Internship 2018

Open positions @ CNRS LIS France:

1 year Post doc / Ing Research grant opens 1st July 2018 in

'Deep Learning for non human bioacoustics, applied to automatic species identification - A data science approach from sensors to science'

Possibly reconducted position for 3 years.
The goal of your research will be to improve the current performance of soundscape / bioacoustic pattern detection and classification, at low signal to noise ratio, and within the 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 and/or unsupervised approaches, and (c) to manage and collect large training data to better model the variability of object categories within terrestrial and/or submarine environments.

The usual representations are based on Fourier descriptors, but have limits. We design mid-level or high-level features based on time-frequency segmentation, wavelet and discrete decomposition, compress sensing, non parametric bayesian representation, while developping specific CNN / LSTM Deep Representation Learning.

The validation of the models are conducted on real complex soundscape analyses, from cetaceans to birds songs, from bats to dolphins biosonars... It can also include boat or AUV alert systems.

Soundscape monitoring, biodiversity analysis and environmental care projects are some of the direct outcomes of this research. You'll develop high level research, and you may collaborate with some industry, which could afterward offer you a permanent position, in addition to academic opportunities from the growing communauty in this field.

You'll be involved into citizen program, including associations on biodiversity / bird conservation. You'll be working on smartphone systems to integrate your software solution (online or deported). Applications will take place on the Conservatoire du Littoral, in Var, Foncin House, at domaine du Rayol Var, and at Port-Cros National Parc. More details on some experimental work are given in

Your profile would cover one or few of these items:

  • Machine learning / Data Science or Applied Mathematics / Computer Science, or Electrical Engineering / Signal Processing,
  • Solid mathematics knowledge (especially linear algebra and statistics),
  • Creative and highly motivated, good programming skill (Python,...), Tensorflow, a bonus is for mobile applications
  • Fluent in English, both written and spoken,
  • Prior knowledge in the areas of pattern recognition is a plus.


Current positions are available on the university of Toulon, in the CNRS lab LIS that is heading the international project. A general view of the location is given here. Toulon campus provides scientific facilities and is located in the beautiful Provence area. LIS lab actually gathers 260 researchers professors and PhD students in computer science, signal analysis and pattern recognition.
Your research will be conducted within collaborations, like National Parks (Port-Cros, La Reunion, Alpin integral reserve...), international labs (CIBRA in Pavia univ., Brisbane univ. in Australia, Cornell univ. USA, Berlin Museum, Victoria univ. Canada, Queen Mary UK, Santiago univ, Chili...), and will include outdoors signal experiments on cetaceans, birds..., AUV... Worldwide collaborations offers real opportunities to travel. You'll work with Pr H. Glotin, Pr associate Ricard Marxer, Sebastien Paris and Joseph Razik, and the students of the teams (3 PhDs students, 5 masters).


DYNI / academic LIS lab is seeking a PhD student and a Post doc in Toulon, France, to investigate deep learning for efficient acoustic / bioacoustic representations, applied to soundscape, human speech, bird and whales sound analyses and classification. Evaluation will be conducted on international benchmarks. Since 2012, DYNI heads the SABIOD consortium ( ) on Scaled Acoustic Biodiversity, joining several international teams expert in machine learning, signal processing and bioacoustics. DYNI chaired several workshops on machine learning meetings bioacoustics at ICML 2013 and 2014, NIPS 2013, and ICDM 2015. DYNI has the chair of Scene Analysis at Inst. Univ. de France (, and th group is dedicated to multimodal scene analysis from signal to automatic indexing.

DYNI maintains close ties with theoretical research groups in Paris (DATA team; Sorbonne Univ...), INRIA, Cornell Univ, NYU, Victoria Univ, Pavia Univ., and deep learning community. DYNI has close ties with experimental research groups in Scaled Bioacoustic: Ocean Network Canada (UVIC), Antares deep sea platform... some ONGs (OrcaLab, XenoCanto), and industrial partnairs (DCNS France, Biosong, NortekMed, Cetacean Research...).
Applicants should have a strong background in machine learning (maths, statistics, computer science) and a genuine interest in understanding neural computation in perceptual intelligence. Prior exposure to neural computation and machine learning and programming skills is advantageous. Applicants with interest in combining machine learning, feature learning and signal processing are encouraged to apply.

Submit your application (a single .PDF) or informal inquiries to:

Pr. Glotin (director of the Phd program)

Screening of applications begins in end of May 2018.
Application materials should include a CV (university grades, honors / awards, brief statement of research interests, contact details of 2 referees), + 1 or 2 work samples, anything that is genuinely the own work of the applicant (e.g. thesis, computer code, web site demo, research manuscript / essay).
(ps: Some other positions are available as: Master Intership, Engineers ; spontaneous applications are welcome).