Method, medium, and system classifying music themes using music titles

• US 20070208990A1
• Filed: 01/08/2007
• Published: 09/06/2007
• Est. Priority Date: 02/23/2006
• Status: Active Grant

• Current Assignee: Samsung Electronics Co. Ltd.
• Original Assignee: Samsung Electronics Co. Ltd.
• Inventors: Kim, Jung Eun, Kim, Hyoung Gook
• Granted Patent: US 7,863,510 B2
• Time in Patent Office: Days
• US Class Current: 715/203
• CPC Class Codes: G06F 16/68 Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually

Abstract

A method, medium, and system classifying a music theme for music by using a corresponding music title, by generating a theme class vector in association with the music theme, generating a music title class vector in association with the music title, calculating similarity between the theme class vector and the music title class vector, and assigning a theme of the music title based on the similarity.

Claims

1. A method of classifying music, comprising:

generating a theme class vector corresponding to at least one music theme;

generating a music title class vector corresponding to a music title for the music;

calculating a similarity between the theme class vector and the music title class vector; and

assigning a theme of the music title, to classify the music according to theme, based on the similarity.

2. The method of claim 1, wherein the generating of the theme class vector comprises:

extracting feature candidates from the music title;

selecting a feature from the extracted feature candidates; and

generating the theme class vector by assigning a feature value of the selected feature.

3. The method of claim 2, wherein the extracting of the feature candidates from the music title comprises:

analyzing a morpheme of the music title; and

extracting a class unigram and class co-occurrence of the music title.

4. The method of claim 3, wherein the extracting of the class unigram and class co-occurrence comprises:

extracting a content word and an end of a word from the music title; and

assigning a class to the respective content word and the end of the word via an ontology search.

5. The method of claim 3, wherein the extracting of the class unigram and class co-occurrence comprises:

expressing the music title in a row of a class; and

extracting two certain classes as the feature candidates when the two certain classes are detected in one music title.

6. The method of claim 5, wherein the extracting of the two certain classes as the feature candidates comprises extracting class co-occurrences C_i*C_j as the feature candidates when classes C_i and C_j satisfy a following condition,

c_i⊂

m_k and c_j⊂

m_k and |L(c_i)−

L(c_j)|≦

α

,

wherein m_k is the music title expressed in the row and L(x) is an index of x in the m_k.

7. The method of claim 2, wherein the selecting of the feature from the extracted feature candidates comprises selecting the feature from the extracted feature candidates based on predetermined chi square statistics.

8. The method of claim 7, wherein the selecting of the feature from the extracted feature candidates based on predetermined chi square statistics comprises:

calculating chi square statistics as associated with each feature candidate;

calculating an average of the calculated chi square statistics; and

selecting class having a chi square statistic greater than the average of the chi square statistics as the feature.

9. The method of claim 2, wherein the generating of the theme class vector by assigning the feature value of the selected feature comprises assigning the feature value of the feature by using binary numbers.

10. The method of claim 9, wherein the assigning of the feature value of the feature by using binary numbers comprises:

establishing a binary 1 as the feature value when the respective feature corresponds to a relevant theme;

establishing a binary 0 as the feature value when the respective feature does not correspond to the relevant theme; and

generating the theme class vector based on the established feature value.

11. The method of claim 2, further comprising maintaining the music title in a music title database.

12. The method of claim 1, wherein the calculating of the similarity between the theme class vector and the music title class vector comprises:

calculating an inner product of the theme class vector and the music title class vector; and

determining the calculated inner product to be the similarity.

13. The method of claim 1, wherein the assigning of the theme of the music title based on the similarity comprises assigning the theme having a maximum similarity value as the theme of the music title.

14. At least one medium comprising computer readable code to implement a method of classifying music, the method comprising:

generating a theme class vector corresponding to at least one music theme;

generating a music title class vector corresponding to a music title for the music;

calculating a similarity between the theme class vector and the music title class vector; and

assigning a theme of the music title, to classify the music according to theme, based on the similarity.

15. A system classifying music, comprising:

a theme class vector generation unit to generate a theme class vector corresponding to at least one music theme;

a music title class vector generation unit to generate a music title class vector corresponding to a music title for the music;

a similarity calculation unit to calculate a similarity between the theme class vector and the music title class vector; and

a music title theme assignment unit to assign a theme of the music title, to classify the music according to theme, based on the similarity.

16. The system of claim 15, further comprising:

a feature candidate extraction unit to extract feature candidates from the music title; and

a feature selection unit to select a feature from the extracted feature candidates,

wherein the theme class vector generation unit generates the theme class vector by assigning a feature value of the selected feature.

17. The system of claim 16, wherein the feature candidate extraction unit analyzes a morpheme of the music title and extracts a class unigram and class co-occurrence of the music title.

18. The system of claim 17, wherein the feature candidate extraction unit extracts a content word and an end of a word from the music title and assigns a class to the respective content word and the end of the word via an ontology search.

19. The system of claim 17, wherein the feature candidate extraction unit expresses the music title in a row of a class and extracts two certain classes as the feature candidates when the two certain classes are detected in one music title.

20. The system of claim 16, wherein the feature selection unit selects the feature from the extracted feature candidates based on predetermined chi square statistics.

21. The system of claim 20, wherein the feature selection unit calculates chi square statistics as associated with each feature candidate, calculates an average of the calculated chi square statistics, and selects a class having a chi square statistic greater than the average of the chi square statistics as the feature.

22. The system of claim 16, wherein the theme class vector generation unit establishes a binary 1 as the feature value when the respective feature corresponds to a relevant theme, establishes a binary 0 as the feature value when the respective feature does not correspond to the relevant theme, and generates the theme class vector based on the established feature value.

23. The system of claim 16, further comprising a music title database for maintaining at least a plurality of music titles, including the music title.

24. The system of claim 15, wherein the music title class vector generation unit extracts a feature by analyzing a morpheme of the music title, and by extracting a class unigram and class co-occurrence of the music title, and generates the music title class vector by assigning a feature value to the extracted feature.

25. The system of claim 15, wherein the similarity calculation unit calculates an inner product of the theme class vector and the music title class vector and determines the calculated inner product to be the similarity.

26. The system of claim 15, wherein the music title theme assignment unit assigns the theme having a maximum similarity value as the theme of the music title.

27. A method of classifying music, comprising:

generating a music title class vector corresponding to a music title for music;

calculating a similarity between a theme class vector and the music title class vector, wherein the theme class vector corresponds to at least one music theme; and

assigning a theme of the music title, to classify the music according to theme, based on the similarity.