Shaofei Xue

20 papers Misc 5Journal 8Unranked 7
YearRankTypeTitle / Venue / Authors
2026 J jnl
A Hybrid Discriminative and Generative System for Universal Speech Enhancement.
CoRR
Yinghao Liu, Chengwei Liu, Xiaotao Liang, Haoyin Yan, Shaofei Xue, Zheng Xue
2025 J jnl
OmniAvatar: Efficient Audio-Driven Avatar Video Generation with Adaptive Body Animation.
CoRR
Qijun Gan, Ruizi Yang, Jianke Zhu, Shaofei Xue, Steven Hoi
2025 J jnl
QuarkAudio Technical Report.
CoRR
Chengwei Liu, Haoyin Yan, Shaofei Xue, Xiaotao Liang, Xiaofu Chen, Bin Gong, Zheng Xue, Gang Song
2025 J jnl
Synaspot: A Lightweight, Streaming Multi-modal Framework for Keyword Spotting with Audio-Text Synergy.
CoRR
Kewei Li, Yinan Zhong, Xiaotao Liang, Tianchi Dai, Shaofei Xue
2025 J jnl
UniSE: A Unified Framework for Decoder-only Autoregressive LM-based Speech Enhancement.
CoRR
Haoyin Yan, Chengwei Liu, Shaofei Xue, Xiaotao Liang, Zheng Xue
2025 J jnl
UniTok-Audio: A Unified Audio Generation Framework via Generative Modeling on Discrete Codec Tokens.
CoRR
Chengwei Liu, Haoyin Yan, Shaofei Xue, Xiaotao Liang, Yinghao Liu, Zheng Xue, Gang Song, Boyang Zhou
2022 — conf
Improving Speech Recognition with Augmented Synthesized Data and Conditional Model Training.
ISCSLP
Shaofei Xue, Jian Tang, Yazhu Liu
2022 — conf
Multi-Resolution Stacked 1D-CNN for Small-Footprint keyword Spotting with Two-Stage Detection.
ISCSLP
Jian Tang, Shaofei Xue
2018 — conf
A Study on Improving Acoustic Model for Robust and Far-Field Speech Recognition.
DSP
Shaofei Xue, Zhijie Yan, Tao Yu, Zhang Liu
2017 Misc conf
Improving latency-controlled BLSTM acoustic models for online speech recognition.
ICASSP
Shaofei Xue, Zhijie Yan
2016 — conf
Rapid speaker adaptation based on D-code extracted from BLSTM-RNN in LVCSR.
ISCSLP
Shaofei Xue, Zhijie Yan, Zhiying Huang, Li-Rong Dai
2016 J jnl
Speaker Adaptation of Hybrid NN/HMM Model for Speech Recognition Based on Singular Value Decomposition.
J. Signal Process. Syst.
Shaofei Xue, Hui Jiang, Li-Rong Dai, Qingfeng Liu
2016 Misc conf
Speaker adaptation OF RNN-BLSTM for speech recognition based on speaker code.
ICASSP
Zhiying Huang, Jian Tang, Shaofei Xue, Li-Rong Dai
2016 — conf
Unsupervised speaker adaptation of BLSTM-RNN for LVCSR based on speaker code.
ISCSLP
Zhiying Huang, Shaofei Xue, Zhijie Yan, Li-Rong Dai
2015 Misc conf
Multi-task deep neural network acoustic models with model adaptation using discriminative speaker identity for whisper recognition.
ICASSP
Jingjie Li, Ian McLoughlin, Cong Liu, Shaofei Xue, Si Wei
2015 Misc conf
Unsupervised speaker adaptation of deep neural network based on the combination of speaker codes and singular value decomposition for speech recognition.
ICASSP
Shaofei Xue, Hui Jiang, Li-Rong Dai, Qingfeng Liu
2014 Misc conf
Direct adaptation of hybrid DNN/HMM model for fast speaker adaptation in LVCSR based on speaker code.
ICASSP
Shaofei Xue, Ossama Abdel-Hamid, Hui Jiang, Li-Rong Dai
2014 J jnl
Fast adaptation of deep neural network based on discriminant codes for speech recognition.
IEEE ACM Trans. Audio Speech Lang. Process.
Shaofei Xue, Ossama Abdel-Hamid, Hui Jiang, Li-Rong Dai, Qingfeng Liu
2014 — conf
Speaker adaptation of hybrid NN/HMM model for speech recognition based on singular value decomposition.
ISCSLP
Shaofei Xue, Hui Jiang, Li-Rong Dai
2014 — conf
Speaker adaptive bottleneck features extraction for LVCSR based on discriminative learning of speaker codes.
ISCSLP
Changqing Kong, Shaofei Xue, Jianqing Gao, Wu Guo, Li-Rong Dai, Hui Jiang