IEEE EMBC 2026 || Toronto, Canada || 26-30 July 2026

We.1.2.1

Diffusion-Based Heart Sound Generation Evaluation with Physiological Signal Metrics, Classifiers, and Expert Listening

Xinqi Bao, KTH Royal Institute of Technology; Jia Bi, Rutherford Appleton Laboratory; Xin Chen, Peng Cheng Laboratory; Ernest Kamavuako,, King's College London; Saikat Chatterjee, KTH Royal Institute of Technology

Session:

We.1.2: Generative and Self-Supervised Learning for Neural Signals Oral

Location:

Room 801A

Presentation Time:

Wednesday, 29 July, 08:30 - 08:45

Session Co-Chairs:

Bramsh Qamar Chandio and Xinqi Bao

Session We.1.2

We.1.2.1: Diffusion-Based Heart Sound Generation Evaluation with Physiological Signal Metrics, Classifiers, and Expert Listening

We.1.2.2: Random Feature Mapping vs. Last-Layer Fine-Tuning for Biosignal Transfer Learning: Toward a Zero-Source Baseline

Takayuki Hoshino, Keio University / National Institute of Advanced Industrial Science and Technology; Suguru Kanoga, National Institute of Advanced Industrial Science and Technology; Atsushi Aoyama, Keio University

We.1.2.3: RL-BIOAUG: LABEL-EFFICIENT REINFORCEMENT LEARNING FOR SELF-SUPERVISED EEG REPRESENTATION LEARNING

Cheol-Hui Lee, Hwa-Yeon Lee, Seoul National University Hospital; Dong-Joo Kim, Korea Unversity

We.1.2.4: MTSSRL-MD: Multi-Task Self-Supervised Representation Learning for EEG Signals across Multiple Datasets

I-Hui Li, Oscar Tai-Yuan Chen, Vincent S. Tseng, National Yang Ming Chiao Tung University

We.1.2.5: WaveTok: A Wavelet Tokenizer for Self-Supervised EEG Representation Learning

Jing Wang, Ercan Engin Kuruoglu, Tsinghua University

We.1.2.6: Class-Conditioned Diffusion-Based EEG Generation for Motor Imagery in the Spectral Domain

Deeksha Kashyap, Srirama Swamy, Chaitanya Makkar, Gowri Srinivasa, PES University