Timing prediction method and timing prediction device

Patent metadata

Field	Value
Publication number	US-10699685-B2
Application number	US-201916252128-A
Country	US
Kind code	B2
Filing date	Jan 18, 2019
Priority date	Jul 22, 2016
Publication date	Jun 30, 2020
Grant date	Jun 30, 2020

Abstract

A timing prediction method includes updating a state variable relating to the timing of a next sound generation event in a performance using a plurality of observation values relating to a timing of sound generation in a performance, and outputting an updated state variable that has been updated.

First claim

What is claims:

1. A timing prediction method comprising:
receiving two or more observation values relating to a timing of a sound generation in a performance;
selecting a plurality of observation values that are used to update a state variable from among the two or more observation values, the state variable relating to a timing of a next sound generation event in the performance;
updating the state variable, using the plurality of observation values;
outputting an updated state variable that has been updated; and
causing a sound generation device to emit a sound at a timing that is set based on the updated state variable;
the plurality of observation values being selected according to a ratio of a density of music notes that indicate generation of sound by a performer in the performance to a density of music notes that indicate generation of sound by the sound generation device in the performance.

2. The timing prediction method according to claim 1 , wherein
a mode of the selecting is changed according to the ratio.

3. The timing prediction method according to claim 1 , wherein
in the selecting, when the ratio is larger than a designated threshold value, the number of the plurality of observation values that are selected is decreased compared to when the ratio is less than or equal to the designated threshold value.

4. The timing prediction method according to claim 1 , wherein
the plurality of observation values are observation values selected from among the two or more observation values during a selection period, and
the plurality of observation values are selected such that the selection period when the ratio is greater than a designated threshold value is shorter than when the ratio is less than or equal to the designated threshold value.

5. A timing prediction device comprising:
an electronic controller including at least one processor,
the electronic controller being configured to execute a plurality of modules including
a reception module that receives two or more observation values relating to a timing of sound generation in a performance,
a selection module that selects a plurality of observation values that are used to update a state variable from among the two or more observation values, the state variable relating to a timing of a next sound generation event in the performance,
an updating module that updates the state variable, using the plurality of observation values, and outputs an updated state variable that has been updated, and
an output module that outputs the updated state variable to cause a sound generation device to emit a sound at a timing that is set based on the updated state variable,

the selection module selecting the plurality of observation values according to a ratio of a density of music notes that indicate generation of sound by a performer in the performance to a density of music notes that indicate generation of sound by the sound generation device in the performance.

6. The timing prediction device according to claim 5 , wherein
the selection module changes a mode of select of the plurality of observation values according to the ratio.

7. The timing prediction device according to claim 5 , wherein
when the ratio is larger than a designated threshold value, the selection module decreases the number of the plurality of observation values that are selected compared to when the ratio is less than or equal to the designated threshold value.

8. The timing prediction device according to claim 5 , wherein
the plurality of observation values are observation values selected from among the two or more observation values during a selection period, and
the selection module selects the plurality of observation values such that the selection period when the ratio is greater than a designated threshold value is shorter than when the ratio is less than or equal to the designated threshold value.

Assignees

• Yamaha Corp

Inventors

• Maezawa Akira

Classifications

• G10H1/40 Primary

  Rhythm · CPC title

• G10G3/04

  using electrical means · CPC title

• G10H2250/015

  Markov chains, e.g. hidden Markov models [HMM], for musical processing, e.g. musical analysis or musical composition · CPC title

• G10H1/00

  Details of electrophonic musical instruments · CPC title

• G10H2240/325

  Synchronizing two or more audio tracks or files according to musical features or musical timings · CPC title