Publications

Xulong Zhang, Jiashu Wang, Xiaoyang Qu, Hui Tian, Jianzong Wang (2025). Turbo-TTS: Enhancing Diffusion Model TTS with an Improved ODE Solver. In ICONIP2025 (CCF-C).

Cite

Pengcheng Li~, Botao Zhao, Zuheng Kang, Junqing Peng, Xiaoyang Qu, Yayun He, Jianzong Wang (2025). EMO-RL: Emotion-Rule-Based Reinforcement Learning Enhanced Audio-Language Model for Generalized Speech Emotion Recognition. In EMNLP2025 (CCF-B).

Cite arXiv

Jiaqi Shi, Xulong Zhang, Xiaoyang Qu, Junfei Xie, Jianzong Wang (2025). Knowledge Distillation for Financial Large Language Models: A Systematic Review of Strategies, Applications, and Evaluation. In [J], Frontiers of Information Technology & Electronic Engineering (FITEE) (SCI IF=2.9).

Cite

Lin Zhu, Lingwei Kong, Xin Ning, Xiaoyang Qu, Jianzong Wang (2025). Publicly Verifiable Private Information Retrieval Protocols Based on Function Secret Sharing. In Inscrypt2025 (CCF-C).

Cite arXiv

Jianhan Wu, Xiaoyang Qu, Zhangcheng Huang, Jianzong Wang (2025). Federated Domain Generalization with Domain-specific Soft Prompts Generation. In ICCV2025 (CCF-A).

Cite arXiv

Jialu Cao, Hui Tian, Peng Tian, Haizhou Li, Jianzong Wang (2025). Robust Detection of Partially Spoofed Audio Using Semantic-Aware Inconsistency Learning. In [J], IEEE Transactions on Audio, Speech and Language Processing (T-ASLP) (CCF-B).

Cite IEEE

Junjie Li, Nan Zhang, Xiaoyang Qu, Kai Lu, Guokuan Li, Jiguang Wan, Jianzong Wang (2025). RATE-Nav: Region-Aware Termination Enhancement for Zero-shot Object Navigation with Vision-Language Models. In ACL2025 (CCF-A).

Cite arXiv

Wei Tao, Haocheng Lu, Xiaoyang Qu, Bin Zhang, Kai Lu, Jiguang Wan, Jianzong Wang (2025). MoQAE: Mixed-Precision Quantization for Long-Context LLM Inference via Mixture of Quantization-Aware Experts. In ACL2025 (CCF-A).

Cite arXiv

Ziqi Jia, Anmin Wang, Xiaoyang Qu, Xiaowen Yang, Jianzong Wang (2025). Hierarchical-Task-Aware Multi-modal Mixture of Incremental LoRA Experts for Embodied Continual Learning. In ACL2025 (CCF-A).

Cite arXiv

Jianzong Wang, Xulong Zhang, Xiaoyang Qu (2025). Rano: Restorable Speaker Anonymization via Conditional Invertible Neural Network. In IJCNN2025 (CCF-C).

Cite

Wei Tao, Xiaoyang Qu, Kai Lu, Jiguang Wan, Guokuan Li, Jianzong Wang (2025). MADLLM: Multivariate Anomaly Detection via Pre-trained LLMs. In ICME2025 (CCF-B).

Cite arXiv

Bingyuan Zhang, Xulong Zhang, Yong Zhang, Jun Yu, Jianzong Wang (2025). Logic Consistency Makes Large Language Models Personalized Reasoning Teachers. In IJCNN2025 (CCF-C).

Cite

Botao Zhao, Zuheng Kang, Yayun He, Xiaoyang Qu, Junqing Peng, Jing Xiao, Jianzong Wang (2025). Generalized Audio Deepfake Detection Using Frame-level Latent Information Entropy. In ICME2025 (CCF-B).

Cite arXiv

Jianzong Wang, Bin Zhang, Chendong Zhao, Xiaoyang Qu (2025). Data-free Black-box Knowledge Amalgamation. In IJCNN2025 (CCF-C).

