View source for Sanas.ai Inc. (20250014587). SYSTEM AND METHOD FOR BACKGROUND NOISE SUPPRESSION

=SYSTEM AND METHOD FOR BACKGROUND NOISE SUPPRESSION=


==Organization Name==

[[:Category:Sanas.ai Inc.|Sanas.ai Inc.]]


[[Category:Sanas.ai Inc.]]

==Inventor(s)==

[[:Category:Lukas Pfeifenberger of Salzburg (AT)|Lukas Pfeifenberger of Salzburg (AT)]][[Category:Lukas Pfeifenberger of Salzburg (AT)]]

[[:Category:Shawn Zhang of Palo Alto CA (US)|Shawn Zhang of Palo Alto CA (US)]][[Category:Shawn Zhang of Palo Alto CA (US)]]

[[:Category:Monal Patel of Naperville IL (US)|Monal Patel of Naperville IL (US)]][[Category:Monal Patel of Naperville IL (US)]]

[[:Category:Maxim Serebryakov of Palo Alto CA (US)|Maxim Serebryakov of Palo Alto CA (US)]][[Category:Maxim Serebryakov of Palo Alto CA (US)]]

[[:Category:Raj Vardhan of Bangalore (IN)|Raj Vardhan of Bangalore (IN)]][[Category:Raj Vardhan of Bangalore (IN)]]

[[:Category:Lan Shek of San Ramon CA (US)|Lan Shek of San Ramon CA (US)]][[Category:Lan Shek of San Ramon CA (US)]]

[[:Category:Ankita Jha of Bangalore (IN)|Ankita Jha of Bangalore (IN)]][[Category:Ankita Jha of Bangalore (IN)]]

==SYSTEM AND METHOD FOR BACKGROUND NOISE SUPPRESSION==


This abstract first appeared for US patent application 20250014587 titled 'SYSTEM AND METHOD FOR BACKGROUND NOISE SUPPRESSION




==Original Abstract Submitted==

the disclosed technology relates to methods, background noise suppression systems, and non-transitory computer readable media for background noise suppression. in some examples, frames fragmented from input audio data are projected into a higher dimension space than the input audio data. an estimated speech mask is applied to the frames to separate speech components and noise components of the frames. the speech components are then transformed into a feature domain of the input audio data by performing an inverse projection on the speech components to generate output audio data. the output audio data is provided via an audio interface. the output audio data advantageously comprises a noise-suppressed version of the input audio data.



[[Category:G10L21/0208]]
[[Category:G10L25/63]]
[[Category:CPC_G10L21/0208]]