Whiting School of Engineering,
Johns Hopkins University, Baltimore

Email: hwang258@jhu.edu

Phone: +1 667-354-9059

[Curriculum Vitae]

General

I am a third-year PhD student at Johns Hopkins University and expect to graduate in May 2026. Before that, I received my Bachelor's Degree from Tsinghua University in 2019 and my Master's Degree from Peking University in 2022. My research interest majorly lies in AI for speech and audio signal processing, encompassing audio generation tasks such as source separation and text-to-speech synthesis, as well as audio understanding tasks like audio classification and captioning.
(Note: I am actively looking for any collaboration opportunities. Please feel free to contact me.)

News

• 5 Sep, 2024: Our INTERSPEECH paper "Noise-robust Speech Separation with Fast Generative Correction" has been nominated for the Best Student Paper Award and the Best Paper Award (5 out of 1,030 accepted papers)!

• 21 May, 2022: I have got Outstanding Graduate Student & Thesis Award of Peking University!

• 19 April, 2022: I have got 100 citations in the Google Scholar!

Research Interests

Machine Learning, Audio Processing, Speech Processing, Natural Language Processing

Educations

• Department of Electronic and Computer Engineering, Johns Hopkins University
  August 2022 - Now

• School of Electronic and Computer Engineering, Peking University
  August 2019 - July 2022

• Department of Automation, Tsinghua University
  August 2015 - July 2019

Experiences

• August 2022 - Now
  Johns Hopkins University, Center for Language and Speech Processing (CLSP), Baltimore, USA, Research Assistant.
  Supervisors: Najim Dehak, Laureano Moro-Velázquez and Jesús Villalba

• May 2024 - August 2024
  Tencent AI Lab, Speech Group, Bellevue, USA, Intern.
  Supervisors: Meng Yu and Dong Yu

• December 2022 - December 2023
  Amazon General Intelligence (AGI), Speech Team, Baltimore, USA, Student Researcher.
  Supervisors: Venkatesh Ravichandran and Milind Rao

• February 2022 - May 2022
  Microsoft STCA, NLP Group, Beijing, China, Intern.
  Supervisors: Linjun Shou and Ming Gong

• May 2020 - November 2021
  Tencent AI Lab, Speech Group, Shenzhen, China, Intern.
  Supervisors: Bo Wu and Chao Weng

• August 2019 - July 2022
  Peking University, ADSP Lab, Shenzhen, China, master student.
  Supervisor: Yuexian Zou
  Co-author: Wenwu Wang

• July 2019 - September 2019
  Ubtech Robotics Inc., Speech Group, Shenzhen, China, Intern.
  Supervisor: Dongyan Huang

• July 2018 - September 2018
  University of California Berkeley, California Path Lab, Berkeley, USA, Summer Research.
  Supervisor: Masayoshi Tomizuka

Selected Publications

• Helin Wang, Meng Yu, Jiarui Hai, Chen Chen, Yuchen Hu, Rilin Chen, Najim Dehak, Dong Yu
  SSR-Speech: Towards Stable, Safe and Robust Zero-shot Text-based Speech Editing and Synthesis
  Submitted to ICASSP, 2025. [Code]

• Helin Wang*, Jiarui Hai*, Yen-Ju Lu, Karan Thakkar, Mounya Elhilali, Najim Dehak
  SoloAudio: Target Sound Extraction with Language-oriented Audio Diffusion Transformer
  Submitted to ICASSP, 2025. [Code]

• Helin Wang, Jesus Villalba, Laureano Moro-Velazquez, Jiarui Hai, Thomas Thebaud, Najim Dehak
  Noise-robust Speech Separation with Fast Generative Correction
  Interspeech, 2024. [Code]

• Jiarui Hai*,Helin Wang*, Dongchao Yang, Karan Thakkar, Najim Dehak, Mounya Elhilali
  DPM-TSE: A Diffusion Probabilistic Model for Target Sound Extraction
  ICASSP, 2024. [Code]

• Helin Wang, Venkatesh Ravichandran, Milind Rao, Becky Lammers, Becky Lammers, Myra Sydnor, Nicholas Maragakis, Ankur A. Butala, Jayne Zhang, Lora Clawson, Victoria Chovaz, Laureano Moro-Velazquez
  Improving fairness for spoken language understanding in atypical speech with Text-to-Speech
  NeurIPS Workshop on Synthetic Data Generation with Generative AI, 2023. [Code]

• Helin Wang, Thomas Thebaud, Jesus Villalba, Myra Sydnor, Becky Lammers, Najim Dehak, Laureano Moro-Velazquez
  DuTa-VC: A Duration-aware Typical-to-atypical Voice Conversion Approach with Diffusion Probabilistic Model
  Interspeech, 2023. [Code]

• Dading Chong*,Helin Wang*, Peilin Zhou, Qingcheng Zeng
  Masked Spectrogram Prediction For Self- Supervised Audio Pre-Training
  ICASSP, 2023. [Code]

• Helin Wang, Yuexian Zou, Wenwu Wang
  SpecAugment++: A Hidden Space Data Augmentation Method for Acoustic Scene Classification
  Interspeech, 2021. [Code]

Teaching

• 2024/02 - 2024/05, Teaching Assistant, Johns Hopkins University, Baltimore, USA:
  EN.520.123: Computational Modeling for Electrical and Computer Engineering in Spring 2024 in the Department of Electrical and Computer Engineering

Services (Reviewer or PC Member)

• IEEE/ACM Transactions on Audio, Speech, and Language Processing
• IEEE Signal Processing Letters
• Neurocomputing
• NeurIPS
• ICLR
• Interspeech
• ICASSP

Selected Awards