US 11,924,368 B2
Data correction apparatus, data correction method, and program
Sachiko Kurihara, Tokyo (JP); and Noboru Harada, Tokyo (JP)
Assigned to NIPPON TELEGRAPH AND TELEPHONE CORPORATION, Tokyo (JP)
Appl. No. 17/608,823
Filed by NIPPON TELEGRAPH AND TELEPHONE CORPORATION, Tokyo (JP)
PCT Filed May 7, 2019, PCT No. PCT/JP2019/018261
§ 371(c)(1), (2) Date Nov. 4, 2021,
PCT Pub. No. WO2020/225851, PCT Pub. Date Nov. 12, 2020.
Prior Publication US 2022/0279066 A1, Sep. 1, 2022
Int. Cl. H04M 1/24 (2006.01); G10L 21/0232 (2013.01); G10L 25/60 (2013.01); G10L 25/84 (2013.01); H04M 3/08 (2006.01); H04M 3/22 (2006.01); H04M 3/26 (2006.01); G10L 21/0208 (2013.01)
CPC H04M 3/2236 (2013.01) [G10L 21/0232 (2013.01); G10L 25/60 (2013.01); G10L 25/84 (2013.01); H04M 3/26 (2013.01); G10L 2021/02082 (2013.01)] 7 Claims
OG exemplary drawing
 
1. A data correction apparatus configured to compare, in a call performed between a plurality of communication terminals, an evaluation target sound in which a voice output from a first communication terminal of the plurality of communication terminals is recorded and a reference sound in which a voice spoken by a call partner using a second communication terminal of the plurality of communication terminals is recorded to correct test data used in evaluation of acoustic quality of the call, the apparatus comprising:
processing circuitry configured to: execute
a correction target determination processing configured to determine, as a correction target section, a voiced section that does not include the voice of the call partner detected from an acoustic signal representing the reference sound; and
a correction execution processing configured to update the correction target section of the acoustic signal representing the reference sound with a non-voice signal predetermined.