Dongseong Hwang

32 papers A* 1A 7C 1Misc 6Journal 16Unranked 1

Year	Rank	Type	Title / Venue / Authors
2025	J	`jnl`	AXLearn: Modular Large Model Training on Heterogeneous Infrastructure. CoRR Mark Lee, Tom Gunter, Chang Lan, John Peebles, Hanzhi Zhou, Kelvin Zou, Sneha Bangalore, Chung-Cheng Chiu, Nan Du, Xianzhi Du, Philipp Dufter, Ruixuan Hou, Haoshuo Huang, Dongseong Hwang, Xiang Kong, Jinhao Lei, Tao Lei, Meng Li, Li Li, Jiarui Lu, Zhiyun Lu, Yiping Ma, David Qiu, Vivek Rathod, Senyu Tong, Zhucheng Tu, Jianyu Wang, Yongqiang Wang, Zirui Wang, Floris Weers, Sam Wiseman, Guoli Yin, Bowen Zhang, Xiyou Zhou, Danyang Zhuo, Cheng Leong, Ruoming Pang
2024	A	`conf`	AdaRA: Adaptive Rank Allocation of Residual Adapters for Speech Foundation Model. INTERSPEECH Zhouyuan Huo, Dongseong Hwang, Gan Song, Khe Chai Sim, Weiran Wang
2024	Misc	`conf`	Extreme Encoder Output Frame Rate Reduction: Improving Computational Latencies of Large End-to-End Models. ICASSP Rohit Prabhavalkar, Zhong Meng, Weiran Wang, Adam Stooke, Xingyu Cai, Yanzhang He, Arun Narayanan, Dongseong Hwang, Tara N. Sainath, Pedro J. Moreno
2024	J	`jnl`	Extreme Encoder Output Frame Rate Reduction: Improving Computational Latencies of Large End-to-End Models. CoRR Rohit Prabhavalkar, Zhong Meng, Weiran Wang, Adam Stooke, Xingyu Cai, Yanzhang He, Arun Narayanan, Dongseong Hwang, Tara N. Sainath, Pedro J. Moreno
2024	J	`jnl`	FAdam: Adam is a natural gradient optimizer using diagonal empirical Fisher information. CoRR Dongseong Hwang
2024	Misc	`conf`	Improving Speech Recognition for African American English with Audio Classification. ICASSP Shefali Garg, Zhouyuan Huo, Khe Chai Sim, Suzan Schwartz, Mason Chua, Alëna Aksënova, Tsendsuren Munkhdalai, Levi King, Darryl Wright, Zion Mengesha, Dongseong Hwang, Tara N. Sainath, Françoise Beaufays, Pedro Moreno Mengibar
2024	—	`conf`	Massive End-to-end Speech Recognition Models with Time Reduction. NAACL-HLT Weiran Wang, Rohit Prabhavalkar, Haozhe Shan, Zhong Meng, Dongseong Hwang, Qiujia Li, Khe Chai Sim, Bo Li, James Qin, Xingyu Cai, Adam Stooke, Chengjian Zheng, Yanzhang He, Tara N. Sainath, Pedro Moreno Mengibar
2024	J	`jnl`	TransformerFAM: Feedback attention is working memory. CoRR Dongseong Hwang, Weiran Wang, Zhuoyuan Huo, Khe Chai Sim, Pedro Moreno Mengibar
2023	Misc	`conf`	Comparison of Soft and Hard Target RNN-T Distillation for Large-Scale ASR. ICASSP Dongseong Hwang, Khe Chai Sim, Yu Zhang, Trevor Strohman
2023	J	`jnl`	Edit Distance based RL for RNNT decoding. CoRR Dongseong Hwang, Changwan Ryu, Khe Chai Sim
2023	C	`conf`	Efficient Cascaded Streaming ASR System Via Frame Rate Reduction. ASRU Xingyu Cai, David Qiu, Shaojin Ding, Dongseong Hwang, Weiran Wang, Antoine Bruguier, Rohit Prabhavalkar, Tara N. Sainath, Yanzhang He
2023	Misc	`conf`	Efficient Domain Adaptation for Speech Foundation Models. ICASSP Bo Li, Dongseong Hwang, Zhouyuan Huo, Junwen Bai, Guru Prakash, Tara N. Sainath, Khe Chai Sim, Yu Zhang, Wei Han, Trevor Strohman, Françoise Beaufays
2023	J	`jnl`	Efficient Domain Adaptation for Speech Foundation Models. CoRR Bo Li, Dongseong Hwang, Zhouyuan Huo, Junwen Bai, Guru Prakash, Tara N. Sainath, Khe Chai Sim, Yu Zhang, Wei Han, Trevor Strohman, Françoise Beaufays
2023	J	`jnl`	Improving Speech Recognition for African American English With Audio Classification. CoRR Shefali Garg, Zhouyuan Huo, Khe Chai Sim, Suzan Schwartz, Mason Chua, Alëna Aksënova, Tsendsuren Munkhdalai, Levi King, Darryl Wright, Zion Mengesha, Dongseong Hwang, Tara N. Sainath, Françoise Beaufays, Pedro Moreno Mengibar
