Publiée 20 juillet 2026
PhD Position F/M Robust and generalizable sign-to-text translation for French and German sign languages
Inria
Nancy, Grand-Est 54000, France
CDI
Contexte et atouts du poste
The PhD project will be carried out in the MULTISPEECH team at Loria . The PhD candidate will be supervised by Slim Ouni (professor, University of Lorraine) and Mostafa Sadeghi (researcher, Inria), and will benefit from the research environment, expertise, and powerful computational resources (GPUs & CPUs) of the team.
This PhD position is fully funded within the framework of RoGSiLT: Robust and Generalizable Sign Language Translation , a collaborative research project between Inria in France and DFKI in Germany. The project aims to advance AI-based translation technologies for French Sign Language (LSF) and German Sign Language (DGS), covering both translation from sign-language videos into written language and translation from written language into sign language. The PhD candidate will work with the Inria team and collaborate closely with DFKI, with a specific focus on the data, alignment, and representation-learning foundations required for robust and generalizable sign-to-text translation.
Mission confiée
Motivation and context
Sign languages are natural languages with their own grammar, structure, and rich visual-expressive features. Unlike spoken languages, they convey meaning through a combination of hand movements, body posture, facial expressions, mouthing, spatial organization, and timing. Automatic translation from sign language videos into written text therefore requires modelling complex visual and temporal information, rather than simply recognizing isolated gestures.
A common approach in sign language translation relies on glosses, i.e., written labels that roughly represent signs using words from a spoken language. Glosses are useful as an intermediate representation, but they are costly to annotate, scarce for many sign languages, and unable to capture the full linguistic richness of signed communication, such as facial grammar, spatial references, or prosody. As a result, existing systems often depend on limited gloss-annotated data, generalize poorly across signers and recording conditions, and produce translations that lack fluency, completeness, or semantic accuracy [1].
Principales activités
Project description
The PhD project will contribute to the development of robust and generalizable sign-to-text translation for low-resource sign languages, with a focus on LSF and DGS. Rather than concentrating only on the final translation model, the PhD will address the upstream components that are essential for reliable sign-to-text translation: data collection and curation, privacy-aware data processing, automatic video-text alignment, and sign-language representation learning.
A first objective will be to identify, collect, structure, and curate sign-language video resources for LSF and DGS, for which available resources remain more limited than for some other sign languages and domains [2,3]. The work will exploit existing and newly identified video-text resources, including open repositories and potential data sources from associations or broadcasters. Since sign-language data typically consists of videos of identifiable signers, the PhD will also address privacy and ethical challenges, including consent, anonymization, secure data handling, metadata quality, and linguistic diversity.
A second objective will be to develop automatic methods for aligning sign-language videos with corresponding written transcriptions, subtitles, or other textual material. Such alignment is essential for transforming raw or weakly structured video-text data into resources that can be used for machine learning. The PhD will therefore investigate multimodal approaches that connect visual sign-language information with textual representations under low-resource conditions, using techniques from computer vision, natural language processing, and representation learning [4,5].
A third objective will be to study how sign-language videos can be represented in a way that captures the visual and temporal complexity of signed communication, including manual signs, body posture, facial expression, mouthing, spatial structure, and timing. The PhD will explore how sign-language-specific pre-trained and multimodal models can be adapted to LSF and DGS data, in order to support video-text alignment, representation learning, and downstream sign-to-text translation [9,10].
Implementation plan
The first stage of the PhD will focus on data collection and curation. The candidate will identify and gather relevant LSF and DGS video-text resources from open repositories and other potential sources. This will include the analysis of available metadata, text-video correspondence, recording conditions, signer variation, and data quality. Particular attention will be paid to privacy-aware processing, including anonymization strategies, secure data handling, and the possible use of pose-based or derived representations to reduce identifiability.
The second stage will focus on automatic alignment between sign-language videos and written text. The candidate will investigate methods for aligning videos with subtitles, transcriptions, or other textual material, to transform weakly structured data into usable training and evaluation resources. This work may involve temporal segmentation, visual feature extraction, sentence-level semantic representations, multimodal similarity learning, and Transformer-based or CLIP-like architectures adapted to sign-language data [4,5].
