Jiawei (Gavin) Du 杜嘉炜
Ph.D. Student
Georgia Institute of Technology
AI Virtual Assistant (AVA) Lab

Hi! I am Jiawei Du, a Ph.D. student in the School of Electrical and Computer Engineering at Georgia Tech, advised by Dr. Larry Heck. My research interests lie in speech and audio processing, particularly audio large language models for real-time conversational and multi-party speech understanding.

Before joining Georgia Tech, I was a Research Assistant in the Graduate Institute of Networking and Multimedia at National Taiwan University, supervised by Dr. Hung-Yi Lee. I received my M.S. degree in Computer Science and Information Engineering from National Taiwan University, where I was advised by Dr. Jyh-Shing Roger Jang and worked closely with Dr. Hung-Yi Lee on audio coding and anti-spoofing. During my graduate studies, I was a Research Intern at Samsung Research SRC-B, focusing on streaming and lightweight neural audio codecs. Prior to that, I earned my B.S. degree (ranked 1st/79) in Information and Telecommunications Engineering (now Electrical Engineering) from Ming Chuan University, supervised by Dr. Shu-Yin Chiang. I also completed an exchange program in Computer Science and Engineering at Shanghai Jiao Tong University.


Education
  • Georgia Institute of Technology
    Georgia Institute of Technology
    Atlanta
    Incoming Ph.D. Student
    School of Electrical and Computer Engineering
    Aug. 2026 - present
  • National Taiwan University
    National Taiwan University
    Taipei
    M.S. in Computer Science and Information Engineering
    Sep. 2022 - Jun. 2025
  • Ming Chuan University
    Ming Chuan University
    Taoyuan
    B.S. in Information and Telecommunications Engineering
    Sep. 2018 - Jun. 2022
Experience
  • National Taiwan University
    National Taiwan University
    Taipei
    Research Assistant
    Speech Processing and Machine Learning Lab
    Sep. 2025 - Aug. 2026
  • Samsung Research SRC-B
    Samsung Research SRC-B
    Beijing
    Research Intern in Speech Team
    Feb. 2025 - May. 2025
  • Shanghai Jiao Tong University
    Shanghai Jiao Tong University
    Shanghai
    Exchange Student in Computer Science and Engineering
    Sep. 2020 - Jan. 2021
News
2026
One journal paper accepted to IEEE TASLP.
May 02
I decided to pursue my Ph.D. in Electrical and Computer Engineering at Georgia Tech, looking forward to Atlanta!
Apr 15
2025
I started as a Research Assistant in GINM at National Taiwan University.
Sep 08
I graduated from National Taiwan University (M.S. in CSIE).
Jun 10
I completed my four-month research internship at Samsung, a great experience!
May 15
Selected Publications (view all )
CodecFake+: Codec-Based Resynthesized Data as a Proxy for Detecting CodecFake Speech
CodecFake+: Codec-Based Resynthesized Data as a Proxy for Detecting CodecFake Speech

Jiawei Du*, Xuanjun Chen*, Haibin Wu, Lin Zhang, I-Ming Lin, I-Hsiang Chiu, Wenze Ren, Yuan Tseng, Yu Tsao, Jyh-Shing Roger Jang, Hung-Yi Lee (* equal contribution)

IEEE Transactions on Audio, Speech and Language Processing (TASLP) 2026

CodecFake+ is a large-scale dataset and taxonomy for detecting codec-based deepfake speech generated by neural audio codecs. It provides diverse training and evaluation data across many codec architectures and enables more systematic analysis for building stronger audio anti-spoofing models.

CodecFake+: Codec-Based Resynthesized Data as a Proxy for Detecting CodecFake Speech

Jiawei Du*, Xuanjun Chen*, Haibin Wu, Lin Zhang, I-Ming Lin, I-Hsiang Chiu, Wenze Ren, Yuan Tseng, Yu Tsao, Jyh-Shing Roger Jang, Hung-Yi Lee (* equal contribution)

IEEE Transactions on Audio, Speech and Language Processing (TASLP) 2026

CodecFake+ is a large-scale dataset and taxonomy for detecting codec-based deepfake speech generated by neural audio codecs. It provides diverse training and evaluation data across many codec architectures and enables more systematic analysis for building stronger audio anti-spoofing models.