Cite

Jianzong Wang, Xulong Zhang, Xiaoyang Qu (2025). Bridging the Modality Gap: Semantic-Calibrated Zero-shot Speech Emotion Captioning. In IJCNN2025 (CCF-C).

Cite

Wei Tao, Xiaoyang Qu, Kai Lu, Jiguang Wan, Shenglin He, Jianzong Wang (2025). BAGNet: A Boundary-Aware Graph Attention Network for 3D Point Cloud Semantic Segmentation. In IJCNN2025 (CCF-C).

Cite arXiv

Ziqi Jia, Junjie Li, Xiaoyang Qu, Jianzong Wang (2025). Enhancing Multi-Agent Systems via Reinforcement Learning with LLM-based Planner and Graph-based Policy. In ICRA2025 (CCF-B).

Cite arXiv

Bin Zhang, Xiaoyang Qu, Guokuan Li, Jiguang Wan, Jianzong Wang (2025). VisTa: Visual-contextual and Text-augmented Zero-shot Object-level OOD Detection. In ICASSP2025 (CCF-B).

PDF Cite arXiv IEEE

Wei Tao, Shenglin He, Xiaoyang Qu, Jiguang Wan, Jianzong Wang (2025). PointActionCLIP: Preventing Transfer Degradation in Point Cloud Action Recognition with a Triple-Path CLIP. In ICASSP2025 (CCF-B).

PDF Cite IEEE

Shihao Gao, Xiaoyan Yu, Yu Cai, Xulong Zhang, Jianzong Wang, Taisong Jin (2025). Homogeneous Graph Extraction: An Approach to Learning Heterogeneous Graph Embedding. In ICASSP2025 (CCF-B).

PDF Cite IEEE

Shihao Gao, Caoshuo Li, Cunli Mao, Xulong Zhang, Xiaoyang Qu, Taisong Jin, Jianzong Wang (2025). Graph Contrastive Learning with Decoupled Augmentation. In ICASSP2025 (CCF-B).

PDF Cite IEEE

Ziqi Liang, Xulong Zhang, Chang Liu, Xiaoyang Qu, Weifeng Zhao, Jianzong Wang (2025). CycleFlow: Leveraging Cycle Consistency in Flow Matching for Speaker Style Adaptation. In ICASSP2025 (CCF-B).

Cite arXiv IEEE

Bin Zhang, Jinggang Chen, Xiaoyang Qu, Guokuan Li, Kai Lu, Jiguang Wan, Jing Xiao, Jianzong Wang (2025). RUNA: Object-level Out-of-Distribution Detection via Regional Uncertainty Alignment of Multimodal Representations. In AAAI2025 (CCF-A).

Cite arXiv

Botao Zhao, Xiaoyang Qu, Zuheng Kang, Junqing Peng, Jing Xiao, Jianzong Wang (2025). ACCon: Angle-Compensated Contrastive Regularizer for Deep Regression. In AAAI2025 (CCF-A).

Cite arXiv

Wei Tao, Bin Zhang, Xiaoyang Qu, Jiguang Wan, Jianzong Wang (2025). Cocktail:Chunk-AdaptiveMixed-Precision Ouanization for Long-Context LLM inference. In DATE2025 (CCF-B) Best Paper Award.

Cite arXiv

Ziqi Jia, Xiaoyang Qu, Chenghao Liu, Jianzong Wang (2024). Incremental Label Distribution Learning With Scalable Graph Convolutional Networks. In HPCC2024 (CCF-C).

Cite arXiv

Shuanglong Li, Xulong Zhang, Jianzong Wang (2024). A Novel Optimization Scheme for Named Entity Recognition with Pre-trained Language Models. In [J], Journal of Electronic Research and Application (JERA) (EI).

Cite JERA

Pengcheng Li, Xulong Zhang, Jing Xiao, Jianzong Wang (2024). IDEAW: Robust Neural Audio Watermarking with Invertible Dual-Embedding. In EMNLP2024 (CCF-B).

Cite Code arXiv ACL DEMO

Jiaqi Li, Chenyu Zhao, Yuzhu Mao, Xinlei Chen, Wenbo Ding, Xiaoyang Qu, Jianzong Wang (2024). FormerReckoning: Physics Inspired Transformer for Accurate Inertial Navigation. In PICASSO2024.

