Real-Time Monophonic and Polyphonic Audio Classification from Power Spectra

Maxime Baelde (1, 2, 3) , Christophe Biernacki (4) , Raphaël Greff (1)

1 A-Volute [Roubaix]
2 MODAL - MOdel for Data Analysis and Learning
3 LPP - Laboratoire Paul Painlevé - UMR 8524
4 SELECT - Model selection in statistical learning

This work addresses the recurring challenge of real-time monophonic and poly-phonic audio source classification. The whole power spectrum is directly involved in the proposed process, avoiding complex and hazardous traditional feature extraction. It is also a natural candidate for polyphonic events thanks to its additive property in such cases. The classification task is performed through a nonparametric kernel-based generative modeling of the power spectrum. Advantage of this model is twofold: it is almost hypothesis free and it allows to straightforwardly obtain the maximum a posteriori classification rule of online signals. Moreover it makes use of the monophonic dataset to build the polyphonic one. Then, to reach the real-time target, the complexity of the method can be tuned by using a standard hierarchical clustering preprocessing of sound models, revealing a particularly efficient computation time and classification accuracy trade-off. Finally, it is shown that the resulting real-time audio classification method outperforms the state-of-the-art methods in the monophonic and polyphonic cases on benchmark and owned datasets, even in real-time situation.

Mots clés: real-time; audio classification; machine learning; monophonic; polyphonic; generative model; nonparametric estimation

Domaines: Machine Learning [stat.ML]; Traitement du signal et de l'image [eess.SP]

Maxime Baelde, Christophe Biernacki, Raphaël Greff. Real-Time Monophonic and Polyphonic Audio Classification from Power Spectra. 2018. ⟨hal-01834221v1⟩