发明名称 |
METHOD AND DEVICE FOR PREDICTING WORD ERROR RATE FROM TEXT |
摘要 |
PROBLEM TO BE SOLVED: To provide a method and a device for predicting a word error rate from a text. SOLUTION: A method of modeling a speech recognition system includes generation of a predicted speech unit sequence by decoding a speech signal generated from a learning text. The learning text includes an actual speech unit sequence used together with the predicted speech unit sequence to form a confusion model. In another embodiment, a text is decoded by using a confusion model and a speech recognition system discriminates the error rate predicted when a speech is decoded on the basis of the text. COPYRIGHT: (C)2004,JPO&NCIPI
|
申请公布号 |
JP2004246368(A) |
申请公布日期 |
2004.09.02 |
申请号 |
JP20040037147 |
申请日期 |
2004.02.13 |
申请人 |
MICROSOFT CORP |
发明人 |
MAHAJAN MILIND;DENG YONGGANG;ACERO ALEJANDRO;GUNAWARDANA ASELA J R;CHELBA CIPRIAN |
分类号 |
G10L15/28;G10L13/08;G10L15/00;G10L15/06;G10L15/14;G10L15/18;(IPC1-7):G10L15/28 |
主分类号 |
G10L15/28 |
代理机构 |
|
代理人 |
|
主权项 |
|
地址 |
|