Refining media playback

• US 10,318,236 B1
• Filed: 05/05/2016
• Issued: 06/11/2019
• Est. Priority Date: 05/05/2016
• Status: Active Grant

• Current Assignee: Amazon Technologies, Inc. (Amazon.com, Inc.)
• Original Assignee: Amazon Technologies, Inc. (Amazon.com, Inc.)
• Inventors: Pal, Rickesh, Brahmbhatt, Kintan Dilipkumar, Durham, Brandon Scott, Feinstein, Jonathan Barnett, Paik, Yun Suk, Ryan, Daniel Paul
• Primary Examiner(s): Tsang, Fan S
• Assistant Examiner(s): Siegel, David
• Application Number:
  US15/147,191
• Time in Patent Office: 1,132 Days
• CPC Class Codes: G06F 3/167 Audio in a user interface, e.g. using voice commands for navigating, audio feedback
• CPC Class Codes: G06F 40/30 Semantic analysis
• CPC Class Codes: G06F 40/56 Natural language generation
• CPC Class Codes: G10L 15/22 Procedures used during a speech recognition process, e.g. man-machine dialogue
• CPC Class Codes: G10L 17/00 Speaker identification or verification techniques
• CPC Class Codes: G10L 2015/088 Word spotting
• CPC Class Codes: G10L 2015/223 Execution procedure of a spoken command

Abstract

Approaches provide for using a voice communications device to control, refine, or otherwise manage the playback of media content in response to a spoken instruction. For example, the voice communications device can receive a request to refine and/or initiate the playback of media content, such as music, news, audio books, audio broadcasts, and other such content. Audio input data that includes the request can be received by the voice communications device and an application executing on the voice communications device or otherwise in communication with the voice communications device can analyze the audio input data to determine how to carry out the request. The application can determine whether there is an active play queue of media content configured to play using the voice communications device. In the situation where there is no media content being played using the voice communications device, the application can determine media content using information in the request. In the situation where there is an active play queue of media content, the information can be used to refine the play queue. Thereafter, the application can cause the media content associated with the active play queue to play using the voice-enable communications device.

Claims

1. A computing system, comprising:

a device processor;

a memory device including instructions that, when executed by the device processor, cause the computing system to;

receive audio input data from a voice communications device, the audio input data corresponding to an utterance received by a microphone of the voice communications device;

generate text data from the audio input data by performing automated speech recognition on the audio input data;

determine queue refinement information by performing natural language processing on the text data, the queue refinement information used to modify an active play queue using music from a catalog of music;

determine an active state of the active play queue;

analyze attributes associated with music in the catalog of music using the queue refinement information, the attributes being stored in a data store, wherein the attributes are correlated, via a calculated value, with the music in the catalog of music, the calculated value based at least in part on properties of the music, personal user preferences, and a user profile, to generate an updated active play queue by determining music from the catalog of music having attributes corresponding to the queue refinement information, when the calculated value is greater than a threshold amount, to include in the active play queue and music to remove from the active play queue; and

cause the updated active play queue to be played using the voice communications device.

2. The computing system of claim 1, wherein the instructions, when executed further enable the computing system to:

identify a list of queue refinements that includes one or more queue refinements;

use automatic speech recognition (ASR) techniques on the audio input data to generate the text data that represents words;

use natural language understanding (NLU) techniques on the text data to identify a queue refinement; and

analyze the list of queue refinements to identify the queue refinement as one of the one or more queue refinements.

3. The computing system of claim 1, wherein the instructions, when executed further enable the computing system to:

identify music in the catalog of music associated with the queue refinement information;

remove music from the active play queue that is not associated with the queue refinement information; and

add music from the catalog of music that is associated with the queue refinement information.

4. The computing system of claim 1, wherein the instructions, when executed further enable the computing system to:

analyze the catalog of music to determine a feature associated with music of the catalog of music; and

map a queue refinement of a list of queue refinements to the feature.

