambridge MA US |
