System for recognizing and responding to environmental noises
AssigneeAmazon Technologies, Inc.
InventorsJohn Daniel Thimsen, Gregory Michael Hart, Ryan Paul Thomas
Life of this patent
Estimating the term…
Abstract
An audio controlled assistant captures environmental noise and converts the environmental noise into audio signals. The audio signals are provided to a system which analyzes the audio signals for a plurality of audio prompts, which have been customized for the acoustic environment surrounding the audio controlled assistant by an acoustic modeling system. The system configured to detect the presence of an audio prompt in the audio signals and transmit instructions associated with the detected audio prompt to at least one of the audio controlled assistant or one or more cloud based services, in response.
Claims20
A method comprising:
- receiving, by one or more servers over a network from a first device, a signal representative of sound detected by the first device within a physical environment, the sound including a detected noise determined by the first device to be similar to a non-conversational noise, wherein the first device determining the detected noise to be similar to the non-conversational noise comprises the first device analyzing the detected noise using an acoustic machine learning model, and wherein the sound is limited to the non-conversational noise and the sound does not include a conversational noise;
- and
- sending, by the one or more servers, at least in part in response to the determining by the first device that the detected noise is similar to the non-conversational noise, second data over the network to a second device, the second data causing the second device to output a notification.
One or more servers comprising:
- one or more processors;
- and
- one or more computer readable storage media storing instructions that, when executed on the one or more processors, perform acts comprising:
- receiving, from a first device over a network, a signal representative of sound detected by the first device within a physical environment, the sound including a detected noise determined by the first device to be similar to a non-conversational noise, wherein the first device determining the detected noise to be similar to the non-conversational noise comprises the first device analyzing the detected noise using an acoustic machine learning model, and wherein the sound is limited to the non-conversational noise and the sound does not include a conversational noise;
- and
- sending, at least in part in response to the determining by the first device that the detected noise is similar to the non-conversational noise, second data over the network to a second device, the second data causing the second device to output a notification.
A device comprising:
- one or more microphones to generate an audio signal based on sound detected from an environment in which the device is located;
- one or more communication interfaces;
- one or more processors;
- one or more computer readable storage media storing instructions that, when executed on the one or more processors, cause the device to perform acts comprising:
- comparing detected noises within the audio signal with a first non-conversational noise, wherein the comparing comprises analyzing the detected noises using an acoustic machine learning model, and wherein the first non-conversational noise is different than a conversational noise identifiable by the device;
- identifying, within the audio signal, the first non-conversational noise;
- and
- causing, in response to identifying the first non-conversational noise within the audio signal, output of a second non-conversational noise that is different from the first non-conversational noise.
Dependencies are inferred from the claim text.