3 papers
cs.CL2025
Dynamic Context-Aware Streaming Pretrained Language Model For Inverse Text Normalization
Luong Ho, Khanh Le, Vinh Pham +3
Inverse Text Normalization (ITN) is crucial for converting spoken Automatic Speech Recognition (ASR) outputs into well-formatted written text, enhancing both readability and usabil…
cs.SD2025
Improving Streaming Speech Recognition With Time-Shifted Contextual Attention And Dynamic Right Context Masking
Khanh Le, Duc Chau
Chunk-based inference stands out as a popular approach in developing real-time streaming speech recognition, valued for its simplicity and efficiency. However, because it restricts…
cs.LG2024
Towards Layer-Wise Personalized Federated Learning: Adaptive Layer Disentanglement via Conflicting Gradients
Minh Duong Nguyen, Khanh Le, Khoi Do +4
In personalized Federated Learning (pFL), high data heterogeneity can cause significant gradient divergence across devices, adversely affecting the learning process. This divergenc…