Two engineering positions on conversational agents for Audio Mobility 2030 – 9/10/2024
These positions on conversational agents are proposed in the framework of the Audio Mobility 2030 (AM2030) project, which started in April 2023. AM2030 aims at enabling car manufacturers to have their own in-car audio application, regardless of the operating system. They will be able to deploy a global audio experience and offer the best content and proactive services to drivers. It is positioned as a true road companion that will help consumers adopt eco-responsible behaviors: vehicle self-diagnosis and maintenance reports, advice on driving and the use of on-board equipment.
Project partners: ETX Studio (Lead), Continental Automotive FRANCE SAS, Université de Toulouse – ANITI, École Polytechnique de Paris.
ANITI’s role in the project is related to working on human-computer interactions, in particular on natural language understanding. This will include a conversational model that can exploit conversational structure as well as content provided by modern transformer-based models. The model will learn constraints on the user’s preferences, from the conversation and from his previous choices.
The conversational assistant will go considerably beyond the art of current finite state dialogue systems but offering a transparency, guarantees and explainability that large transformer models by themselves cannot. It will interact with voice based components as well as a recommendation model for actions based on the information acquired by the conversational assistant.
Required skills
Applicants should have good programming skills. English communication skills are also required.
Contract : post-doc
Duration : 12 months
Salary : according to experience
Location : Computer Science Research Institute of Toulouse (IRIT), Toulouse, France
Advisor : Nicolas Asher
Application
Formal applications should include detailed CV, a motivation letter and reference letters.
Samples of published research by the candidate will be a plus.
Applications should be send by email to: asher@irit.fr
Automatic speech recognition for an in-car voice assistant – 2/10/2024
This PostDoc position is proposed in the framework of the Audio Mobility 2030 (AM2030) project, which started in April 2023. AM2030 aims at enabling car manufacturers to have their own in-car audio application, regardless of the operating system. They will be able to deploy a global audio experience and offer the best content and proactive services to drivers. It is positioned as a true road companion that will help consumers adopt eco-responsible behaviors: vehicle self-diagnosis and maintenance reports, advice on driving and the use of on-board equipment.
Project partners: ETX Studio (Lead), Continental Automotive FRANCE SAS, ANITI, Université de Toulouse, École Polytechnique de Paris.
ANITI’s role in the project is related to working on human-computer interactions, in particular on natural language understanding. The role of the hired PostDoc researcher will be to work more specifically on automatic speech (ASR, Speech-To-Text) in a noisy environment (the interior of a car).
The envisaged line of research focuses on the use of modern text-to-speech systems to generate synthetic speech data. An initial study conducted on the Google Speech Commands dataset demonstrated the feasibility of using 100% synthetic data to train a classifier satisfactorily. This study also revealed that it is still possible to easily distinguish real speech from synthetic speech using representations derived from self-supervised models such as WavLM. We aim to continue this characterization by identifying the dimensions involved in this distinction. Additionally, we seek to optimally align the distributions of real and synthetic speech in the space of self-supervised representations, using GANs or flow matching techniques.
This research will be conducted in connection
with the two other aspects treated by ANITI: 1) the study of the conversational structures between the driver and the assistant and their semantic interpretation, 2) the detection of
emotions and states of mind based on speech and transcription cues.
The hired PostDoc will be based at the Computer Science Research Institute of Toulouse (IRIT, located in the campus of the Toulouse III Paul Sabatier University.
Required skills
Applicants should have a PhD in machine learning, ideally in speech/natural language processing.
Good programming and English communication skills are also required.
Contract : post-doc
Duration : 14 months
Salary : according to experience
Location : Computer Science Research Institute of Toulouse (IRIT), Toulouse, France
Advisor : Thomas Pellegrini
Application
Formal applications should include detailed CV, a motivation letter and reference letters.
Samples of published research by the candidate will be a plus.
Applications should be send by email to Thomas Pelligrini
French 
English