2023	J	`jnl`	Massive End-to-end Models for Short Search Queries. CoRR Weiran Wang, Rohit Prabhavalkar, Dongseong Hwang, Qiujia Li, Khe Chai Sim, Bo Li, James Qin, Xingyu Cai, Adam Stooke, Zhong Meng, CJ Zheng, Yanzhang He, Tara N. Sainath, Pedro Moreno Mengibar
2023	A	`conf`	Modular Domain Adaptation for Conformer-Based Streaming ASR. INTERSPEECH Qiujia Li, Bo Li, Dongseong Hwang, Tara N. Sainath, Pedro Moreno Mengibar
2023	J	`jnl`	Modular Domain Adaptation for Conformer-Based Streaming ASR. CoRR Qiujia Li, Bo Li, Dongseong Hwang, Tara N. Sainath, Pedro Moreno Mengibar
2023	A	`conf`	Re-investigating the Efficient Transfer Learning of Speech Foundation Model using Feature Fusion Methods. INTERSPEECH Zhouyuan Huo, Khe Chai Sim, Dongseong Hwang, Tsendsuren Munkhdalai, Tara N. Sainath, Pedro Moreno Mengibar
2023	Misc	`conf`	Resource-Efficient Transfer Learning from Speech Foundation Model Using Hierarchical Feature Fusion. ICASSP Zhouyuan Huo, Khe Chai Sim, Bo Li, Dongseong Hwang, Tara N. Sainath, Trevor Strohman
2023	A*	`conf`	Revisiting the Entropy Semiring for Neural Speech Recognition. ICLR Oscar Chang, Dongseong Hwang, Olivier Siohan
2023	J	`jnl`	Revisiting the Entropy Semiring for Neural Speech Recognition. CoRR Oscar Chang, Dongseong Hwang, Olivier Siohan
2022	A	`conf`	A Unified Cascaded Encoder ASR Model for Dynamic Model Sizes. INTERSPEECH Shaojin Ding, Weiran Wang, Ding Zhao, Tara N. Sainath, Yanzhang He, Robert David, Rami Botros, Xin Wang, Rina Panigrahy, Qiao Liang, Dongseong Hwang, Ian McGraw, Rohit Prabhavalkar, Trevor Strohman
2022	J	`jnl`	A Unified Cascaded Encoder ASR Model for Dynamic Model Sizes. CoRR Shaojin Ding, Weiran Wang, Ding Zhao, Tara N. Sainath, Yanzhang He, Robert David, Rami Botros, Xin Wang, Rina Panigrahy, Qiao Liang, Dongseong Hwang, Ian McGraw, Rohit Prabhavalkar, Trevor Strohman
2022	J	`jnl`	Comparison of Soft and Hard Target RNN-T Distillation for Large-scale ASR. CoRR Dongseong Hwang, Khe Chai Sim, Yu Zhang, Trevor Strohman
2022	A	`conf`	Incremental Layer-Wise Self-Supervised Learning for Efficient Unsupervised Speech Domain Adaptation On Device. INTERSPEECH Zhouyuan Huo, Dongseong Hwang, Khe Chai Sim, Shefali Garg, Ananya Misra, Nikhil Siddhartha, Trevor Strohman, Françoise Beaufays
2022	Misc	`conf`	Large-Scale ASR Domain Adaptation Using Self- and Semi-Supervised Learning. ICASSP Dongseong Hwang, Ananya Misra, Zhouyuan Huo, Nikhil Siddhartha, Shefali Garg, David Qiu, Khe Chai Sim, Trevor Strohman, Françoise Beaufays, Yanzhang He
2022	A	`conf`	Pseudo Label Is Better Than Human Label. INTERSPEECH Dongseong Hwang, Khe Chai Sim, Zhouyuan Huo, Trevor Strohman
2022	J	`jnl`	Pseudo Label Is Better Than Human Label. CoRR Dongseong Hwang, Khe Chai Sim, Zhouyuan Huo, Trevor Strohman
2022	J	`jnl`	Resource-Efficient Transfer Learning From Speech Foundation Model Using Hierarchical Feature Fusion. CoRR Zhouyuan Huo, Khe Chai Sim, Bo Li, Dongseong Hwang, Tara N. Sainath, Trevor Strohman
2021	A	`conf`	A Comparison of Supervised and Unsupervised Pre-Training of End-to-End Models. Interspeech Ananya Misra, Dongseong Hwang, Zhouyuan Huo, Shefali Garg, Nikhil Siddhartha, Arun Narayanan, Khe Chai Sim
2021	J	`jnl`	Incremental Layer-wise Self-Supervised Learning for Efficient Speech Domain Adaptation On Device. CoRR Zhouyuan Huo, Dongseong Hwang, Khe Chai Sim, Shefali Garg, Ananya Misra, Nikhil Siddhartha, Trevor Strohman, Françoise Beaufays
2021	J	`jnl`	Large-scale ASR Domain Adaptation using Self- and Semi-supervised Learning. CoRR Dongseong Hwang, Ananya Misra, Zhouyuan Huo, Nikhil Siddhartha, Shefali Garg, David Qiu, Khe Chai Sim, Trevor Strohman, Françoise Beaufays, Yanzhang He