PDF Cite ACM

Jiaqi Li, Xiaoyang Qu, Wenbo Ding, Zihao Zhao, Jianzong Wang (2024). Beyond Aggregation: Efficient Federated Model Consolidation with Heterogeneity-Adaptive Weights Diffusion. In CIKM2024 (CCF-B).

Cite ACM

Ming Li, Yong Zhang, Shwai He, Zhitao Li, Hongyu Zhao, Jianzong Wang, Ning Cheng, Tianyi Zhou (2024). Superfiltering: Weak-to-Strong Data Filtering for Fast Instruction-Tuning. In ACL2024 (CCF-A).

Cite Code arXiv

Jianzong Wang, Haoxiang Shi, Kaiyi Luo, Xulong Zhang, Ning Cheng, Jing Xiao (2024). RREH: Reconstruction Relations Embedded Hashing for Semi-Paired Cross-Modal Retrieval. In ICIC2024 (CCF-C).

Cite arXiv Springer

Haoxiang Shi, Xulong Zhang, Ning Cheng, Yong Zhang, Jun Yu, Jing Xiao, Jianzong Wang (2024). Enhancing Emotion Prediction and Recognition in Conversation through Fine-Grained Emotional Cue Analysis and Cross-Modal Fusion. In ICIC2024 (CCF-C).

Cite arXiv Springer

Haoxiang Shi, Jianzong Wang, Xulong Zhang, Ning Cheng, Jun Yu, Jing Xiao (2024). RSET: Remapping-based Sorting Method for Emotion Transfer Speech Synthesis. In APWeb2024 (CCF-C).

Cite arXiv Springer

Zuheng Kang, Yayun He, Botao Zhao, Xiaoyang Qu, Junqing Peng, Jing Xiao, Jianzong Wang (2024). Retrieval-Augmented Audio Deepfake Detection. In ICMR2024 (CCF-B).

Cite arXiv ACM

Zhiyuan Wang, Bokui Chen, Xiaoyang Qu, Zhenhou Hong, Jing Xiao, Jianzong Wang (2024). Task-Agnostic Decision Transformer for Multi-Type Agent Control with Federated Split Training. In IJCNN2024 (CCF-C).

Cite arXiv IEEE

Sheng Ouyang, Jianzong Wang, Yong Zhang, Zhitao Li, Ziqi Liang, Xulong Zhang, Ning Cheng, Jing Xiao (2024). QLSC: A Query Latent Semantic Calibrator for Robust Extractive Question Answering. In IJCNN2024 (CCF-C).

Cite arXiv IEEE

Shenglin He, Xiaoyang Qu, Jiguang Wan, Guokuan Li, Changsheng Xie, Jianzong Wang (2024). PRENet: A Plane-Fit Redundancy Encoding Point Cloud Sequence Network for Real-Time 3D Action Recognition. In IJCNN2024 (CCF-C).

Cite arXiv IEEE

Pengcheng Li, Jianzong Wang, Xulong Zhang, Yong Zhang, Jing Xiao, Ning Cheng (2024). MAIN-VC: Lightweight Speech Representation Disentanglement for One-Shot Voice Conversion. In IJCNN2024 (CCF-C).

Cite arXiv DEMO IEEE

Yimin Deng, Jianzong Wang, Xulong Zhang, Ning Cheng, Jing Xiao (2024). Learning Expressive Disentangled Speech Representations with Soft Speech Units and Adversarial Style Augmentation. In IJCNN2024 (CCF-C).

Cite arXiv IEEE

Baoping Deng, Jinggang Chen, Zhenhou Hong, Xiaoyang Qu, Guokuan Li, Jiguang Wan, Changsheng Xie, Jianzong Wang (2024). Enhancing Anomalous Sound Detection with Multi-Level Memory Bank. In IJCNN2024 (CCF-C).

Cite IEEE

Jianzong Wang, Ziqi Liang, Xulong Zhang, Ning Cheng, Jing Xiao (2024). EfficientASR: Speech Recognition Network Compression via Attention Redundancy and Chunk-Level FFN Optimization. In IJCNN2024 (CCF-C).

