EUVIMEDEUVIMED entdecken
Open Access · CC BY-NC-ND 4.0

A developmental model of audio-visual attention (MAVA) for bimodal language learning in infants and robots

Raphaël Bergoin, Sofiane Boucenna, Raphaël D'Urso, David Cohen, Alexandre Pitti

Scientific Reports · 2024

DOI: 10.1038/s41598-024-69245-2 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Scientific Reports, 2024. Verfasst von Raphaël Bergoin und 4 weiteren Autor:innen. Beteiligte Einrichtung: ETIS, UMR 8051, ENSEA, CY Cergy Paris Université, CNRS, Cergy-Pontoise, France. Hauptthemen laut MEDLINE: Robotics, Attention. Die Arbeit wurde bisher 1-mal zitiert (Crossref) und nennt 52 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY-NC-ND 4.0).

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

A social individual needs to effectively manage the amount of complex information in his or her environment relative to his or her own purpose to obtain relevant information. This paper presents a neural architecture aiming to reproduce attention mechanisms (alerting/orienting/selecting) that are efficient in humans during audiovisual tasks in robots. We evaluated the system based on its ability to identify relevant sources of information on faces of subjects emitting vowels. We propose a developmental model of audio-visual attention (MAVA) combining Hebbian learning and a competition between saliency maps based on visual movement and audio energy. MAVA effectively combines bottom-up and top-down information to orient the system toward pertinent areas. The system has several advantages, including online and autonomous learning abilities, low computation time and robustness to environmental noise. MAVA outperforms other artificial models for detecting speech sources under various noise conditions.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

RoboticsAttentionHumansInfantLearningVisual PerceptionLanguage DevelopmentAuditory PerceptionLanguage

Autor:innen und Institutionen

  • ETIS, UMR 8051, ENSEA, CY Cergy Paris Université, CNRS, Cergy-Pontoise, France.
  • ETIS, UMR 8051, ENSEA, CY Cergy Paris Université, CNRS, Cergy-Pontoise, France. sofiane.boucenna@cyu.fr.
  • Service de Psychiatrie de l'Enfant et de l'Adolescent, Hôpital Pitié-Salpêtrière, AP-HP, Paris, France.
  • Institut des Systèmes Intelligents et de Robotiques, Université Pierre et Marie Curie, Paris, France.

Zitieren

APA

Bergoin, R., Boucenna, S., D'Urso, R., Cohen, D., & Pitti, A. (2024). A developmental model of audio-visual attention (MAVA) for bimodal language learning in infants and robots. Scientific Reports. https://doi.org/10.1038/s41598-024-69245-2

Vancouver

Bergoin R, Boucenna S, D'Urso R, Cohen D, Pitti A. A developmental model of audio-visual attention (MAVA) for bimodal language learning in infants and robots. Scientific Reports. 2024. doi:10.1038/s41598-024-69245-2

BibTeX
@article{Bergoin2024,
  author = {Bergoin, Raphaël and Boucenna, Sofiane and D'Urso, Raphaël and Cohen, David and Pitti, Alexandre},
  title = {A developmental model of audio-visual attention (MAVA) for bimodal language learning in infants and robots},
  journal = {Scientific Reports},
  year = {2024},
  doi = {10.1038/s41598-024-69245-2}
}
Kostenlos starten →