We present a method for melody detection in polyphonic musical signals based on a model of the human auditory system. First, a set of pitch candidates is obtained for each frame, based on the output of an ear model and periodicity detection using correlograms. Trajectories of the most salient pitches are then constructed. Next, note candidates are obtained by trajectory segmentation (in terms of frequency and pitch salience variations). Too short, low-salience and harmonically-related notes are then eliminated. Finally, the melody is extracted by selecting the most important notes at each time, based on their pitch salience. We tested our method with excerpts from 12 songs encompassing several gen-res. In the songs where the solo stands out clearly, most of the melody notes were successfully detected. However, for songs where the melody is not that salient, the algorithm was not very accurate. Nevertheless, the followed approach seems promising.
Subject
Music Information Retrieval
Conference
Computer Music Modeling and Retrieval: Second International Symposium, CMMR 2004, February 2004
PDF File
Cited by
Year 2012 : 1 citations
1. Haifeng Sun, Zhang Tian Marlene (2012). “Melody discovery technology based on music cognition principles”, 3rd International Conference on Frontiers of Manufacturing and Design Science - ICFMD 2012 (in Chinese).
Year 2011 : 2 citations
BoKook Yoon & SeongYong Hong (2011). “A Design of Music Retrieval and Recommendation System based on Emotion”, Proceedings of Korea Information Science 2011, 38, Issue 1, pp. 153-155 (in Korean).
Dressler K. (2011). “Pitch Estimation by the Pair-Wise Evaluation of Spectral Peaks”,42nd International AES Conference: Semantic Audio.
Year 2010 : 2 citations
Waters, J., and Allen, R.B. (2010). Music Metadata in a New Key: Metadata and Annotation for Music in a Digital World Journal of Library Metadata, in press.
???, et al. "?????????????????." ???? 26.010 (2010): 1456-1465.
Year 2009 : 2 citations
Cano E. and Cheng C. (2009). “Melody Line Detection and Source Separation in Classical Saxophone Recordings”. International conference on Digital Audio Effects – DAFx’09.
Goto M and Ogata J. (2009). “A Survey on Research for Recognizing and Understanding Audio Signals of Music and Speech”. JSSSTCS, Vol. 26. No. 1 (2009). (in Japanese).
Year 2008 : 1 citations
1. Casey M. A., Veltkamp R., Goto M., Leman M., Rhodes C. and Slaney M. (2008). “Content-Based Music Information Retrieval: Current Directions and Future Challenge”, Proceedings of the IEEE, Vol. 96, No. 4. (April 2008), pp. 668-696.
Year 2006 : 2 citations
Goto M. (2006). “Analysis of Music Audio Signals”, in Computational Auditory Scene Analysis: Principles, Algorithms, and Applications, edited by DeLiang Wang and Guy J. Brown, John Wiley and sons.
Klapuri A. and Davy M. (2006). Signal processing methods for music transcription. Springer.
