Search Results for author:
Found 5 papers, 0 papers with code
Effective Integration of KAN for Keyword Spotting
Keyword spotting (KWS) is an important speech processing component for smart devices with voice assistance capability.
Query-by-Example Keyword Spotting Using Spectral-Temporal Graph Attentive Pooling and Multi-Task Learning
Existing keyword spotting (KWS) systems primarily rely on predefined keyword phrases.
Certifying Global Robustness for Deep Neural Networks
This paper presents a systematic and efficient method to evaluate and verify global robustness for deep neural networks, leveraging the PAC verification framework for solid guarantees on verification results.
Incentivizing Federated Learning
We theoretically prove that clients will use as much data as they can possibly possess to participate in federated learning under certain conditions with our incentive mechanism
KNN-enhanced Deep Learning Against Noisy Labels
Inspired by the robustness of K-Nearest Neighbors (KNN) against data noise, in this work, we propose to apply deep KNN for label cleanup.