The third stage will explore the use of pre-trained and foundation models for sign-language representation learning. The candidate will study how computer vision models, multimodal models, and large language models can be adapted or fine-tuned for sign-language data. This may include keypoint-based, video-based, or hybrid representations, as well as weakly supervised or contrastive learning strategies for connecting visual and textual information.
In the final stage, the developed data-processing, alignment, and representation-learning components will be assessed in relation to downstream sign-to-text translation. The work will include quantitative and qualitative analysis of alignment quality, robustness across data sources and signers, and the usefulness of the learned representations for translation-oriented tasks. While the PhD is not primarily centred on evaluation methodology, the candidate will use appropriate automatic and human-informed analyses to validate the proposed methods [6].
Expected outcomes
The PhD candidate is expected to contribute to both scientific knowledge and practical resources for the sign language technology community. Expected outcomes may include:
[1] N. C. Camgöz, S. Hadfield, O. Koller, H. Ney, and R. Bowden, "Neural Sign Language Translation," in Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR) , 2018.
[2] J. Forster, C. Schmidt, O. Koller, M. Bellgardt, and H. Ney, "Extensions of the Sign Language Recognition and Translation Corpus RWTH-PHOENIX-Weather," in Proceedings of the International Conference on Language Resources and Evaluation (LREC) , 2014.
[3] J. Halbout, D. Fabre, Y. Ouakrim, J. Lascar, A. Braffort, et al., "Matignon-LSF: A Large Corpus of Interpreted French Sign Language," in Proceedings of the LREC-COLING Workshop on the Representation and Processing of Sign Languages , 2024.
[4] H. Bull, T. Afouras, G. Varol, S. Albanie, L. Momeni, and A. Zisserman, "Aligning Subtitles in Sign Language Videos," in Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV) , 2021.
[5] Y. Hamidullah, J. van Genabith, and C. España-Bonet, "Sign Language Translation with Sentence Embedding Supervision," in Proceedings of the Annual Meeting of the Association for Computational Linguistics (ACL), Short Papers , 2024.
[6] M. Müller et al., "Findings of the Second WMT Shared Task on Sign Language Translation," in Proceedings of the Conference on Machine Translation (WMT) , 2023.
[7] G. Fauré, M. Sadeghi, S. Bigeard, and S. Ouni, "Towards Skeletal and Signer Noise Reduction in Sign Language Production via Quaternion-Based Pose Encoding and Contrastive Learning," in Proceedings of SLTAT 2025: 9th Workshop on Sign Language Translation and Avatar Technologies , 2025.
[8] G. Fauré, M. Sadeghi, S. Bigeard, and S. Ouni, "The Impact of VAE Design on Latent Pose Representations for Diffusion-based Sign Language Production," in Proceedings of GenSign: Generative AI for Sign Language, CVPR 2026 Workshop , 2026.
[9] Z. Jiang, G. Sant, A. Moryossef, M. Müller, R. Sennrich, and S. Ebling, "SignCLIP: Connecting Text and Sign Language by Contrastive Learning," in Proceedings of the Conference on Empirical Methods in Natural Language Processing (EMNLP), pp. 9171-9193, 2024.
[10] P. Jiao, Y. Min, and X. Chen, "Visual Alignment Pre-training for Sign Language Translation," in Proceedings of the European Conference on Computer Vision (ECCV), pp. 349-367, 2024.
Compétences
Applicants should have, or be close to obtaining, a Master's degree or equivalent in computer science, artificial intelligence, computational linguistics, natural language processing, computer vision, machine learning, or a related field.
A strong candidate will have experience or interest in several of the following areas:
Programming experience in Python and familiarity with deep learning frameworks such as PyTorch are expected. Knowledge of sign languages, LSF, DGS, or Deaf studies is welcome but not mandatory. The candidate should be willing to work in an interdisciplinary and collaborative setting.
Avantages
Rémunération
2300€ gross/month
The PhD project will be carried out in the MULTISPEECH team at Loria . The PhD candidate will be supervised by Slim Ouni (professor, University of Lorraine) and Mostafa Sadeghi (researcher, Inria), and will benefit from the research environment, expertise, and powerful computational resources (GPUs & CPUs) of the team.
