%0 Conference Paper %1 Pohle:LSAS2006 %A Pohle, Tim %A Schedl, Markus %A Knees, Peter %A Widmer, Gerhard %B Proceedings of the 1st Workshop on Learning the Semantics of Audio Signals %C Athens, Greece %D 2006 %K PhD %T Automatically Adapting the Structure of Audio Similarity Spaces %X Today, among the best-performing audio-based music simi- larity measures are algorithms based on Mel Frequency Cepstrum Coef- ficients (MFCCs). In these algorithms, each music track is modelled as a Gaussian Mixture Model (GMM) of MFCCs. The similarity between two tracks is computed by comparing their GMMs. One drawback of this ap- proach is that the distance space obtained this way has some undesirable properties. In this paper, a number of approaches to correct these undesirable prop- erties are investigated. They use knowledge about the properties of music by using other music tracks as a reference. These reference tracks can either be the music collection itself, or they may be an external set of reference tracks. Our results show that the proposed techniques clearly improve the qual- ity of this audio similarity measure. Furthermore, preliminary experi- ments indicate that the techniques also help to improve other similarity measures. They may even be useful in completely different domains, most notably text information retrieval.

@inproceedings{Pohle:LSAS2006, abstract = {Today, among the best-performing audio-based music simi- larity measures are algorithms based on Mel Frequency Cepstrum Coef- ficients (MFCCs). In these algorithms, each music track is modelled as a Gaussian Mixture Model (GMM) of MFCCs. The similarity between two tracks is computed by comparing their GMMs. One drawback of this ap- proach is that the distance space obtained this way has some undesirable properties. In this paper, a number of approaches to correct these undesirable prop- erties are investigated. They use knowledge about the properties of music by using other music tracks as a reference. These reference tracks can either be the music collection itself, or they may be an external set of reference tracks. Our results show that the proposed techniques clearly improve the qual- ity of this audio similarity measure. Furthermore, preliminary experi- ments indicate that the techniques also help to improve other similarity measures. They may even be useful in completely different domains, most notably text information retrieval.}, added-at = {2009-01-08T17:22:16.000+0100}, address = {Athens, Greece}, author = {Pohle, Tim and Schedl, Markus and Knees, Peter and Widmer, Gerhard}, biburl = {https://www.bibsonomy.org/bibtex/2308d7cd673ff71a01b5d9715be366243/ocelma}, booktitle = {Proceedings of the 1st Workshop on Learning the Semantics of Audio Signals}, description = {PhD}, interhash = {184cfe39701deeec7c55bf294d416d9c}, intrahash = {308d7cd673ff71a01b5d9715be366243}, keywords = {PhD}, location = {Athens, Greece}, timestamp = {2009-01-08T17:23:03.000+0100}, title = {Automatically Adapting the Structure of Audio Similarity Spaces}, year = 2006 }