Personal information

Speech Processing, Self-supervised Learning, Speech Recognition

Activities

Education and qualifications (2)

Massachusetts Institute of Technology: Cambridge, Massachusetts, US

2022 to 2027 | Ph.D. (Electrical Engineering and Computer Science)
Education
Source: Self-asserted source
Heng-Jui Chang

National Taiwan University: Taipei, Taipei, TW

2017 to 2021 | B.S. (Electrical Engineering)
Education
Source: Self-asserted source
Heng-Jui Chang

Works (9)

A Large-Scale Evaluation of Speech Foundation Models

IEEE/ACM Transactions on Audio, Speech, and Language Processing
2024 | Journal article
Contributors: Shu-wen Yang; Heng-Jui Chang; Zili Huang; Andy T. Liu; Cheng-I Lai; Haibin Wu; Jiatong Shi; Xuankai Chang; Hsiang-Sheng Tsai; Wen-Chin Huang et al.
Source: check_circle
Crossref

DISTILHUBERT: SPEECH REPRESENTATION LEARNING BY LAYER-WISE DISTILLATION OF HIDDEN-UNIT BERT

IEEE International Conference on Acoustics, Speech, and Signal Processing
2022 | Conference paper
Contributors: Chang, Heng-Jui; Yang, Shu-wen; Lee, Hung-yi
Source: check_circle
Web of Science Researcher Profile Sync
grade
Preferred source (of 3)‎

M-SpeechCLIP: Leveraging Large-Scale, Pre-Trained Models for Multilingual Speech to Image Retrieval

ArXiv
2022 | Journal article
Contributors: Berry, Layne; Shih, Yi-Jen; Wang, Hsuan-Fu; Chang, Heng-Jui; Lee, Hung-yi; Harwath, David
Source: check_circle
Web of Science Researcher Profile Sync

SPEECHCLIP: INTEGRATING SPEECH WITH PRE-TRAINED VISION AND LANGUAGE MODEL

ArXiv
2022 | Journal article
Contributors: Shih, Yi-Jen; Wang, Hsuan-Fu; Chang, Heng-Jui; Berry, Layne; Lee, Hung-yi; Harwath, David
Source: check_circle
Web of Science Researcher Profile Sync

SUPERB-SG: Enhanced Speech processing Universal PERformance Benchmark for Semantic and Generative Capabilities

PROCEEDINGS OF THE ANNUAL MEETING OF THE ASSOCIATION FOR COMPUTATIONAL LINGUISTICS (ACL), VOL 1: (LONG PAPERS)
2022 | Journal article
Contributors: Tsai, Hsiang-Sheng; Chang, Heng-Jui; Huang, Wen-Chin; Huang, Zili; Lakhotia, Kushal; Yang, Shu-wen; Dong, Shuyan; Liu, Andy T.; Lai, Cheng-I Jeff; Shi, Jiatong et al.
Source: check_circle
Web of Science Researcher Profile Sync

Mandarin-English Code-switching Speech Recognition with Self-supervised Speech Representation Models

ArXiv
2021 | Journal article
Contributors: Tseng, Liang-Hsuan; Fu, Yu-Kuan; Chang, Heng-Jui; Lee, Hung-yi
Source: check_circle
Web of Science Researcher Profile Sync

NON-AUTOREGRESSIVE MANDARIN-ENGLISH CODE-SWITCHING SPEECH RECOGNITION

IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)
2021 | Conference paper
Contributors: Chuang, Shun-Po; Chang, Heng-Jui; Huang, Sung-Feng; Lee, Hung-yi
Source: check_circle
Web of Science Researcher Profile Sync

Towards Lifelong Learning of End-to-end ASR

Annual Conference of the International Speech Communication Association
2021 | Conference paper
Contributors: Chang, Heng-Jui; Lee, Hung-yi; Lee, Lin-shan
Source: check_circle
Web of Science Researcher Profile Sync

End-to-end Whispered Speech Recognition with Frequency-weighted Approaches and Pseudo Whisper Pre-training

ArXiv
2020 | Journal article
Contributors: Chang, Heng-Jui; H. Liu, Alexander; Lee, Hung-yi; Lee, Lin-shan
Source: check_circle
Web of Science Researcher Profile Sync
grade
Preferred source (of 3)‎

Peer review (2 reviews for 1 publication/grant)

Review activity for IEEE journal of selected topics in signal processing. (2)