EXTRACTING A COMMON SIGNAL FROM MULTIPLE AUDIO SIGNALS

Patent №

US 9,820,073

Granted

2017-11-14

Filed 2017

Owner

TLS CORP.

Lab

AI components

1

speech

Assignment

Recorded

Dataset

AIPD

2023_r1 edition

Application

15591549

Extracting a common signal from multiple audio signals may include summing a first signal and a second signal to obtain a first+second signal; subtracting the second signal from the first signal to obtain a first−second signal; transforming the first+second signal and the first−second signal to frequency domain representations; calculating absolute value of the frequency domain representations of the first+second signal and the first−second signal; subtracting the absolute value of the frequency domain representation of the first−second signal from the absolute value of the frequency domain representation of the first+second signal to obtain a difference signal; multiplying the difference signal by the frequency domain representation of the first+second signal to obtain a product signal; dividing the product signal by the absolute value of the frequency domain representation of the first+second signal to obtain a frequency domain representation of the common signal; and transforming the frequency domain representation to the common signal.

SpeechH04S 5/005H03G 3/301H03G 3/3005H03G 5/165H03G 9/025H03G 2201/106H04S 2400/05H04S 2400/07

AI classification

Speech0.82
Natural language0.01
Vision0.00
Knowledge representation0.00
Evolutionary computation0.00
Machine learning0.00
AI hardware0.00
Planning0.00

Ownership

TLS CORP.

assignment · 423880598

Assignors

FOTI, FRANK

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

© 2026 NYSGPT2525 LLC