Jiamin Xie

13 papers A 5B 2C 1Misc 1Journal 3Unranked 1
YearRankTypeTitle / Venue / Authors
2025 C conf
Bridging the Modality Gap: Softly Discretizing Audio Representation for LLM-based Automatic Speech Recognition.
ASRU
Mu Yang, Szu-Jui Chen, Jiamin Xie, John H. L. Hansen
2025 A conf
Thinking in Directivity: Speech Large Language Model for Multi-Talker Directional Speech Recognition.
INTERSPEECH
Jiamin Xie, Ju Lin, Yiteng Huang, Tyler Vuong, Zhaojiang Lin, Zhaojun Yang, Peng Su, Prashant Rawat, Sangeeta Srivastava, Ming Sun, Florian Metze
2025 J jnl
Thinking in Directivity: Speech Large Language Model for Multi-Talker Directional Speech Recognition.
CoRR
Jiamin Xie, Ju Lin, Yiteng Huang, Tyler Vuong, Zhaojiang Lin, Zhaojun Yang, Peng Su, Prashant Rawat, Sangeeta Srivastava, Ming Sun, Florian Metze
2024 Misc conf
Dynamic ASR Pathways: An Adaptive Masking Approach Towards Efficient Pruning of a Multilingual ASR Model.
ICASSP
Jiamin Xie, Ke Li, Jinxi Guo, Andros Tjandra, Yuan Shangguan, Leda Sari, Chunyang Wu, Junteng Jia, Jay Mahadeokar, Ozlem Kalinli
2023 J jnl
Dynamic ASR Pathways: An Adaptive Masking Approach Towards Efficient Pruning of A Multilingual ASR Model.
CoRR
Jiamin Xie, Ke Li, Jinxi Guo, Andros Tjandra, Yuan Shangguan, Leda Sari, Chunyang Wu, Junteng Jia, Jay Mahadeokar, Ozlem Kalinli
2023 A conf
MixRep: Hidden Representation Mixup for Low-Resource Speech Recognition.
INTERSPEECH
Jiamin Xie, John H. L. Hansen
2022 A conf
DEFORMER: Coupling Deformed Localized Patterns with Global Context for Robust End-to-end Speech Recognition.
INTERSPEECH
Jiamin Xie, John H. L. Hansen
2022 A conf
FeaRLESS: Feature Refinement Loss for Ensembling Self-Supervised Learning Features in Robust End-to-end Speech Recognition.
INTERSPEECH
Szu-Jui Chen, Jiamin Xie, John H. L. Hansen
2022 J jnl
FeaRLESS: Feature Refinement Loss for Ensembling Self-Supervised Learning Features in Robust End-to-end Speech Recognition.
CoRR
Szu-Jui Chen, Jiamin Xie, John H. L. Hansen
2021 — conf
Measuring and influencing factors of social service efficiency in universities based on DEA-BCC-Malmquist-Tobit model.
EBIMCS
Peng Lei, Jiamin Xie
2021 B conf
SGCNet: a scale-aware and global context network for linear lesion segmentation in MCSL fundus images of high myopia.
Image Processing
Gaohui Luo, Qianlong Zhu, Xinjian Chen, Fei Shi, Ying Fan, Jiamin Xie, Qiuying Chen, Lingjiao Pan, Weifang Zhu
2021 B conf
Segmentation of RBCC disruption and myopic stretch line in retinal OCT images using an improved U-shape network.
Image Processing
Yichao Diao, Xinjian Chen, Ying Fan, Jiamin Xie, Qiuying Chen, Lingjiao Pan, Weifang Zhu
2019 A conf
Multi-PLDA Diarization on Children's Speech.
INTERSPEECH
Jiamin Xie, Leibny Paola García-Perera, Daniel Povey, Sanjeev Khudanpur