Upsampling
Downsampling
Extraction: Partition and Distribution Coefficients
Improving Translational Accuracy
Extraction: Advanced Methods
Linear Approximation in Frequency Domain
You might also read
Articles linked to this work by shared authors, journal, and citation graph.
Updated: Sep 4, 2025

Augmenting Large Language Models via Vector Embeddings to Improve Domain-Specific Responsiveness
Published on: December 6, 2024
Yating Huang1, Yunzhe Hao1, Jiaming Xu2
1Institute of Automation, Chinese Academy of Sciences (CAS), Beijing, China; School of Future Technology, University of Chinese Academy of Sciences, Beijing, China.
We developed TinyWASE, a lightweight speaker extraction model for resource-constrained devices. This model achieves significant compression (8.97x) with minimal performance loss, enabling efficient on-device audio processing.
Area of Science:
Background:
Purpose of the Study:
Main Methods:
Main Results:
Conclusions: