EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

End-to-end audio-visual learning for cochlear implant sound coding simulations in noisy environments

Meng-Ping Lin, Enoch Hsin-Ho Huang iD, Shao-Yi Chien iD, Yu Tsao iD

JASA Express Letters · 2026

DOI: 10.1121/10.0042198 ↗

Kurz gefasst

Fachartikel in der Zeitschrift JASA Express Letters, 2026. Verfasst von Meng-Ping Lin und 3 weiteren Autor:innen. Beteiligte Einrichtung: Graduate Institute of Electronics Engineering and the Department of Electrical Engineering, National Taiwan University, Taipei 106319, Taiwan. Hauptthemen laut MEDLINE: Cochlear Implants, Noise, Deep Learning. Die Arbeit nennt 36 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Academia Sinica.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

The cochlear implant (CI) is a successful biomedical device that enables individuals with severe-to-profound hearing loss to perceive sound through electrical stimulation, yet listening in noise remains challenging. Recent deep learning advances offer promising potential for CI sound coding by integrating visual cues. In this study, an audio-visual speech enhancement (AVSE) module is integrated with the ElectrodeNet-CS (ECS) model to form the end-to-end CI system, AVSE-ECS. Simulations show that the AVSE-ECS system with joint training achieves high objective speech intelligibility and improves the signal-to-error ratio by 7.4666 dB compared to the advanced combination encoder strategy. These findings underscore the potential of AVSE-based CI sound coding.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Cochlear ImplantsNoiseDeep LearningHumansSpeech PerceptionComputer SimulationSpeech Intelligibility

Autor:innen und Institutionen

  • Graduate Institute of Electronics Engineering and the Department of Electrical Engineering, National Taiwan University, Taipei 106319, Taiwan.
  • Research Center for Information Technology Innovation Technology, Academia Sinica, Taipei 115201, Taiwan.
  • Department of Electrical Engineering, Chung Yuan Christian University, Taoyuan 320314, Taiwan.

ORCID-Profile: Enoch Hsin-Ho Huang, Shao-Yi Chien, Yu Tsao

Förderung

  • Academia Sinica

Zitieren

APA

Lin, M. P., Huang, E. H., Chien, S. Y., & Tsao, Y. (2026). End-to-end audio-visual learning for cochlear implant sound coding simulations in noisy environments. JASA Express Letters. https://doi.org/10.1121/10.0042198

Vancouver

Lin MP, Huang EH, Chien SY, Tsao Y. End-to-end audio-visual learning for cochlear implant sound coding simulations in noisy environments. JASA Express Letters. 2026. doi:10.1121/10.0042198

BibTeX
@article{Lin2026,
  author = {Lin, Meng-Ping and Huang, Enoch Hsin-Ho and Chien, Shao-Yi and Tsao, Yu},
  title = {End-to-end audio-visual learning for cochlear implant sound coding simulations in noisy environments},
  journal = {JASA Express Letters},
  year = {2026},
  doi = {10.1121/10.0042198}
}
Kostenlos starten →