Dsp Concepts, Inc.

Shashank Bharathi

Paul Eric Beckmann

Arvind Ramanthan

A method of processing microphone signals generates a specified or required multichannel microphone input for a voice recognition system. The method comprises receiving first and second microphone signal from first and second microphones that have a spacing that is required by a voice response or recognition system. The first and second microphone signals are processed using at least one additional microphone signal to generate a first modified microphone signal and a second modified microphone signal respectively. The first and second modified microphone signals are then provided as required microphone inputs to a voice response or recognition system.

Processing of microphone signals required by a voice recognition system

A method and apparatus for handling both echo cancellation and noise in a given space using a single adaptive filter. The proposed method utilizes just a single adaptive filter and without any control logic, the system is capable of handling both the AEC and the noise in a given space. The technology as proposed and claimed herein proposes using a single adaptive filter to cancel referenced noise AEC and unreferenced noise ANC in a given physical space using a beamformer. By adding the far end reference and a beam pointed dynamically on the noise source in the given physical space this can be achieved. This invention also reduces the processing load and memory.

Growing community of inventors

San Jose, CA, United States of America

Shashank Bharathi