SOUND SIGNAL SYNTHESIS METHOD, GENERATIVE MODEL TRAINING METHOD, SOUND SIGNAL SYNTHESIS SYSTEM, AND PROGRAM

Title:

SOUND SIGNAL SYNTHESIS METHOD, GENERATIVE MODEL TRAINING METHOD, SOUND SIGNAL SYNTHESIS SYSTEM, AND PROGRAM

Document Type and Number:

WIPO Patent Application WO/2020/171033

Kind Code:

A1

Abstract:

This sound signal synthesis method to be realized by a computer: generates first data indicating a sound source spectrum of a sound signal, and second data indicating a spectrum envelope of the sound signal, in accordance with control data indicating sound signal conditions; and synthesizes the sound signal in accordance with the sound source spectrum indicated by the first data and the spectrum envelope indicated by the second data.

Inventors:

BONADA JORDI (ES)
BLAAUW MERLIJN (ES)
DAIDO RYUNOSUKE (JP)

Application Number:

PCT/JP2020/006158

Publication Date:

August 27, 2020

Filing Date:

February 18, 2020

Export Citation:

Click for automatic bibliography generation Help

Assignee:

YAMAHA CORP (JP)

International Classes:

G10L13/00; G10H7/08

Domestic Patent References:

WO2012053150A1

2012-04-26

Other References:

WANG, XIN AND TAKAKI SHINJI; YAMAGISHI JUNICHI: "NEURAL SOURCE-FILTER-BASED WAVEFORM MODEL FOR STATISTICAL PARAMETRIC SPEECH SYNTHESIS", ARXIV PREPRINT, ARXIV:1810.11946V1, 29 October 2018 (2018-10-29), pages 5916 - 5920, XP033564878, Retrieved from the Internet [retrieved on 20200513], DOI: 10.1109/ICASSP.2019.8682298

Attorney, Agent or Firm:

OHBAYASHI, Akira et al. (JP)

Download PDF:

View/Download PDF PDF Help

Previous Patent: METHOD FOR PRODUCING MICROWAVE OVEN-RESISTANT SHEET TO BE USED IN FOAMED THERMAL INSULATION PAPER CO...

Next Patent: SOUND SIGNAL GENERATION METHOD, GENERATIVE MODEL TRAINING METHOD, SOUND SIGNAL GENERATION SYSTEM, AN...