A Methodology for Detection of Melody in Polyphonic Musical Signals



QBH in polyphonic music signals requires a melody representation of the songs in the database. This is a complex problem for which there is no general and accurate solution yet.
In this paper, we present a bottom-up method for melody detection in polyphonic musical signals. Our approach is based on the assumption that the melodic line is often salient in terms of note intensity (energy). First, trajectories of the most intense harmonic groups are constructed. Then, note candidates are obtained by trajectory segmentation (in terms of frequency and energy variations). Too short, low-energy and octave-related notes are then eliminated. Finally, the melody is extracted by selecting the most important notes at each time, based on energy criteria.
We tested our method with excerpts from 12 songs encompassing several genres. In the songs where the sole stands out clearly, most of melody notes were successfully extracted. However, for songs where the melody is not that salient, the results are poor. Nevertheless, we could say that the results are encouraging.


melody extraction, query-by-humming, music information retrieval


Music Information Retrieval


AES116, May 2004

PDF File

Cited by

Year 2012 : 1 citations

 1. YH Sim, CW Teo, SH Neo, KS Chong (2012). “Segmenting a humming signal into musical notes”, US Patent 8,193,436, 2012

Year 2011 : 2 citations

 Seokhwan Jo, Chang D. Yoo, and Arnaud Doucet, “Melody Tracking based on Sequential Bayesian Model”, to appear for publication in IEEE Journal of Selected Topics in Signal Processing, November 2011.

 Sihyun Joo, Sanghun Park, Seokhwan Jo, Chang D. Yoo (2011). “Melody Extraction based on Harmonic Coded Structure”. ISMIR 2011: 227-232.

Year 2010 : 2 citations

 Jo S. etal. (2010). “Melody Pitch Estimation Based on Range Estimation and Candidate Extraction Using Harmonic Structure Model”, InterSpeech 2010.

 Streitenberger F., Weis M., Derboven C. and Cremer M. (2010). “VERFAHREN UND VORRICHTUNG ZUR EXTRAKTION EINER EINEM AUDIOSIGNAL ZU GRUNDE LIEGENDEN MELODIE”. Germany Patent Application.

Year 2009 : 3 citations

 Hwee et al. (2009). “Segmenting a Humming Signal Into Musical Notes”. United States Patent Application.

 Joo S. et al. (2009). “Melody extraction from polyphonic audio signal”, MIREX 2009.

 Lachambre H. (2009). “Caractérisation de l'environnement musical dans les documents audiovisuels”. PhD Thesis, Institut de Recherche en Informatique de Toulouse (IRIT).

Year 2008 : 1 citations

 1. Salamon J. J. (2008). “Chroma-based Predominant Melody and Bass Line Extraction from Music Audio Signals”. MSc Thesis. University Pompeu Fabra, Barcelona, Spain.

Year 2007 : 2 citations

 Poliner G., Ellis D., Ehmann A., Gomez E., Streich S. and Ong B. (2007). “Melody Transcription from Music Audio: Approaches and Evaluation”. IEEE Transactions on Audio, Speech, and Language Processing, Vol. 15, No. 4 pp. 1247 - 1256.

 Serrà J. (2007). “Music Similarity based on Sequences of Descriptors: Tonal Features Applied to Audio Cover Song Identification”. MSc Thesis, Department of Information and Communication Technologies, Universitat Pompeu Fabra, Barcelona, Spain.

Year 2006 : 8 citations

 Brossier P. (2006). “Automatic Annotation of Musical Audio for Interactive Applications”. PhD Thesis, Centre for Digital Music Queen Mary, University of London.

 Ellis D. and Poliner G. (2006). “Classification-Based Melody Transcription”. Machine Learning Journal, Vol. 65, No. 2-3, pp. 439-456.

 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.

 Sim, Y. H. et. al (2006). “Segmenting a Humming Signal into Musical Notes”, PatenScope.

 Streitenberger F., Weis M., Derboven C. and Cremer M. (2006). “Method and Device for Harmonic Rendering of a Melody Line”. United States Patent Application.

 Streitenberger F., Weis M., Derboven C. and Cremer M. (2006). “Method and Device for Extracting a Melody Underlying an Audio Signal”. United States Patent Application.

 Streitenberger F., Weis M., Derboven C. and Cremer M. (2006). “Verfahren und Vorrichtung zur Glättung eines Melodieliniensegments”. Germany Patent Application.

Year 2005 : 3 citations

 Poliner G. and Ellis D. (2005). “ A Classification Approach to Melody Transcription”. International Conference on Music Information Retrieval – ISMIR’2005.

 Sim et al. (2005). “Segmenting a Humming Signal Into Musical Notes”. United States Patent Application Publication, US 2009/0171485

 Streitenberger F., Weis M., Derboven C. and Cremer M. (2005). “Method and Device for Smoothing a Melody Line Segment”. United States Patent, Patent number: 6951977, Issue date: 4 Oct 2005.