Patent · US Active

Separating desired audio content from undesired content

US11227621B2 · kind B2 · utility

0Cited by

9References

20Claims

0Family size

Assignee

Dolby International AB · IE

Inventors

Pedro Jafeth Villasana Tinajero · Stockholm, SE
Stanislaw Gorlow · Paris, FR

Key dates

Filing date	Sep 16, 2019
Grant date	Jan 18, 2022
Priority date	—
Expiry date	Mar 26, 2040

Classification

Technology area (CPC G)Physics
CPC primaryG10L21/0364
WIPO fieldComputer technology
WIPO sectorElectrical engineering

Abstract

The present disclosure provides new variants of non-negative matrix factorization suitable for separating desired audio content from undesired audio content. In certain embodiments, a multi-dimensional non-negative representation of an audio signal is decomposed into desired content and undesired content by performing convolutional non-negative matrix factorization (CNMF) on multiple layers, each layer having a respective non-negative matrix representation. In certain embodiments, the desired content is represented by a first dictionary and the undesired content is represented by a second dictionary, and sparsity is imposed on activations of basic elements of the first or the second dictionary, wherein a degree of sparsity is controlled by setting a minimum number of components with significant activations of the first or second dictionary, respectively.

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