Scholar
Dung N. Tran
Google Scholar ID: tHsQCKMAAAAJ
Senior Researcher at Microsoft
Citations & Impact
Citations
323
H-index
10
i10-index
10
Publications
20
Co-authors
18
list available
Contact
Publications
Browse publications on Google Scholar (top-right) ↗
Resume (English only)
Academic Achievements
- Publications:
- - 'Learned Image Compression with Text Quality Enhancement', 2024 IEEE International Conference on Image Processing (ICIP)
- - 'ConsistencyTTA: Accelerating Diffusion-Based Text-to-Audio Generation with Consistency Distillation', Interspeech 2024
- - 'LiveSpeech: Low-Latency Zero-Shot Text-to-Speech via Autoregressive Modeling of Audio Discrete Codes', Interspeech 2024
- - 'uaMix-MAE: Efficient Tuning of Pretrained Audio Transformers with Unsupervised Audio Mixtures', ICASSP 2024
- - 'Improving Low-Latency Mono-Channel Speech Enhancement by Compensation Windows in STFT Analysis', International Conference on Complex Networks and Their Applications, 2023
- - 'Training Robust Zero-Shot Voice Conversion Models with Self-supervised Features', ICASSP 2022
- - 'Single-Channel Speech Enhancement Using Learnable Loss Mixup', Interspeech 2021
- - 'Robust Pitch Regression with Voiced/Unvoiced Classification in Nonstationary Noise Environments', Interspeech 2020
- - 'Single-Channel Speech Enhancement by Subspace Affinity Minimization', Interspeech 2020
Research Experience
- Senior Researcher in Microsoft's Applied Sciences Group (ASG).
Education
- Ph.D. in Electrical and Computer Engineering, Johns Hopkins University; M.S. in Applied Mathematics and Statistics, Johns Hopkins University.
Background
- Research interests: at the intersection of machine learning and signal processing, applied to sound and speech processing and computer vision.
Miscellany
- Hobbies: Playing soccer.
