Dan Oneață

Picture of Dan Oneata
oneata

Hello and welcome to my web-page! My name is Dan and I'm a research scientist at the University politehnica of Bucharest in the SpeeD lab. Previously, I have worked in the industry at Fordaq and Eloquentix. I have received my PhD in computer vision and machine learning from the Université Grenoble Alpes, where I was fortunate to work under the supervision of Cordelia Schmid and Jakob Verbeek. Before that I have received an MSc in artificial intelligence from the University of Edinburgh and I did my dissertation under Iain Murray. My research interests include general machine learning techniques and its applications to computer vision, speech, and natural language processing. I also enjoy reading about category theory and its applications.

You can find below some of my publications and presentations. The complete list of publications is available on my Google scholar profile.

Publications

Conference paper ◇ paper · poster · code · webpage
Seeing what tastes good: Revisiting multimodal distributional semantics in the billion parameter era
Findings of the Annual Meeting of the Association for Computational Linguistics, 2025
Dan Oneață, Stella Frank and Desmond Elliott.
Conference paper ◇ paper · code
The mutual exclusivity bias of bilingual visually grounded speech models
Interspeech, 2025
Dan Oneață, Leanne Nortje, Yevgen Matusevych and Herman Kamper.
Conference paper ◇ paper · code
Circumventing shortcuts in audio-visual deepfake detection datasets with unsupervised learning
IEEE Conference on Computer Vision and Pattern Recognition, 2025
Ștefan Smeu, Dragoș-Alexandru Boldișor, Dan Oneață and Elisabeta Oneață.
Conference paper ◇ paper · poster
Easy, interpretable, effective: openSMILE for voice deepfake detection
IEEE International Conference on Acoustics, Speech, and Signal Processing, 2025
Octavian Pascu, Dan Oneață, Horia Cucu and Nicolas Müller.
Conference paper ◇ paper · code · poster
Translating speech with just images
Interspeech, 2024
Dan Oneață and Herman Kamper.
Conference paper ◇ paper · code
Towards generalisable and calibrated synthetic speech detection with self-supervised representations
Interspeech, 2024
Octavian Pascu, Adriana Stan, Dan Oneață, Elisabeta Oneață and Horia Cucu.
Journal paper ◇ paper
Visually grounded speech models have a mutual exclusivity bias
Transactions of the Association for Computational Linguistics, 2024
Leanne Nortje, Dan Oneață, Yevgen Matusevych and Herman Kamper.
Journal paper ◇ paper · webpage
Visually grounded few-shot word learning in low-resource settings
IEEE/ACM Transactions on Audio, Speech, and Language, 2024
Leanne Nortje, Dan Oneață and Herman Kamper.
Translation symbol
Conference paper ◇ paper · code
Multilingual multimodal learning with machine translated text
Findings of Empirical Methods in Natural Language Processing, 2022
Chen Qiu, Dan Oneață, Stella Frank and Desmond Elliott.
Journal paper ◇ paper
Keyword localisation in untranscribed speech using visually grounded speech models
IEEE Journal of Selected Topics in Signal Processing, 2022
Kayode Olaleye, Dan Oneață and Herman Kamper.
Conference paper ◇ paper · slides
Improving multimodal speech recognition by data augmentation and speech representations
IEEE Conference on Computer Vision and Pattern Recognition Workshops, 2022
Dan Oneață and Horia Cucu.
Journal paper ◇ paper
Multimodal speech recognition for unmanned aerial vehicles
Computers & Electrical Engineering, 2021
Dan Oneață and Horia Cucu.
Conference paper ◇ paper · slides
An evaluation of word-level confidence estimation for end-to-end automatic speech recognition
IEEE Spoken Language Technology, 2021
Dan Oneață, Alexandru Caranica, Adriana Stan and Horia Cucu.
Conference paper ◇ paper
Data-filtering methods for self-training of automatic speech recognition systems
IEEE Spoken Language Technology, 2021
Lucian Georgescu, Cristian Manolache, Dan Oneață, Horia Cucu and Corneliu Burileanu.
Conference paper ◇ paper · slides · presentation · code
Revisiting SincNet: An evaluation of feature and network hyperparameters for speaker recognition
European Signal Processing Conference, 2020
Dan Oneață, Lucian Georgescu, Horia Cucu, Dragoș Burileanu and Corneliu Burileanu.
Conference paper ◇ paper · poster · webpage
Kite: Automatic speech recognition for unmanned aerial vehicles
Interspeech, 2019
Dan Oneață and Horia Cucu.
Competition report ◇ paper · code
The Quo Vadis submission at Traffic4cast 2019
arXiv, 2019
Dan Oneață, Cosmin George Alexandru, Marius Stănescu, Octavian Pascu, Alexandru Măgan, Adrian Postelnicu and Horia Cucu.
Optical flow stabilization
Journal paper ◇ paper · code
A robust and efficient video representation for action recognition
International Journal of Computer Vision, 2015
Heng Wang, Dan Oneață, Jakob Verbeek and Cordelia Schmid.
Spatio temporal proposals
Conference paper ◇ paper · poster · code
Spatio-temporal object detection proposals
European Conference on Computer Vision, 2014
Dan Oneață, Jérôme Revaud, Jakob Verbeek and Cordelia Schmid.
Approximate normalization of Fisher vectors
Conference paper ◇ paper
Efficient action localization with approximately normalized Fisher vectors
IEEE Conference on Computer Vision and Pattern Recognition, 2014
Dan Oneață, Jakob Verbeek and Cordelia Schmid.
Action recognition results
Conference paper ◇ paper · poster · code
Action and event recognition with Fisher vectors on a compact feature set
IEEE International Conference on Computer Vision, 2013
Dan Oneață, Jakob Verbeek and Cordelia Schmid.

