US 12,067,971 B2
Information processing apparatus and information processing method
Ichitaro Kohara, Tokyo (JP); and Tatsuma Sakurai, Tokyo (JP)
Assigned to SONY CORPORATION, Tokyo (JP)
Appl. No. 17/250,271
Filed by SONY CORPORATION, Tokyo (JP)
PCT Filed Jun. 20, 2019, PCT No. PCT/JP2019/024475
§ 371(c)(1), (2) Date Dec. 23, 2020,
PCT Pub. No. WO2020/004213, PCT Pub. Date Jan. 2, 2020.
Claims priority of application No. 2018-124856 (JP), filed on Jun. 29, 2018.
Prior Publication US 2021/0264899 A1, Aug. 26, 2021
Int. Cl. G10L 15/06 (2013.01); G10L 15/01 (2013.01); G10L 15/22 (2006.01); G10L 15/32 (2013.01)
CPC G10L 15/06 (2013.01) [G10L 15/01 (2013.01); G10L 15/22 (2013.01); G10L 15/32 (2013.01)] 18 Claims
OG exemplary drawing
 
1. An information processing apparatus, comprising:
a first dictionary configured to register a first plurality of utterance expressions, wherein the first plurality of utterance expressions is frequently used by a user;
a second dictionary configured to register a second plurality of utterance expressions lesser than the first plurality of utterance expressions, wherein the first plurality of utterance expressions is different from the second plurality of utterance expressions; and
a processor configured to:
execute a voice recognition process based on the first dictionary and the second dictionary, wherein the execution of the voice recognition process based on the second dictionary is subsequent to the execution of the voice recognition process based on the first dictionary; and
update the first plurality of utterance expressions registered in the first dictionary based on usage performance of utterance of the user, wherein
the updating of the first plurality of utterance expressions includes deletion of a first utterance expression having a low usage performance of utterance from the first dictionary and transfer of the first utterance expression to the second dictionary.