Intelligent audio output devices

Patent metadata

Field	Value
Publication number	US-9685926-B2
Application number	US-201414566525-A
Country	US
Kind code	B2
Filing date	Dec 10, 2014
Priority date	Dec 10, 2014
Publication date	Jun 20, 2017
Grant date	Jun 20, 2017

Abstract

An audio output device may include one or more audio sensors configured to detect ambient sound and noises around the audio output device. The audio output device may include a controller configured to analyze the detected sound and noises and may adjust audio settings of the audio output device accordingly. In an embodiment, the controller may analyze and recognize that the detected noise is another person's attempt to get the user's attention or to talk to the user, such as audio sound of the user's name. In response, the controller may stop the audio output or lower the volume of the audio output.

First claim

What is claimed is:

1. An audio output device comprising:
an audio sensor that detects ambient sound in an environment and an audio occurrence in the environment that deviates from the ambient sound in the environment;
a speaker configured to output audio signals;
a non-transitory memory configured to store a plurality of audio preferences and recognition data for the audio occurrence, wherein one of the plurality of audio preferences comprises a sound profile for an audio setting of the speaker in response to detecting the ambient sound and the audio occurrence, and wherein the recognition data for the audio occurrence is generated based on past audio occurrences occurring with adjustments to audio settings of the speaker; and
a controller configured to:
receive the ambient sound and the audio occurrence from the audio sensor;
access the plurality of audio preferences and the recognition data;
determine the one of the plurality of audio preferences based on the ambient sound and the audio occurrence received from the audio sensor, wherein the one of the plurality of audio preferences is further determined using the audio occurrence with the recognition data;
determine a probability of a user's preference for the one of the plurality of audio references in response to the ambient sound or the audio occurrence; and
adjust the audio settings of the speaker based on the one of the plurality of audio preference when the probability exceeds a threshold.

2. The audio output device of claim 1 , wherein the controller is further configured to:
monitor the adjustments to the audio settings made by the user in response to the ambient sound and the audio occurrence; and
determine user preferences for the audio settings of the speaker for the ambient sound and the audio occurrence based on the adjustments, wherein the user preferences are stored with the recognition data.

3. The audio output device of claim 1 , wherein the controller is further configured to:
determine a similarity score between a detected ambient sound or audio occurrence and a particular ambient sound or audio occurrence designated with a particular audio setting; and
adjust the audio settings of the speaker to the particular audio setting in response to detecting the particular ambient sound or audio occurrence when the similarity score between the detected ambient sound or audio occurrence and the particular ambient sound or audio occurrence exceeds a threshold.

4. The audio output device of claim 1 , wherein the controller is further configured to:
determine that a voice of the user of the audio output device is detected by the audio sensor as the audio occurrence, wherein the one of the plurality of audio preferences lowers a volume level of the speaker in response to detecting the voice of the user.

5. The audio output device of claim 4 , wherein the controller is further configured to:
continue monitoring voices of the user or another user by the audio sensor;
determine when a conversation between the user and the another user ends; and
control the speaker to return to a previous volume level when the conversation ends.

6. The audio output device of claim 1 , wherein the controller is further configured to:
determine that the audio occurrence is a voice of another user calling a name of the user of the audio output device, wherein the one of the plurality of audio preferences lowers a volume level of the speaker in response to the audio occurrence.

7. The audio output device of claim 6 , wherein the controller is further configured to analyze the voice of the another user by voice recognition and natural language processing.

8. The audio output device of claim 1 , wherein the controller is further configured to:
determine that the audio occurrence is a siren and that the ambient sound is the user driving in a vehicle as detected by the audio sensor, and wherein the one of the plurality of audio preferences lowers a volume level of the speaker in response to the audio occurrence and the ambient sound.

9. The audio output device of claim 1 , wherein the controller is further configured to:
determine that the audio occurrence is a doorbell of a house of the user, wherein the one of the plurality of audio preferences lowers a volume level of the speaker in response to the audio occurrence.

10. The audio output device of claim 1 , wherein the controller is further configured to:
determine that the audio occurrence is a phone ring of the user, wherein the one of the plurality of audio preferences lower a volume level of the speaker in response to the audio occurrence.

11. The audio output device of claim 1 , wherein the controller is further configured to:
determine that the ambient sound is that of a public venue, wherein the one of the plurality of audio preferences modify a volume level of the speaker based on a noise level of the public venue.

12. The audio output device of claim 11 , wherein the controller is further configured to increase the volume level of the speaker when the noise level of the public venue increases.

13. The audio output device of claim 12 , wherein the controller is further configured to decrease the volume level of the speaker when a voice associated with a name of the user of the audio output device is detected even when the noise level of the public venue is increased.

14. The audio output device of claim 1 , wherein the ambient sound comprises background noises of a location and the audio occurrence is an audio signal that further deviates from the background noises at the location.

15. A method comprising:
detecting, by an audio sensor of an audio output device, ambient sound in an environment and an audio occurrence in the environment that deviates from the ambient sound in the environment;
accessing, by a controller of the audio output device, a plurality of audio preferences and recognition data for the audio occurrence, wherein one of the plurality of audio preferences comprises a sound profile for an audio setting of the audio output device in response to detecting the ambient sound and the audio occurrence, and wherein the recognition data for the audio occurrence is generated based on past audio occurrences occurring with adjustments to audio settings of the speaker;
determining, by the controller of the audio output device, the one of the plurality of audio preferences based on the ambient and the audio occurrence received from the audio sensor, wherein the one of the plurality of audio preferences is further determined using the audio occurrence with the recognition data;
determining a probability of a user's preference for the one of the plurality of audio preferences in response to the ambient sound or the audio occurrence; and
adjusting, by the controller of the audio output device, the audio settings of the speaker based on the one of the plurality of audio preferences when the probability exceeds a threshold.

16. The method of claim 15 further comprising:
determining, by the controller, that the audio occurrence detected by the audio sensor is a voice of the user of the audio output device, and wherein the one of the plurality of audio preferences decrease, by the controller, a volume level of the speaker in response to the audio occurrence.

17. The method of claim 15 further comprising:
determining, by the controller, that the audio occurrence detected by the audio sensor is a voice of another user calling a name of the user of the audio output device, and wherein the one of the plurality of audio preferences decrease, by the contr

Assignees

• Ebay Inc

Inventors

• Mehta Jigish

Classifications

• H03G3/32 Primary

  the control being dependent upon ambient noise level or sound level · CPC title