Education
Experience
About Me
As a researcher, I am pursuing my Ph.D. at Johns Hopkins University, where I build AI systems for audio, speech, and music. My work bridges language and audio, enabling machines to understand, reason about, and generate sound. I also develop open-source projects and datasets that advance the broader audio and speech research community.
As a musician, I am an active music producer with a deep interest in the intersection of AI and music. I enjoy exploring how new technologies expand the creative process and unlock new possibilities for music creation and production.
Introducing OpenSound
News
† Research mentorship
Research Highlights
CapSpeech: Enabling Downstream Applications in Style-Captioned Text-to-Speech
A style-captioned TTS dataset and framework enabling controllable, style-aware text-to-speech for downstream applications.
Dataset IEEE Transactions on Audio, Speech and Language Processing (TASLP) | 2026
CapSpeech: Enabling Downstream Applications in Style-Captioned Text-to-Speech
A style-captioned TTS dataset and framework enabling controllable, style-aware text-to-speech for downstream applications.
Dataset IEEE Transactions on Audio, Speech and Language Processing (TASLP) | 2026
FlexSED: Towards Open-Vocabulary Sound Event Detection
An open-vocabulary sound event detection approach that generalizes to unseen classes via flexible text-conditioned modeling.
Spotlight IEEE Workshop on Applications of Signal Processing to Audio and Acoustics (WASPAA) | 2025
FlexSED: Towards Open-Vocabulary Sound Event Detection
An open-vocabulary sound event detection approach that generalizes to unseen classes via flexible text-conditioned modeling.
Spotlight IEEE Workshop on Applications of Signal Processing to Audio and Acoustics (WASPAA) | 2025
EzAudio: Enhancing Text-to-Audio Generation with Efficient Diffusion Transformer
An efficient diffusion transformer that improves text-to-audio generation quality while reducing compute.
Oral Interspeech | 2025
EzAudio: Enhancing Text-to-Audio Generation with Efficient Diffusion Transformer
An efficient diffusion transformer that improves text-to-audio generation quality while reducing compute.
Oral Interspeech | 2025
Diff-Pitcher: Diffusion-based Singing Voice Pitch Correction
A diffusion-based method for singing voice pitch correction that adjusts pitch while preserving timbre and expression.
Oral IEEE Workshop on Applications of Signal Processing to Audio and Acoustics (WASPAA) | 2023
Diff-Pitcher: Diffusion-based Singing Voice Pitch Correction
A diffusion-based method for singing voice pitch correction that adjusts pitch while preserving timbre and expression.
Oral IEEE Workshop on Applications of Signal Processing to Audio and Acoustics (WASPAA) | 2023
More Projects
Education
Experience