US 12,266,339 B2
Correction method of synthesized speech set for hearing aid
Hiroshi Ono, Tokyo (JP)
Assigned to SPACE LIVE. Inc., Tokyo (JP)
Appl. No. 17/760,256
Filed by SPACE LIVE. Inc., Tokyo (JP)
PCT Filed Feb. 7, 2020, PCT No. PCT/JP2020/004766
§ 371(c)(1), (2) Date Aug. 5, 2022,
PCT Pub. No. WO2021/157052, PCT Pub. Date Aug. 12, 2021.
Prior Publication US 2023/0038118 A1, Feb. 9, 2023
Int. Cl. G10L 13/02 (2013.01); G10L 13/08 (2013.01); H04R 25/00 (2006.01)
CPC G10L 13/02 (2013.01) [G10L 13/08 (2013.01); H04R 25/505 (2013.01)] 13 Claims
OG exemplary drawing
 
1. A method for correcting a synthesized speech set for hearing aid in which each of a plurality of phoneme labels is correlated with synthesized speech data for hearing aid for outputting synthesized speech for hearing aid, on the basis of a result of testing using a synthesized speech set for testing in which each of the plurality of phoneme labels is correlated with synthesized speech data for testing for outputting synthesized speech for testing, the method comprising the steps of:
outputting first synthesized speech for testing on the basis of first synthesized speech data for testing correlated with a first phoneme label in the synthesized speech set for testing;
accepting a first answer selected by a user as a phoneme label perceived to represent the first synthesized speech for testing that is output;
outputting second synthesized speech for testing on the basis of second synthesized speech data for testing correlated with a second phoneme label in the synthesized speech set for testing;
accepting a second answer selected by the user as a phoneme label perceived to represent the second synthesized speech for testing that is output; and
correlating first synthesized speech data for hearing aid correlated with the first phoneme label, with the second phoneme label, instead of second synthesized speech data for hearing aid correlated with the second phoneme label in the synthesized speech set for hearing aid, in a case in which the first answer matches the second phoneme label and also the second answer does not match the second phoneme label.