US 12,475,904 B2
Audio signal conversion model learning apparatus, audio signal conversion apparatus, audio signal conversion model learning method and program
Takuhiro Kaneko, Musashino (JP); Hirokazu Kameoka, Musashino (JP); Ko Tanaka, Musashino (JP); and Nobukatsu Hojo, Musashino (JP)
Assigned to NTT, Inc., Tokyo (JP)
Appl. No. 18/032,529
Filed by NTT, Inc., Tokyo (JP)
PCT Filed Oct. 23, 2020, PCT No. PCT/JP2020/039975
§ 371(c)(1), (2) Date Apr. 18, 2023,
PCT Pub. No. WO2022/085197, PCT Pub. Date Apr. 28, 2022.
Prior Publication US 2023/0386489 A1, Nov. 30, 2023
Int. Cl. G10L 21/007 (2013.01); G06N 20/00 (2019.01); G10L 25/30 (2013.01)
CPC G10L 21/007 (2013.01) [G06N 20/00 (2019.01); G10L 25/30 (2013.01)] 6 Claims
OG exemplary drawing
 
1. A voice signal conversion model learning device comprising:
a processor; and
a storage medium having computer program instructions stored thereon, wherein the computer program instruction, when executed by the processor, perform processing of:
acquiring learning input data which is an input voice signal; and
executing a conversion learning model which is a model of machine learning including learning stage conversion processing of converting the learning input data into learning stage conversion destination data which is a voice signal of a conversion destination, wherein
the learning stage conversion processing includes local feature quantity acquisition processing of acquiring a feature quantity for each learning input-side subset which is a subset of processing target input data having the processing target input data as a population, based on the processing target input data which is data to be processed,
the conversion learning model further includes adjustment parameter value acquisition processing of acquiring an adjustment parameter value, which is a value of a parameter for adjusting a statistical value of a distribution of the feature quantity, based on the learning input data, and
the learning stage conversion processing converts the learning input data into the learning stage conversion destination data using a result of a predetermined calculation based on the adjustment parameter value, where the predetermined calculation converts the feature quantity according to the adjustment parameter value using affine conversion.