PhD Position F/M Explainable and frugal audio scene description
il y a 4 semaines
Contexte et atouts du poste
Inria Défense&Sécurité (Inria D&S) was created in 2020 to federate Inria’s actions for the benefit of military forces. The PhD will be carried out within the audio processing research team of Inria D&S, under the supervision of Jean-François Bonastre and co-supervised by Raphaël Duroselle.
The automatic audio scene description task is to present operators with a summary of the information present in the scene, in the form of augmented text. This text provides a visual summary of the most important information, while efficiently structuring access to specific information. Here is an illustrative example of a summary: « This five-minute recording features three different speakers. Speaker A corresponds to a known identity in the database and speaks French with a strong Monawa accent, speakers B and C are unknown in the database and speak English in their interactions with A and use an unidentified language when talking to each other. The voices of B and C show strong similarities with speakers from the Eastern Quabar region. The main theme of the recording concerns a transfer of goods between the cities of Orienta and Flagrance. The date July 8, 2023 is mentioned three times.». Clicking on A gives the operator information about A and details of the voice identification performed. There will be direct access to the time segments during which A spoke and to their transcription. The transcription will highlight names of people, places or dates (named entities).
Mission confiée
Goal
The aim of this thesis is to propose a general framework for processing audio recordings for intelligence purposes. It consists in defining a high-level application adapted to the needs of end users, favouring the presentation of a recording in the form of a summary report to highlight its salient points.
Approach
This approach is inspired both by textual description of video scenes [1] and by dialogue systems based on audio-visual scenes [2]. The system will be based on the extraction of speech signal representations at different scales (frame, speech segment or sound event, complete recording), possibly dedicated to different tasks. The representations, useful for the various technological bricks of the system, will be embeddings extracted from deep neural networks, either generic [3] or dedicated to each task. The fusion between the different levels of information can be achieved with an architecture inspired by the multi-stream "Encoder-Decoder" scheme [4], with several encoders producing sequences of representations and one or more decoders performing the tasks or sub-tasks required by the system. One of these decoders will produce a textual summary of the scene.
Potential research directions, aiming to go beyond an audio scene description system by assembling existing bricks, can be discussed and refined with the candidate.
Principales activités
Bibliography, development and evaluation of deep learning systems ; Definition of a new task, definition of a corpus and evaluation protocol ; Work on the alignment between self-supervised representations of the speech signal and large language models ; Weakly supervised system training ; System evaluation.
Compétences
Master level in computer science, mathematics or phonetics.
Strong interest in applied research.
Written and spoken English
Signal processing
Machine learning and deep learning
Experience with deep learning toolkits such as pytorch or keras
Speech processing experience, knowledge of open source toolkits such as kaldi or speechbrain.
References
[1] Aafaq, N., Mian, A., Liu, W., Gilani, S. Z., & Shah, M. . Video description: A survey of methods, datasets, and evaluation metrics. ACM Computing Surveys (CSUR), 52, 1-37.
[2] Hori, Chiori, Huda Alamri, Jue Wang, Gordon Wichern, Takaaki Hori, Anoop Cherian, Tim K. Marks, et al. « End-to-End Audio Visual Scene-Aware Dialog Using Multimodal Attention-Based Video Features ». In ICASSP 2019 - 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 2352‑56. Brighton, United Kingdom: IEEE, 2019. [3] Zhang, C., & Tian, Y. (2016, December). Automatic video description generation via lstm with joint two-stream encoding. In 2016 23rd International Conference on Pattern Recognition (ICPR) (pp. 2924-2929). IEEE.
[4] Pratap, Vineel, Andros Tjandra, Bowen Shi, Paden Tomasello, Arun Babu, Sayani Kundu, Ali Elkahky, et al. 2023. « Scaling Speech Technology to 1,000+ Languages ». arXiv.
