Context In the context of Music Genre Classification, we propose to use, as entries of a CNN, a set of eight music features chosen along three main music dimensions: dynamics, timbre and tonality. With CNNs (Figure 1) trained in such a way that filter dimensions are interpretable in time and frequency, results show that only eight music features are as
Context The SAMoVA research team is contributing to the analysis and characterization of pathological voices through three main projects: The Carcinologic Speech Severity Index (C2SI): a Speech Disorder Severity Index to measure the impact of oral and pharyngeal cavity on speech production, in partnership with CHU Toulouse, LPL Aix-en-Provence, PETRA MSH Toulouse, URI Octogone-Lordat Toulouse, Université d’Avignon et des Pays de
Context As part of the DIADEMS project on indexing ethno-musicological audio recordings, segmentation in singer turns automatically appeared to be essential. In our study, we present the problem of segmentation in singer turns of musical recordings and our experiments in this direction by using the MFCC features and exploring a method based on the Bayesian Information Criterion (BIC), which are used in
Context The recent tendency in multimedia domain is the semantic video understanding by automatic video analyzing. For that purpose, it is very important to know and study the video contents; i.e. background, actions, objects and their movements to better understand their meaning. Accordingly, object properties are very important issues. One important property which can significantly facilitate the understanding of object
Context The analysis of instrumental activities of daily life is an important tool in the early diagnosis of dementia such as Alzheimer. The IMMED project investigates tele-monitoring technologies to support doctors in the diagnostic and follow-up of the illnesses. The project aims to automatically produce indexes to facilitate the doctor’s navigation throughout the individual video recordings. Water sound recognition is
Overview Detecting when multiple harmonic sources are present is essential for structuring various type of audio content. We propose a method for detecting area with simultaneous harmonic sources using graph analysis of the tracking of the main frequencies. As our approach seems to work on choir detection, we propose to generalise our approach to identify overlapping harmonic sources using the
The detection of unison choir is a difficult problem as the different singers aims at singing the same thing at the same time. This leads some algorithm to classify such area as monophonic. However, we can observe little divergence between the harmonics of the different singers as shown in the figure below. Example of solo and unison choir part. The
Overview Rhythm is an important information for understanding audio data. On both music and speech analysis, the rhythm can help to describe and segment different kind of phenomena. The approach we present led us to propose two new representation : The Rhythm Spectrum and the Tempogram Our approach is not based on any musicological or speech knowledge and aims at finding periodicity in changes
Context In many fields of music analysis (for example: source separation, instruments recognition,…), it could be usefull to know how many instruments are present, or how many notes are played at the same time. We propose here a method for this last problem. Here, a “monophonic” sound is defined as one note played at a time (either played by an
Context We make the hypothesis that basic video or audio features present homogeneous values depending on a special context: homogeneity can be exploited by a GLR-BIC segmentation algorithm. The homogeneity criterion is evaluated by the ability to describe this feature values with a Gaussian law.This method consists in applying the GLR algorithm until convergence to the best repartition of Gaussian