METHOD FOR SEPARATING SOURCE SIGNALS AND APPARATUS THEREOF

Patent №

US 8,364,483

Granted

2013-01-29

Filed 2009

Owner

ELECTRONICS AND TELECOMMUNICATIONS RESEARCH INSTITUTE

Lab

AI components

1

speech

Assignment

Recorded

Dataset

AIPD

2023_r1 edition

Application

12488215

A method for separating a sound source from a mixed signal, includes Transforming a mixed signal to channel signals in frequency domain; and grouping several frequency bands for each channel signal to form frequency clusters. Further, the method for separating the sound source from the mixed signal includes separating the frequency clusters by applying a blind source separation to signals in frequency domain for each frequency cluster; and integrating the spectrums of the separated signal to restore the sound source in a time domain wherein each of the separated signals expresses one sound source.

SpeechH04R 3/005H04R 27/00H04R 2430/03

AI classification

Speech1.00
Machine learning0.16
Natural language0.01
AI hardware0.00
Vision0.00
Knowledge representation0.00
Evolutionary computation0.00
Planning0.00

Ownership

ELECTRONICS AND TELECOMMUNICATIONS RESEARCH INSTITUTE

assignment · 228720034

Assignors

PARK, KI-YOUNG, JUNG, HO-YOUNG, LEE, YUN KEUN, PARK, JEON GUE, KANG, JEOM JA, CHUNG, HOON, LEE, SUNG JOO, KANG, BYUNG OK, WANG, JI HYUN, CHUNG, EUI SOK, JEON, HYUNG-BAE, KIM, JONG JIN

On an employer assignment, the assignors are typically the inventors.

From the same owner

© 2026 NYSGPT2525 LLC