Method for creating a database for comparing music

• US 6,539,395 B1
• Filed: 03/22/2000
• Issued: 03/25/2003
• Est. Priority Date: 03/22/2000
• Status: Expired due to Term

• Current Assignee: Rovi Technologies Corporation (Adeia Inc.)
• Original Assignee: MOOD Logic Incorporated
• Inventors: Khan, Rehan M., Sulzer, Thomas R., Mathys, Marc, Pirkner, Christian D., Gjerdingen, Robert O., Rice, Pete W.
• Primary Examiner(s): AMSBURY, WAYNE P
• Application Number:
  US09/533,045
• Time in Patent Office: 1,098 Days
• Field of Search: 707/6, 707/102
• US Class Current: 1/1
• CPC Class Codes: G06F 16/635 Filtering based on additional data, e.g. user or group profiles
• CPC Class Codes: G06F 16/68 Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually
• CPC Class Codes: G06F 16/683 using metadata automatically derived from the content
• CPC Class Codes: G10H 2240/081 Genre classification, i.e. descriptive metadata for classification or selection of musical pieces according to style
• CPC Class Codes: G10H 2240/155 Library update, i.e. making or modifying a musical database using musical parameters as indices
• CPC Class Codes: Y10S 707/99936 Pattern matching access
• CPC Class Codes: Y10S 707/99943 Generating database or data structure, e.g. via user interface

Abstract

A method for creating a database that allows content based searching in the music domain is provided. The process provides music samples to music listeners, wherein the music listeners include a plurality of average music listeners and a plurality of expert music listeners. The process further provides a plurality of questions to the average music listeners and the expert music listeners; wherein the plurality of questions require a listener response and every listener response assigns a value to a feature vector, wherein the feature vector defines a music attribute. The process then compares the plurality of music samples, wherein comparing the feature vectors compares the music sample. Thereafter, the process stores the compared data.

Claims

1. A method for creating a database that allows content based searching in the music domain, comprising:

providing music samples to music listeners, wherein the music listeners include a plurality of average music listeners and a plurality of expert music listeners;

providing a plurality of questions to the average music listeners and the expert music listeners;

wherein the plurality of questions require a listener response and every listener response assigns a value to a feature vector, wherein the feature vector defines a music attribute; and

comparing the plurality of music samples, wherein the music sample is compared by comparing the feature vectors.

2. The method of claim 1, further comprising:

storing the compared music samples in a production database.

3. The method of claim 1, wherein the plurality of average music listeners are asked a plurality of questions and the music listeners response to the questions defines an emotional quality vector, wherein the emotional quality vector is based upon the music listener'"'"'s response indicating that the music sample is Intense, Happy, Sad, Mellow, Romantic, Heartbreaking, Aggressive, or Upbeat.

4. The method of claim 1, wherein the plurality of average music listeners are asked a plurality of questions and the response to the questions defines a vocal vector, wherein the vocal vector is based upon the music listener'"'"'s response indicating that the music sample includes a Sexy voice, a Smooth voice, a Powerful voice, a Great voice, or a Soulful voice.

5. The method of claim 1, wherein the plurality of

average music listeners are asked a plurality of questions and the response to the questions defines a sound quality vector, wherein the sound quality vector is based upon the music listener'"'"'s response indicating if the music has a, Strong beat, or is Simple, or has a good groove, or is Fast, or is speech like, or emphasizes a melody.

6. The method of claim 1, wherein the plurality of

average music listeners are asked a plurality of questions and the response defines a situational quality vector, wherein the situational quality vector is based on the music listener'"'"'s response indicating if the music sample is, good for a workout, a shopping mall, a dinner party, a dance party, for slow dancing, or for studying.

7. The method of claim 1, wherein the plurality of expert music listeners are asked a plurality of questions and the response to the questions defines a genre vector, wherein genre vector depends the expert listener'"'"'s response to the questions indicating if the music sample belongs to a plurality of genres including, Alternative, Blues, Country, Electronic/Dance, Folk, Gospel, Jazz, Latin, New Age, R&

B, Soul, Rap, Hip-Hop, Reggae, Rock or others.