This PhD position is fully funded within the framework of RoGSiLT: Robust and Generalizable Sign Language Translation , a collaborative research project between Inria in France and DFKI in Germany. The project aims to advance AI-based translation technologies for French Sign Language (LSF) and German Sign Language (DGS), covering both translation from sign-language videos into written language and translation from written language into sign language. The PhD candidate will work with the Inria team and collaborate closely with DFKI, with a specific focus on the data, alignment, and representation-learning foundations required for robust and generalizable sign-to-text translation.
Mission confiée
Motivation and context
Sign languages are natural languages with their own grammar, structure, and rich visual-expressive features. Unlike spoken languages, they convey meaning through a combination of hand movements, body posture, facial expressions, mouthing, spatial organization, and timing. Automatic translation from sign language videos into written text therefore requires modelling complex visual and temporal information, rather than simply recognizing isolated gestures.
A common approach in sign language translation relies on glosses, i.e., written labels that roughly represent signs using words from a spoken language. Glosses are useful as an intermediate representation, but they are costly to annotate, scarce for many sign languages, and unable to capture the full linguistic richness of signed communication, such as facial grammar, spatial references, or prosody. As a result, existing systems often depend on limited gloss-annotated data, generalize poorly across signers and recording conditions, and produce translations that lack fluency, completeness, or semantic accuracy [1].
Principales activités
Project description
The PhD project will contribute to the development of robust and generalizable sign-to-text translation for low-resource sign languages, with a focus on LSF and DGS. Rather than concentrating only on the final translation model, the PhD will address the upstream components that are essential for reliable sign-to-text translation: data collection and curation, privacy-aware data processing, automatic video-text alignment, and sign-language representation learning.
A first objective will be to identify, collect, structure, and curate sign-language video resources for LSF and DGS, for which available resources remain more limited than for some other sign languages and domains [2,3]. The work will exploit existing and newly identified video-text resources, including open repositories and potential data sources from associations or broadcasters. Since sign-language data typically consists of videos of identifiable signers, the PhD will also address privacy and ethical challenges, including consent, anonymization, secure data handling, metadata quality, and linguistic diversity.
A second objective will be to develop automatic methods for aligning sign-language videos with corresponding written transcriptions, subtitles, or other textual material. Such alignment is essential for transforming raw or weakly structured video-text data into resources that can be used for machine learning. The PhD will therefore investigate multimodal approaches that connect visual sign-language information with textual representations under low-resource conditions, using techniques from computer vision, natural language processing, and representation learning [4,5].
A third objective will be to study how sign-language videos can be represented in a way that captures the visual and temporal complexity of signed communication, including manual signs, body posture, facial expression, mouthing, spatial structure, and timing. The PhD will explore how sign-language-specific pre-trained and multimodal models can be adapted to LSF and DGS data, in order to support video-text alignment, representation learning, and downstream sign-to-text translation [9,10].
Implementation plan
The first stage of the PhD will focus on data collection and curation. The candidate will identify and gather relevant LSF and DGS video-text resources from open repositories and other potential sources. This will include the analysis of available metadata, text-video correspondence, recording conditions, signer variation, and data quality. Particular attention will be paid to privacy-aware processing, including anonymization strategies, secure data handling, and the possible use of pose-based or derived representations to reduce identifiability.
The second stage will focus on automatic alignment between sign-language videos and written text. The candidate will investigate methods for aligning videos with subtitles, transcriptions, or other textual material, to transform weakly structured data into usable training and evaluation resources. This work may involve temporal segmentation, visual feature extraction, sentence-level semantic representations, multimodal similarity learning, and Transformer-based or CLIP-like architectures adapted to sign-language data [4,5].
The third stage will explore the use of pre-trained and foundation models for sign-language representation learning. The candidate will study how computer vision models, multimodal models, and large language models can be adapted or fine-tuned for sign-language data. This may include keypoint-based, video-based, or hybrid representations, as well as weakly supervised or contrastive learning strategies for connecting visual and textual information.
In the final stage, the developed data-processing, alignment, and representation-learning components will be assessed in relation to downstream sign-to-text translation. The work will include quantitative and qualitative analysis of alignment quality, robustness across data sources and signers, and the usefulness of the learned representations for translation-oriented tasks. While the PhD is not primarily centred on evaluation methodology, the candidate will use appropriate automatic and human-informed analyses to validate the proposed methods [6].
