A Music Information System Based on Improved Melody Contour Extraction

Author(s):  
Nattha Phiwma ◽  
Parinya Sanguansat
2021 ◽  
Vol 11 (13) ◽  
pp. 5913
Author(s):  
Zhuang He ◽  
Yin Feng

Automatic singing transcription and analysis from polyphonic music records are essential in a number of indexing techniques for computational auditory scenes. To obtain a note-level sequence in this work, we divide the singing transcription task into two subtasks: melody extraction and note transcription. We construct a salience function in terms of harmonic and rhythmic similarity and a measurement of spectral balance. Central to our proposed method is the measurement of melody contours, which are calculated using edge searching based on their continuity properties. We calculate the mean contour salience by separating melody analysis from the adjacent breakpoint connective strength matrix, and we select the final melody contour to determine MIDI notes. This unique method, combining audio signals with image edge analysis, provides a more interpretable analysis platform for continuous singing signals. Experimental analysis using Music Information Retrieval Evaluation Exchange (MIREX) datasets shows that our technique achieves promising results both for audio melody extraction and polyphonic singing transcription.


2011 ◽  
Vol 47 (3) ◽  
pp. 426-439 ◽  
Author(s):  
Markus Schedl ◽  
Gerhard Widmer ◽  
Peter Knees ◽  
Tim Pohle

Author(s):  
Niall Conroy

Music information system design is aided through attention to real-world user behaviours. However, further work is necessary to understand and accommodate the subjective and emotional qualities people ascribe to music, the social component of music search, and the tools necessary to facilitate information management practices associated with large personal collections. Some design proposals are discussed as they related to three broad challenges facing system design.L’attention aux comportements des utilisateurs entrent dans la conception de systèmes d’information musicale. Cependant, plus de recherche est nécessaire pour comprendre et accommoder les qualités subjectives et émotionnelles que les gens attribuent à la musique, la composante sociale de la recherche de musique et les outils nécessaires pour faciliter les pratiques de gestion de l’information associées aux vastes collections personnelles. Certaines propositions de conception en lien avec les trois grands défis auxquels font face ces systèmes seront discutées.


Sign in / Sign up

Export Citation Format

Share Document