Content based audio classification and retrieval using joint time-frequency analysis

A Survey of Evaluation in Music Genre Recognition

“…For instance, Burred and Peeters [50] cite the F-measure of their MGR system, as well as its Mean accuracy, Recall, and Precision. We find the ROC in only 7 references [105,121,245,349,432,440,466]. For instance, Watanabe and Sato [440] plot the ROC of their sparrows trained to discriminate Baroque and Modern music.…”

Audio Music Genre Classification Using Different Classifiers and Feature Selection Methods

“…Automatic analysis of the musical databases is one of the required components of the MIR. Most of the current music databases are indexed based on song title or artist name and in this format improper indexing can result in incorrect search results [1]. These methods become useless when text descriptions of the title or the artist name are not available.…”

Machine learning for automatic classification of volcano-seismic signatures

“…Specifically, we consider for the classification of volcano-seismic data, an extensive set of features proposed in several fields such as seismic [2], acoustics (environmental, bio-acoustics, animal [3], [4], [5], [6] or anthropic [7] ambient and/or landscape noises), speech and speech analysis [8], [9], [10] and music signals [11]. More in details, we take into account features such as those proposed in the recent work [2] where seismic waves are represented by few classically features such as duration time, statistical descriptors (skewness, kurtosis, statistics ratios) and fundamental frequencies.…”

“…Finally, similar features are also used in music classification. We can mention [6] in which music genres are discriminated using entropy, centroid, centroid ratio, bandwidth or silence ratio or [11] who recognize orchestral instruments with centroid, skewness, kurtosis or centroid velocity. We collect and adapt a large part of these features to our dataset.…”