Systems and methods for determining content preferences based on vocal utterances and/or movement by a user

• US 9,202,520 B1
• Filed: 10/17/2012
• Issued: 12/01/2015
• Est. Priority Date: 10/17/2012
• Status: Active Grant

• Current Assignee: Amazon Technologies, Inc. (Amazon.com, Inc.)
• Original Assignee: Amazon Technologies, Inc. (Amazon.com, Inc.)
• Inventors: Tang, Joshua K.
• Primary Examiner(s): Rao, Andy
• Assistant Examiner(s): Billah, Masum
• Application Number:
  US13/654,066
• Time in Patent Office: 1,140 Days
• Field of Search: 348/77
• US Class Current: 1/1
• CPC Class Codes: G06V 40/20 Movements or behaviour, e.g. gesture recognition recognition of facial expressions G06V40/16
• CPC Class Codes: G10H 1/0008 Associated control or indicating means
• CPC Class Codes: G10H 2210/056 for extraction or identification of individual instrumental parts, e.g. melody, chords, bass; Identification or separation of instrumental parts by their characteristic voices or timbres
• CPC Class Codes: G10H 2210/071 for rhythm pattern analysis or rhythm style recognition rhythm pattern per se G10H2210/341
• CPC Class Codes: G10H 2210/081 for automatic key or tonality recognition, e.g. using musical rules or a knowledge base
• CPC Class Codes: G10L 15/22 Procedures used during a speech recognition process, e.g. man-machine dialogue
• CPC Class Codes: G10L 15/24 Speech recognition using non-acoustical features
• CPC Class Codes: G10L 2015/227 of the speaker; Human-factor methodology
• CPC Class Codes: G10L 25/63 for estimating an emotional state
• CPC Class Codes: G11B 27/00 Editing; Indexing; Addressing; Timing or synchronising; Monitoring; Measuring tape travel
• CPC Class Codes: G11B 27/102 Programmed access in sequence to addressed parts of tracks of operating record carriers access by moving the head G11B3/08, G11B5/54, G11B7/085, G11B21/022; by moving the record carrier G11B15/005, G11B17/005, by driving of both record carrier and head G11B15/1816
• CPC Class Codes: G11B 27/28 by using information signals recorded by the same method as the main recording G11B27/22 takes precedence

Abstract

This disclosure relates to systems and methods for determining when a user likes a piece of content based, at least in part, on analyzing user responses to the content. In one embodiment, the user'"'"'s response may be monitored by audio and motion detection devices to determine when the user'"'"'s vocals or movements are emulating the content. When the user'"'"'s emulation exceeds a threshold amount the content may be designated as “liked.” In certain instances, a similar piece of content may be selected to play when the current content is finished.

Claims

1. A system, comprising:

at least one memory comprising computer-executable instructions and one or more songs;

at least one accelerometer to detect movement by a user;

at least one camera to capture a plurality of images of the user, the plurality of images used to detect an image movement by the user, wherein the image movement is movement detected by the at least one camera;

at least one microphone to detect a vocal utterance by the user;

at least one processor configured to execute the computer-executable instructions to;

determine a song is playing, the song comprising lyrics, a melody, a tempo, or a rhythm;

detect the movement, the image movement, or the vocal utterance of the user based, at least in part, on the accelerometer, the camera, or the microphone;

determine that the movement, the image movement, or the vocal utterance by the user is synchronized in timing with one or more of the lyrics, the melody, the tempo, or the rhythm;

determine a synchronization amount based, at least in part, on timing synchronization of one or more of the movement, the image movement, or the vocal utterance by the user with one or more of the lyrics, the melody, the tempo, or the rhythm; and

determine that the user likes the song based, at least in part, on a determination that the synchronization amount exceeds a synchronization threshold amount.

2. The system of claim 1, wherein the lyrics comprise one or more words that are sung or spoken in the song and the words are arranged into a vocal melody, and wherein determining that the user likes the song comprises determining that the vocal utterance by the user corresponds to the lyrics based, at least in part, on the vocal utterance comprising one or more words spoken or sung by the user correspond to the lyrics to within a lyric threshold amount or a vocal sound by the user that corresponds to the vocal melody to within another lyric threshold amount.

3. The system of claim 1, wherein:

the movement comprises leg movement, arm movement, torso movement, or head movement; and

the image movement comprises the leg movement, the arm movement, the torso movement, or the head movement.

4. The system of claim 1, wherein the melody comprises instrumental tones arranged in a pattern, and wherein determining that the user likes the song comprises determining that the vocal utterance by the user corresponds to the melody based, at least in part, on the vocal utterance comprising a vocal sound by the user that corresponds to the melody to within a melody threshold amount.

5. The system of claim 1, wherein the tempo comprises a pace of the song measured in a unit of time, and wherein determining that the user likes the song comprises determining that the vocal utterance by the user corresponds to the tempo based, at least in part, on the vocal utterance comprising a vocal sound by the user that corresponds to the tempo to within a tempo threshold amount.

6. The system of claim 1, wherein the rhythm comprises a patterned reoccurrence of a beat within the song, and wherein determining that the user likes the song comprises determining that the vocal utterance by the user corresponds to the rhythm based, at least in part, on the vocal utterance comprising a vocal sound by the user that corresponds to the rhythm within a rhythm threshold amount.

