Ricard Marxer

ml, audio, cv, nlp, speech, bioacoustics // Assoc. Prof. at Université de Toulon, researcher at LIS CNRS UMR 7020, director of master-mir.eu in marine robotics and AI

2025-06-07

Our paper on the study of vocal complexity of #orcas is out.

doi.org/10.1016/j.ecoinf.2025.

In this #bioacoustics work, we computationally analyse passive acoustic recordings spanning 5 years of orcas in the wild. We perform DL-based automatic classification of calls and measure complexity. Resulting metrics are contrasted to pod sizes, as a way to approach the social complexity hypothesis in #cetaceans

Great collaboration with Paul Best, Marion Poupard, Paul Spong, Helena Symonds and Hervé Glotin

2025-05-21

Happy to see this work out there. Good job @charlylamothe.bsky. social et al. it really nice working with you all!

nature.com/articles/s41597-025

2024-11-13

Today @tiagoCuervoG and I are presenting our study on "Scaling Properties of Speech Language Models" at #EMNLP2024. More details soon. Can't wait? come chat with us at Poster session D.

2024-10-17

Check out our latest survey on the use of #machinelearning for #bioacoustics ! We aimed to make it interesting to both biologists and computer scientists.

I had a great time working with this team.

doi.org/10.1111/brv.13155

Ricard Marxer boosted:
Dan Stowelldanstowell
2024-08-28

Great "signal analysis for biodiversity" session today at ! For me one of the interesting aspects was the diversity of sensors: sound, image, hyperspectral, DNA, and some specialist devices.

Busy research conference venue, posterboards with people clustering around explaining things to each other. You can also see some title slides from talks
Ricard Marxer boosted:
Dan Stowelldanstowell
2024-08-12

I'm excited to share this research paper, finally published!
"Bird song comparison using deep learning trained from avian perceptual judgments"
doi.org/10.1371/journal.pcbi.1
We attempted something quite audacious: instead of using human labels, or unsupervised learning, to train machine learning on animal sounds -- can we train an algorithm directly from the birds' own perceptual judgments?
How do birds hear the differences between their songs?

A group of zebra finches in the lab. Cute little fluffy birds with red beaks and colourful cheek patches. Cute eh? Wait till you listen to them...
Ricard Marxer boosted:
Dan Stowelldanstowell
2024-03-28

with us! Postdoctoral researcher (postdoc) in AI for acoustic biodiversity monitoring tiu.nu/22215 An EU-funded position using AI to monitor birds. (Please share!)

2024-03-05

EUSIPCO'24 deadline is now Mar. 10, 2024. 5 days to go, please remember to select the SS "Signal Analysis for Biodiversity" when submitting.

2024-03-01

So happy to finally be presenting this work with @clboittiaux@x.com et al.

In SUCRe, we use SfM/MVS dense reconstruction to recover colors from underwater images.

This work, funded by
@ifremer_fr will be presented at #3DV2024 in March.

#underwater #deepsea #ai #machinelearning #computervision

Ricard Marxer boosted:
Dan Stowelldanstowell
2024-03-01

Extended deadline! EUSIPCO deadline now 10th March - for everyone interested in our special session on "Signal Analysis for Biodiversity" - please do submit: mcld.co.uk/blog/2024/eusipco-2

2024-01-30

We are organising a special session on "Signal Analysis for Biodiversity", EUSIPCO'24 eusipcolyon.sciencesconf.org/ with A Härmä, @danstowell & P Somervuo. Working on #signalprocessing, #machinelearning, #artificialintelligence on #biodiversity? Submit your work! Deadline: Mar. 3, 2024

2023-10-27

Become a 4th wave student of our #ErasmusMundus #MSc in Marine and maritime Intelligent Robotics (MIR)

An international program combining #AI and #Robotics for #Ocean applications 🧠🤖🌊

Applications open tomorrow October 28th 2023

More here: master-mir.eu/emjmd-mir-new-ap

2023-08-22

Our team secured a 1st position in the Clarity Prediction Challenge 2 (claritychallenge.org). Fantastic job @tiagoCuervoG@x.com !!!

2023-07-08

Working on #bioacoustics with such a great group of people is fun and stimulating! Thank you all, and specially @arikkershenbaum @JacobCDunn @Cambridge_Uni for the invitation.

2023-06-02

Clémentin Boittiaux presenting the Homography-Based Loss at #ICRA2023 !! 👏👏

Ricard Marxer boosted:
2023-02-07

🫂 Enjoying #pyannote speaker diarization pipelines?

👥 What if it could do speaker separation as well?

🗣️ Share the word if you want to make it happen!

🥳 We are hiring!

Twice!

2 years research engineer (or postdoc) position in sunny Toulouse, France
github.com/pyannote/pyannote-a

3 years PhD position in sunny Toulon and Toulouse, France
github.com/pyannote/pyannote-a

Ricard Marxer boosted:
Christophe Cerisaracerisara@mastodon.online
2023-01-23

Chomsky at Neural Network's rescue: arxiv.org/abs/2207.02098

Ricard Marxer boosted:
Dan Stowelldanstowell
2023-01-18

Client Info

Server: https://mastodon.social
Version: 2025.04
Repository: https://github.com/cyevgeniy/lmst