2 papers
eess.AS2025
On the use of Performer and Agent Attention for Spoken Language Identification
Jitendra Kumar dhiman, Jainag Ambati
One of the methods for language Identification (LID) involves deriving speech representation from pre-trained models using self-supervised learning, followed by fine-tuning the mod…
eess.AS2025
Synergistic Effects of Knowledge Distillation and Structured Pruning for Self-Supervised Speech Models
Shiva Kumar C, Jitendra Kumar Dhiman, Nagaraj Adiga +1
Traditionally, Knowledge Distillation (KD) is used for model compression, often leading to suboptimal performance. In this paper, we evaluate the impact of combining KD loss with a…