Effective Acoustic Model-Based Beamforming Training for Static and Dynamic Hri Applications
Sensors · 2024
DOI: 10.3390/s24206644 ↗Kurz gefasst
Fachartikel in der Zeitschrift Sensors, 2024. Verfasst von Alejandro Luzanto und 5 weiteren Autor:innen. Beteiligte Einrichtung: Speech Processing and Transmission Laboratory, Electrical Engineering Department, University of Chile, Santiago 8370451, Chile. Hauptthemen laut MEDLINE: Acoustics, Robotics. Die Arbeit wurde bisher 1-mal zitiert (Crossref) und nennt 85 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Agencia Nacional de Investigación y Desarrollo.
Abstract (Originalsprache)
Human–robot collaboration will play an important role in the fourth industrial revolution in applications related to hostile environments, mining, industry, forestry, education, natural disaster and defense. Effective collaboration requires robots to understand human intentions and tasks, which involves advanced user profiling. Voice-based communication, rich in complex information, is key to this. Beamforming, a technology that enhances speech signals, can help robots extract semantic, emotional, or health-related information from speech. This paper describes the implementation of a system that provides substantially improved signal-to-noise ratio (SNR) and speech recognition accuracy to a moving robotic platform for use in human–robot interaction (HRI) applications in static and dynamic contexts. This study focuses on training deep learning-based beamformers using acoustic model-based multi-style training with measured room impulse responses (RIRs). The results show that this approach outperforms training with simulated RIRs or matched measured RIRs, especially in dynamic conditions involving robot motion. The findings suggest that training with a broad range of measured RIRs is sufficient for effective HRI in various environments, making additional data recording or augmentation unnecessary. This research demonstrates that deep learning-based beamforming can significantly improve HRI performance, particularly in challenging acoustic environments, surpassing traditional beamforming methods.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Speech Processing and Transmission Laboratory, Electrical Engineering Department, University of Chile, Santiago 8370451, Chile.
- Department of Electrical and Computer Engineering, Carnegie Mellon University, Pittsburgh, PA 15213, USA.
ORCID-Profile: Nicolás Bohmer, Rodrigo Mahu, Richard M Stern, Néstor Becerra Yoma
Förderung
- Agencia Nacional de Investigación y Desarrollo
Zitieren
APA
Luzanto, A., Bohmer, N., Mahu, R., Alvarado, E., Stern, R. M., & Becerra Yoma, N. (2024). Effective Acoustic Model-Based Beamforming Training for Static and Dynamic Hri Applications. Sensors. https://doi.org/10.3390/s24206644
Vancouver
Luzanto A, Bohmer N, Mahu R, Alvarado E, Stern RM, Becerra Yoma N. Effective Acoustic Model-Based Beamforming Training for Static and Dynamic Hri Applications. Sensors. 2024. doi:10.3390/s24206644
BibTeX
@article{Luzanto2024,
author = {Luzanto, Alejandro and Bohmer, Nicolás and Mahu, Rodrigo and Alvarado, Eduardo and Stern, Richard M and Becerra Yoma, Néstor},
title = {Effective Acoustic Model-Based Beamforming Training for Static and Dynamic Hri Applications},
journal = {Sensors},
year = {2024},
doi = {10.3390/s24206644}
}
EUVIMED