Theses

University of Grenoble logo
Doctoral thesis ◇ thesis
Robust and efficient models for action recognition and localization
Université Grenoble Alpes, 2015
Dan Oneață
University of Edinburgh logo
Master's thesis ◇ thesis · slides
Fast low-rank metric learning
University of Edinburgh, 2011
Dan Oneață
Politehnica University of Bucharest logo
Bachelor's thesis (in Romanian) ◇ thesis
Detecția de fețe utilizând metoda Viola-Jones
University politehnica of Bucharest, 2010
Dan Oneață

Presentations

Bucharest CV logo
Paper presentation ◇ slides
Deep image prior
Bucharest CV reading group · Bucharest, Romania · February, 2018
Bucharest FP logo
Coding dojo ◇ slides · code
A simple Sudoku solver in Haskell
Bucharest FP meet-up · Bucharest, Romania · June, 2017
SpeeD lab logo
Short course ◇ lectures 1 · 2 · 3 · 4
An introduction to machine learning
Course at SpeeD lab · Bucharest, Romania · June, 2016
Eloquentix logo
Tutorial ◇ slides
An introduction to machine learning
Eloquentix annual meeting · Brașov, Romania · October, 2015
Meet up logo
Tutorial ◇ slides
Keynote format
A tutorial on action recognition in video
Grenoble Data Science meet-up · Grenoble, France · March, 2015
Thumos'14 logo
Talk ◇ slides 1 · 2
LEAR—INRIA submission at Thumos’14
THUMOS'14 workshop · Zürich, Switzerland · September, 2014
NIST logo
Talk ◇ slides
AXES @ TRECVid MED 2013
TRECVid'13 workshop · Gaithersburg, USA · November, 2013
Graphical models
Paper presentation ◇ slides
A thousand frames in just a few words
LEAR–XRCE reading group · Grenoble, France · August, 2013
Spectral learning
Paper presentation ◇ slides · extra
A spectral algorithm for learning hidden Markov models
LEAR–XRCE reading group · Grenoble, France · March, 2013
Stochastic gradient with Langevin dynamics
Paper presentation ◇ slides
Posterior sampling with stochastic gradients
LEAR reading group · Grenoble, France · July, 2012
Latent temporal model
Paper presentation ◇ slides
Learning latent temporal structure for complex event detection
LEAR reading group · Grenoble, France · August, 2012

What's new

2025-06 · Finished teaching the Research Project in Speech Technology at the BIOSINF masters program.
2025-05 · Reviewed for Interspeech, ACM Multimedia, Open Journal of Signal Processing.
2025-04 · Attended ICASSP in Hyderabad, India to present our paper Easy, interpretable, effective: openSMILE for voice deepfake detection.
2025-01 · Appointed Associate Editor at Open Journal of Signal Processing.
2024-10 · Visited the LAMP group in Copenhagen, Denmark. Thanks Desmond for hosting me!

Service

Associate Editor for Open Journal of Signal Processing (since January 2025). Reviewer for Interspeech (since 2021), ACM Multimedia (2025), Open Journal of Signal Processing, Speech Communications, Pattern Recognition, EURASIP Journal on Audio, Speech and Music Processing.

Artefacts

Writing ◇ link
Scratchpad
being a collection of notes.
Tool ◇ link
Chalk
being a declarative drawing library for Python, developed with Sasha Rush. The library's desgin is inspired by Haskell's diagrams and Scala's doodle.
Teaching ◇ A1 · A2 · A3
Assignments on speaker recognition and verification
being the coursework for the Research Project in Speech Technology course from the BIOSINF masters program.
Tool ◇ code · demo
Neural Schottky
being a method for characterizing Schottky diodes using bilevel optimization. This work done for the project SBD-SPECS project.
Project ◇ link
Vorbis: Multimodal speech recognition
being my post-doctoral project in which we attempt to improve automatic speech recognition by incorporating the visual context of what the speaker sees.
Tool ◇ link
NHLA grading tool
being an user interface implemented in Javascript that allows NHLA grading of wooden boards. The tool was developed for the Neural Grader project at Fordaq.
Code gist ◇ link
Fisher vectors
being a minimal Python implementation of the Fisher vectors method based on numpy and scikit-learn. For an application of Fisher vectors for action recognition in videos, check out the fv4a repository.
Code gist ◇ link
Sudoku
being an exploration into applicative functors and a solution to a puzzle by Conor McBride. The snippet was highlighted as an example of functor-oriented programming. For more exercises on the functorial kit checkout this other exercise from Conor McBride and Jeremy Gibbons's paper, Calculating Functional Programs.
Challenge ◇ link
Diacritics restoration
being a machine learning challenge I set up for the second-year students. The goal was to add the missing diacritics marks for a given text in Romanian.
Code ◇ link
Haskell playground
being the place where I go down the rabbit hole into the Haskell world and I toy with free monoids, comondas, anamorphisms and others.
Cheatsheet ◇ link
Algebra of programming
being an incomplete cheatsheet of equational properties in category theory to ease my way through the Algebra of Programming book.