Expected outcomes
The PhD candidate is expected to contribute to both scientific knowledge and practical resources for the sign language technology community. Expected outcomes may include:
- Curated or enriched LSF and DGS video-text resources;
- Improved automatic alignment methods for sign videos and written text;
- Multimodal representations of sign-language videos suitable for downstream translation;
- Adaptation of pre-trained computer vision, multimodal, and language models to sign-language data;
- Open-source implementations of data-processing, alignment, and modelling components;
- Experimental analyses demonstrating the usefulness of the proposed methods for sign-to-text translation;
- Publications in leading conferences and workshops in NLP, computer vision, or sign language technology.
[1] N. C. Camgöz, S. Hadfield, O. Koller, H. Ney, and R. Bowden, "Neural Sign Language Translation," in Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR) , 2018.
[2] J. Forster, C. Schmidt, O. Koller, M. Bellgardt, and H. Ney, "Extensions of the Sign Language Recognition and Translation Corpus RWTH-PHOENIX-Weather," in Proceedings of the International Conference on Language Resources and Evaluation (LREC) , 2014.
[3] J. Halbout, D. Fabre, Y. Ouakrim, J. Lascar, A. Braffort, et al., "Matignon-LSF: A Large Corpus of Interpreted French Sign Language," in Proceedings of the LREC-COLING Workshop on the Representation and Processing of Sign Languages , 2024.
[4] H. Bull, T. Afouras, G. Varol, S. Albanie, L. Momeni, and A. Zisserman, "Aligning Subtitles in Sign Language Videos," in Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV) , 2021.
[5] Y. Hamidullah, J. van Genabith, and C. España-Bonet, "Sign Language Translation with Sentence Embedding Supervision," in Proceedings of the Annual Meeting of the Association for Computational Linguistics (ACL), Short Papers , 2024.
[6] M. Müller et al., "Findings of the Second WMT Shared Task on Sign Language Translation," in Proceedings of the Conference on Machine Translation (WMT) , 2023.
[7] G. Fauré, M. Sadeghi, S. Bigeard, and S. Ouni, "Towards Skeletal and Signer Noise Reduction in Sign Language Production via Quaternion-Based Pose Encoding and Contrastive Learning," in Proceedings of SLTAT 2025: 9th Workshop on Sign Language Translation and Avatar Technologies , 2025.
[8] G. Fauré, M. Sadeghi, S. Bigeard, and S. Ouni, "The Impact of VAE Design on Latent Pose Representations for Diffusion-based Sign Language Production," in Proceedings of GenSign: Generative AI for Sign Language, CVPR 2026 Workshop , 2026.
[9] Z. Jiang, G. Sant, A. Moryossef, M. Müller, R. Sennrich, and S. Ebling, "SignCLIP: Connecting Text and Sign Language by Contrastive Learning," in Proceedings of the Conference on Empirical Methods in Natural Language Processing (EMNLP), pp. 9171-9193, 2024.
[10] P. Jiao, Y. Min, and X. Chen, "Visual Alignment Pre-training for Sign Language Translation," in Proceedings of the European Conference on Computer Vision (ECCV), pp. 349-367, 2024.
Compétences
Applicants should have, or be close to obtaining, a Master's degree or equivalent in computer science, artificial intelligence, computational linguistics, natural language processing, computer vision, machine learning, or a related field.
A strong candidate will have experience or interest in several of the following areas:
- Machine learning and deep learning;
- Natural language processing or neural machine translation;
- Computer vision or video understanding;
- Multimodal learning;
- Large language models.
Programming experience in Python and familiarity with deep learning frameworks such as PyTorch are expected. Knowledge of sign languages, LSF, DGS, or Deaf studies is welcome but not mandatory. The candidate should be willing to work in an interdisciplinary and collaborative setting.
Avantages
- Subsidized meals
- Partial reimbursement of public transport costs
- Leave: 7 weeks of annual leave + 10 extra days off due to RTT (statutory reduction in working hours) + possibility of exceptional leave (sick children, moving home, etc.)
- Possibility of teleworking (after 6 months of employment) and flexible organization of working hours
- Professional equipment available (videoconferencing, loan of computer equipment, etc.)
- Social, cultural and sports events and activities
- Access to vocational training
- Social security coverage
Rémunération
2300€ gross/month
