Method and device for mood detection

• US 7,921,067 B2
• Filed: 06/18/2007
• Issued: 04/05/2011
• Est. Priority Date: 09/04/2006
• Status: Expired due to Fees

• Current Assignee: Sony Deutschland GmbH (Sony Group Corp.)
• Original Assignee: Sony Deutschland GmbH (Sony Group Corp.)
• Inventors: Tolos-Rigueiro, Marta, Kemp, Thomas
• Primary Examiner(s): Holmes; Michael B.
• Assistant Examiner(s): Kim; David H
• Application Number:
  US11/764,617
• Publication Number:
  US 20080201370A1
• Time in Patent Office: 1,387 Days
• Field of Search: 706/25, 706/11, 706/14, 706/20, 706/45, 846/00, 846/11, 846/09, 846/12, 846/16, 846/68, 707/999.005, 707/734
• US Class Current: 706/14
• CPC Class Codes: G06F 16/40 of multimedia data, e.g. slideshows comprising image and additional audio data retrieval of still image data G06F16/50; retrieval of audio data G06F16/60; retrieval of video data G06F16/70
• CPC Class Codes: G06F 16/634 Query by example, e.g. query by humming
• 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: G06F 16/687 using geographical or spatial information, e.g. location
• CPC Class Codes: G10H 1/0008 Associated control or indicating means
• CPC Class Codes: G10H 2240/085 Mood, i.e. generation, detection or selection of a particular emotional content or atmosphere in a musical piece
• CPC Class Codes: G11B 27/105 of operating discs

Abstract

A method for mood detection, comprising receiving audio data, determining a mood for the audio data based on at least one mood model, receiving user feedback of a user for the determined mood, the user feedback being on a gradual scale and indicative as to whether the determined mood corresponds to a perceived mood of the user for the audio data, and adapting the mood model based on the user feedback.

Claims

1. A method for mood detection using a mood detection device having a processor comprising:

receiving audio data;

assigning a user to a predetermined group of users;

determining, using the mood detection device, a mood for said audio data based on at least one mood model, wherein said determining includes determining or receiving a union mood model, which corresponds to a mood model for said predetermined group of users, and using said union mood model as mood model for determining said mood;

communicating the determined mood to the user;

thereafter, receiving user feedback of the user for said determined mood, said user feedback being on a gradual scale and indicative as to whether said determined mood corresponds to a perceived mood of said user for said audio data; and

adapting said mood model based on said user feedback.

2. The method according to claim 1, further comprising:

determining new training data for said mood model based on said user feedback; and

adapting said mood model based on said new training data.

3. The method according to claim 1, wherein said adapting comprises modifying said mood model based on said user feedback.

4. The method according to claim 2, wherein said adapting comprises re-training said mood model based on said new training data.

5. The method according to claim 1, wherein said adapting comprises transforming said mood model based on said user feedback.

6. The method according to claim 5, wherein said transforming said mood model comprises applying a linear transformation, wherein said linear transformation is determined based on said new training data.

7. The method according to claim 1, wherein said adapting comprises modifying said mood model according to corresponding mood models of other users.

8. The method according to claim 1, wherein said user is assigned to said predetermined group of users based on collaborative filtering algorithms.

9. The method according to claim 1, wherein said predetermined group of users comprises of users having a similar taste of music as said user.

10. The method according to claim 9, wherein said similar taste is determined by comparing a music collection of said user with music collections of other users of said predetermined group of users.

11. The method according to claim 1, wherein said predetermined group of users comprises or consists of users having similar perception of mood for a song.

12. The method according to claim 1, wherein said predetermined group of users comprises or consists of users from a same geographic location and/or having a same ethnic background.

13. The method according to claim 1, further comprising determining or selecting an initial mood model as mood model, said initial mood model corresponding to a mood model of users from a same geographic location and/or having a same ethnic background.

14. A device for mood detection, comprising:

receiving means for receiving audio data;

assigning means for assigning a user to a predetermined group of users;

mood classification means for determining a mood for said audio data based on at least one mood model, wherein determining includes determining or receiving a union mood model, which corresponds to a mood model for said predetermined group of users, and using said union mood model as mood model for determining said mood;

communication means for communicating said determined mood to the user;

feedback means for thereafter obtaining user feedback of said user for said determined mood, said user feedback being on a gradual scale and indicative as to whether said determined mood corresponds to a perceived mood of said user for said audio data; and

mood adaptation means for adapting said mood model based on said user feedback.

15. A non-transitory computer readable storage medium having encoded thereon a program that, when executed on a computer, causes the computer to perform a method of mood detection comprising:

receiving audio data;

assigning a user to a predetermined group of users;

determining a mood for said audio data based on at least one mood model, wherein the determining includes determining or receiving a union mood model, which corresponds to a mood model for said predetermined group of users, and using said union mood model as mood model for determining said mood;

communicating the determined mood to the user;

thereafter, receiving user feedback of the user for said determined mood, said user feedback being on a gradual scale and indicative as to whether said determined mood corresponds to a perceived mood of said user for said audio data; and

adapting said mood model based on said user feedback.

16. A system for mood detection, comprising:

a receiving device configured to receive audio data;

an assigning device configured to assign a user to a predetermined group of users;

a mood classification device configured to determine a mood for said audio data based on at least one mood model by determining or receiving a union mood model, which corresponds to a mood model for said predetermined group of users, and using said union mood model as mood model for determining said mood;

a communication device configured to communicate said determined mood to a user;

a feedback device configured to thereafter obtain user feedback of said user for said determined mood, said user feedback being on a gradual scale and indicative as to whether said determined mood corresponds to a perceived mood of said user for said audio data; and

a mood adaptation device configured to adapt said mood model based on said user feedback.