Heng-Jui Chang

33 papers A* 1A 3C 3Misc 3Journal 18Unranked 5

Year	Rank	Type	Title / Venue / Authors
2025	A	`conf`	DC-Spin: A Speaker-invariant Speech Tokenizer for Spoken Language Models. INTERSPEECH Heng-Jui Chang, Hongyu Gong, Changhan Wang, James R. Glass, Yu-An Chung
2025	J	`jnl`	Pushing the Frontier of Audiovisual Perception with Large-Scale Multimodal Correspondence Learning. CoRR Apoorv Vyas, Heng-Jui Chang, Cheng-Fu Yang, Po-Yao Huang, Luya Gao, Julius Richter, Sanyuan Chen, Matt Le, Piotr Dollár, Christoph Feichtenhofer, Ann Lee, Wei-Ning Hsu
2025	C	`conf`	USAD: Universal Speech and Audio Representation via Distillation. ASRU Heng-Jui Chang, Saurabhchand Bhati, James R. Glass, Alexander H. Liu
2025	J	`jnl`	USAD: Universal Speech and Audio Representation via Distillation. CoRR Heng-Jui Chang, Saurabhchand Bhati, James Glass, Alexander H. Liu
2024	J	`jnl`	A Large-Scale Evaluation of Speech Foundation Models. CoRR 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, Tzu-hsun Feng, Po-Han Chi, Yist Y. Lin, Yung-Sung Chuang, Tzu-Hsien Huang, Wei-Cheng Tseng, Kushal Lakhotia, Shang-wen Li, Abdelrahman Mohamed, Shinji Watanabe, Hung-yi Lee
2024	J	`jnl`	A Large-Scale Evaluation of Speech Foundation Models. IEEE ACM Trans. Audio Speech Lang. Process. 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, Tzu-hsun Feng, Po-Han Chi, Yist Y. Lin, Yung-Sung Chuang, Tzu-Hsien Huang, Wei-Cheng Tseng, Kushal Lakhotia, Shang-wen Li, Abdelrahman Mohamed, Shinji Watanabe, Hung-yi Lee
2024	Misc	`conf`	COLLD: Contrastive Layer-to-Layer Distillation for Compressing Multilingual Pre-Trained Speech Encoders. ICASSP Heng-Jui Chang, Ning Dong, Ruslan Mavlyutov, Sravya Popuri, Yu-An Chung
2024	J	`jnl`	DC-Spin: A Speaker-invariant Speech Tokenizer for Spoken Language Models. CoRR Heng-Jui Chang, Hongyu Gong, Changhan Wang, James R. Glass, Yu-An Chung
2024	—	`conf`	R-Spin: Efficient Speaker and Noise-invariant Representation Learning with Acoustic Pieces. NAACL-HLT Heng-Jui Chang, James R. Glass
2024	—	`conf`	SpeechCLIP+: Self-Supervised Multi-Task Representation Learning for Speech Via Clip and Speech-Image Data. ICASSP Workshops Hsuan-Fu Wang, Yi-Jen Shih, Heng-Jui Chang, Layne Berry, Puyuan Peng, Hung-yi Lee, Hsin-Min Wang, David Harwath
2024	J	`jnl`	SpeechCLIP+: Self-supervised multi-task representation learning for speech via CLIP and speech-image data. CoRR Hsuan-Fu Wang, Yi-Jen Shih, Heng-Jui Chang, Layne Berry, Puyuan Peng, Hung-yi Lee, Hsin-Min Wang, David Harwath
2023	J	`jnl`	CoLLD: Contrastive Layer-to-layer Distillation for Compressing Multilingual Pre-trained Speech Encoders. CoRR Heng-Jui Chang, Ning Dong, Ruslan Mavlyutov, Sravya Popuri, Yu-An Chung
2023	A*	`conf`	DinoSR: Self-Distillation and Online Clustering for Self-supervised Speech Representation Learning. NeurIPS Alexander H. Liu, Heng-Jui Chang, Michael Auli, Wei-Ning Hsu, James R. Glass
2023	J	`jnl`	DinoSR: Self-Distillation and Online Clustering for Self-supervised Speech Representation Learning. CoRR Alexander H. Liu, Heng-Jui Chang, Michael Auli, Wei-Ning Hsu, James R. Glass
2023	Misc	`conf`	M-SpeechCLIP: Leveraging Large-Scale, Pre-Trained Models for Multilingual Speech to Image Retrieval. ICASSP Layne Berry, Yi-Jen Shih, Hsuan-Fu Wang, Heng-Jui Chang, Hung-yi Lee, David Harwath
2023	J	`jnl`	R-Spin: Efficient Speaker and Noise-invariant Representation Learning with Acoustic Pieces. CoRR Heng-Jui Chang, James R. Glass