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 and flexible organization of working hours, Professional equipment available (videoconferencing, loan of computer equipment, etc.), Social, cultural and sports events and activities,
Rémunération
1st and 2nd year : 2082 € bruts - gross /month 3rd year : 2190 € bruts - gross /month-
Paris, France INRIA Temps pleinContexte et atouts du poste Inria Défense&Sécurité (Inria D&S) a été créé en 2020 pour fédérer les actions d’Inria répondant aux besoins numériques des forces armées et forces de l’intérieur. La thèse sera réalisée au sein de l’équipe de recherche en traitement de l’audio de Inria D&S, sous la direction de Jean-François...
-
Audio Editor
il y a 4 semaines
Paris, France Tongues Translation Services LLC Temps pleinThis is a remote position. We are looking for a talented audio editor as our go-to source for audio editing needs on the projects. To guarantee that expectations and timelines are followed, the audio editor must be experienced in the post-production process. The ideal applicant will have prior experience editing audio-books and podcasts. The ideal applicant...
-
Paris, France INRIA Temps pleinPhD Position F/M Campagne Doctorant: verification of Linux kernel source code Le descriptif de l’offre ci-dessous est en Anglais Type de contrat : CDD Niveau de diplôme exigé : Bac + 5 ou équivalent Fonction : Doctorant Mission confiée Understand the opportunities and challenges that arise in verifying the source code of...
-
Post-doctoral position in the “Immunity and Cancer”
il y a 4 semaines
Paris, France Institut Curie Temps pleinThe department of Immunology headed by Ana-Maria Lennon-Duménil is actively looking for a Post-doc motivated to work on an ambitious project in translational Immunology. Institut Curie ( is one of the most renowned European institutions for cancer research with a strong interdisciplinary tradition. It is located in the center of Paris, in a culturally and...
-
PhD Position F/M
il y a 2 semaines
Paris, France INRIA Temps pleinContexte et atouts du poste The selected candidate will do her/his research at the OURAGAN team which is a joint team of Inria Paris and IMJ-PRG Sorbonne Université. She/he will be located at Sorbonne University and she/he will work with Elias Tsigaridas. Mission confiée Singular Learning Theory (SLT) is a framework in statistical...
-
PhD Program Manager
il y a 4 semaines
Paris, France Institut Curie Temps pleinThe Institut Curie Research CenterInstitut Curie is a major player in research and the fight against cancer. It brings together an advanced Hospital Group and an internationally renowned Research Centre with over 1,000 aim of Institut Curie’s Research Center is to develop cutting-edge fundamental research and apply it to improve the diagnosis, prognosis...
-
PhD Position F/M
il y a 1 semaine
Paris, France INRIA Temps pleinContexte et atouts du poste The MIMOVE team at Inria Paris undertakes research enabling next-generation mobile distributed systems, from their conception and design to their runtime support, focusing on middleware and data. MIMOVE has longstanding expertise in mobile and service-oriented computing, semantic technologies, interoperability, system...
-
Postdoc Position: Crosstalk Between Tumorigenesis
il y a 4 semaines
Paris, France Springer Nature Temps plein**Postdoc position: Crosstalk between tumorigenesis and microglia development at Paris Brain Institute**: - Employer- Paris Brain Institute - Franck Bielle Lab- Location- Paris, Ile-de-France (FR)- Salary- 29,000 Euros/yr net- Closing date- 17 Mar 2024- Discipline Life Science Job Type Postdoctoral Employment - Hours Full time Duration Fixed term ...
-
A Post-doctoral Researcher Position
il y a 4 semaines
Paris 13e, France ICM Institut du Cerveau Temps plein**The Paris Brain Institute (ICM) is recruiting a Post-Doctoral Researcher position** **3-year position starting March 2023** - The Paris Brain Institute ICM is a private foundation recognized as being of public utility, whose purpose is fundamental and clinical research on the nervous system, located in the heart of the Salpêtrière Hospital in Paris....
-
Innovative Product Development Officer
il y a 4 semaines
Paris, France ProductLife Group Temps pleinGroup 10 Responsibilities ProductLife Group provides world-class regulatory outsourcing and consulting services for the global life sciences industry. Founded in 1994, it has since become a global industry leader, thanks to the firm’s driven and talented employees, who are always motivated by a supportive team environment as well as...
