System and methods for providing automatic classification of media entities according to melodic movement properties

• US 7,574,276 B2
• Filed: 12/21/2005
• Issued: 08/11/2009
• Est. Priority Date: 08/29/2001
• Status: Expired due to Fees

• Current Assignee: Microsoft Technology Licensing LLC (Microsoft Corporation)
• Original Assignee: Microsoft Corporation
• Inventors: Weare, Christopher B., Hoekman, Jeffrey S.
• Primary Examiner(s): Kuntz; Curtis
• Assistant Examiner(s): Flanders; Andrew C
• Application Number:
  US11/316,047
• Publication Number:
  US 20060096447A1
• Time in Patent Office: 1,329 Days
• Field of Search: 700/94, 381/58, 381/56, 84600-606, 84609-612, 84615-618, 84634-636, 84649-656, 84666-668, 707/1, 707/2, 707/4
• US Class Current: 700/94
• 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 16/639 using playlists
• CPC Class Codes: G06F 16/683 using metadata automatically derived from the content

Abstract

In connection with a classification system for classifying media entities that merges perceptual classification techniques and digital signal processing classification techniques for improved classification of media entities, a system and methods are provided for automatically classifying and characterizing melodic movement properties of media entities. Such a system and methods may be useful for the indexing of a database or other storage collection of media entities, such as media entities that are audio files, or have portions that are audio files. The methods also help to determine media entities that have similar, or dissimilar as a request may indicate, melodic movement by utilizing classification chain techniques that test distances between media entities in terms of their properties. For example, a neighborhood of songs may be determined within which each song has similar melodic movement properties.

Claims

1. A computer implemented method for classifying songs according to melodic movement properties of the songs, comprising:

assigning, by a user, a plurality of songs to at least one melodic movement class, wherein the assigning is based on the user'"'"'s perceptually observed relevant melodic properties of the songs, wherein the melodic properties are associated with at least one of said melodic movement classes, respectively;

processing, by computer implemented digital signal processing techniques, each of said plurality of songs to extract at least one melodic movement characteristic based on the digital signal processing of each song of said plurality of songs;

generating a melodic movement properties vector for each song of said plurality of songs, wherein each melodic movement properties vector includes said at least one melodic movement class, as assigned by the user, and said at least one melodic movement characteristic, as determined by the computer;

forming a classification chain data structure corresponding to the plurality of songs based upon the plurality of melodic movement properties vectors generated for the plurality of songs, respectively; and

storing the classification chain in a user accessible memory,

processing an unclassified song other than the plurality of songs to extract at least one melodic movement characteristic based on digital signal processing of the unclassified song;

generating a vector for the unclassified song including said at least one melodic movement characteristic;

presenting the vector for the unclassified song to the classification chain data structure; and

classifying the unclassified song with an estimate of the melodic movement class by calculating the representative melodic movement characteristic of the subset of the plurality of vectors of the classification chain located in a neighborhood of the vector for the unclassified song in a classification chain space.

2. A method according to claim 1, further including calculating a neighborhood distance that defines a distance within which two vectors in the classification chain space are in the same neighborhood for purposes of being in the same melodic movement class.

3. A method according to claim 1, wherein said classifying of the unclassified song includes classifying the unclassified song with a median melodic movement class represented by the neighborhood.

4. A method according to claim 1, wherein said melodic movement class is described by a numerical value and said classifying of the unclassified song includes classifying the unclassified song with a mean of numerical melodic movement properties values found in the neighborhood.

5. A method according to claim 1, wherein said classifying includes returning at least one number indicating a level of confidence of the melodic movement class estimate.

6. The method of claim 1, wherein the classification chain data structure is an array of the melodic movement properties vectors.

7. The method of claim 1, wherein the classification chain data structure is a list of the melodic movement properties vectors.

8. A computer implemented system for classifying songs according to melodic movement properties of the songs, comprising:

a computer readable medium with a classification chain data structure stored thereon comprising a plurality of classification vectors, wherein each vector includes data representative of one or more of a plurality of melodic movement classes, as assigned by a user according to at least one of melodic properties perceptually observed by the user, wherein the at least one melodic properties is associated with at least one of said melodic movement classes, respectively, and wherein each vector additionally includes data representative of one or more melodic movement characteristics, as determined by a computer implementing digital signal processing techniques; and

processing means for comparing an unclassified song to the classification chain data structure to determine an estimate of the melodic movement class of the unclassified song according to a determined relationship of the unclassified song to the plurality of vectors comprising the classification chain data structure, said processing means storing said estimate of the melodic movement class of the unclassified song.

9. A computing system according to claim 8, wherein said determining of an estimate of the melodic movement class includes returning at least one number indicating the level of confidence of the melodic movement class assignment.

10. A computing system according to claim 9, wherein the performance level of the classification chain improves over time due to the examination of unclassified songs that have a low confidence level associated with the melodic movement class assignment.