US 12,014,705 B2
Audio analysis method and audio analysis device
Kouhei Sumi, Shizuoka (JP)
Assigned to YAMAHA CORPORATION, Shizuoka (JP)
Filed by Yamaha Corporation, Shizuoka (JP)
Filed on May 26, 2021, as Appl. No. 17/331,520.
Application 17/331,520 is a continuation of application No. PCT/JP2020/000374, filed on Jan. 9, 2020.
Claims priority of application No. 2019-003324 (JP), filed on Jan. 11, 2019.
Prior Publication US 2021/0287641 A1, Sep. 16, 2021
Int. Cl. G10H 1/00 (2006.01); G06N 20/00 (2019.01)
CPC G10H 1/0008 (2013.01) [G06N 20/00 (2019.01); G10H 2210/056 (2013.01)] 14 Claims
OG exemplary drawing
 
1. An audio analysis method realized by a computer, the audio analysis method comprising:
generating key information which represents a key, by inputting a time series of a feature amount of an audio signal into a learned model that has learned a relationship between keys and time series of feature amounts of audio signals,
the key information being generated for each of a plurality of continuation sections, each of which is a section in which a same chord of the audio signal continues, by inputting the feature amount of the audio signal into the learned model for each of the plurality of continuation sections.