Christophe Charbuillet

Learn More
Moving music indexing technologies developed in a research lab to their integration and use in the context of a third-party search and navigation engine that indexes music files, archives of TV music programs and video-clips, involves a set of choices and works that we relate here. First one has to choose technologies that perform well, which are scalable(More)
Timbral modeling is fundamental in content based music similarity systems. It is usually achieved by modeling the short term features by a Gaussian Model (GM) or Gaussian Mixture Models (GMM). In this article we propose to achieve this goal by using the GMM-supervector approach. This method allows to represent complex statistical models by an Euclidean(More)
This is a PDF file of an unedited manuscript that has been accepted for publication. As a service to our customers we are providing this early version of the manuscript. The manuscript will undergo copyediting, typesetting, and review of the resulting proof before it is published in its final form. Please note that during the production process errors may(More)
Speech recognition systems usually need a feature extraction stage which aims at obtaining the best signal representation. State of the art speaker verification systems are based on cep-stral features like MFCC, LFCC or LPCC. In this article, we propose a feature extraction system based on the combination of three feature extractors adapted to the speaker(More)
Speech recognition systems usually need a feature extraction stage aiming at obtaining the best signal representation. In this article we propose to use genetic algorithms to design a feature extraction method adapted to the speaker diarization task. We present an adaptation of the common MFCC feature extractor which consists in designing a filter bank,(More)
Speech recognition systems usually need a feature extraction stage aiming at obtaining the best signal representation. State of the art speaker verification systems are based on cepstrals features like MFCC, LFCC or LPCC. In this article, we propose to use a genetic algorithm to provide new features able to complete the LFCC's. We present an adaptation of(More)
A study on properties of data sets representing public domain audio and visual content and their relation to their indexability is presented. Data analysis considers the pairwise distance distributions and various techniques to estimate the true intrinsic dimensionality of the studied data. One own alternative to dimensionality estimation is also presented.(More)
A comparative study of distributions and properties of datasets representing public domain audio and visual content is presented. The criteria adopted in this study incorporate the analysis of the pairwise distance distribution histograms and estimation of intrinsic dimensionality. In order to better understand the results, auxiliary datasets have been also(More)