Login| Sign Up| Help| Contact|

Patent Searching and Data


Title:
SOUND MODEL GENERATION DEVICE, SOUND MODEL GENERATION METHOD, AND RECORDING MEDIUM
Document Type and Number:
WIPO Patent Application WO/2021/001998
Kind Code:
A1
Abstract:
Provided are a sound model generation device and the like that make it possible to more easily generate a sound model capable of distinguishing sound events using a plurality of feature amounts. A linking unit (20) links a plurality of feature amounts of sound signals that are learning data and generates a linked feature amount. A learning unit (30) uses a generated linked feature amount to subject a sound model for distinguishing a sound event from a sound signal to learning using the generated linked feature amount.

Inventors:
MISHIMA Sakiko (JP)
KIYOKAWA Yu (JP)
TOIZUMI Takahiro (JP)
SAGI Kazutoshi (JP)
Application Number:
JP2019/026659
Publication Date:
January 07, 2021
Filing Date:
July 04, 2019
Export Citation:
Click for automatic bibliography generation   Help
Assignee:
NEC CORPORATION (JP)
International Classes:
G10L25/51; G10L17/00; G10L25/30
Attorney, Agent or Firm:
SHIMOSAKA Naoki (JP)
Download PDF: