Title:
LANGUAGE PROCESSING METHOD, LANGUAGE PROCESSING DEVICE, AND PROGRAM
Document Type and Number:
WIPO Patent Application WO/2023/228313
Kind Code:
A1
Abstract:
In a language processing method according to one aspect of the present disclosure, a computer executes an error sentence creation procedure in which: an error dictionary in which a token sequence is associated with a plurality of first error token sequences, which respectively represent token sequences that are vocally close to the token sequence but portions of which are different from the token sequence, is used to replace a portion of an original sentence token sequence, which represents a token sequence in original text included in given text data, with the first error token sequences; and a second error token sequence, which represents a token sequence that is vocally close to the original text token sequence but a portion of which is different from the original text token sequence, is created as data for language model construction.
Inventors:
OSUGI YASUHITO (JP)
SAITO ITSUMI (JP)
NISHIDA KYOSUKE (JP)
YOSHIDA SEN (JP)
SAITO ITSUMI (JP)
NISHIDA KYOSUKE (JP)
YOSHIDA SEN (JP)
Application Number:
PCT/JP2022/021380
Publication Date:
November 30, 2023
Filing Date:
May 25, 2022
Export Citation:
Assignee:
NIPPON TELEGRAPH & TELEPHONE (JP)
International Classes:
G10L15/16; G10L15/18
Domestic Patent References:
| WO2022085296A1 | 2022-04-28 | |||
| WO2021100181A1 | 2021-05-27 |
Foreign References:
| JP2016110082A | 2016-06-20 | |||
| US10388272B1 | 2019-08-20 |
Other References:
TSUTSUI, RYOHEI; SUZUKI, MOTOYUKI; ITO AKINORI; MAKINO SHOZO: "Speech recognition of English spoken by Japanese native speekers using N-gram trained from generated text", IEICE TECHNICAL REPORT, NLC, IEICE, JP, vol. 107, no. 405, NLC2007-54, 1 December 2007 (2007-12-01), JP, pages 125 - 130, XP009550668
Attorney, Agent or Firm:
ITOH, Tadashige et al. (JP)
Download PDF: