Improvements of Audio-Based Music Similarity and Genre Classificaton
نویسندگان
چکیده
Audio-based music similarity measures can be used to automatically generate playlists or recommendations. In this paper the similarity measure that won the ISMIR’04 genre classification contest is reviewed. In addition, further improvements are presented. In particular, two new descriptors are presented and combined with two previously published similarity measures. The performance is evaluated in a series of experiments on four music collections. The evaluations are based on genre classification, assuming that very similar tracks belong to the same genre. On two collections the improvements lead to a substantial performance increase.
منابع مشابه
Genre-oriented Organization of Music Collections Using the SOMeJB System: An Analysis of Rhythm Patterns and Other Features
With the advent of larger electronic music repositories, the automatic organization of music into different genre categories is receiving increased attention. The creation of such genre hierarchies, as well as ways for providing useful interfaces to these, poses an interesting challenge. With the SOM-enhanced JukeBox (SOMeJB) system we developed an approach for automatically organizing pieces o...
متن کاملThinkit’s Submissions for Mirex2009 Audio Music Classification and Similarity Tasks
This full abstract describes our submitted systems for the MIREX09 audio classification tasks (genre, mood, classical composer, audio tagging) and music similarity and retrieval task. All the classification systems are based on basic acoustic features (e.g. MFCC) and the modeling framework of GSV-SVM, which has been successfully applied in speaker recognition field. And the similarity systems a...
متن کاملUsing Timbre, Rhythm and Tempo Models for Music Genre Classification
In this submission, audio features that approximate timbre, rhythm and tempo are used for genre classification and music similarity estimation. This abstract describes the feature set, distance computation method, and classifier model used for the submitted algorithms.
متن کاملUsing Timbre Models for Audio Music Similarity Estimation
In this submission, audio features that approximate timbre are used for genre classification and music similarity estimation. This abstract describes the feature set, distance computation method, and classifier model used for the submitted algorithms.
متن کاملUsing Timbre, Rhythm and Tempo Models for Audio Music Similarity Estimation
In this submission, audio features that approximate timbre, rhythm and tempo are used for genre classification and music similarity estimation. This abstract describes the feature set, distance computation method, and classifier model used for the submitted algorithms.
متن کامل