Source Detection Using Repetitive Structure

 

This paper addresses the issue of source detection when more sources than mixtures overlap in time and frequency.  We show that repetitive structure in the form of time-time correlation matrices can reveal when each source is active.


 

Related publication:

Source Detection Using Repetitive Structure

R. Mitchell Parry and Irfan Essa
To appear in Proc. Int’l Conference on Acoustics, Speech, and Signal Processing, ICASSP 2006
Paper [PDF] 480 KB | Poster [PDF] 2.20 MB | BIBTeX


 

 

 

Feature Weighting for Segmentation

 

This paper proposes the use of feature weights to reveal the hierarchical nature of music audio. Feature weighting has been exploited in machine learning, but has not been applied to music audio segmentation. We describe both a global and a local approach to automatic feature weighting. The global approach assigns a single weighting to all features in a song. The local approach uses the local separability directly. Both approaches reveal structure that is obscured by standard features, and emphasize segments of a particular size.

 


 

Related publication:

Feature Weighting for Segmentation

Mitchell Parry and Irfan Essa
In Proc. Int’l Conference on Music Information Retrieval, ISMIR 2004
Paper [PDF] 851 KB | Poster [PDF] 2.20 MB | BIBTeX


 

 

 

Rhythmic Similarity through Elaboration

 

Rhythmic similarity techniques for audio tend to evaluate how close to identical two rhythms are. This paper proposes a similarity metric based on rhythmic elaboration that matches rhythms that share the same beats regardless of tempo or identicalness. Elaborations can help an application decide where to transition between songs. Potential applications include automatically generating a non-stop music mix or sonically browsing a music library.

 


Related publication:

Rhythmic Similarity through Elaboration

Mitchell Parry and Irfan Essa
In Proc. Int’l Conference on Music Information Retrieval, ISMIR 2003
Paper [PDF] 651 KB | Poster [PDF] 2.20 MB | BIBTeX