ERMITES 2015 Summer School brings together international leading researchers and provides participants the opportunity to gain deeper insight into current research trends in scaled audiovisual information retrieval within an interdisciplinary framework. It is organized as a series of long talks, during which attendies are invited to interact.
The goal of these session is to improve the current performance of soundscape / bioacoustic pattern detection and classification, at low signal to noise ratio, and/or into large data set (Big Data paradigm). Thus, the objectives here are three-fold: (a) to make the signal representation more robust, (b) to develop classification model more efficient on complex bioacoustic patterns, with supervised but also unsupervised approaches, and (c) to manage and collect additional training data to better model the variability of object categories (within some terrestrial or submarine recording experiments). The frequent representations are either based on Fourier descriptors or MFCC. However we design mid-level or high-level features based on time-frequency segmentation, wavelet and discrete decomposition, compress sensing, non parametric bayesian representation, Conv. Neural Net. / Deep Neural Net. The validation of the models are conducted from cetaceans to birds songs, bats to dolphins biosonars, from frogs to insects calls. Biodiversity analysis and environmental care projects are some of the direct outcomes of this research. You'll learn more how to develop sur systems and conduct research in this area.
H. Glotin, Professor Inst. Univ France, UTLN, CNRS LSIS
Big Data bioacoustic mining applied to biosonar & communicative biological sounds - SABIOD project. Example on scaled Amazonia bird & whale songs classification.
P. Flandrin, Professor, Académie des Sciences, ENS Lyon
Time frequency complexity analysis in bioacoustic signals.
A. Joly, Researcher, INRIA Montpellier
Towards multimodal environmental data indexing (images, video in Life Clef).
J. Sueur, Associate Professor, MNHN Paris
Statistical indices of biodiversity.
O. Gérard *, Research Director, DGA Toulon
Classification of odontocets.
T. Aubin, Research Director, CNRS d'Orsay
Long-term analysis of song shapes and behaviors of birds.
G. Pavan, Senior Researcher, Univ. of Pavia
Long term bioacoustic and ecological analysis of marine and terrestrial soundscapes joint to noise monitoring.
C. Gervaise, Researcher, GIPSA Lab, Grenoble
Biophonics and 3D transect. Classification of marine biotopes.
D. Mauuary, PhD, Cyberio S.A.
Real-time tracking of chiroptera.* - to be confirmed
ERMITES is supported by Université de Toulon, MASTODONS CNRS project, IUF, CNRS, LSIS, and SABIOD.
Registration fees are 80 euros per person, including all taxes. These include 2 meals, coffee breaks, and proceedings. For additional 20 euros you can subscribe to the gala dinner. Please confirm in your pre-registration message if you intend to attend to this event.
Payments can be made by bank card or order form to UTLN (starting 1 February 2015). Payments are accepted until 30 March 2015. After this date, all unpaid registrations shall be canceled.
A pre-registration via e-mail at email@example.com is open starting 20 December 2014 and is mandatory. Please include in your message your name, affiliation and contact details for payment.
Organizing co. : H. Glotin, J . Razik and L. Alecu
Program co. : H. Glotin (Pres.)
Contact : firstname.lastname@example.org