发明名称 |
SPEECH TRANSLATION SYSTEM, CONTROL APPARATUS AND CONTROL METHOD |
摘要 |
In speech translation, it has been impossible to select appropriate processing results and to select appropriate apparatuses. Provided is a control apparatus configured to: receive a speech recognition processing result, which contains a speech recognition result and a speech recognition score, from each of two or more speech recognition apparatuses; select the most probable one of the speech recognition results by using the speech recognition scores; transmit the thus selected speech recognition result to two or more translation apparatuses; receive a translation processing result, which contains a translation result and a translation score for the speech recognition result, from each of the two or more translation apparatuses; select the most probable one of the translation results by using the translation scores; transmit the thus selected translation result to two or more speech synthesis apparatuses; receive a speech synthesis processing result, which contains a speech synthesis result and a speech synthesis score, from each of the two or more speech synthesis apparatuses; select one of the speech synthesis results by using the speech synthesis scores; and transmit the thus selected speech synthesis result to a second terminal apparatus. Use of the control apparatus makes it possible to select appropriate processing results and to select appropriate apparatuses. |
申请公布号 |
WO2011048826(A1) |
申请公布日期 |
2011.04.28 |
申请号 |
WO2010JP53420 |
申请日期 |
2010.03.03 |
申请人 |
NATIONAL INSTITUTE OF INFORMATION AND COMMUNICATIONS TECHNOLOGY;NAKAMURA, SATOSHI;SUMITA, EIICHIRO;ASHIKARI, YUTAKA;KIMURA, NORIYUKI;HORI, CHIORI |
发明人 |
NAKAMURA, SATOSHI;SUMITA, EIICHIRO;ASHIKARI, YUTAKA;KIMURA, NORIYUKI;HORI, CHIORI |
分类号 |
G10L15/10;G06F3/16;G06F17/28;G10L13/00;G10L15/00 |
主分类号 |
G10L15/10 |
代理机构 |
|
代理人 |
|
主权项 |
|
地址 |
|