METHOD AND DEVICE FOR MOOD DETECTION

• US 20080201370A1
• Filed: 06/18/2007
• Published: 08/21/2008
• Est. Priority Date: 09/04/2006
• Status: Active Grant

• Current Assignee: Sony Deutschland GmbH (Sony Group Corp.)
• Original Assignee: Sony Deutschland GmbH (Sony Group Corp.)
• Inventors: Kemp, Thomas, Tolos-Rigueiro, Marta
• Granted Patent: US 7,921,067 B2
• Time in Patent Office: Days
• US Class Current: 707/104.1
• 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 is proposed, comprising: receiving audio data (1), determining a mood (3) for said audio data (1) based on at least one mood model (8-1, 8-2, 8-3), receiving user feedback (F) of a user for said determined mood (3), said user feedback being indicative as to whether said determined mood (3) corresponds to a perceived mood of said user for said audio data (1), and adapting said mood model (8-1, 8-2, 8-3) based on said user feedback.

Claims

1. Method for mood detection comprising:

receiving audio data (1),

determining a mood (3) for said audio data (1) based on at least one mood model (8-1, 8-2, 8-3),

receiving user feedback (F) of a user for said determined mood (3), said user feedback being indicative as to whether said determined mood (3) corresponds to a perceived mood of said user for said audio data (1), and

adapting said mood model (8-1, 8-2, 8-3) based on said user feedback.

2. Method according to any one of the preceding claims, comprising:

determining new training data for said mood model based on said user feedback (F), and

adapting said mood model based on said new training data.

3. Method according to claim 1 or 2, wherein said adapting comprises modifying said mood model based on said user feedback (F).

4. Method according to claim 2 or 3, wherein said adapting comprises retraining said mood model based on said new training data.

5. Method according to any one of the preceding claims, wherein said adapting comprises transforming said mood model based on said user feedback.

6. Method according to claim 5, wherein for transforming said mood model a linear transformation is applied, which linear transformation is determined based on said new training data.

7. Method according to any one of the preceding claims, wherein said adapting comprises modifying said mood model in dependence of corresponding mood models of other users.

8. Method according to any one of the preceding claims, comprising:

assigning said user to a predetermined group of users,

determining or receiving a union mood model, which corresponds to a mood model for said group of users,

using said union mood model as mood model for determining said mood.

9. Method according to claim 8, wherein said user is assigned to said group of users based on collaborative filtering algorithms.

10. Method according to claim 8 or 9, wherein said group of users comprises or consists of users having a similar taste of music as said user.

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

12. Method according to any one of claims 8 to 11, wherein said group of users comprises or consists of users having similar perception of mood for the same song.

13. Method according to any one of claims 8 to 12, wherein said group of users comprises or consists of users from the same geographic location and/or having the same ethnical background.

14. Method according to any one of the preceding claims, comprising a step of determining or selecting an initial mood model as mood model, which initial mood model corresponds to a mood model of users from the same geographic location and/or having the same ethnical background.

16. Signal processing system, which is capable of performing a method for mood detection according to any one of claims 1 to 14 and/or the steps thereof.

17. Computer program product, comprising computer program means adapted to perform and/or to realize a method of mood detection according to any one of the claims 1 to 14 and/or the steps thereof, when it is executed on a computer, a digital signal processing means, and/or the like.

18. Computer readable storage medium, comprising a computer program product according to claim 17.

15. Device for mood detection, comprising:

receiving means (19) adapted for receiving audio data,

mood classification means (2) for determining a mood for said audio data based on at least one mood model,

feedback means (5) for obtaining user feedback of a user for said determined mood, said user feedback being indicative as to whether said determined mood corresponds to a perceived mood of said user for said audio data, and

mood adaptation means (20) for adapting said mood model based on said user feedback.