Performance analysis method and performance analysis device
AssigneeYamaha Corporation
InventorAkira Maezawa
Life of this patent
Estimating the term…
Abstract
A performance analysis method is realized by a computer and includes acquiring a time series of input data representing played pitch that is played, inputting the acquired time series of input data into an estimation model that has learned a relationship between a plurality of items of training input data representing pitch and a plurality of items of training output data representing an acoustic effect to be added to sound having the pitch, and generating a time series of output data for controlling an acoustic effect to be added to sound having the played pitch represented by the acquired time series of input data.
Claims20
A performance analysis method realized by a computer, the performance analysis method comprising:
- acquiring a time series of input data that are pitch data representing pitches and that are generated from performance data which are musical instrument digital interface data representing a performance by a user on an electronic instrument;
- and
- inputting the time series of input data into an estimation model, thereby generating a time series of output data for controlling an acoustic effect to be added to sound having the pitches,
- the estimation model being a model
- that is trained by the computer, or trained and transferred from an estimation model construction device, and
- that has learned a relationship between a plurality of items of training input data representing training pitches and a plurality of items of training output data representing a training acoustic effect to be added to training sound having the training pitches.
A performance analysis device comprising:
- an electronic controller including at least one processor, the electronic controller being configured to execute a plurality of modules including
- an input data acquisition module that acquires a time series of input data that are pitch data representing pitches and that are generated from performance data representing a performance by a user on an electronic instrument, and
- an output data generation module that inputs the time series of input data into an estimation model, thereby generating a time series of output data for controlling an acoustic effect to be added to sound having the pitches
- the estimation model being a model
- that is trained by the electronic controller, or trained and transferred from an estimation model construction device, and
- that has learned a relationship between a plurality of items of training input data representing training pitches and a plurality of items of training output data representing a training acoustic effect to be added to training sound having the training pitches.
Dependencies are inferred from the claim text.