Processing

Please wait...

Settings

Settings

Goto Application

1. WO2020080239 - INFORMATION PROCESSING METHOD, INFORMATION PROCESSING DEVICE, AND INFORMATION PROCESSING PROGRAM

Publication Number WO/2020/080239
Publication Date 23.04.2020
International Application No. PCT/JP2019/039939
International Filing Date 10.10.2019
IPC
G10H 1/00 2006.1
GPHYSICS
10MUSICAL INSTRUMENTS; ACOUSTICS
HELECTROPHONIC MUSICAL INSTRUMENTS; INSTRUMENTS IN WHICH THE TONES ARE GENERATED BY ELECTROMECHANICAL MEANS OR ELECTRONIC GENERATORS, OR IN WHICH THE TONES ARE SYNTHESISED FROM A DATA STORE
1Details of electrophonic musical instruments
G06N 3/02 2006.1
GPHYSICS
06COMPUTING; CALCULATING OR COUNTING
NCOMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS
3Computer systems based on biological models
02using neural network models
G06N 20/00 2019.1
GPHYSICS
06COMPUTING; CALCULATING OR COUNTING
NCOMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS
20Machine learning
CPC
G06N 3/0454
GPHYSICS
06COMPUTING; CALCULATING; COUNTING
NCOMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS
3Computer systems based on biological models
02using neural network models
04Architectures, e.g. interconnection topology
0454using a combination of multiple neural nets
G06N 3/0472
GPHYSICS
06COMPUTING; CALCULATING; COUNTING
NCOMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS
3Computer systems based on biological models
02using neural network models
04Architectures, e.g. interconnection topology
0472using probabilistic elements, e.g. p-rams, stochastic processors
G06N 3/08
GPHYSICS
06COMPUTING; CALCULATING; COUNTING
NCOMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS
3Computer systems based on biological models
02using neural network models
08Learning methods
G06N 3/088
GPHYSICS
06COMPUTING; CALCULATING; COUNTING
NCOMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS
3Computer systems based on biological models
02using neural network models
08Learning methods
088Non-supervised learning, e.g. competitive learning
G10H 1/0025
GPHYSICS
10MUSICAL INSTRUMENTS; ACOUSTICS
HELECTROPHONIC MUSICAL INSTRUMENTS
1Details of electrophonic musical instruments
0008Associated control or indicating means
0025Automatic or semi-automatic music composition, e.g. producing random music, applying rules from music theory or modifying a musical piece
G10H 2210/031
GPHYSICS
10MUSICAL INSTRUMENTS; ACOUSTICS
HELECTROPHONIC MUSICAL INSTRUMENTS
2210Aspects or methods of musical processing having intrinsic musical character, i.e. involving musical theory or musical parameters or relying on musical knowledge, as applied in electrophonic musical tools or instruments
031Musical analysis, i.e. isolation, extraction or identification of musical elements or musical parameters from a raw acoustic signal or from an encoded audio signal
Applicants
  • ソニー株式会社 SONY CORPORATION [JP]/[JP]
Inventors
  • 赤間 健人 AKAMA, Taketo
Agents
  • 特許業務法人酒井国際特許事務所 SAKAI INTERNATIONAL PATENT OFFICE
Priority Data
2018-19797219.10.2018JP
2019-06104027.03.2019JP
Publication Language Japanese (ja)
Filing Language Japanese (JA)
Designated States
Title
(EN) INFORMATION PROCESSING METHOD, INFORMATION PROCESSING DEVICE, AND INFORMATION PROCESSING PROGRAM
(FR) PROCÉDÉ DE TRAITEMENT D'INFORMATIONS, DISPOSITIF DE TRAITEMENT D'INFORMATIONS ET PROGRAMME DE TRAITEMENT D'INFORMATIONS
(JA) 情報処理方法、情報処理装置及び情報処理プログラム
Abstract
(EN) This information processing device (100) comprises: an extraction unit (131) that extracts first data from elements constituting first content; and a model generation unit (132) that generates trained models having a first encoder (50) that calculates a first feature value being the feature value for the first content and a second encoder (55) that calculates a second feature value being a feature value for the extracted first data.
(FR) La présente invention concerne un dispositif de traitement d'informations (100) qui comprend : une unité d'extraction (131) qui extrait des premières données d'éléments constituant un premier contenu ; et une unité de génération de modèles (132) qui génère des modèles entraînés comprenant un premier codeur (50) qui calcule une première valeur de caractéristique qui est la valeur de caractéristique pour le premier contenu et un second codeur (55) qui calcule une seconde valeur de caractéristique qui est une valeur de caractéristique pour les premières données extraites.
(JA) 本開示に係る情報処理装置(100)は、第1コンテンツを構成する要素から第1データを抽出する抽出部(131)と、第1コンテンツの特徴量である第1特徴量を算出する第1エンコーダ(50)と、抽出された第1データの特徴量である第2特徴量を算出する第2エンコーダ(55)とを有する学習済みモデルを生成するモデル生成部(132)と、を備える。
Latest bibliographic data on file with the International Bureau