pith. sign in

Heng-Jui Chang

Identifiers

  • name variant Heng-Jui Chang 0.60 · backfill

Papers (18)

  1. USAD 2.0: Scaling Representation Distillation for Universal Audio Understanding eess.AS · 2026 · author #1
  2. Proteo-R1: Reasoning Foundation Models for De Novo Protein Design cs.LG · 2026 · author #5
  3. USAD: Universal Speech and Audio Representation via Distillation cs.SD · 2025 · author #1
  4. DC-Spin: A Speaker-invariant Speech Tokenizer for Spoken Language Models eess.AS · 2024 · author #1
  5. A Large-Scale Evaluation of Speech Foundation Models eess.AS · 2024 · author #2
  6. SpeechCLIP+: Self-supervised multi-task representation learning for speech via CLIP and speech-image data cs.CL · 2024 · author #3
  7. R-Spin: Efficient Speaker and Noise-invariant Representation Learning with Acoustic Pieces cs.CL · 2023 · author #1
  8. CoLLD: Contrastive Layer-to-layer Distillation for Compressing Multilingual Pre-trained Speech Encoders cs.CL · 2023 · author #1
  9. Self-supervised Fine-tuning for Improved Content Representations by Speaker-invariant Clustering cs.CL · 2023 · author #1
  10. DinoSR: Self-Distillation and Online Clustering for Self-supervised Speech Representation Learning cs.CL · 2023 · author #2
  11. M-SpeechCLIP: Leveraging Large-Scale, Pre-Trained Models for Multilingual Speech to Image Retrieval cs.CL · 2022 · author #4
  12. SpeechCLIP: Integrating Speech with Pre-Trained Vision and Language Model cs.CL · 2022 · author #3
  13. SUPERB-SG: Enhanced Speech processing Universal PERformance Benchmark for Semantic and Generative Capabilities cs.CL · 2022 · author #2
  14. Mandarin-English Code-switching Speech Recognition with Self-supervised Speech Representation Models cs.CL · 2021 · author #3
  15. DistilHuBERT: Speech Representation Learning by Layer-wise Distillation of Hidden-unit BERT cs.CL · 2021 · author #1
  16. Non-autoregressive Mandarin-English Code-switching Speech Recognition cs.CL · 2021 · author #2
  17. Towards Lifelong Learning of End-to-end ASR cs.CL · 2021 · author #1
  18. End-to-end Whispered Speech Recognition with Frequency-weighted Approaches and Pseudo Whisper Pre-training cs.CL · 2020 · author #1

Mentions

  • 2506.18843 #1 · arxiv_oai · confidence 0.70 Heng-Jui Chang
  • 2410.24177 #1 · arxiv_oai · confidence 0.70 Heng-Jui Chang
  • 2404.09385 #2 · arxiv_oai · confidence 0.70 Heng-Jui Chang
  • 2311.09117 #1 · arxiv_oai · confidence 0.70 Heng-Jui Chang
  • 2402.06959 #3 · arxiv_oai · confidence 0.70 Heng-Jui Chang
  • 2305.10005 #2 · arxiv_oai · confidence 0.70 Heng-Jui Chang
  • 2309.07707 #1 · arxiv_oai · confidence 0.70 Heng-Jui Chang
  • 2305.11072 #1 · arxiv_oai · confidence 0.70 Heng-Jui Chang
  • 2211.01180 #4 · arxiv_oai · confidence 0.70 Heng-Jui Chang
  • 2210.00705 #3 · arxiv_oai · confidence 0.70 Heng-Jui Chang
  • 2110.01900 #1 · arxiv_oai · confidence 0.70 Heng-Jui Chang
  • 2203.06849 #2 · arxiv_oai · confidence 0.70 Heng-Jui Chang
  • 2110.03504 #3 · arxiv_oai · confidence 0.70 Heng-Jui Chang
  • 2104.02258 #2 · arxiv_oai · confidence 0.70 Heng-Jui Chang
  • 2104.01616 #1 · arxiv_oai · confidence 0.70 Heng-Jui Chang
  • 2005.01972 #1 · arxiv_oai · confidence 0.70 Heng-Jui Chang
  • 2606.06444 #1 · arxiv_oai · confidence 0.70 Heng-Jui Chang

Frequent Coauthors