Identifying a location of a voice-input device

Patent metadata

Field	Value
Publication number	US-9922646-B1
Application number	US-201213624592-A
Country	US
Kind code	B1
Filing date	Sep 21, 2012
Priority date	Sep 21, 2012
Publication date	Mar 20, 2018
Grant date	Mar 20, 2018

Abstract

Techniques for identifying a location of a voice-controlled device within an environment. After identifying a location of the device, the device may receive a voice command from a user within the environment and may determine a response to the command based in part on the location, may determine how to output a response based in part on the location or may determine how to interact with the user based in part on the location.

First claim

What is claimed is:

1. An apparatus comprising:
a microphone unit;
at least one processor; and
computer-readable media storing computer-executable instructions that, when executed on the at least one processor, cause the at least one processor to perform acts comprising:
receiving an audio signal generated at least partly by the microphone unit, the microphone unit configured to generate the audio signal based on sound captured within an environment in which the apparatus resides, the environment including at least a first physical location having at least a first sound characteristic and a second physical location having at least a second sound characteristic;
determining that the apparatus is located at the first physical location within the environment based at least in part on a first portion of the audio signal representing at least the first sound characteristic;
analyzing a second portion of the audio signal to identify a request from a user; and
performing an operation responsive to the request identified in the second portion of the audio signal, the performing of the operation being based at least in part on the apparatus being located at the first physical location within the environment.

2. The apparatus as recited in claim 1 , wherein the first sound characteristic represents one or more first background noises associated with the first physical location within the environment and the second sound characteristics represents one or more second background noises associated with the second physical location within the environment, and the determining further comprises analyzing the one or more the first background noises to determine that the apparatus is located at the first physical location within the environment.

3. The apparatus as recited in claim 1 , wherein the first portion of the audio signal includes an indication from the user of a location of the apparatus, and wherein the determining further comprises determining that the apparatus is located at the first physical location within the environment based at least in part on the indication from the user.

4. The apparatus as recited in claim 1 , wherein the performing comprises determining one or more prior voice commands received at the apparatus; and determining that the apparatus is located at the first physical location within the environment based, at least in part, on the one or more prior voice commands received at the apparatus.

5. The apparatus as recited in claim 1 , wherein the performing comprises:
determining which of multiple operations to perform based at least in part on the apparatus being located at the first physical location;
determining how to perform the operation based at least in part on the apparatus being located at the first physical location; or
determining how to interact with the user based at least in part on the apparatus being located at the first physical location.

6. The apparatus as recited in claim 1 , wherein the performing comprises:
identifying, from the first portion of the audio signal, a first echo characteristic associated with the first physical location or a second echo characteristic associated with the second physical location; and
comparing the identified first echo characteristic or the second echo characteristic with a first location profile associated with known echo characteristics of the first physical location within the environment and to a second location profile associated with known echo characteristics of the second physical location within the environment.

7. Non-transitory computer-readable media storing computer-executable instructions that, when executed on at least one processor, cause the at least one processor to perform acts comprising:
receiving, at a device in an environment, an audio signal from a microphone unit of the device;
analyzing a first portion of the audio signal to identify a first characteristic of sound or a second characteristic of sound;
comparing the identified first characteristic of sound or second characteristic of sound to a first location profile associated with a first physical location within the environment and to a second location profile associated with a second physical location within the environment;
determining that the device is located at the first physical location within the environment based at least in part on the comparing;
analyzing a second portion of the audio signal to identify a request from a user;
determining a response to the request based at least in part on the first physical location of the device; and
outputting audio using the speaker of the device, the audio being based at least in part on the determined response.

8. The non-transitory computer-readable media as recited in claim 7 , wherein the determining that the device is located at the first physical location within the environment comprises determining a room within the environment in which the device resides by analyzing the first portion of the audio signal to identify background noise captured by the microphone unit and mapping the identified background noise to the determined room.

9. The non-transitory computer-readable media as recited in claim 7 , wherein:
the device includes a sensor; and
the determining that the device is located at the first physical location within the environment comprises determining a room within the environment in which the device resides based by mapping data gathered by the sensor to the determined room.

10. The non-transitory computer-readable media as recited in claim 9 , wherein the sensor comprises a light sensor, a temperature sensor, or a camera.

11. The non-transitory computer-readable media as recited in claim 7 , wherein the determining that the device is located at the first physical location within the environment comprises determining a room within the environment in which the device resides by analyzing the first portion of the audio signal to map previous voice interactions between the device and users within the environment to the determined room.

12. The non-transitory computer-readable media as recited in claim 7 , wherein the determining that the device is located at the first physical location within the environment comprises determining a room within the environment in which the device resides by analyzing the first portion of the audio signal to map identities of users that have previously interacted with the device to the determined room.

13. The non-transitory computer-readable media as recited in claim 7 , wherein the determining that the device is located at the first physical location within the environment comprises determining a room within the environment in which the device resides based at least in part on a user indicating the room in which the device resides.

14. The non-transitory computer-readable media as recited in claim 7 , wherein the determining that the device is located at the first physical location within the environment comprises determining a room within the environment in which the device resides based at least in part on information indicative of an echo in a second audio signal generated by the microphone unit of the device.

15. The non-transitory computer-readable media as recited in claim 7 , the acts further comprising identifying one or more other devices that are proximate to the device, and wherein the determining that the device is located at the first physical location within the environment comprises determining a room within the environment in which the device resides by mapping the identified one or more other devices to the determined room.

16.

Assignees

• Blanksteen Scott I
• Amazon Tech Inc

Inventors

• Blanksteen Scott I

Classifications

• G06F3/167

  Audio in a user interface, e.g. using voice commands for navigating, audio feedback · CPC title

• G06F3/165

  Management of the audio stream, e.g. setting of volume, audio stream path · CPC title

• G10L2015/223

  Execution procedure of a spoken command · CPC title

• G10L2015/226

  using non-speech characteristics · CPC title

• H04S7/305

  Electronic adaptation of stereophonic audio signals to reverberation of the listening space (H04S7/301 takes precedence) · CPC title