Leveraging Self-Supervised Audio-Visual Pretrained Models to Improve Vocoded Speech Intelligibility in Cochlear Implant Simulation

Lai, Richard LeeRichard LeeLaiHou, Jen-ChengJen-ChengHouChern, I-ChunI-ChunChernHung, Kuo-HsuanKuo-HsuanHungChen, Yi-TingYi-TingChenGogate, MandarMandarGogateArslan, TughrulTughrulArslanHussain, AmirAmirHussainCHII-WANN LINTsao, YuYuTsao2025-10-272025-10-272025https://scholars.lib.ntu.edu.tw/handle/123456789/733063[SDGs]SDG10Leveraging Self-Supervised Audio-Visual Pretrained Models to Improve Vocoded Speech Intelligibility in Cochlear Implant Simulationjournal article10.1109/tbme.2025.3610284