CONVERSATIONAL AUDIO ASSISTANT

• US 20190035397A1
• Filed: 07/30/2018
• Published: 01/31/2019
• Est. Priority Date: 07/31/2017
• Status: Active Grant

• Current Assignee: Bose Corporation
• Original Assignee: Bose Corporation
• Inventors: Reily, Todd Richard, Martin, Keith Dana, Hostage, Christine M., Batlle-Rafferty, Lya, Sheehan, Conor William, Geiger, Joseph M., Querze, Elio Dante, Carbonell, Ruben M., Bard, Curtis, Khanwalkar, Saurabh
• Granted Patent: US 10,657,965 B2
• Time in Patent Office: Days
• CPC Class Codes: G06F 16/632 Query formulation
• CPC Class Codes: G06F 16/635 Filtering based on additional data, e.g. user or group profiles
• CPC Class Codes: G06F 16/638 Presentation of query results
• CPC Class Codes: G06F 3/165 Management of the audio stream, e.g. setting of volume, audio stream path
• CPC Class Codes: G06F 3/167 Audio in a user interface, e.g. using voice commands for navigating, audio feedback
• CPC Class Codes: G06F 40/279 Recognition of textual entities
• CPC Class Codes: G06F 40/35 Discourse or dialogue representation
• CPC Class Codes: G10L 15/1815 Semantic context, e.g. disambiguation of the recognition hypotheses based on word meaning
• CPC Class Codes: G10L 15/22 Procedures used during a speech recognition process, e.g. man-machine dialogue
• CPC Class Codes: G10L 15/30 Distributed recognition, e.g. in client-server systems, for mobile phones or network applications
• CPC Class Codes: G10L 2015/223 Execution procedure of a spoken command

Abstract

Various implementations include audio systems for controlling audio feedback to user requests. In some particular cases, a headphone system includes at least one headphone including an acoustic transducer having a sound-radiating surface for providing an audio output; at least one microphone for receiving an audio input from a user; and a control system including a recommendation engine, the control system coupled with the at least one headphone and the at least one microphone, the recommendation engine configured to: analyze the audio input for a non-specific request from the user; and provide an audio sample to the user along with a prompt for feedback about the audio sample in response to the non-specific request.

Claims

1. A speaker system comprising:

at least one speaker including an acoustic transducer having a sound-radiating surface for providing an audio output;

at least one microphone for receiving an audio input from a user; and

a control system including a recommendation engine, the control system coupled with the at least one speaker and the at least one microphone, the recommendation engine configured to;

analyze the audio input for a non-specific request from the user; and

provide an audio sample to the user along with a prompt for feedback about the audio sample in response to the non-specific request.

2. The speaker system of claim 1, wherein the non-specific request includes at least one syntactically ambiguous clause.

3. The speaker system of claim 1, wherein the non-specific request includes a request to play a style of music or an open-ended query for a music recommendation.

4. The speaker system of claim 1, wherein the recommendation engine is further configured to:

receive negative feedback from the user about the audio sample; and

provide an additional audio sample to the user along with an additional prompt for feedback about the additional audio sample in response to receiving the negative feedback.

5. The speaker system of claim 4, wherein the negative feedback includes an audio input from the user or a response to an interface prompt.

6. The speaker system of claim 1, wherein the recommendation engine is further configured to:

receive positive feedback from the user about the audio sample; and

continue an audio feed of the audio sample in response to receiving the positive feedback from the user about the audio sample.

7. The speaker system of claim 6, wherein the positive feedback includes an audio input from the user, a response to an interface prompt or a null response.

8. The speaker system of claim 1, wherein the prompt for feedback is provided to the user without an intervening audio input prompt from the user.

9. The speaker system of claim 1, wherein the control system maintains the at least one microphone in a query mode during the providing of the audio sample.

10. The speaker system of claim 1, wherein the recommendation engine is further coupled with a profile system including a user profile for the user, and the recommendation engine is further configured to determine a type of the audio sample based upon the user profile.

11. The speaker system of claim 10, wherein the profile system is located in one of a local server or a cloud-based server.

12. The speaker system of claim 1, wherein the audio sample is provided through the at least one speaker at a decibel level ranging between approximately 50-70 decibels (dB).

13. The speaker system of claim 12, wherein the prompt is provided at an approximately equal or greater volume to the user than the audio sample.

14. The speaker system of claim 1, further comprising a sensor system coupled with the control system, the sensor system configured to detect an environmental condition proximate the at least one speaker, wherein the recommendation engine is further configured to:

receive data about the environmental condition from the sensor system; and

determine a type of the audio sample based at least in part upon the environmental condition.

15. The speaker system of claim 1, wherein the recommendation engine further selects the audio sample based upon at least one of:

a syntax of the non-specific request from the user, a profile of the user, a demographic profile of a plurality of users with at least one common attribute with the user or a categorical popularity of the audio sample.

16. The speaker system of claim 1, wherein the recommendation engine is further configured to provide an explanation for selection of the audio sample in response to receiving one of positive feedback from the user about the audio sample or negative feedback from the user about the audio sample.

17. The speaker system of claim 1, wherein the non-specific request includes a request for an audio output associated with at least one other user, and wherein the recommendation engine selects the audio sample based upon profile data or activity data about the at least one other user.

18. The speaker system of claim 17, wherein the user profile data includes demographic data about the at least one other user, and the activity data includes audio preferences associated with the at least one other user.

19. A computer-implemented method of controlling an audio system configured to provide an audio output, the method comprising:

analyzing an audio input for a non-specific request from a user; and

providing an audio sample to the user along with a prompt for feedback about the audio sample in response to the non-specific request.

20. The method of claim 19, further comprising:

receiving negative feedback from the user about the audio sample; and

providing an additional audio sample to the user along with an additional prompt for feedback about the additional audio sample in response to receiving the negative feedback.

21. The method of claim 19, wherein the audio system includes at least one microphone for receiving an audio input from the user, the method further comprising maintaining the at least one microphone in a query mode during the providing of the audio sample.