Musical genre classification of audio signals Export

@article{10850, abstract = {Musical genres are categorical labels created by humans to characterize pieces of music. A musical genre is characterized by the common characteristics shared by its members. These characteristics typically are related to the instrumentation, rhythmic structure, and harmonic content of the music. Genre hierarchies are commonly used to structure the large collections of music available on the Web. Currently musical genre annotation is performed manually. Automatic musical genre classification can assist or replace the human user in this process and would be a valuable addition to music information retrieval systems. In addition, automatic musical genre classification provides a framework for developing and evaluating features for any type of content-based analysis of musical signals. In this paper, the automatic classification of audio signals into an hierarchy of musical genres is explored. More specifically, three feature sets for representing timbral texture, rhythmic content and pitch content are proposed. The performance and relative importance of the proposed features is investigated by training statistical pattern recognition classifiers using real-world audio collections. Both whole file and real-time frame-based classification schemes are described. Using the proposed feature sets, classification of 61\% for ten musical genres is achieved. This result is comparable to results reported for human musical genre classification.}, author = {Tzanetakis, G. and Cook, P.}, citeulike-article-id = {3355139}, citeulike-linkout-0 = {http://dx.doi.org/10.1109/TSA.2002.800560}, doi = {10.1109/TSA.2002.800560}, issn = {1063-6676}, journal = {Speech and Audio Processing, IEEE Transactions on}, keywords = {analysis, annotation, audio, automatic, classification, classifiers, content, content-based, databases, extraction, feature, file, frame-based, genre, harmonic, hierarchies, human, information, instrumentation, library, music, musical, pattern, pitch, processing, real-time, recognition, retrieval, rhythmic, sets, signal, signals, statistical, structure, systems, texture, timbral, training, web, whole, wide, world}, number = {5}, pages = {293--302}, posted-at = {2008-09-30 05:56:25}, priority = {2}, title = {Musical genre classification of audio signals}, url = {http://dx.doi.org/10.1109/TSA.2002.800560}, volume = {10}, year = {2002} }

TY - JOUR ID - 10850 L3 - citeulike-article-id:3355139 N2 - Musical genres are categorical labels created by humans to characterize pieces of music. A musical genre is characterized by the common characteristics shared by its members. These characteristics typically are related to the instrumentation, rhythmic structure, and harmonic content of the music. Genre hierarchies are commonly used to structure the large collections of music available on the Web. Currently musical genre annotation is performed manually. Automatic musical genre classification can assist or replace the human user in this process and would be a valuable addition to music information retrieval systems. In addition, automatic musical genre classification provides a framework for developing and evaluating features for any type of content-based analysis of musical signals. In this paper, the automatic classification of audio signals into an hierarchy of musical genres is explored. More specifically, three feature sets for representing timbral texture, rhythmic content and pitch content are proposed. The performance and relative importance of the proposed features is investigated by training statistical pattern recognition classifiers using real-world audio collections. Both whole file and real-time frame-based classification schemes are described. Using the proposed feature sets, classification of 61% for ten musical genres is achieved. This result is comparable to results reported for human musical genre classification. IS - 5 JF - Speech and Audio Processing, IEEE Transactions on SN - 1063-6676 EP - 302 TI - Musical genre classification of audio signals VL - 10 SP - 293 KW - analysis KW - annotation KW - audio KW - automatic KW - classification KW - classifiers KW - content KW - content-based KW - databases KW - extraction KW - feature KW - file KW - frame-based KW - genre KW - harmonic KW - hierarchies KW - human KW - information KW - instrumentation KW - library KW - music KW - musical KW - pattern KW - pitch KW - processing KW - real-time KW - recognition KW - retrieval KW - rhythmic KW - sets KW - signal KW - signals KW - statistical KW - structure KW - systems KW - texture KW - timbral KW - training KW - web KW - whole KW - wide KW - world AU - Tzanetakis, G AU - Cook, P PY - 2002/// UR - http://dx.doi.org/10.1109/TSA.2002.800560 ER -