5. A computing system, comprising:

a computing device processor;

a memory device including instructions that, when executed by the computing device processor, enable the computing system to;

receive audio input data from a computing device that is associated with a customer account;

generate text data based at least in part on the audio input data;

determine an attribute associated with a type of media content based at least in part on the audio input data;

analyze a set of media content using the attribute, the attribute being correlated to the media content via a calculated value determined at least in part on properties of media content of the set of media content, personal user preferences, and a user profile, wherein the attribute and respective correlation to the media content is stored within an accessible data store, to determine a subset of media content of the set of media content associated with the type of media content having the calculated value that is above a threshold amount; and

enable the subset of media content to be played using the computing device.

6. The computing system of claim 5, wherein the type of media content includes one of music, songs, music playlists, audio books, news information, weather information, events information, restaurant information, or movie information.

7. The computing system of claim 5, wherein the instructions, when executed further enable the computing system to:

identify a list of attributes that includes one or more attributes;

use automatic speech recognition (ASR) techniques on the audio input data to generate the text data that represents words;

use natural language understanding (NLU) techniques on the text data to identify an attribute; and

analyze the list of attributes to identify the attribute as one of the one or more attributes.

8. The computing system of claim 7, wherein the list of attributes are used to identify similar media content, media content associated with a mood, a tempo, a genre, an artist, a year, a decade, an activity, or a relevance value.

9. The computing system of claim 5, wherein the attribute is used to refine a queue of music tracks, and wherein the instructions, when executed further enable the computing system to:

determine an active play queue of music configured to play using the computing device;

identify music included in the active play queue of music associated with the attribute; and

remove music from the active play queue of music that is not associated with the attribute.

10. The computing system of claim 9, wherein the instructions, when executed further enable the computing system to:

determine an active play queue of music is not playing; and

cause the computing device to recommend tracks of music based at least in part on the attribute.

11. The computing system of claim 5, wherein the subset of media content is determined based at least in part on a plurality of attributes included in the audio input data.

12. The computing system of claim 5, wherein the set of media content includes at least one of an active play queue of media content or a catalog of media content.

13. The computing system of claim 5, wherein the instructions, when executed further enable the computing system to:

identify media content in the set of media content associated with the attribute; and

remove media content from the set of media content that is not associated with the attribute.

14. The computing system of claim 13, wherein the instructions, when executed further enable the computing system to:

analyze a catalog of media content using the attribute, and

add media content from the catalog of media content associated with the attribute to the set of media content.

15. The computing system of claim 5, wherein the instructions, when executed further enable the computing system to:

identify a catalog of media content associated with a media type;

analyze the catalog of media content to determine a feature associated with respective media content of the catalog of media content; and

map at least one attribute of a list of attributes to a feature associated with media content of the catalog of media content.

16. The computing system of claim 5, wherein the instructions, when executed further enable the computing system to:

receive additional audio input from the computing device;

analyze the additional audio input to identify an additional attribute; and

analyze the subset of media content using the additional attribute to determine one or more media content to be played using the computing device.

17. A method, comprising:

receiving audio input data from a computing device that is associated with a customer account;

generating text data based at least in part on the audio input data by applying automatic speech recognition (ASR) techniques on the audio input data;

determining an attribute associated with a type of media content based at least in part on the audio input data;

analyzing a set of media content using the attribute, the attribute being correlated to the media content via a calculated value determined at least in part on properties of media content of the set of media content, personal user preferences, and a user profile, wherein the attribute and respective correlation to the media content is stored within an accessible data store, to determine a subset of media content of the set of media content associated with the type of media content having the calculated value that is above a threshold amount; and

enabling the subset of media content to be played using the computing device.

18. The method of claim 17, further including:

identifying a list of attributes that includes one or more attributes;

using natural language understanding (NLU) techniques on the text data to identify an attribute; and

analyzing the list of attributes to identify the attribute as one of the one or more attributes.

19. The method of claim 17, wherein the attribute is used to refine a queue of music tracks, the method further comprising:

determining an active play queue of music configured to play using the computing device;

identifying music included in the active play queue of music associated with the attribute; and

removing music from the active play queue of music that is not associated with the attribute.

20. The method of claim 17, further comprising:

receiving additional audio input from the computing device;

analyzing the additional audio input to identify an additional attribute; and

analyzing the subset of media content using the additional attribute to determine one or more media content to be played using the computing device.