Cite arXiv IEEE

Zuheng Kang, Yayun He, Jianzong Wang, Junqing Peng, Jing Xiao (2024). Efficient Multi-Model Fusion with Adversarial Complementary Representation Learning. In IJCNN2024 (CCF-C).

Cite arXiv IEEE

Ziqi Liang, Jianzong Wang, Xulong Zhang, Yong Zhang, Ning Cheng, Jing Xiao (2024). EAD-VC: Enhancing Speech Auto-Disentanglement for Voice Conversion with IFUB Estimator and Joint Text-Guided Consistent Learning. In IJCNN2024 (CCF-C).

Cite arXiv DEMO IEEE

Jianzong Wang, Pengcheng Li, Xulong Zhang, Ning Cheng, Jing Xiao (2024). CONTUNER: Singing Voice Beautifying with Pitch and Expressiveness Condition. In IJCNN2024 (CCF-C).

Cite arXiv DEMO IEEE

Ming Li, Yong Zhang, Zhitao Li, Jiuhai Chen, Lichang Chen, Ning Cheng, Jianzong Wang, Tianyi Zhou, Jing Xiao (2024). From Quantity to Quality: Boosting LLM Performance with Self-Guided Data Selection for Instruction Tuning. In NAACL2024 (CCF-B).

Cite Code arXiv

Jianzong Wang, Pengcheng Li, Xulong Zhang, Ning Cheng, Jing Xiao (2024). Medical Speech Symptoms Classification via Disentangled Representation. In CSCWD2024 (CCF-C).

Cite arXiv IEEE

Liang Wang, Xiaoyang Qu, Jianzong Wang, Guokuan Li, Jiguang Wan, Nan Zhang, Song Guo, Jing Xiao (2024). Gecko: Resource-Efficient and Accurate Queries in Real-Time Video Streams at the Edge. In INFOCOM2024 (CCF-A).

PDF Cite

Bingyuan Zhang, Xulong Zhang, Ning Cheng, Jun Yu, Jing Xiao, Jianzong Wang (2024). EmoTalker: Emotionally Editable Talking Face Generation via Diffusion Model. In ICASSP2024 (CCF-B).

Cite arXiv Dataset IEEE

Haobin Tang, Xulong Zhang, Ning Cheng, Jing Xiao, Jianzong Wang (2024). ED-TTS: Multi-Scale Emotion Modeling Using Cross-Domain Emotion Diarization for Emotional Speech Synthesis. In ICASSP2024 (CCF-B).

Cite arXiv IEEE

Yimin Deng, Huaizhen Tang, Xulong Zhang, Ning Cheng, Jing Xiao, Jianzong Wang (2024). Learning Disentangled Speech Representations with Contrastive Learning and Time-Invariant Retrieval. In ICASSP2024 (CCF-B).

Cite arXiv IEEE

Zhiyuan Wang, Xiaoyang Qu, Jing Xiao, Bokui Chen, Jianzong Wang (2024). P2DT: Mitigating Forgetting in Task-Incremental Learning with Progressive Prompt Decision Transformer. In ICASSP2024 (CCF-B).

Cite arXiv IEEE

Yong Zhang, Hanzhang Li, Zhitao Li, Ning Cheng, Ming Li, Jing Xiao, Jianzong Wang (2024). Leveraging Biases in Large Language Models: bias-kNN for Effective Few-Shot Learning. In ICASSP2024 (CCF-B).

Cite arXiv IEEE

Zhiyuan Wang, Xiaoyang Qu, Jing Xiao, Bokui Chen, Jianzong Wang (2024). INCPrompt: Task-Aware Incremental Prompting for Rehearsal-Free Class-incremental Learning. In ICASSP2024 (CCF-B).

Cite arXiv IEEE

Jianzong Wang, Xulong Zhang, Guilin Jiang, Ning Cheng, Jing Xiao (2024). Research on Audio Model Generation Technology Based on Hierarchical Federated Framework. In CAAI TIT.

