Patent · US Active

Method and system for enhancing a speech signal of a human speaker in a video using visual information

US10475465B2 · kind B2 · utility

2Cited by

1References

24Claims

0Family size

Assignee

YISSUM RESEARCH DEVELOPMENT COMPANY OF THE HEBREW UNIVERSITY OF JERUSALEM LTD. · IL

Inventors

Shmuel Peleg · Mevaseret Tsiyon, IL
Asaph Shamir · Jerusalem, IL
Tavi Halperin · Beer Sheva, IL
Aviv Gabbay · Jerusalem, IL
Ariel Ephrat · Jerusalem, IL

Key dates

Filing date	Jul 3, 2018
Grant date	Nov 12, 2019
Priority date	—
Expiry date	Jul 3, 2038

Classification

Technology area (CPC G)Physics
CPC primaryG06F2218/08
WIPO fieldComputer technology
WIPO sectorElectrical engineering

Abstract

A method and system for enhancing a speech signal is provided herein. The method may include the following steps: obtaining an original video, wherein the original video includes a sequence of original input images showing a face of at least one human speaker, and an original soundtrack synchronized with said sequence of images; and processing, using a computer processor, the original video, to yield an enhanced speech signal of said at least one human speaker, by detecting sounds that are acoustically unrelated to the speech of the at least one human speaker, based on visual data derived from the sequence of original input images.

Source: USPTO / EPO open patent data. Objective bibliographic and citation counts.