4 papers
Uncertainty-Aware Knowledge Distillation for Multimodal Large Language Models
Jingchen Sun, Shaobo Han, Deep Patel +3
Knowledge distillation establishes a learning paradigm that leverages both data supervision and teacher guidance. However, determining the optimal balance between learning from dat…
Event Classification by Physics-informed Inpainting for Distributed Multichannel Acoustic Sensor with Partially Degraded Channels
Noriyuki Tonami, Wataru Kohno, Yoshiyuki Yajima +4
Distributed multichannel acoustic sensing (DMAS) enables large-scale sound event classification (SEC), but performance drops when many channels are degraded and when sensor layouts…
CLAP-S: Support Set Based Adaptation for Downstream Fiber-optic Acoustic Recognition
Jingchen Sun, Shaobo Han, Wataru Kohno +1
Contrastive Language-Audio Pretraining (CLAP) models have demonstrated unprecedented performance in various acoustic signal recognition tasks. Fiber-optic-based acoustic recognitio…
Trainingless Adaptation of Pretrained Models for Environmental Sound Classification
Noriyuki Tonami, Wataru Kohno, Keisuke Imoto +4
Deep neural network (DNN)-based models for environmental sound classification are not robust against a domain to which training data do not belong, that is, out-of-distribution or…