4 papers and 1 tutorial are accepted to ICASSP 23
- Papers
-
From English to More Languages: Parameter-Efficient Model Reprogramming for Cross-Lingual Speech Recognition (with Google Research)
-
A Quantum Kernel Learning Approach to Acoustic Modeling for Spoken Command Recognition (with Georgia Tech and Google)
-
Low-Resource Music Genre Classification with Cross-Modal Neural Model Reprogramming (with Georiga Tech)
-
Certified Robustness of Quantum Classifiers against Adversarial Examples through Quantum Noise (with NYCU and IBM Research AI)
- ICASSP Tutorial
Thank the speech and signals processing community again to recognize our works again.
I will give one tutorial at ICASSP 23
- Tutorial: Parameter-Efficient Learning for Speech and Language Processing: Adapters, Prompts, and Reprogramming
with Dr. Pin-Yu Chen (IBM Research AI) and Prof. Hung-Yi Lee (National Taiwan University)