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.
AI classification
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.