Zeyu Jin

10 papers · 2020–2025 · 3 conferences · across top CS/AI conferences

Achievements

🐣 Hot Topic Early Bird 🧭 Keyword Pioneer 🌍 Conference Polyglot (3) 🏃 Academic Marathon (5) 🐝 Cross-Pollinator (7) 🌈 Renaissance Researcher (5) 🌉 Interdisciplinary Bridge 🗺️ Taxonomy Completionist (16) 💎 Century Club (10)

Conferences

INTERSPEECH (7) ICML (2) ICLR (1)

Top co-authors

Adam Finkelstein (3) Jiaqi Su (3) Sonal Kumar (2) Pranay Manocha (2) Dinesh Manocha (2) Sreyan Ghosh (2) Gautham J. Mysore (2) Oriol Nieto (2) Nicholas J. Bryan (2) Chandra Kiran Reddy Evuru (2)

Keywords

speech enhancement (2) speech separation (1) source separation (1) human perception (1) feature matching (1) efficient computing (1) multilabel classification (1) audio processing (1) generative model (1) diffusion model (1) convolutional neural network (1) open-set recognition (1) discrete token (1) perceptual metric (1) just noticeable difference (1) adversarial network (1) neural vocoder (1) user control (1) speech denoising (1) prosody generation (1)

Papers

DMOSpeech: Direct Metric Optimization via Distilled Diffusion Model in Zero-Shot Speech Synthesis ICML 2025

Visual Description Grounding Reduces Hallucinations and Boosts Reasoning in LVLMs ICLR 2025

Improving Generalization of Speech Separation in Real-World Scenarios: Strategies in Simulation, Optimization, and Evaluation INTERSPEECH 2024

A Closer Look at the Limitations of Instruction Tuning ICML 2024

Genhancer: High-Fidelity Speech Enhancement via Generative Modeling on Discrete Codec Tokens INTERSPEECH 2024

Efficient Spoken Language Recognition via Multilabel Classification INTERSPEECH 2023

Audio Similarity is Unreliable as a Proxy for Audio Quality INTERSPEECH 2022

HiFi-GAN: High-Fidelity Denoising and Dereverberation Based on Speech Deep Features in Adversarial Networks INTERSPEECH 2020

A Differentiable Perceptual Audio Metric Learned from Just Noticeable Differences INTERSPEECH 2020

Controllable Neural Prosody Synthesis INTERSPEECH 2020