Login| Sign Up| Help| Contact|

Patent Searching and Data


Title:
音声処理装置、音声処理方法および音声処理プログラム
Document Type and Number:
Japanese Patent JP7085500
Kind Code:
B2
Abstract:
To provide a voice processor, a voice processing method and a voice processing program, which can determine whether a response is to be made or not by considering property of a break of user's utterance.SOLUTION: A server device 20 comprises: an utterance section detection section 231 for acquiring voice data and detecting an utterance section being a section including user's utterance from the voice data; an utterance situation analysis section 233 for generating utterance situation information indicating an utterance situation of a user on the basis of the voice data in the utterance section; and a response determination section 234 for determining whether a response from a voice output device is to be made or not for utterance included in the utterance section on the basis of the utterance situation information.SELECTED DRAWING: Figure 2

Inventors:
Kenji Ishikawa
Application Number:
JP2019023125A
Publication Date:
June 16, 2022
Filing Date:
February 13, 2019
Export Citation:
Click for automatic bibliography generation   Help
Assignee:
Yahoo Japan Corporation
International Classes:
G10L13/00; G10L13/02; G10L15/04; G10L15/22
Domestic Patent References:
JP6400871B1
JP2017121680A
JP2018040897A
JP2018109663A
JP2006178063A
JP2004513445A
JP200826463A
JP2017106988A
JP2017211596A
Other References:
宮崎昇,"話しことばを扱う音声対話システム",第37回言語・音声理解と対話処理研究会資料,2003年03月07日,pp.21-27
木下裕介 他,"言語に依存した韻律モデルによる発話継続/終了推定",日本音響学会2011年秋季研究発表会講演論文集CD-ROM,2011年09月13日,pp.85-88
Attorney, Agent or Firm:
Intellectual Property Office