Audio signal conversion model learning apparatus, audio signal conversion apparatus, audio signal conversion model learning method and program
The present invention is a voice signal conversion model learning device provided with: a learning data acquisition unit for acquiring learning input data, which is an input voice signal; and a learning stage conversion unit for executing a conversion learning model, which is a machine learning model, including learning stage conversion processing for converting the learning input data into learning stage conversion-destination data, which is a conversion-destination voice signal. The learning stage conversion processing includes local feature acquisition processing for acquiring, on the basis of input data to be processed, a feature for each learning input-side subset. The conversion learning model further includes adjustment-parameter-value acquisition processing for acquiring, on the basis of the learning input data, an adjustment parameter value. The learning stage conversion processing converts the learning input data into the learning stage conversion-destination data by using a result of a predetermined computation based on the adjustment parameter value.
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.
2 . The voice signal conversion model learning device according to claim 1 , wherein
the processing of converting the feature quantity is executed for each element of the feature quantity.
3 . A voice signal conversion 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 a voice signal to be converted; and
converting the conversion target using a learned conversion learning model obtained by a voice signal conversion model learning device including 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.
4 . A voice signal conversion model learning method comprising:
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.
5 . A non-transitory computer readable medium which stores a program for causing a computer to function as the voice signal conversion model learning device according to claim 1 .
6 . The voice signal conversion model learning device of claim 1 wherein the feature quantity includes the input voice signal or acoustic feature quantities derived from the input voice signal.