MOOCs gratuits : catalogue de cours en ligne ouverts et massifs
MOOC Binaural Hearing for Robots
This MOOC describes the computational principles of binaural hearing. How these principles could be implemented on a robot head and how they could lead towards robust interaction capabilities.
Informations pratiques sur le MOOC Binaural Hearing for Robots
- Type: MOOC, cours en ligne, quizz
- Temps d'apprentissage: 5 semaines
- Niveau: à partir du niveau master
- Durée: 02:00h/semaine
- Langues: anglais
- Contenu: vidéos
- Public cible: étudiants en sciences, doctorants, chercheurs et praticiens
- Age attendu: 21 et +
- Droits: Licence Creative Commons BY-NC-ND
Description du MOOC Binaural Hearing for Robots
Robots have gradually moved from factory floors to populated areas. Therefore, there is a crucial need to endow robots with perceptual and interaction skills enabling them to communicate with people in the most natural way. With auditory signals distinctively characterizing physical environments and speech being the most effective means of communication among people, robots must be able to fully extract the rich auditory information from their environment.
This MOOC will address fundamental issues in robot hearing. It will describe methodologies requiring two or more microphones embedded into a robot head, thus enabling sound-source localization, sound-source separation, and fusion of auditory and visual information.
- The MOOC will start by briefly describing the role of hearing in human-robot interaction, overviewing the human binaural system, and introducing the computational auditory scene analysis paradigm. Then, it will describe in detail : sound propagation models
- audio signal processing techniques
- geometric models for source localization
- unsupervised and supervised machine learning techniques for characterizing binaural hearing
- fusing acoustic and visual data
- designing practical algorithms
The MOOC will be illustrated with numerous videos shot in the author's laboratory.
Five weeks for this course. Every week consists in approximately 10 sessions (each one containing a video about 6 minutes).
Plan du MOOC
- Week 1 : Introduction to Robot Hearing
- Week 2 : Methodological Foundations
- Week 3 : Sound-Source Localization
- Week 4 : Machine Learning and Binaural Hearing
- Week 5 : Fusion of Audio and Vision
Quizz are associated to session.
- Public visé : The MOOC is intended for Master of Science students with good background in signal processing and machine learning. The MOOC is also valuable to PhD students, researchers and practitioners, who work in signal and image processing, machine learning, robotics, or human-machine interaction, and who wish to acquire competences in binaural hearing methodologies.
- The MOOC material will allow the attendants to design and develop robot and machine hearing algorithms.
- Pré-requis : Introductory courses in digital signal processing, probability and statistics, computer science.
Objectif pédagogique du MOOC
- Objectif : Describe the importance of Hearing for Robots in these interaction with people.
- of the course : Licence Creative Commons BY-NC-ND : the name of the author should always be mentionned. The user may not use the material for commercial purposes. The user can exploit the work except in a commercial context and he cannot make changes in the original work.
- of the content produced by users : Licence Creative Commons BY-NC-ND : the name of the author should always be mentioned. The user may not use the material for commercial purposes.The user can exploit the work except in a commercial context and he cannot make changes in the original work.
- Radu Horaud
INRIA Grenoble Rhône-Alpes
- MOOC Mobile robots and autonomous vehicles
- MOOC Optique non-linéaire
- Lancement de ma-fac2sciences.fr
- Faq2Sciences - Poursuite des actions d'orientation et d'appui à l'entrée à l'université pour les filières scientifiques
- Faq2Sciences : pour vous évaluer, conforter votre orientation et vous remettre à niveau