Personalized VR for hearing research with embedded devices

Michon R, Serafin S, Serizel R. Personalized VR for hearing research with embedded devices. In: Convention Paper. Audio Engineering Society; 2026. Paper 10265. Available from: https://aes.org/publications/elibrary-page/?id=23180

@inproceedings{Michon2026_23180,
  author = {Michon, Romain and Serafin, Stefania and Serizel, Romain},
  title = {{Personalized VR for hearing research with embedded devices}},
  note = {Paper 10265},
  year = {2026},
  month = may,
  publisher = {Audio Engineering Society},
  url = {https://aes.org/publications/elibrary-page/?id=23180}
}

TY  - CPAPER
TI  - Personalized VR for hearing research with embedded devices
AU  - Michon, Romain
AU  - Serafin, Stefania
AU  - Serizel, Romain
M1  - Paper 10265
PY  - 2026
DA  - 2026/05/28
UR  - https://aes.org/publications/elibrary-page/?id=23180
PB  - Audio Engineering Society
LA  - en
AB  - Deep learning has significantly improved speech enhancement performance in controlled laboratory conditions, yet these advances rarely translate into robust real-world benefit for hearing aid users. Current algorithms are often trained and evaluated in simplified acoustic scenarios, neglecting multimodal cues, user interaction, environmental dynamics, and the strict latency and power constraints of embedded devices. As a result, a persistent gap remains between algorithmic performance and everyday listening experience. This position paper reviews recent progress in speech enhancement, embedded Artificial Intelligence hardware, and hearing aid systems, and argues for a shift toward ecologically valid evaluation and hardware-aware design. We propose virtual reality as a reproducible, multisensory benchmarking platform enabling joint assessment of human perception and algorithmic processing. This perspective outlines a research roadmap toward adaptive, context-aware, and practically deployable hearing technologies.
ER  -