Cite CAAI

Wei Tao, Shenglin He, Kai Lu, Xiaoyang Qu, Guokuan Li, Jiguang Wan, Jianzong Wang, Jing Xiao (2024). Value-Driven Mixed-Precision Quantization for Patch-Based Inference on Microcontrollers. In DATE2024 (CCF-B).

Cite arXiv IEEE

Liang Wang, Kai Lu, Nan Zhang, Xiaoyang Qu, Jianzong Wang, Jiguang Wan, Guokuan Li, Jing Xiao (2023). Shoggoth: Towards Efficient Edge-Cloud Collaborative Real-Time Video Inference via Adaptive Online Learning. In DAC2023 (CCF-A).

Cite arXiv

Yimin Deng, Huaizhen Tang, Xulong Zhang, Jianzong Wang, Ning Cheng, Jing Xiao (2023). PMVC: Data Augmentation-Based Prosody Modeling for Expressive Voice Conversion. In MM2023 (CCF-A).

PDF Cite arXiv DEMO ACM

Tong Ye, Shijing Si, Jianzong Wang, Ning Cheng, Zhitao Li, Jing Xiao (2023). On the Calibration and Uncertainty with Pólya-Gamma Augmentation for Dialog Retrieval Models. In AAAI2023 (CCF-A).

PDF Cite arXiv AAAI

Jinggang Chen, Junjie Li, Xiaoyang Qu, Jianzong Wang, Jiguang Wan, Jing Xiao (2023). GAIA: Delving into Gradient-based Attribution Abnormality for Out-of-distribution Detection. In NeurIPS2023 (CCF-A).

PDF Cite Poster Slides

Chenghao Liu, Xiaoyang Qu, Jianzong Wang, Jing Xiao (2023). FedET: A Communication-Efficient Federated Class-Incremental Learning Framework Based on Enhanced Transformer. In IJCAI2023 (CCF-A).

PDF Cite arXiv IJCAI

Jianzong Wang, Pengcheng Li, Xulong Zhang, Ning Cheng, Jing Xiao (2023). DQR-TTS: Semi-supervised Text-to-speech Synthesis with Dynamic Quantized Representation. In BDCloud2023.

Cite arXiv IEEE

Jianzong Wang, Yimin Deng, Ziqi Liang, Xulong Zhang, Ning Cheng, Jing Xiao (2023). CP-EB: Talking Face Generation with Controllable Pose and Eye Blinking Embedding. In ISPA2023 (CCF-C).

Cite arXiv IEEE

Yimin Deng, Xulong Zhang, Jianzong Wang, Ning Cheng, Jing Xiao (2023). CLN-VC: Text-Free Voice Conversion Based on Fine-Grained Style Control and Contrastive Learning with Negative Samples Augmentation. In SpaCCS2023.

Cite arXiv IEEE

Haoyan Yang, Zhitao Li, Yong Zhang, Jianzong Wang, Ning Cheng, Ming Li, Jing Xiao (2023). PRCA: Fitting Black-Box Large Language Models for Retrieval Question Answering via Pluggable Reward-Driven Contextual Adapter. In EMNLP2023 (CCF-B).

PDF Cite arXiv ACL

Yayun He, Zuheng Kang, Jianzong Wang, Junqing Peng, Jing Xiao (2023). VoiceExtender: Short-utterance Text-independent Speaker Verification with Guided Diffusion Model. In ASRU2023.

Cite arXiv IEEE

Jianzong Wang, Xulong Zhang, Aolan Sun, Ning Cheng, Jing Xiao (2023). FastGraphTTS: An Ultrafast Syntax-Aware Speech Synthesis Framework. In ICTAI2023 (CCF-C).

Cite arXiv IEEE DEMO

Kaiyi Luo, Xulong Zhang, Jianzong Wang, Huaxiong Li, Ning Cheng, Jing Xiao (2023). Contrastive Latent Space Reconstruction Learning for Audio-Text Retrieval. In ICTAI2023 (CCF-C).

Cite arXiv IEEE

Yazhong Si, Xulong Zhang, Fan Yang, Jianzong Wang, Ning Cheng, Jing Xiao (2023). AOSR-Net: All-in-One Sandstorm Removal Network. In ICTAI2023 (CCF-C).

