Autonomous Sensorimotor Learning for Sound Source Localization by a Humanoid Robot - Archive ouverte HAL Accéder directement au contenu
Communication Dans Un Congrès Année : 2018

Autonomous Sensorimotor Learning for Sound Source Localization by a Humanoid Robot

Résumé

We consider the problem of learning to localize a speech source using a humanoid robot equipped with a binaural hearing system. We aim to map binaural audio features into the relative angle between the robot's head direction and the target source direction based on a sensorimotor training framework. To this end, we make the following contributions: (i) a procedure to automatically collect and label audio and motor data for sensorimotor training; (ii) the use of a convolutional neural network (CNN) trained with white noise signal and ground truth relative source direction. Experimental evaluation with speech signals shows that the CNN can localize the speech source even without an explicit algorithm for dealing with missing spectral features.
Fichier principal
Vignette du fichier
IROS2018_CLIR_Quan_camera_ready.pdf (2.54 Mo) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)
Loading...

Dates et versions

hal-01921882 , version 1 (14-11-2018)

Identifiants

  • HAL Id : hal-01921882 , version 1

Citer

Quan Nguyen, Laurent Girin, Gérard Bailly, Frédéric Elisei, Duc-Canh Nguyen. Autonomous Sensorimotor Learning for Sound Source Localization by a Humanoid Robot. IROS 2018 - Workshop on Crossmodal Learning for Intelligent Robotics in conjunction with IEEE/RSJ IROS, Oct 2018, Madrid, Spain. ⟨hal-01921882⟩
249 Consultations
117 Téléchargements

Partager

Gmail Facebook X LinkedIn More