To select an expert unit suited to an utterance of a user.
The interaction processor includes: a voice input unit for inputting voice; a voice recognition unit for recognizing the input voice; a plurality of expert units, when performing a predetermined process, determining whether or not continuing the process or not based on the recognition result recognized by the voice recognition unit, and when not performing the process, presuming adaptability based on the recognition result recognized by the voice recognition unit; and a motion comprehension unit, when determining that the expert unit performing the process out of the plurality of expert units does not continue the process, selecting an expert unit for performing the process based on the adaptability presumed when not performing the process.
FUNAKOSHI KOTARO
KOMATANI KAZUNORI
OKUNO HIROSHI
SATO HAYATO
JP2003167875A | 2003-06-13 | |||
JP2000305872A | 2000-11-02 | |||
JP2003167875A | 2003-06-13 | |||
JP2000305872A | 2000-11-02 |
WO2009028647A1 | 2009-03-05 | |||
WO2007013521A1 | 2007-02-01 | |||
WO2009028647A1 | 2009-03-05 |
CSNG200600443009; 神田直之、外6名: '複数ドメイン音声対話システムにおける対話履歴を利用したドメイン選択の高精度化' 情報処理学会研究報告 Vol. SLP-60, No. 11, 20060204, pp. 55-60, 社団法人情報処理学会
Tadashi Takahashi
Yoshifumi Saeki
Suzuki Mitsuyoshi
Kazuya Nishi
Yasuhiko Murayama
Next Patent: SOUND SOURCE SEPARATION DEVICE AND SOUND SOURCE SEPARATION METHOD