2023	A	`conf`	Self-supervised Fine-tuning for Improved Content Representations by Speaker-invariant Clustering. INTERSPEECH Heng-Jui Chang, Alexander H. Liu, James R. Glass
2023	J	`jnl`	Self-supervised Fine-tuning for Improved Content Representations by Speaker-invariant Clustering. CoRR Heng-Jui Chang, Alexander H. Liu, James R. Glass
2022	Misc	`conf`	Distilhubert: Speech Representation Learning by Layer-Wise Distillation of Hidden-Unit Bert. ICASSP Heng-Jui Chang, Shu-Wen Yang, Hung-yi Lee
2022	J	`jnl`	M-SpeechCLIP: Leveraging Large-Scale, Pre-Trained Models for Multilingual Speech to Image Retrieval. CoRR Layne Berry, Yi-Jen Shih, Hsuan-Fu Wang, Heng-Jui Chang, Hung-yi Lee, David Harwath
2022	—	`conf`	SUPERB-SG: Enhanced Speech processing Universal PERformance Benchmark for Semantic and Generative Capabilities. ACL (1) Hsiang-Sheng Tsai, Heng-Jui Chang, Wen-Chin Huang, Zili Huang, Kushal Lakhotia, Shu-Wen Yang, Shuyan Dong, Andy T. Liu, Cheng-I Lai, Jiatong Shi, Xuankai Chang, Phil Hall, Hsuan-Jui Chen, Shang-wen Li, Shinji Watanabe, Abdelrahman Mohamed, Hung-yi Lee
2022	J	`jnl`	SUPERB-SG: Enhanced Speech processing Universal PERformance Benchmark for Semantic and Generative Capabilities. CoRR Hsiang-Sheng Tsai, Heng-Jui Chang, Wen-Chin Huang, Zili Huang, Kushal Lakhotia, Shu-Wen Yang, Shuyan Dong, Andy T. Liu, Cheng-I Jeff Lai, Jiatong Shi, Xuankai Chang, Phil Hall, Hsuan-Jui Chen, Shang-wen Li, Shinji Watanabe, Abdelrahman Mohamed, Hung-yi Lee
2022	—	`conf`	SpeechCLIP: Integrating Speech with Pre-Trained Vision and Language Model. SLT Yi-Jen Shih, Hsuan-Fu Wang, Heng-Jui Chang, Layne Berry, Hung-yi Lee, David Harwath
2022	J	`jnl`	SpeechCLIP: Integrating Speech with Pre-Trained Vision and Language Model. CoRR Yi-Jen Shih, Hsuan-Fu Wang, Heng-Jui Chang, Layne Berry, Hung-yi Lee, David Harwath
2021	J	`jnl`	DistilHuBERT: Speech Representation Learning by Layer-wise Distillation of Hidden-unit BERT. CoRR Heng-Jui Chang, Shu-Wen Yang, Hung-yi Lee
2021	—	`conf`	End-to-End Whispered Speech Recognition with Frequency-Weighted Approaches and Pseudo Whisper Pre-training. SLT Heng-Jui Chang, Alexander H. Liu, Hung-yi Lee, Lin-Shan Lee
2021	J	`jnl`	Mandarin-English Code-switching Speech Recognition with Self-supervised Speech Representation Models. CoRR Liang-Hsuan Tseng, Yu-Kuan Fu, Heng-Jui Chang, Hung-yi Lee
2021	C	`conf`	Non-Autoregressive Mandarin-English Code-Switching Speech Recognition. ASRU Shun-Po Chuang, Heng-Jui Chang, Sung-Feng Huang, Hung-yi Lee
2021	J	`jnl`	Non-autoregressive Mandarin-English Code-switching Speech Recognition with Pinyin Mask-CTC and Word Embedding Regularization. CoRR Shun-Po Chuang, Heng-Jui Chang, Sung-Feng Huang, Hung-yi Lee
2021	A	`conf`	Towards Lifelong Learning of End-to-End ASR. Interspeech Heng-Jui Chang, Hung-yi Lee, Lin-Shan Lee
2021	J	`jnl`	Towards Lifelong Learning of End-to-end ASR. CoRR Heng-Jui Chang, Hung-yi Lee, Lin-Shan Lee
2021	C	`conf`	Transmission-Line Fault Location Identifications in HV Transmission Networks and different MV Wind Farms using Non-intrusive Monitoring Techniques. IAS Hsueh-Hsien Chang, Tse-Chih Lai, Heng-Jui Chang, Wei-Jen Lee
2020	J	`jnl`	End-to-end Whispered Speech Recognition with Frequency-weighted Approaches and Layer-wise Transfer Learning. CoRR Heng-Jui Chang, Alexander H. Liu, Hung-yi Lee, Lin-Shan Lee