Robust two microphone noise suppression system

Abstract

A system for noise reduction comprises a first means for producing a speech estimate signal (240) from one or more acoustic signals, a second means for producing a noise estimate signal (250) from one or more acoustic signals, and at least one robust dual input spectral subtraction noise suppressor, RDINS, (305) for producing a noise reduced speech signal from the produced speech estimate signal and the produced noise estimate signal. A method for noise reduction is also disclosed and claimed.

Description

technical field [0001] The present invention relates to systems and methods for processing multiple acoustic signals, and more particularly to separating acoustic signals by filtering. Background technique [0002] Detecting and responding to informative signals in noisy environments is often difficult. In communications where users often speak in noisy environments, it is desirable to separate the user's speech signal from background noise. Background noise can include many noisy signals generated by the general environment, signals generated by other people's background conversations, and reflections and reverberation generated from each signal. [0003] In noisy environments, uplink communication can be a serious problem. Most solutions to this noise problem only work on certain types of noise, such as stationary noise, or produce significant audio artifacts that can annoy users as much as noise signals. All existing solutions have drawbacks with respect to the source ...

AI Technical Summary

Problems solved by technology

All existing solutions have drawbacks with respect to source and noise location, and the type of noise they are trying to suppress

Images