Title:
VOICE DATA CREATION DEVICE
Document Type and Number:
WIPO Patent Application WO/2021/215352
Kind Code:
A1
Abstract:
This voice data creation device creates voice data including an additional word that is a word to be added to an object to be recognized in a voice recognition system, and is provided with: a sentence example extraction unit that extracts one or more text corpora including the additional word from a text corpus group including a plurality of text corpora each comprising a sentence example including a plurality of words; a sentence example selection unit that selects, as an optimal sentence example for the additional word, a text corpus having the highest standard indicating the ease of production as a sentence among the text corpora extracted by the sentence example extraction unit 11; and a voice creation unit that outputs, as voice data corresponding to the additional word, a synthesized voice of the optimal sentence example generated by a predetermined voice synthesis system.
Inventors:
KATOU TAKU (JP)
NAKASHIMA YUSUKE (JP)
ASAMI TAICHI (JP)
NAKASHIMA YUSUKE (JP)
ASAMI TAICHI (JP)
Application Number:
PCT/JP2021/015637
Publication Date:
October 28, 2021
Filing Date:
April 15, 2021
Export Citation:
Assignee:
NTT DOCOMO INC (JP)
International Classes:
G10L13/00; G10L15/06
Domestic Patent References:
| WO2017061027A1 | 2017-04-13 |
Foreign References:
| JP2003029776A | 2003-01-31 | |||
| JP2019120841A | 2019-07-22 | |||
| JP2014235345A | 2014-12-15 | |||
| JP2012037619A | 2012-02-23 | |||
| JP2011248001A | 2011-12-08 |
Attorney, Agent or Firm:
HASEGAWA Yoshiki et al. (JP)
Download PDF: