Characterizing environment using ultrasound pilot tones
First Claim
1. An apparatus comprising:
- a speaker;
a microphone unit;
a control module configured to;
produce a pilot tone for output by the speaker within an environment that includes the apparatus;
subsequent to producing the pilot tone, generate, by the microphone unit, a first audio signal related to the pilot tone based on sound captured by the microphone unit, at least a portion of the sound comprising the pilot tone as reflected by one or more surfaces within the environment, the first audio signal including one or more characteristics;
analyze the first audio signal to determine if the one or more characteristics of the first audio signal have been altered with respect to one or more characteristics of the pilot tone;
generate, by the microphone unit, a second audio signal;
based at least in part upon the analyzing, at least one of (i) select a signal processing model for performing speech recognition on the second audio signal, or (ii) alter a signal processing model for performing speech recognition on the second audio signal; and
perform speech recognition on the second audio signal using the at least one of the selected or altered signal processing model.
2 Assignments
0 Petitions
Accused Products
Abstract
A voice-activated computing device configured to transmit a pilot tone and then capture or receive a signal, which corresponds to the pilot tone, reflected from within the environment containing the voice-activated computing device. The voice-activated computing device, or some other computing system or device, analyzes the received signal in order to determine analyze one or more characteristics present within the signal, i.e. noise, echo, etc. Based upon the analysis, models for signal processing can be determined, selected and/or altered. Future signals received by the voice-activated computing device can be processed with such models. The analysis can also allow for the models to be dynamically updated and for models to be dynamically created.
308 Citations
23 Claims
-
1. An apparatus comprising:
-
a speaker; a microphone unit; a control module configured to; produce a pilot tone for output by the speaker within an environment that includes the apparatus; subsequent to producing the pilot tone, generate, by the microphone unit, a first audio signal related to the pilot tone based on sound captured by the microphone unit, at least a portion of the sound comprising the pilot tone as reflected by one or more surfaces within the environment, the first audio signal including one or more characteristics; analyze the first audio signal to determine if the one or more characteristics of the first audio signal have been altered with respect to one or more characteristics of the pilot tone; generate, by the microphone unit, a second audio signal; based at least in part upon the analyzing, at least one of (i) select a signal processing model for performing speech recognition on the second audio signal, or (ii) alter a signal processing model for performing speech recognition on the second audio signal; and perform speech recognition on the second audio signal using the at least one of the selected or altered signal processing model. - View Dependent Claims (2, 3, 4, 5, 6, 7, 8)
-
-
9. A method of characterizing an environment in which a device resides, the device comprising at least one speaker and at least one microphone, and the method comprising:
-
producing a pilot tone by the at least one speaker; subsequent to producing the pilot tone, generating, by the at least one microphone, a first audio signal based on sound from the environment, wherein at least a portion of the sound comprises the pilot tone as reflected by one or more surfaces within the environment and the first audio signal includes one or more characteristics; analyzing the first audio signal to determine if the one or more characteristics of the first audio signal have been altered with respect to one or more characteristics of the pilot tone; generating a second audio signal by the at least one microphone; based at least in part upon the analyzing of the first audio signal, at least one of (i) selecting a signal processing model for performing speech recognition on the second audio signal, or (ii) altering a signal processing model for performing speech recognition on the second audio signal; and performing speech recognition on the second audio signal using the at least one of the selected or altered signal processing model. - View Dependent Claims (10, 11, 12, 13, 14, 15, 16, 17, 18, 19, 20)
-
-
21. Non-transitory computer-readable media storing computer-executable instructions that, when executed on a processor, cause the processor to perform acts comprising:
-
producing, within an environment, a pilot tone by at least one speaker of a device, the device including the at least one speaker and at least one microphone; generating, by the at least one microphone, a first audio signal based on sound of the pilot tone as reflected by one or more surfaces within the environment; analyzing the first audio signal to determine if one or more characteristics present in the first audio signal have been altered with respect to one or more characteristics present in the pilot tone; generating a second audio signal by the at least one microphone; based at least in part upon the analyzing, at least one of selecting or altering a signal processing model for performing speech recognition on the second audio signal; and performing speech recognition on the second audio signal using the at least one of the selected or altered signal processing model. - View Dependent Claims (22, 23)
-
Specification