Yukun Qian

23 papers A* 1A 3Misc 5Journal 12Unranked 2
YearRankTypeTitle / Venue / Authors
2026 A* conf
D²PPO: Diffusion Policy Policy Optimization with Dispersive Loss.
AAAI
Guowei Zou, Weibing Li, Hejun Wu, Yukun Qian, Yuhang Wang, Haitao Wang
2026 — conf
LCKPose: Laplacian Candidate Keypoints Modeling for 6D Object Pose Estimation.
MMM (2)
Zhiyang Mai, Yukun Qian, Haitao Wang, Hejun Wu, Liangliang Zhou
2026 J jnl
Learning generalizable representations with adversarial domain adaptation for snoring-based sleep apnea detection.
Biomed. Signal Process. Control.
Heng Li, Yun Lu, Yukun Qian, Lianyu Zhou, Mingjiang Wang, Hanrong Cheng
2026 J jnl
MS-VBRVQ: Multi-scale variable bitrate speech residual vector quantization.
Speech Commun.
Yukun Qian, Shiyun Xu, Xuyi Zhuang, Zehua Zhang, Mingjiang Wang
2026 J jnl
One Step Is Enough: Dispersive MeanFlow Policy Optimization.
CoRR
Guowei Zou, Haitao Wang, Hejun Wu, Yukun Qian, Yuhang Wang, Weibing Li
2025 Misc conf
A Novel Compressive Compound Word Encoding and Independent Word Attention for Symbolic Music Generation.
ICASSP
Lianyu Zhou, Liang Yin, Yukun Qian
2025 Misc conf
CSMT: Combining Snoring and Metadata-based Text for Sleep Apnea Severity Classification.
ICASSP
Heng Li, Yukun Qian, Yun Lu, Mingjiang Wang
2025 J jnl
D2PPO: Diffusion Policy Policy Optimization with Dispersive Loss.
CoRR
Guowei Zou, Weibing Li, Hejun Wu, Yukun Qian, Yuhang Wang, Haitao Wang
2025 J jnl
DM1: MeanFlow with Dispersive Regularization for 1-Step Robotic Manipulation.
CoRR
Guowei Zou, Haitao Wang, Hejun Wu, Yukun Qian, Yuhang Wang, Weibing Li
2025 J jnl
Head information bottleneck (HIB): leveraging information bottleneck for efficient transformer head attribution and pruning.
EURASIP J. Audio Speech Music. Process.
Yukun Qian, Xuyi Zhuang, Mingjiang Wang
2025 J jnl
Hypformer: A Fast Hypothesis-Driven Rescoring Speech Recognition Framework.
IEEE Signal Process. Lett.
Xuyi Zhuang, Yukun Qian, Mingjiang Wang
2025 Misc conf
Joint Training Framework for Accent and Speech Recognition Based on Conformer Low-Rank Adaptation.
ICASSP
Xuyi Zhuang, Yukun Qian, Shiyun Xu, Mingjiang Wang
2025 J jnl
MLAT: a multi-level attention transformer capturing multi-level information in compound word encoding for symbolic music generation.
EURASIP J. Audio Speech Music. Process.
Lianyu Zhou, Liang Yin, Yukun Qian, Mingjiang Wang
2025 J jnl
SF-AN: A lightweight shuffle Fourier attention network for multi-channel speech enhancement.
Speech Commun.
Shiyun Xu, Yinghan Cao, Zehua Zhang, Yukun Qian, Changjun He, Mingjiang Wang
2024 A conf
Lightweight Dynamic Sparse Transformer for Monaural Speech Enhancement.
INTERSPEECH
Zehua Zhang, Xuyi Zhuang, Yukun Qian, Mingjiang Wang
2024 J jnl
SVQ-MAE: an efficient speech pre-training framework with constrained computational resources.
EURASIP J. Audio Speech Music. Process.
Xuyi Zhuang, Yukun Qian, Mingjiang Wang
2024 J jnl
Supervised Attention Multi-Scale Temporal Convolutional Network for monaural speech enhancement.
EURASIP J. Audio Speech Music. Process.
Zehua Zhang, Lu Zhang, Xuyi Zhuang, Yukun Qian, Mingjiang Wang
2023 A conf
Automatic Speech Recognition Transformer with Global Contextual Information Decoder.
INTERSPEECH
Yukun Qian, Xuyi Zhuang, Mingjiang Wang
2023 Misc conf
Half-Temporal and Half-Frequency Attention U
ICASSP
Zehua Zhang, Shiyun Xu, Xuyi Zhuang, Yukun Qian, Lianyu Zhou, Mingjiang Wang
2022 A conf
Coarse-Grained Attention Fusion With Joint Training Framework for Complex Speech Enhancement and End-to-End Speech Recognition.
INTERSPEECH
Xuyi Zhuang, Lu Zhang, Zehua Zhang, Yukun Qian, Mingjiang Wang
2022 J jnl
Contactless sleep apnea detection in snoring signals using hybrid deep neural networks targeted for embedded hardware platform with real-time applications.
Biomed. Signal Process. Control.
Xu Lin, Hanrong Cheng, Yun Lu, Huaiwen Luo, Heng Li, Yukun Qian, Lianyu Zhou, Lu Zhang, Mingjiang Wang
2022 — conf
Cross-Individual Obstructive Obstructive Apnea Detection in Snoring Signals Using Hybrid Deep Neural Networks.
ACAI
Xu Lin, Yun Lu, Heng Li, Yukun Qian, Lianyu Zhou, Mingjiang Wang
2022 Misc conf
FB-MSTCN: A Full-Band Single-Channel Speech Enhancement Method Based on Multi-Scale Temporal Convolutional Network.
ICASSP
Zehua Zhang, Lu Zhang, Xuyi Zhuang, Yukun Qian, Heng Li, Mingjiang Wang