Invention Grant
- Patent Title: Voice dialogue apparatus, voice dialogue method, and non-transitory computer readable media
-
Application No.: US16181524Application Date: 2018-11-06
-
Publication No.: US10825455B2Publication Date: 2020-11-03
- Inventor: Narimasa Watanabe
- Applicant: TOYOTA JIDOSHA KABUSHIKI KAISHA
- Applicant Address: JP Toyota-shi
- Assignee: TOYOTA JIDOSHA KABUSHIKI KAISHA
- Current Assignee: TOYOTA JIDOSHA KABUSHIKI KAISHA
- Current Assignee Address: JP Toyota-shi
- Agency: Oblon, McClelland, Maier & Neustadt, L.L.P.
- Priority: com.zzzhc.datahub.patent.etl.us.BibliographicData$PriorityClaim@ef9cfe9
- Main IPC: G10L15/22
- IPC: G10L15/22 ; G06F40/56 ; G06F40/268 ; G10L15/28

Abstract:
A voice dialogue apparatus analyzes an acquired user's voice, generates a parrot-like response sentence and outputs the generated parrot-like response sentence. The voice dialogue apparatus includes storage means for storing the user's past voice, average calculation means for calculating an average value of voice sentence lengths each indicating a length of the user's voice based on the user's past voice, candidate generation means for combining a dependency word, which establishes a dependency relation with a noun included in the acquired user's voice, with the noun to generate a plurality of response sentence candidates, and repetition generation means for selecting, in association with the average value of the voice sentence lengths, one response sentence candidate from among the plurality of response sentence candidates and using the selected response sentence candidate as it is or processing the selected response sentence candidate to generate the parrot-like response sentence.
Public/Granted literature
- US20190164550A1 VOICE DIALOGUE APPARATUS, VOICE DIALOGUE METHOD, AND NON-TRANSITORY COMPUTER READABLE MEDIA Public/Granted day:2019-05-30
Information query