SCORE: Self-Supervised Correspondence Fine-Tuning for Improved Content Representations
A Meghanani, T Hain - ICASSP 2024-2024 IEEE International …, 2024 - ieeexplore.ieee.org
There is a growing interest in cost-effective self-supervised fine-tuning (SSFT) of self-
supervised learning (SSL)-based speech models to obtain task-specific representations …
supervised learning (SSL)-based speech models to obtain task-specific representations …