Learning model generation method, learning model generation device, and automatic musical performance robot
AssigneeYamaha Corporation
InventorKazuhiko Yamamoto
Life of this patent
Estimating the term…
Abstract
Disclosed is a learning model generation method executed by a computer, including: striking a percussion instrument with a striking member to emit a musical sound; and conducting machine learning upon receiving an input of the musical sound emitted from the percussion instrument, and generating, based on the machine learning, a learning model for outputting numerical values for setting musical performance parameters for an automatic musical performance of the percussion instrument that is struck when the striking member is driven.
Claims9
A learning model generation method executed by a computer, comprising:
- storing basic values of musical performance parameters in a memory;
- striking a percussion instrument with a striking member to emit a musical sound;
- conducting machine learning upon receiving an input of the musical sound emitted from the percussion instrument, wherein the machine learning is based on an error in the musical sound;
- and
- generating, based on the machine learning, a learning model for outputting adjustment values for adjusting the stored basic values of the musical performance parameters for an automatic musical performance of the percussion instrument that is struck when the striking member is driven, wherein the learning model outputs, with respect to the error in the musical sound at a first time point on a time axis, the adjustment values for adjusting the stored basic values of the musical performance parameters at a second time point later than the first time point.
A learning model generation device, comprising:
- a memory configured to store basic values of musical performance parameters;
- a musical performance control section configured to strike a percussion instrument with a striking member to emit a musical sound;
- and
- a learning processing section configured to:
- conduct machine learning upon receiving an input of the musical sound emitted from the percussion instrument, wherein the machine learning is based on an error in the musical sound;
- and
- generate, based on the machine learning, a learning model to output adjustment values to adjust the stored basic values of the musical performance parameters for an automatic musical performance of the percussion instrument that is struck when the striking member is driven, wherein the learning model outputs, with respect to the error in the musical sound at a first time point on a time axis, the adjustment values to adjust the stored basic values of the musical performance parameters at a second time point later than the first time point.
An automatic musical performance robot, comprising:
- a stick;
- a memory configured to store basic values of musical performance parameters;
- and
- an electronic controller including at least one processor, wherein the electronic controller is configured to execute a plurality of modules including
- a striking module configured to strike a percussion instrument with the stick to emit a musical sound;
- and
- a conducting machine learning module configured to:
- conduct machine learning upon receiving an input of the musical sound emitted from the percussion instrument, wherein the machine learning is based on an error in the musical sound;
- and
- generate, based on the machine learning, a learning model to output adjustment values to adjust the stored basic values of the musical performance parameters for an automatic musical performance of the percussion instrument that is struck when the stick is driven, wherein the learning model outputs, with respect to the error in the musical sound at a first time point on a time axis, the adjustment values to adjust the stored basic values of the musical performance parameters at a second time point later than the first time point.
Dependencies are inferred from the claim text.