Heng-Jui Chang
7 papers · 2021–2026 · 5 venues · across top CS/AI venues
Authors are matched by name, so researchers who share a name ("Yang Liu", "Wei Wang") appear as a single profile and their paper counts, venues and achievements are combined. How identity is handled.
Achievements
Jump to papers ↓+1 more ↓ Show less ↑
🌍 Conference Polyglot · Silver 🏃 Academic Marathon · Sprint 🌉 Interdisciplinary Bridge · Silver 🗺️ Taxonomy Completionist (17) 🧬 Topic Evolution
🔥
Unstoppable · Bronze
Top co-authors
Research topics
Deep Learning
(5)
Machine Learning
(5)
Learning Types · Machine Learning
(5)
Speech & Audio
(3)
Core Methods
(3)
Learning Types · Deep Learning
(3)
Artificial Intelligence
(2)
Architectures
(2)
Core AI
(2)
Natural Language Processing
(1)
Analysis
(1)
Application Areas
(1)
Generation
(1)
Processing
(1)
Recognition
(1)
Keywords
self-supervised learning
(3)
speech processing
(2)
representation learning
(2)
domain generalization
(1)
transfer learning
(1)
online clustering
(1)
speech recognition
(1)
sequential learning
(1)
lifelong learning
(1)
cross-modal embedding
(1)
masked language modeling
(1)
contextualized embedding
(1)
joint embedding
(1)
speech representation
(1)
self-supervised fine-tuning
(1)
speech tokenization
(1)
spoken language model
(1)
speaker disentanglement
(1)
end-to-end speech recognition
(1)
speech retrieval
(1)
Papers
Pushing the Frontier of Audiovisual Perception with Large-Scale Multimodal Correspondence Learning
CVPR 2026
DC-Spin: A Speaker-invariant Speech Tokenizer for Spoken Language Models
Interspeech 2025
R-Spin: Efficient Speaker and Noise-invariant Representation Learning with Acoustic Pieces
NAACL 2024
DinoSR: Self-Distillation and Online Clustering for Self-supervised Speech Representation Learning
NeurIPS 2023
Self-supervised Fine-tuning for Improved Content Representations by Speaker-invariant Clustering
Interspeech 2023
SUPERB-SG: Enhanced Speech processing Universal PERformance Benchmark for Semantic and Generative Capabilities
ACL 2022
Towards Lifelong Learning of End-to-End ASR
Interspeech 2021