IEEE Transactions on Audio Speech and Language Processing · 2012 · 434 citations · 27 references
HumanitiesMusicologyMusic AnalysisPhoneticsPsychoacousticsMelodic AnalysisTonal AnalysisComparative EvaluationMelodic ContourMelodic IdentificationMelodic SegmentationMelody ExtractionMusical Pattern RecognitionPitch Contour AnalysisSelection Techniques
The paper presents a system that automatically extracts the main melody from polyphonic music recordings and evaluates its limitations to suggest future improvements. The method builds continuous pitch contours from candidate pitches, characterizes them with statistical features, and applies rule‑based criteria to separate melodic from non‑melodic contours, supplemented by qualitative error analysis and parameter studies. The approach introduces new voicing detection, octave error minimization, and melody selection techniques, achieving higher overall accuracy than existing systems, and identifies remaining limitations while proposing future research directions.
We present a novel system for the automatic extraction of the main melody from polyphonic music recordings. Our approach is based on the creation and characterization of pitch contours, time continuous sequences of pitch candidates grouped using auditory streaming cues. We define a set of contour characteristics and show that by studying their distributions we can devise rules to distinguish between melodic and non-melodic contours. This leads to the development of new voicing detection, octave error minimization and melody selection techniques. A comparative evaluation of the proposed approach shows that it outperforms current state-of-the-art melody extraction systems in terms of overall accuracy. Further evaluation of the algorithm is provided in the form of a qualitative error analysis and the study of the effect of key parameters and algorithmic components on system performance. Finally, we conduct a glass ceiling analysis to study the current limitations of the method, and possible directions for future work are proposed.
27