A MIREX Meta-analysis of Hubness in Audio Music Similarity
نویسندگان
چکیده
We use results from the 2011 MIREX “Audio Music Similarity and Retrieval” task for a meta analysis of the hub phenomenon. Hub songs appear similar to an undesirably high number of other songs due to a problem of measuring distances in high dimensional spaces. Comparing 17 algorithms we are able to confirm that different algorithms produce very different degrees of hubness. We also show that hub songs exhibit less perceptual similarity to the songs they are close to, according to an audio similarity function, than non-hub songs. Application of the recently introduced method of “mutual proximity” is able to decisively improve this situation.
منابع مشابه
Mirex 2009 Spectral and Rhythm Audio Features for Music Similarity Retrieval
Contrary to audio music classification, for audio similarity a smaller set of audio features seems to deliver better results.
متن کاملAudio-Based Music Similarity and Retrieval: Combining a Spectral Similarity Model with Information Extracted from Fluctuation Patterns
This paper describes the implementation submitted by the author to the MIREX’06 (Music Information Retrieval eXchange) evaluation track on audio-based music similarity and retrieval. In addition, this paper summarizes the optimization of this implementation and its evaluation prior to submission. Finally, a detailed analysis and discussion of the MIREX results is presented. Overall, this implem...
متن کاملMarsyas Submissions to Mirex 2010
Marsyas is an open source software framework for audio analysis, synthesis and retrieval with specific emphasis on Music Information Retrieval. It is developed by an international team of programmers and researchers led by George Tzanetakis. In MIREX 2010 the Marsyas team participated in the following tasks: Audio Classical Composer Identification, Audio Genre Classification (Latin and Mixed), ...
متن کاملMarsyas Submissions to Mirex 2007
Marsyas is an open source software framework for audio analysis, synthesis and retrieval with specific emphasis on Music Information Retrieval. It is developed by an international team of programmers and researchers led by George Tzanetakis. In MIREX 2007 we participated in the following tasks: Audio Artist Identification, Audio Classical Composer Identification, Audio Genre Classification, Aud...
متن کاملMirex 2007 Combining Audio and Symbolic Descriptors for Audio Music Similarity and Retrieval
At ISMIR 2007 we propose a new approach for an extended feature set for Audio Music Information Retrieval: We transcribe audio data into a symbolic form using a transcription system, extract symbolic descriptors from that representation and combine them with multiple audio features. In the ISMIR paper we show that by this method we are able to further improve music genre classification. At MIRE...
متن کامل