US Patent Application 18032529. AUDIO SIGNAL CONVERSION MODEL LEARNING APPARATUS, AUDIO SIGNAL CONVERSION APPARATUS, AUDIO SIGNAL CONVERSION MODEL LEARNING METHOD AND PROGRAM simplified abstract
AUDIO SIGNAL CONVERSION MODEL LEARNING APPARATUS, AUDIO SIGNAL CONVERSION APPARATUS, AUDIO SIGNAL CONVERSION MODEL LEARNING METHOD AND PROGRAM
Organization Name
NIPPON TELEGRAPH AND TELEPHONE CORPORATION
Inventor(s)
Takuhiro Kaneko of Musashino-shi (JP)
Hirokazu Kameoka of Musashino-shi (JP)
Ko Tanaka of Musashino-shi (JP)
Nobukatsu Hojo of Musashino-shi (JP)
AUDIO SIGNAL CONVERSION MODEL LEARNING APPARATUS, AUDIO SIGNAL CONVERSION APPARATUS, AUDIO SIGNAL CONVERSION MODEL LEARNING METHOD AND PROGRAM - A simplified explanation of the abstract
This abstract first appeared for US patent application 18032529 titled 'AUDIO SIGNAL CONVERSION MODEL LEARNING APPARATUS, AUDIO SIGNAL CONVERSION APPARATUS, AUDIO SIGNAL CONVERSION MODEL LEARNING METHOD AND PROGRAM
Simplified Explanation
The patent application describes a device that learns how to convert voice signals.
- The device acquires input voice signals for learning.
- It uses a machine learning model to convert the input voice signals into a desired voice signal.
- The conversion process involves acquiring feature quantities for subsets of the input data.
- An adjustment parameter value is obtained to adjust the statistical distribution of the feature quantities.
- The learning stage conversion processing converts the input data into the desired voice signal using the adjustment parameter value.
Original Abstract Submitted
A voice signal conversion model learning device comprising: a learning data acquisition unit that acquires learning input data which is an input voice signal; and a learning stage conversion unit that executes 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.
