방법 비교

	음악 분할	멜로디 추출	음악 장르 분류
분야	음악 정보 검색	음악 정보 검색	음악 정보 검색
계열	Machine learning	Machine learning	Machine learning
기원 연도	2001	2008	2002
창시자	Masataka Goto	Anssi Klapuri	George Tzanetakis
유형	Audio structural analysis	Polyphonic audio analysis	Audio feature-based classification
원전	Goto, M., & Hasegawa, Y. (2001). Automatic transcription of popular music audio. In Proceedings of the Fourth International Conference on Music Information Retrieval.	Salamon, J., & Gómez, E. (2014). Melody extraction from polyphonic music signals using pitch contour characteristics. IEEE Transactions on Audio, Speech, and Language Processing, 20(6), 1759-1770.	Tzanetakis, G., & Cook, P. (2002). Musical genre classification of audio signals. IEEE Transactions on Speech and Audio Processing, 10(5), 293-302.
별칭	structural segmentation, music structure analysis, section boundary detection	pitch contour extraction, melodic line extraction, f0 tracking	genre recognition, music categorization, style classification
관련	5	5	5
요약	Music segmentation is the task of dividing a musical recording into distinct structural sections (e.g., verse, chorus, bridge, pre-chorus, outro). Introduced by Goto (2001), it identifies major structural boundaries and labels sections according to musical form. Segmentation is essential for music understanding, audio editing, and composition analysis. It enables higher-level tasks like cover song identification and song structure-aware music generation.	Melody extraction is the task of automatically isolating the main melodic contour from polyphonic music recordings. It originated from music transcription research in the 2000s and addresses the core challenge of human pitch perception: identifying the perceptually dominant pitch when many instruments play simultaneously. Modern approaches use deep learning and are essential for music analysis, cover song detection, and music-to-lyrics alignment.	Music genre classification is the task of automatically assigning genre labels (rock, jazz, classical, pop, etc.) to audio recordings. Introduced formally by Tzanetakis and Cook (2002), it is one of the earliest and most studied music information retrieval problems. It remains critical for music discovery, recommendation systems, digital library organization, and music streaming services. Modern systems achieve high accuracy on standard datasets using deep learning.