Effects of Album and Artist Filters in Audio Similarity Computed for Very Large Music Databases Arthur Flexer 1 and Dominik Schnitzer 1,2 (1) Austrian Research Institute for Artificial Intelligence, Vienna, Austria (2) Department of Computational Perception, Johannes Kepler University Linz, Aus- tria In audio based music recommendation, a well known effect is the dominance of songs from the same artist as the query song in recommendation lists. We verify that this effect also exists in very large databases (> 250000 songs). Since our data set contains multiple albums from individual artists, we can also show that the album effect is relatively bigger than the artist effect. Introduction In Music Information Retrieval, one of the central goals is to automatically recom- mend music to users based on a query song or query artist. This can be done using expert knowledge (e.g. pandora.com), social meta-data (e.g. last.fm), collaborative filtering (e.g. amazon.com/mp3) or by extracting information directly from the audio (e.g. muffin.com). In audio based music recommendation, a well known effect is the dominance of songs from the same artist as the query song in recommendation lists. This effect has been studied mainly in the context of genre classification experiments. Since usually no ground truth with respect to music similarity exists, genre classification is widely used for evaluation of music similarity. Each song is labelled as belonging to a music genre using e.g. music expert advice. High genre classification results indicate good similarity measures. If in genre classification experiments songs from the same artist are allowed in both training and test sets, this can lead to over-optimistic results since usually all songs from an artist have the same genre label. It can be argued that in such a scenario one is doing artist classification rather than genre classification. One could even speculate that the specific sound of an album (mastering and production effects) is being classified. In (10) the use of a so-called “artist filter” ensuring that all songs from an artist are in either the training or the test set is proposed. The authors found that the use of such an artist filter can lower the classification results quite considerably (with one of their music collection even from 71% down to 27%). These over-optimistic accuracy results due to not using an artist filter have been confirmed in other studies (8) (2). Other 1