Cite arXiv IEEE

Siddique Latif, Moazzam Shoukat, Fahad Shamshad, Muhammad Usama, Yi Ren, Heriberto Cuayáhuitl, Wenwu Wang, Xulong Zhang, Roberto Togneri, Björn W. Schuller (2023). Sparks of Large Audio Models: A Survey and Outlook. In arXiv (work in progress).

Cite Code arXiv

Zipeng Qi, Xulong Zhang, Ning Cheng, Jing Xiao, Jianzong Wang (2023). DiffTalker: Co-driven audio-image diffusion for talking faces via intermediate landmarks. In arXiv (work in progress).

Cite Code arXiv

Wenting Liu, Zhaozhong Gui, Guilin Jiang, Lihua Tang, Lichun Zhou, Wan Leng, Xulong Zhang, Yujiang Liu (2023). Stock Volatility Prediction Based on Transformer Model Using Mixed-Frequency Data. In APWeb2023 (CCF-C).

Cite arXiv Springer

Shanyi Zhou, Ning Yan, Zhijun Li, Mo Geng, Xulong Zhang, Hongbiao Si, Lihua Tang, Wenyuan Sun, Longda Zhang, Yi Cao (2023). Research on the Impact of Executive Shareholding on New Investment in Enterprises Based on Multivariable Linear Regression Model. In APWeb2023 (CCF-C).

Cite arXiv Springer

Hao Guo, Hongbiao Si, Guilin Jiang, Wei Zhang, Zhiyan Liu, Xuanyi Zhu, Xulong Zhang, Yang Liu (2023). An Empirical Study of Attention Networks for Semantic Segmentation. In APWeb2023 (CCF-C).

Cite arXiv Springer

Yu Ye, Gongjin Zhang, Hongbiao Si, Liang Xu, Shenghua Hu, Yong Li, Xulong Zhang, Kaiyu Hu, Fangzhou Ye (2023). A Hierarchy-based Analysis Approach for Blended Learning: A Case Study with Chinese Students. In APWeb2023 (CCF-C).

Cite arXiv Springer

Liang Wang, Nan Zhang, Xiaoyang Qu, Jianzong Wang, Jiguang Wan, Guokuan Li, Kaiyu Hu, Guilin Jiang, Jing Xiao (2023). EdgeMA: Model Adaptation System for Real-Time Video Analytics on Edge Devices. In ICONIP2023 (CCF-C).

Cite arXiv

Xulong Zhang, Jianzong Wang, Ning Cheng, Jing Xiao (2023). Voice Conversion with Denoising Diffusion Probabilistic GAN Models. In ADMA2023 (CCF-C).

Cite arXiv Springer

Kexin Zhu, Xulong Zhang, Jianzong Wang, Ning Cheng, Jing Xiao (2023). Symbolic and Acoustic: Multi-domain Music Emotion Modeling for Instrumental Music. In ADMA2023 (CCF-C).

Cite arXiv Springer

Xulong Zhang, Jianzong Wang, Ning Cheng, Yifu Sun, Chuanyao Zhang, Jing Xiao (2023). Machine Unlearning Methodology base on Stochastic Teacher Network. In ADMA2023 (CCF-C).

Cite arXiv Springer

Zuheng Kang, Jianzong Wang, Junqing Peng, Jing Xiao (2023). SVVAD: Personal Voice Activity Detection for Speaker Verification. In INTERSPEECH2023 (CCF-C).

PDF Cite Slides arXiv ISCA

Yong Zhang, Zhitao Li, Jianzong Wang, Yiming Gao, Ning Cheng, Fengying Yu, Jing Xiao (2023). Prompt Guided Copy Mechanism for Conversational Question Answering. In INTERSPEECH2023 (CCF-C).

PDF Cite arXiv ISCA

Yifu Sun, Xulong Zhang, Jianzong Wang, Ning Cheng, Kaiyu Hu, Jing Xiao (2023). Investigation of Music Emotion Recognition Based on Segmented Semi-Supervised Learning. In INTERSPEECH2023 (CCF-C).

