SOUND SOURCE SEPARATION PROGRAM, SOUND SOURCE SEPARATION METHOD, AND SOUND SOURCE SEPARATION DEVICE - TOKYO METROPOLITAN PUBLIC UNIV CORPORATION

Title:

SOUND SOURCE SEPARATION PROGRAM, SOUND SOURCE SEPARATION METHOD, AND SOUND SOURCE SEPARATION DEVICE

Document Type and Number:

WIPO Patent Application WO/2021/172524

Kind Code:

A1

Abstract:

This sound source separation program causes a computer to acquire an acoustic signal, convert the acquired acoustic signal from a time domain to a frequency domain, and perform sound source separation on the acoustic signal converted to the frequency domain by iteratively minimizing an objective function including the quadratic form of a separation vector and the determinant of a separation matrix by performing an update based on an elementary row operation on the separation matrix.

More Like This:

JP7439433	Display control method, display control device and program
JP2019159290	ADAPTIVE BLIND SIGNAL SEPARATION METHOD AND DEVICE THEREFOR
JP5736124	Audio signal processor, method, program, and recording medium

Inventors:

ONO NOBUTAKA (JP)
SCHEIBLER ROBIN (JP)

Application Number:

PCT/JP2021/007398

Publication Date:

September 02, 2021

Filing Date:

February 26, 2021

Export Citation:

Click for automatic bibliography generation Help

Assignee:

TOKYO METROPOLITAN PUBLIC UNIV CORPORATION (JP)

International Classes:

G10L21/0308

Foreign References:

JP2014041308A

2014-03-06

Other References:

March 2020 (2020-03-01), pages 207 - 208, ISSN: 1880-7658
MAKISHIMA NAOKI ET AL.: "Column-wise update algorithm for independent deeply learned matrix analysis", PROCEEDINGS OF THE 23RD INTERNATIONAL CONGRESS ON ACOUSTICS, September 2019 (2019-09-01), pages 2805 - 2812, XP055850727, ISSN: 2570-2092

Attorney, Agent or Firm:

TAZAKI Akira et al. (JP)

Download PDF:

View/Download PDF PDF Help

Previous Patent: STABILIZATION OF POLYSULFIDE

Next Patent: METHOD FOR PRODUCING NEGATIVE THERMAL EXPANSION MATERIAL, METHOD FOR PRODUCING REACTION PRECURSOR OF...