7. The system of claim 1, wherein determining that the user likes the song comprises determining that the movement by the user corresponds to the tempo based, at least in part, on the movement or the image movement corresponding to the tempo to within a tempo movement threshold amount.

8. The system of claim 1, wherein determining that the user likes the song comprises determining that the movement or the image movement by the user corresponds to the rhythm based, at least in part, on the movement or the image movement corresponding to the rhythm to within a rhythm movement threshold amount.

9. The system of claim 1, further comprising computer-executable instructions to determine an accuracy of the correspondence to the song, a quantity of the correspondence to the song, or an intensity of the correspondence to the song.

10. The system of claim 9, wherein the accuracy for the vocal utterance is based, at least in part, on one or more words that are spoken or sung in the song that correspond to the vocal utterance by the user.

11. The system of claim 9, wherein the quantity of the vocal utterance is based, at least in part, on an amount of words that are spoken or sung in the song that correspond to the vocal utterance by the user.

12. The system of claim 9, wherein the intensity of the vocal utterance is based, at least in part, on a decibel level of the vocal utterance by the user.

13. The system of claim 9, wherein the accuracy for the movement or the image movement is based, at least in part, on, the movement or the image movement corresponding to the tempo or the rhythm.

14. The system of claim 1 wherein the quantity of the movement or the image movement is based, at least in part, on how long the movement or the image movement corresponds to the tempo or the rhythm.

15. The system of claim 9, wherein the intensity of the movement is based, at least in part, on an amount of force measured by the accelerometer during the movement or the intensity of the image movement is based, at least in part, on an amount of movement detected in the plurality of images.

16. The system of claim 1, further comprising the computer-executable instructions to select another song that is similar to the song based, at least in part, on artist, genre, song tempo, or song rhythm when the accuracy, quantity, or intensity determinations exceed a ranking threshold amount.

17. A system, comprising:

at least one memory comprising computer-executable instructions and one or more songs;

at least one response detection device to detect sound or movement generated by a user;

at least one processor configured to execute the computer-executable instructions to;

determine a song is playing;

determine a user response to the song based, at least in part, on analysis of information obtained from the response detection device;

determine that the user response is synchronized in timing with one or more components of the song; and

determine the user likes the song based, at least in part, on an amount of synchronization between the user response and one or more audio characteristics associated with the song.

18. The system of claim 17, wherein the audio characteristics associated with the song comprising lyrics, a melody, a tempo, or a rhythm.

19. The system of claim 17, wherein the amount of synchronization is based, at least in part, on the user vocalizing the lyrics of the song for at least a threshold amount.

20. The system of claim 17, wherein the amount of synchronization is based, at least in part, on:

the user vocalizing at the tempo of the song for at least a threshold amount, or

moving a body part at the tempo of the song for at least another threshold amount.

21. The system of claim 17, wherein the amount of synchronization is based, at least in part, on:

the user vocalizing the rhythm of the song for at least a threshold amount, or

the user moving a body part at the rhythm of the song for at least another threshold amount.

22. The system of claim 17, wherein the amount of synchronization is based, at least in part, on:

the user vocalizing the melody of the song for at least a threshold amount;

or

the user moving a body part to the rhythm of the song for at least another threshold amount.

23. The system of claim 17, wherein the response detection device comprises a microphone, an accelerometer, or a camera.

24. The system of claim 17, wherein the user liking the song further comprises determining an intensity of the user response, the intensity being measured in decibels by the microphone, force by the accelerometer, or the user'"'"'s body movement measured by the camera.

25. The system of claim 17, further comprising computer-executable instructions to select another song that is similar to the song when the user likes the song.

26. A method comprising:

determining, using a processor, a song is playing, the song comprising lyrics, a melody, a tempo, or a rhythm;

determining a user response to the song using a vocal detection device that detects user vocal utterances;

determining the user vocal utterances are synchronized in timing with the melody, the tempo, or the rhythm;

determining a synchronization amount based, at least in part, on timing synchronization of the user vocal utterances with one or more of the melody, the tempo, or the rhythm; and

selecting, in response to determining that the synchronization amount exceeds a synchronization threshold amount, another song that is similar to the song.

27. The method of claim 26, wherein the user vocal utterances comprise singing, speaking, humming, or vocal percussion.

28. The method of claim 26, wherein the speaking comprises an indication of a positive comment about the song.

29. The method of claim 26, wherein the user vocal utterances are based, at least in part, on:

determining the user is vocalizing a chorus of the song;

determining the user is vocalizing a verse of the song;

or

determining the user is vocalizing the chorus and the verse of the song.

30. The method of claim 29, wherein exceeding the threshold amount is based, at least in part, on the user vocal utterances comprising the chorus or the verse of the song.

31. One or more non-transitory computer-readable media storing computer-executable instructions that, when executed by at least one processor, configure the at least one processor to perform operations comprising:

determining, using a processor, a song is playing, the song comprising lyrics, a melody, a tempo, or a rhythm;

determining a user response to the song using a motion detection device that detects user movements;

determining the user movements are synchronized in timing with the lyrics, the melody, the tempo, or the rhythm by at least a threshold amount;

determining a synchronization amount based, at least in part, on timing synchronization of the user movements with one or more of the lyrics, the melody, the tempo, or the rhythm; and

selecting, in response to determining that the synchronization amount exceeds a synchronization threshold amount, another song that is similar to the song.