PDF Cite ISCA

Haobin Tang, Xulong Zhang, Jianzong Wang, Ning Cheng, Jing Xiao (2023). EmoMix: Emotion Mixing via Diffusion Models for Emotional Speech Synthesis. In INTERSPEECH2023 (CCF-C).

PDF Cite arXiv ISCA DEMO

Jiaxin Fan, Yong Zhang, Hanzhang Li, Jianzong Wang, Zhitao Li, Sheng Ouyang, Ning Cheng, Jing Xiao (2023). Boosting Chinese ASR Error Correction with Dynamic Error Scaling Mechanism. In INTERSPEECH2023 (CCF-C).

PDF Cite arXiv ISCA

Jianzong Wang, Xulong Zhang, Haobin Tang, Aolan Sun, Ning Cheng, Jing Xiao (2023). SAR: Self-Supervised Anti-Distortion Representation for End-To-End Speech Model. In IJCNN2023 (CCF-C).

Cite arXiv IEEE

Huaizhen Tang, Xulong Zhang, Jianzong Wang, Ning Cheng, Jing Xiao (2023). VQ-CL: Learning Disentangled Speech Representations with Contrastive Learning and Vector Quantization. In ICASSP2023 (CCF-B).

PDF Cite IEEE

Haobin Tang, Xulong Zhang, Jianzong Wang, Ning Cheng, Jing Xiao (2023). QI-TTS: Questioning Intonation Control for Emotional Speech Synthesis. In ICASSP2023 (CCF-B).

Cite arXiv IEEE

Huaizhen Tang, Xulong Zhang, Jianzong Wang, Ning Cheng, Jing Xiao (2023). Learning Speech Representations with Flexible Hidden Feature Dimensions. In ICASSP2023 (CCF-B).

PDF Cite IEEE

Ganghui Ru, Xulong Zhang, Jianzong Wang, Ning Cheng, Jing Xiao (2023). Improving Music Genre Classification from Multi-modal Properties of Music and Genre Correlations Perspective. In ICASSP2023 (CCF-B).

Cite Poster arXiv IEEE

Kexin Zhu, Xulong Zhang, Jianzong Wang, Ning Cheng, Jing Xiao (2023). Improving EEG-based Emotion Recognition by Fusing Time-frequency And Spatial Representations. In ICASSP2023 (CCF-B).

Cite Poster arXiv IEEE

Xulong Zhang, Haobin Tang, Jianzong Wang, Ning Cheng, Jian Luo, Jing Xiao (2023). Dynamic Alignment Mask CTC: Improved Mask-CTC with Aligned Cross Entropy. In ICASSP2023 (CCF-B).

Cite arXiv IEEE

Zuheng Kang, Yayun He, Jianzong Wang, Junqing Peng, Xiaoyang Qu, Jing Xiao (2023). Feature-Rich Audio Model Inversion for Data-Free Knowledge Distillation Towards General Sound Classification. In ICASSP2023 (CCF-B).

Cite arXiv IEEE

Wei Duan, Yi Yu, Xulong Zhang, Suhua Tang, Wei Li, Keizo Oyama (2023). Melody Generation from Lyrics with Local Interpretability. In [J], ACM Transactions on Multimedia Computing, Communications, and Applications (TOMM2023) (CCF-B) (IF=4.094).

Cite ACM

Rongfeng Pan, Jianzong Wang, Lingwei Kong, Zhangcheng Huang, Jing Xiao (2023). Personalized Federated Learning via Gradient Modulation for Heterogeneous Text Summarization. In IJCNN2023 (CCF-C).

Cite arXiv IEEE

Ziqi Yu, Botao Zhao, Yipin Zhang, Shengjie Zhang, Xiang Chen, Haibo Yang, Tingying Peng, Xiao-Yong Zhang (2023). Cross-grained Contrastive Representation for Unsupervised Lesion Segmentation in Medical Images. In ICCV2023 (CCF-A).