Codec-SUPERB @ SLT 2024: A Lightweight Benchmark for Neural Audio Codec Models
Codec-SUPERB @ SLT 2024: A Lightweight Benchmark for Neural Audio Codec Models

Haibin Wu, Jiawei Du*, Xuanjun Chen*, Yi-Cheng Lin*, Kai-Wei Chang*, Ke-Han Lu*, Alexander H. Liu*, Ho-Lam Chung*, Yuan-Kuei Wu*, Dongchao Yang*, Songxiang Liu, Yi-Chiao Wu, Xu Tan, James Glass, Shinji Watanabe, Hung-Yi Lee (* equal contribution)

IEEE Spoken Language Technology Workshop (SLT) 2024 Special Session

Codec-SUPERB introduces a lightweight and standardized benchmark for evaluating neural audio codec models across multiple speech tasks. It enables fair comparison under consistent settings and reveals key trade-offs in preserving linguistic content, speaker characteristics, and audio quality at low bitrates.

Codec-SUPERB @ SLT 2024: A Lightweight Benchmark for Neural Audio Codec Models

Haibin Wu, Jiawei Du*, Xuanjun Chen*, Yi-Cheng Lin*, Kai-Wei Chang*, Ke-Han Lu*, Alexander H. Liu*, Ho-Lam Chung*, Yuan-Kuei Wu*, Dongchao Yang*, Songxiang Liu, Yi-Chiao Wu, Xu Tan, James Glass, Shinji Watanabe, Hung-Yi Lee (* equal contribution)

IEEE Spoken Language Technology Workshop (SLT) 2024 Special Session

Codec-SUPERB introduces a lightweight and standardized benchmark for evaluating neural audio codec models across multiple speech tasks. It enables fair comparison under consistent settings and reveals key trade-offs in preserving linguistic content, speaker characteristics, and audio quality at low bitrates.

DFADD: The Diffusion and Flow-Matching Based Audio Deepfake Dataset
DFADD: The Diffusion and Flow-Matching Based Audio Deepfake Dataset

Jiawei Du*, I-Ming Lin*, I-Hsiang Chiu*, Xuanjun Chen, Haibin Wu, Wenze Ren, Yu Tsao, Hung-Yi Lee, Jyh-Shing Roger Jang (* equal contribution)

IEEE Spoken Language Technology Workshop (SLT) 2024

DFADD is the first dataset for audio deepfake detection that focuses on speech synthesized by diffusion- and flow-matching-based TTS models, and reveals that current anti-spoofing systems still struggle with these more realistic fake audios.

DFADD: The Diffusion and Flow-Matching Based Audio Deepfake Dataset

Jiawei Du*, I-Ming Lin*, I-Hsiang Chiu*, Xuanjun Chen, Haibin Wu, Wenze Ren, Yu Tsao, Hung-Yi Lee, Jyh-Shing Roger Jang (* equal contribution)

IEEE Spoken Language Technology Workshop (SLT) 2024

DFADD is the first dataset for audio deepfake detection that focuses on speech synthesized by diffusion- and flow-matching-based TTS models, and reveals that current anti-spoofing systems still struggle with these more realistic fake audios.

Neural Codec-based Adversarial Sample Detection for Speaker Verification
Neural Codec-based Adversarial Sample Detection for Speaker Verification

Jiawei Du*, Xuanjun Chen*, Haibin Wu, Jyh-Shing Roger Jang, Hung-Yi Lee (* equal contribution)

Interspeech 2024

This paper proposes a neural codec-based method to detect adversarial samples for speaker verification by comparing ASV score differences before and after codec re-synthesis. Experiments across 15 open-source neural codecs show that the approach outperforms seven prior baselines, with Descript Audio Codec giving the best results.

Neural Codec-based Adversarial Sample Detection for Speaker Verification

Jiawei Du*, Xuanjun Chen*, Haibin Wu, Jyh-Shing Roger Jang, Hung-Yi Lee (* equal contribution)

Interspeech 2024

This paper proposes a neural codec-based method to detect adversarial samples for speaker verification by comparing ASV score differences before and after codec re-synthesis. Experiments across 15 open-source neural codecs show that the approach outperforms seven prior baselines, with Descript Audio Codec giving the best results.

All publications