A Computationally Efficient Scheme for Dominant Harmonic Source Separation

Mathieu Lagrange (1) , Luis Gustavo Martins (2) , George Tzanetakis (3)

1 LS2N - Laboratoire des Sciences du Numérique de Nantes
2 Catholic University of Portugal / Porto
3 UVIC - University of Victoria [Canada]

The leading voice is an important feature of musical piece and can often be considered as the dominant harmonic source. We propose in this paper a new scheme for the purpose of efficient dominant harmonic source separation. This is achieved by considering a new harmonicity cue which is first compared with state-of-the-art cues using a generic evaluation methodology. The proposed separation scheme is then compared to a generic Computational Auditory Scene Analysis framework. Computational speed-up and performance comparison is done using source separation and music information retrieval tasks.

Mots clés: Audio Source Separation; Auditory Scene Analysis; Harmonicity; Sinusoidal Modeling

Domaines: Machine Learning [stat.ML]; Traitement du signal et de l'image [eess.SP]; Intelligence artificielle [cs.AI]; Apprentissage [cs.LG]; Multimédia [cs.MM]; Traitement du signal et de l'image [eess.SP]

Mathieu Lagrange, Luis Gustavo Martins, George Tzanetakis. A Computationally Efficient Scheme for Dominant Harmonic Source Separation. ICASSP, IEEE, 2008, Las Vegas, United States. ⟨10.1109/ICASSP.2008.4517572⟩. ⟨hal-01697506⟩