2 papers
eess.AS2024
Leave No Knowledge Behind During Knowledge Distillation: Towards Practical and Effective Knowledge Distillation for Code-Switching ASR Using Realistic Data
Liang-Hsuan Tseng, Zih-Ching Chen, Wei-Shun Chang +3
Recent advances in automatic speech recognition (ASR) often rely on large speech foundation models for generating high-quality transcriptions. However, these models can be impracti…
cs.CL2024
PEFT for Speech: Unveiling Optimal Placement, Merging Strategies, and Ensemble Techniques
Tzu-Han Lin, How-Shing Wang, Hao-Yung Weng +3
Parameter-Efficient Fine-Tuning (PEFT) is increasingly recognized as an effective method in speech processing. However, the optimal approach and the placement of PEFT methods remai…