Combinaison de modèles profonds et syntaxiques pour un système auto-adaptatif de reconnaissance de partitions musicales historiques

Context : Collabscore project

Collabscore is a project founded by ANR (French Research National Agency), led by the CNAM. The goal is to study ancient scores provided by the BNF (Bibliothèque National de France) and Royaumont foundation. Collabscore is a multidisciplinary project. The first task consists in improving OMR (Optical Music Recognition) results using learning techniques. The second action will focus on methods for automatic alignment of the scored score with other multimodal sources. The last one will set up demonstrators based on notated scores at two of the project partners, representative, in various ways, of institutions in charge of musical heritage collections (BnF and Fondation Royaumont). Intuidoc team focuses on the first task of musical score recognition.

Position to be filled

Position: Post-doctoral fellow / engineer

Time commitment: Full-time

Duration of the contract: Up to 32 months (January 1st 2022  (or later)– July 31st 2024)

Supervisors: Bertrand Coüasnon, Aurélie Lemaitre, Yann Soullard

Indicative salary: Up to €36 000 gross annual salary (according to experience),
with social security benefits

Location: IRISA – Rennes


The post-doctoral/engineer fellow will work on the conception of a OMR system. Based on previous works of our research team [Coüasnon & Lemaitre 2017, Pacha et al. 2018], the goal of this position is to enrich an existing system (DMOS-PI) to get a complete self-adaptative OMR system for historical orchestra scores. The tasks are mainly:

  • define a grammatical description of musical notation, using the existing DMOS-PI method;
  • generate unsupervised data for training musical symbols recognizers, using the Isolating-GAN, a novel unsupervised music symbol detection method based on Generative Adversarial Network (GAN);
  • create a gradual mechanism for adapting the system to new partitions to build a self-adaptive system with few annotated data;
  • integrate anomaly detection into the system.

Logical programming from grammars and languages is expected in this work. Machine Learning methods, especially Deep learning-based approaches (GAN, RCNN, SSD…), will be used to solve some of the tasks, as done in our previous works on music symbol detection [ Choi et al. 2019, Choi et al. 2018].

Main Skills

PhD in computer science or Master degree

Experience in document recognition or statistical analysis, skills in grammars and languages and/or logical programming are nice-to-have, as well as knowledge of music notation.

Knowledge in deep learning with an experience with at least one library dedicated to deep learning (Keras, Tensorflow, Pytorch) are expected, but not mandatory.


Candidates should contact via email:, ,


[Coüasnon & Lemaitre 2017] Coüasnon, B., & Lemaitre, A. (2017, November). DMOS, It’s your turn!. In 1st International Workshop on Open Services and Tools for Document Analysis (ICDAR-OST).

[Choi et al. 2019] Choi, K. Y., Coüasnon, B., Ricquebourg, Y., & Zanibbi, R. (2019, September). CNN-Based Accidental Detection in Dense Printed Piano Scores. In 2019 International Conference on Document Analysis and Recognition (ICDAR) (pp. 473-480). IEEE.

[Choi et al. 2018] Choi, K. Y., Coüasnon, B., Ricquebourg, Y., & Zanibbi, R. (2018, September). Music Symbol Detection with Faster R-CNN Using Synthetic Annotations. In 1st International Workshop on Reading Music Systems.

[Pacha et al. 2018] Pacha, A., Choi, K. Y., Coüasnon, B., Ricquebourg, Y., Zanibbi, R., & Eidenberger, H. (2018, April). Handwritten music object detection: Open issues and baseline results. In 2018 13th IAPR International Workshop on Document Analysis Systems (DAS) (pp. 163-168). IEEE.

Voir la fiche de poste