Scholar
Yi Ma
Google Scholar ID: Xt0xIP4AAAAJ
National University of Singapore
Citations & Impact
Citations
383
H-index
7
i10-index
7
Publications
9
Co-authors
4
list available
Publications
Resume (English only)
Academic Achievements
- ExPO: Explainable Phonetic Trait-Oriented Network for Speaker Verification, IEEE Signal Processing Letters (SPL), 2025.
- Gradient weighting for speaker verification in extreme low Signal-to-Noise Ratio, ICASSP, 2024.
- How Do Neural Spoofing Countermeasures Detect Partially Spoofed Audio?, Interspeech, 2024.
- PL-EESR: Perceptual loss based end-to-end robust speaker representation extraction, ASRU, 2021.
- LungRN+ NL: An improved adventitious lung sound classification using non-local block resnet neural network with mixup data augmentation, Interspeech, 2020.
- LungBRN: a Smart Digital Stethoscope for Detecting Respiratory Disease Using bi-ResNet Deep Learning Algorithm, BioCAS, 2019.
- Live Demo: LungSys - Automatic Digital Stethoscope System For Adventitious Respiratory Sound Detection, BioCAS, 2019.
- Enhancing speech recognition for Parkinson’s disease patient using transfer learning technique, Journal of Shanghai Jiaotong University (Science), 2022.
- LungAttn: advanced lung sound classification using attention mechanism with dual TQWT and triple STFT spectrogram, Physiological Measurement, 2021.
Background
- Currently a final-year Ph.D. candidate at the National University of Singapore (NUS), supervised by Professor Li Haizhou. With six years of experience in deep learning, my research specializes in speech processing. My research focuses on extracting speaker information from speech with robustness in noisy environments and developing explainable speaker verification systems.
Miscellany
- Open Source Code: Speaker Verification Framework with Passive Explanation, Robust Speaker Verification Framework Under Noisy Conditions, Speaker Verification Framework trained with Metric Learning Objectives, Abnormal Acoustic Detection and Deployment on an Android Application
