Dung Tran

Dung Tran is a researcher in Microsoft’s Applied Sciences Group (ASG).  His research interests lie at the intersection of machine learning and signal processing, which he applies to sound and speech processing and to computer vision.

He holds a Ph.D. in electrical and computer engineering and an M.S. in applied mathematics and statistics, both from Johns Hopkins University.

In his free time he loves to play soccer.

• Learned Image Compression with Text Quality Enhancement

  Proceedings, 2024 IEEE International Conference on Image Processing (ICIP) October, 2024

  By Andrew Lai (Chih-Yu Lai), Dung Tran, Kazuhito Koishida
• ConsistencyTTA: Accelerating Diffusion-Based Text-to-Audio Generation with Consistency Distillation

  Proceedings, Interspeech 2024 September, 2024

  By Yatong Bai, Trung Dang, Dung Tran, Kazuhito Koishida, Somayeh Sojoudi
• LiveSpeech: Low-Latency Zero-Shot Text-to-Speech via Autoregressive Modeling of Audio Discrete Codes

  Proceedings, Interspeech 2024 September, 2024

  By Trung Dang, David Aponte, Dung Tran, Kazuhito Koishida
• uaMix-MAE: Efficient Tuning of Pretrained Audio Transformers with Unsupervised Audio Mixtures

  Proceedings. ICASSP 2024 April, 2024 Pages 5435-5439

  By Afrina Tabassum, Dung Tran, Trung Dang, Ismini Lourentzou, Kazuhito Koishida
• Improving Low-Latency Mono-Channel Speech Enhancement by Compensation Windows in STFT Analysis

  Proceedings. International Conference on Complex Networks and Their Applications November, 2023 Pages 363-373 ISBN: 978-3-031-53468-3

  By Minh Bui, Dung Tran, Kazuhito Koishida, Trac D. Tran, Peter Chin
• Training Robust Zero-Shot Voice Conversion Models with Self-supervised Features

  Proceedings, ICASSP 2022 May, 2022 Pages 6557-6561

  By Trung Dang, Dung Tran, Peter Chin, Kazuhito Koishida
• Single-Channel Speech Enhancement Using Learnable Loss Mixup

  Proceedings, Interspeech 2021 August, 2021 Pages 2696-2700

  By Oscar Chang, Dung Tran, Kazuhito Koishida
• Robust Pitch Regression with Voiced/Unvoiced Classification in Nonstationary Noise Environments

  Proceedings, Interspeech 2020 October, 2020 Pages 175-179

  By Dung Tran, Uros Batricevic, Kazuhito Koishida
• Single-Channel Speech Enhancement by Subspace Affinity Minimization

  Proceedings, Interspeech 2020 October, 2020 Pages 2447-2451

  By Dung Tran, Kazuhito Koishida