Using the SDIF Sound Description Interchange Format for Audio Features

Juan Jose Burred (1, 2) , Carmine Emanuele Cella (1, 2) , Geoffroy Peeters (1, 2) , Axel Roebel (1, 2) , Diemo Schwarz (1, 2)

1 Analyse et synthèse sonores [Paris]
2 Equipe Systèmes temps-réel

We present a set of extensions to the Sound Description Interchange Format (SDIF) for the purpose of storage and/or transmission of general audio descriptors. The aim is to allow portability and interoperability between the feature extraction module of an audio information retrieval application and the remaining modules, such as training, classification or clustering. A set of techniques addressing the needs of short-time features and temporal modeling over longer windows are proposed, together with the mechanisms that allow further extensions or adaptations by the user. The paper is completed by an overview of the general aspects of SDIF and its practical use by means of a set of existing programming interfaces for, among others, C, C++ and Matlab.

Keywords: feature extraction; SDIF; music information retrieval; file formats

Keywords: Informatique musicale

Domains: Acoustics [physics.class-ph]; Signal and Image processing; Computer Vision and Pattern Recognition [cs.CV]; Other [cs.OH]; Musicology and performing arts; Neuroscience; Sound [cs.SD]; Human-Computer Interaction [cs.HC]; Signal and Image Processing; Machine Learning [cs.LG]; Artificial Intelligence [cs.AI]; Computer Aided Engineering; Multimedia [cs.MM]

Juan Jose Burred, Carmine Emanuele Cella, Geoffroy Peeters, Axel Roebel, Diemo Schwarz. Using the SDIF Sound Description Interchange Format for Audio Features. International Conference on Music Information Retrieval (ISMIR), Sep 2008, NA, France. pp.1-1. ⟨hal-01161398⟩