US 2019/0096429 A1 · PERSISTENT INTERFERENCE DETECTION

Abstract

A multi-microphone algorithm for detecting and differentiating interference sources from desired talker speech in advanced audio processing for smart home applications is described. The approach is based on characterizing a persistent interference source when sounds repeated occur from a fixed spatial location relative to the device, which is also fixed. Some examples of such interference sources include TV, music system, air-conditioner, washing machine, and dishwasher. Real human talkers, in contrast, are not expected to remain stationary and speak continuously from the same position for a long time. The persistency of an acoustic source is established based on identifying historically-recurring inter-microphone frequency-dependent phase profiles in multiple time periods of the audio data. The detection algorithm can be used with a beamforming processor to suppress the interference and for achieving voice quality and automatic speech recognition rate improvements in smart home applications.

Claims22

Dependent claims

A method, comprising:

receiving a first microphone signal and a second microphone signal, wherein the first microphone signal and the second microphone signal signals comprise audio data from acoustic sources recorded using a microphone array at a fixed location in an environment, and wherein the acoustic sources comprise desired talkers and interference sources;
and
identifying an acoustic source as a persistent interference source based, at least in part, on the first microphone signal and the second microphone signal by identifying multiple time periods of the audio data during which the acoustic source is determined to be originating from the same spatial location with respect to the microphone array.

An apparatus, comprising:

an integrated circuit configured to perform steps comprising:
receiving a first microphone signal and a second microphone signal, wherein the first microphone and the second microphone signal comprise audio data from acoustic sources recorded using a microphone array at a fixed location in an environment;
and
identifying an acoustic source as a persistent interference source based, at least in part, on the first microphone signal and the second microphone signal by identifying multiple time periods of the audio data during which the acoustic source is determined to be originating from the same spatial location with respect to the microphone array.

1 more element

Dependencies are inferred from the claim text.

Persistent interference detection

Life of this patent

Persistent interference detection

Life of this patent

Abstract

Claims22