2 papers
cs.SD2025
Cross-Learning Fine-Tuning Strategy for Dysarthric Speech Recognition Via CDSD database
Qing Xiao, Yingshan Peng, PeiPei Zhang
Dysarthric speech recognition faces challenges from severity variations and disparities relative to normal speech. Conventional approaches individually fine-tune ASR models pre-tra…
cs.LG2025
Beyond Adapter Retrieval: Latent Geometry-Preserving Composition via Sparse Task Projection
Pengfei Jin, Peng Shu, Sifan Song +6
Recent advances in parameter-efficient transfer learning have demonstrated the utility of composing LoRA adapters from libraries of pretrained modules. However, most existing appro…