-
PhD Position F/M Modeling of large communication networks
il y a 4 semaines
Paris, France INRIA Temps pleinContexte et atouts du poste The position is funded by the national program on communication networks (PEPR réseaux du Futur, research will be conducted at INRIA and Télécom Paris in LINCS, a joint laboratory on communication networks. Here are links to the relevant laboratories: DYOGENE: LINCS: Mission confiée Conduct research in...
-
Operations Management: Postdoctoral Position
il y a 4 semaines
Paris, France IÉSEG School of Management Temps plein**ABOUT IÉSEG SCHOOL OF MANAGEMENT** **ABOUT THE DEPARTMENT** Our department counts 10+ permanent faculty members from researchers to professors of practice, 5+ teaching and research assistants and post-docs, and several visiting and adjunct professors. Our faculty, academics and accomplished professionals, have a wide range of professional backgrounds in...
-
Senior Director Biostatistics and Statistical
il y a 11 heures
Paris, France Alira Health Temps pleinJoin our global team dedicated to innovation and initiative, where physical walls and different time zones don’t limit, but encourage, collaboration. Where all contributions and new ideas are explored with an open mind and work is driven by our shared values: be courageous, be accountable, be honest, be inclusive and elevate others. Job Description...
-
Ai Research Scientist
il y a 5 jours
Paris, France Meta Temps plein**AI Research Scientist (Leadership) Responsibilities**: - Help Advance the science and technology of intelligent machines - Contribute to research that enables learning the semantics of data (images, video, text, audio and other modalities) - Work on projects, strategies, and problems of moderate to high complexity and scope. Can identify and define both...
-
Paris, France Groupe Français de Rhéologie Temps pleinThèse - PhD Thesis in partnership with Stellantis - Industrial dip-coating process study using complex shapes and non-Newtonian fluids Description : Full description : Context : Dip-coating processes consist in covering an object with a thin layer of liquid, using sequences of immersion in a bath and removal at well-chosen speeds and...
-
Paris, France INRIA Temps pleinContexte et atouts du poste You will work within the ARAMIS Lab ( The PhD thesis will be co-directed by Ninon Burgos (Research Scientist, HDR) and Olivier Colliot (Research Director). The position is funded through the GALAN project, a large-scale national grant in collaboration between the ARAMIS Lab, the Lille Neurosciences and Cognition Research...
-
Experienced Consultant
il y a 4 semaines
Paris, France Amaris Consulting Temps pleinJob description Health Economics and Market Access Department: We have a worldwide presence ensuring key market expertise and efficiency in delivery. We have offices in Montreal, Toronto, London, Paris, Barcelona, Sofia & Shanghai. We are a diverse team of 15 different nationalities. We offer services for 5 major...
-
Paris, France INRIA Temps pleinContexte et atouts du poste We propose a PhD in co-supervision the Antique INRIA team (INRIA Paris, located at ENS Paris); the MaBioS CNRS research group (I2M, Marseille Institute of Mathematics). The main goal is to develop theoretical results on the impact on the dynamics of the Boolean networks when their regulatory functions are...
-
Professorship in Computer Science and/or Applied Mathematics
il y a 4 semaines
Paris, Île-de-France Université Paris 1 Panthéon-Sorbonne Temps pleinThe University Paris 1 Panthéon-Sorbonne is opening a position for a Tenure Track Professorship (Junior Professor Chair) in Computer Science and/or Applied Mathematics, in the field ofAlgorithms and Regulation for Socioeconomic NetworksDescriptionThis is a primarily research-oriented position focusing on the dynamics of Socio-Economic Networks and in...
-
Ai Research Scientist, Intern
il y a 7 jours
Paris, France Meta Temps plein**AI Research Scientist, Intern - FAIR Labs, Brain and AI (MSc, PhD) Responsibilities**: - Perform research to advance the science and technology of intelligent machines - Perform research that enables learning the semantics of data (images, video, text, audio, and other modalities) - Devise better data-driven models of AI system design and optimization -...
