AINeutralarXiv – CS AI · Mar 175/10
🧠
Variational Low-Rank Adaptation for Personalized Impaired Speech Recognition
Researchers developed a novel Bayesian Low-rank Adaptation method for personalizing automatic speech recognition systems to better understand impaired speech. The approach addresses challenges in ASR systems like Whisper that struggle with non-normative speech patterns from conditions like cerebral palsy, using data-efficient fine-tuning on English and German datasets.