8. The method of claim 1, wherein the plurality of expert music listeners are asked a plurality questions and the response to the questions defines an ensemble vector, wherein the ensemble vector depends upon the experts listener'"'"'s response indicating whether the music sample is a female solo, male solo, female duet, male duet, mixed duet, female group, male group or instrumental.

9. The method of claim 1, wherein the plurality of expert music listeners are asked a plurality of questions and the response to the questions defines an instrument vector, wherein the instrument vector depends upon the experts listener'"'"'s response indicating whether the music sample is includes an acoustic guitar, electric guitar, bass, drums, harmonica, organ, piano, synthesizer, horn, or saxophone.

10. The method of claim 1, wherein the music samples to the music listeners and expert listeners are provided over the Internet.

11. A computer-readable medium storing computer-executable process steps of a process for use in a computer system for creating a database that allows content based music searching, comprising of:

providing music samples to music listeners, wherein the music listeners includes a plurality of average music listeners and a plurality of expert music listeners;

providing a plurality of questions to the average music listeners and the expert music listeners;

wherein the plurality of questions require a listener response and every listener response assigns a value to a feature vector, wherein the feature vector defines a music attribute; and

comparing the plurality of music samples, wherein the music sample is compared by comparing the feature vectors.

12. The computer readable medium of claim 11, further comprising:

storing the compared music samples in a database.

13. The computer readable medium of claim 11, wherein the plurality of average music listeners are asked a plurality of questions and the music listeners response to the questions defines an emotional quality vector, wherein the emotional quality vector is based upon the music listener'"'"'s response indicating the music sample is Intense, Happy, Sad, Mellow, Romantic, Heartbreaking, Aggressive, or Upbeat.

14. The computer readable medium of claim 11, wherein the plurality of average music listeners are asked a plurality of questions and the response to the questions defines a vocal vector, wherein the vocal vector is based upon the music listener'"'"'s response indicating that the music sample includes a Sexy voice, a Smooth voice, a Powerful voice, a Great voice, or a Soulful voice.

15. The computer readable medium of claim 11, wherein the plurality of average music listeners are asked a plurality of questions and the response to the questions defines a sound quality vector, wherein the sound quality vector is based upon the music listener'"'"'s response indicating if the music has a, Strong beat, or is Simple, or has a good groove, or is Fast, or is speech like, or emphasizes a melody.

16. The computer readable medium of claim 11, wherein the plurality of average music listeners are asked a plurality of questions and the response defines a situational quality vector, wherein the situational quality vector is based on the music listener'"'"'s response indicating if the music sample is, good for a workout, a shopping mall, a dinner party, a dance party, for slow dancing, or for studying.

17. The computer readable medium of claim 11, wherein the plurality of expert music listeners are asked a plurality of questions and the response to the questions defines a genre vector, wherein genre vector depends the expert listener'"'"'s response to the questions indicating if the music sample belongs to a plurality of genres including, Alternative, Blues, Country, Electronic/Dance, Folk, Gospel, Jazz, Latin, New Age, R&

B, Soul, Rap, Hip-Hop, Reggae, Rock or others.

18. The computer readable medium of claim 11, wherein the plurality of expert music listeners are asked a plurality questions and the response to the questions defines an ensemble vector, wherein the ensemble vector depends upon the experts listener'"'"'s response indicating whether the music sample is a female solo, male solo, female duet, male duet, mixed duet, female group, male group or instrumental.

19. The computer readable medium of claim 11, wherein the plurality of expert music listeners are asked a plurality of questions and the response to the questions defines an instrument vector, wherein the instrument vector depends upon the experts listener'"'"'s response indicating whether the music sample is includes an acoustic guitar, electric guitar, bass, drums, harmonica, organ, piano, synthesizer, horn, or saxophone.

20. The computer readable medium of claim 11, wherein

the music samples to the music listeners and expert listeners are provided over the Internet.