Comparison of QUADS and Prior Methods on the SLURP and FSC Datasets. We report accuracy and F1-score for model performance, alongside GMACs and model size, to evaluate efficiency.
git clone https://github.com/BASHLab/QUADS.git
cd QUADS
pythom3 -m venv venv
source venv/bin/activate
pip install -r requirements.txtpython train.py@inproceedings{biswas25b_interspeech,
title = {{QUADS: Quantized Distillation Framework for Efficient Speech Language Understanding}},
author = {{Subrata Biswas and Mohammad Nur Hossain Khan and Bashima Islam}},
year = {{2025}},
booktitle = {{Interspeech 2025}},
pages = {{4098--4102}},
doi = {{10.21437/Interspeech.2025-532}},
}