Сравнение методов

	Разделение вокала	Извлечение мелодии
Область	Извлечение музыкальной информации	Извлечение музыкальной информации
Семейство	Machine learning	Machine learning
Год появления	2012	2008
Автор метода	Yonggang Han	Anssi Klapuri
Тип	Audio source separation	Polyphonic audio analysis
Основополагающий источник	Han, Y., Qin, Z., & Kang, Z. (2012). Singing voice separation using spectral floor filtered spectrograms. In Proceedings of the International Society for Music Information Retrieval Conference.	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.
Другие названия	singing voice extraction, voice isolation, source demixing	pitch contour extraction, melodic line extraction, f0 tracking
Связанные	5	5
Сводка	Vocal separation is the task of isolating the singing voice from a mixed music recording, leaving the instrumental accompaniment. Introduced formally by Han et al. (2012), it is critical for music editing, remixing, karaoke generation, and music analysis. Modern deep learning approaches (Défossez et al., 2021) have achieved impressive quality, enabling practical applications in music production and streaming services. Vocal separation is a special case of source separation, where the goal is to isolate the most perceptually salient source.	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.