Conference paper
Improving Music Genre Classification by Short Time Feature Integration
Many different short-time features (derived from 10-30ms of audio) have been proposed for music segmentation, retrieval and genre classification. Often the available time frame of the music to make a decision (the decision time horizon) is in the range of seconds instead of milliseconds. The problem of making new features on the larger time scale from the short-time features (feature integration) has only received little attention.
This paper investigates different methods for feature integration (early information fusion) and late information fusion (assembling of probabilistic outputs or decisions from the classifier, e.g. majority voting) for music genre classification.
| Language: | English |
|---|---|
| Year: | 2005 |
| Pages: | 497-500 |
| Proceedings: | 2005 IEEE International Conference on Acoustics, Speech, and Signal Processing |
| ISBN: | 0780388747 and 9780780388741 |
| ISSN: | 2379190x and 15206149 |
| Types: | Conference paper |
| DOI: | 10.1109/ICASSP.2005.1416349 |
| ORCIDs: | Larsen, Jan |
Audio classification Autoregressive Model Feature Integration Information Fusion Music genre early/late Information fusion,
10 to 30 ms AR model Electronic mail Frequency Informatics Mathematical model Multiple signal classification Music information retrieval Principal component analysis Testing Voting Windows acoustic signal processing audio signal processing autoregressive model autoregressive processes decision time horizon late information fusion mean-variance features music music genre classification music retrieval music segmentation short time feature integration signal classification
