A Classification Approach to Melody Transcription

Poliner, Graham E.; Ellis, Daniel P. W.

Melodies provide an important conceptual summarization of polyphonic audio. The extraction of melodic content has practical applications ranging from content-based audio retrieval to the analysis of musical structure. In contrast to previous transcription systems based on a model of the harmonic (or periodic) structure of musical pitches, we present a classification-based system for performing automatic melody transcription that makes no assumptions beyond what is learned from its training data. We evaluate the success of our algorithm by predicting the melody of the ISMIR 2004 Melody Competition evaluation set and on newly-generated test data. We show that a Support Vector Machine melodic classifier produces results comparable to state of the art model-based transcription systems.


Also Published In

ISMIR 2005: 6th International Conference on Music Information Retrieval: Proceedings: Variation 2: Queen Mary, University of London & Goldsmiths College, University of London, 11-15 September, 2005
Queen Mary, University of London

More About This Work

Academic Units
Electrical Engineering
Published Here
June 28, 2012