Beam rejection in multi-beam microphone systems
First Claim
Patent Images
1. A computing device comprising:
- memory;
one or more processors coupled to the memory;
a loudspeaker coupled to the one or more processors;
a plurality of microphones coupled to the one or more processors;
a beamforming component stored in the memory and executable by the one or more processors;
an acoustic echo cancellation (AEC) component stored in the memory and executable by the one or more processors; and
a speech processing component stored in the memory and executable by the one or more processors,wherein the one or more processors are configured to;
cause the plurality of microphones to generate a first audio signal and a second audio signal based on speech input;
cause the beamforming component to process the first audio signal and the second audio signal to generate a first beamformed signal and a second beamformed signal, respectively;
cause the AEC component to perform echo cancellation on the first beamformed signal and the second beamformed signal to generate first echo-canceled data and second echo-canceled data, respectively;
determine that the first beamformed signal is directed towards a reflective surface; and
cause the speech processing component to;
(i) receive the second echo-canceled data;
(ii) send at least a portion of the second echo-canceled data to a remote computing resource;
(iii) receive response data from the remote computing resource, the response data being generated based on the portion of the second echo-canceled data; and
(iv) output audible sound representing the response data.
2 Assignments
0 Petitions
Accused Products
Abstract
The systems, devices, and processes described herein may identify a beam of a voice-controlled device that is directed toward a reflective surface, such as a wall. The beams may be created by a beamformer. An acoustic echo canceller (AEC) may create filter coefficients for a reference sound. The filter coefficients may be analyzed to identify beams that include multiple peaks. The multiple peaks may indicate presence of one or more reflective surfaces. Using the amplitude and the time delay between the peaks, the device may determine that it is close to a reflective surface in a direction of the beam.
29 Citations
20 Claims
-
1. A computing device comprising:
-
memory; one or more processors coupled to the memory; a loudspeaker coupled to the one or more processors; a plurality of microphones coupled to the one or more processors; a beamforming component stored in the memory and executable by the one or more processors; an acoustic echo cancellation (AEC) component stored in the memory and executable by the one or more processors; and a speech processing component stored in the memory and executable by the one or more processors, wherein the one or more processors are configured to; cause the plurality of microphones to generate a first audio signal and a second audio signal based on speech input; cause the beamforming component to process the first audio signal and the second audio signal to generate a first beamformed signal and a second beamformed signal, respectively; cause the AEC component to perform echo cancellation on the first beamformed signal and the second beamformed signal to generate first echo-canceled data and second echo-canceled data, respectively; determine that the first beamformed signal is directed towards a reflective surface; and cause the speech processing component to;
(i) receive the second echo-canceled data;
(ii) send at least a portion of the second echo-canceled data to a remote computing resource;
(iii) receive response data from the remote computing resource, the response data being generated based on the portion of the second echo-canceled data; and
(iv) output audible sound representing the response data. - View Dependent Claims (2, 3, 4, 5, 6)
-
-
7. A computer-implemented method comprising:
-
generating a first audio signal and a second audio signal based on speech input received by a plurality of microphones; processing the first and the second audio signals by a beamforming component to generate a first beamformed signal and a second beamformed signal, respectively; performing acoustic echo cancellation (AEC) on the first beamformed signal and the second beamformed signal to generate first echo-canceled data and second echo-canceled data, respectively; determining that the first beamformed signal is directed towards a reflective surface; sending at least a portion of the second echo-canceled data to a remote computing resource; receiving response data from the remote computing resource as a result of at least processing the second echo-canceled data by the remote computing resource; and causing a loudspeaker to output audible sound representing the response data. - View Dependent Claims (8, 9, 10, 11, 12, 13, 14)
-
-
15. A system comprising:
-
memory; one or more processors coupled to the memory; a plurality of microphones coupled to the one or more processors; a beamforming component stored in the memory and executable by the one or more processors; an acoustic echo cancellation (AEC) component stored in the memory and executable by the one or more processors; and a speech processing component stored in the memory and executable by the one or more processors, wherein the one or more processors are configured to; cause the plurality of microphones to generate a first audio signal and a second audio signal based on speech input; cause the beamforming component to process the first audio signal and the second audio signal to generate a first beamformed signal and a second beamformed signal; cause the AEC component to perform echo cancellation on the first beamformed signal and the second beamformed signal to generate first echo-canceled data and second echo-canceled data, respectively; determine that the first beamformed signal is directed towards a reflective surface; and cause the speech processing component to process the second echo-canceled data to determine a command and in response to processing the command, send at least a portion of the second echo-canceled data to a remote computing resource and receive response data from the remote computing resource, the response data being generated based on the portion of the second echo-canceled data. - View Dependent Claims (16, 17, 18, 19, 20)
-
Specification