Cite

Zuheng Kang, Jianzong Wang, Junqing Peng, Jing Xiao (2022). SVLDL: Improved Speaker Age Estimation Using Selective Variance Label Distribution Learning. In SLT2022.

Cite arXiv IEEE

Xulong Zhang, Jianzong Wang, Ning Cheng, Jing Xiao (2022). Semi-Supervised Learning Based on Reference Model for Low-resource TTS. In MSN2022 (CCF-C).

Cite arXiv IEEE

Xulong Zhang, Jianzong Wang, Ning Cheng, Jing Xiao (2022). MetaSpeech: Speech Effects Switch Along with Environment for Metaverse. In MSN2022 (CCF-C).

Cite arXiv IEEE

Xulong Zhang, Jianzong Wang, Ning Cheng, Mengyuan Zhao, Zhiyong Zhang, Jing Xiao (2022). Linguistic-Enhanced Transformer with CTC Embedding for Speech Recognition. In MSN2022 (CCF-C).

Cite arXiv IEEE

Xulong Zhang, Jianzong Wang, Ning Cheng, Kexin Zhu, Jing Xiao (2022). Improving Speech Representation Learning via Speech-level and Phoneme-level Masking Approach. In MSN2022 (CCF-C).

Cite arXiv IEEE

Xulong Zhang, Jianzong Wang, Ning Cheng, Jing Xiao (2022). Improving Imbalanced Text Classification with Dynamic Curriculum Learning. In MSN2022 (CCF-C).

Cite arXiv IEEE

Xulong Zhang, Jianzong Wang, Ning Cheng, Jing Xiao (2022). Adapitch: Adaption Multi-Speaker Text-to-Speech Conditioned on Pitch Disentangling with Untranscribed Data. In MSN2022 (CCF-C).

Cite arXiv IEEE

Xulong Zhang, Jianzong Wang, Ning Cheng, Edward Xiao, Jing Xiao (2022). Shallow Diffusion Motion Model for Talking Face Generation from Speech. In APWeb-WAIM2022 (CCF-C).

PDF Cite Springer

Shijing Si, Jianzong Wang, Xulong Zhang, Xiaoyang Qu, Ning Cheng, Jing Xiao (2022). Boosting Star-GANs for Voice Conversion with Contrastive Discriminator. In ICONIP2022 (CCF-C).

Cite arXiv Springer

Aolan Sun, Xulong Zhang, Tiandong Ling, Jianzong Wang, Ning Cheng, Jing Xiao (2022). Pre-Avatar: An Automatic Presentation Generation Framework Leveraging Talking Avatar. In ICTAI2022 (CCF-C).

Cite arXiv IEEE

Tong Ye, Shijing Si, Jianzong Wang, Ning Cheng, Jing Xiao (2022). Uncertainty Calibration for Deep Audio Classifiers. In INTERSPEECH2022 (CCF-C).

PDF Cite ISCA

Jian Luo, Jianzong Wang, Ning Cheng, Edward Xiao, Xulong Zhang, Jing Xiao (2022). Tiny-Sepformer: A Tiny Time-Domain Transformer Network For Speech Separation. In INTERSPEECH2022 (CCF-C).

PDF Cite arXiv ISCA

Zuheng Kang, Junqing Peng, Jianzong Wang, Jing Xiao (2022). SpeechEQ: Speech Emotion Recognition based on Multi-scale Unified Datasets and Multitask Learning. In INTERSPEECH2022 (CCF-C).

PDF Cite arXiv ISCA

SiCheng Yang, Methawee Tantrawenith, Haolin Zhuang, Zhiyong Wu, Aolan Sun, Jianzong Wang, Ning Cheng, Huaizhen Tang, Xintao Zhao, Jie Wang, Helen Meng (2022). Speech Representation Disentanglement with Adversarial Mutual Information Learning for One-shot Voice Conversion. In INTERSPEECH2022 (CCF-C).

PDF Cite arXiv ISCA DEMO

Yifu Sun, Xulong Zhang, Xi Chen, Yi Yu, Wei Li (2022). Investigation of Singing Voice Separation for Singing Voice Detection in Polyphonic Music. In CSMT2022 (Best Paper Award).

Cite arXiv Springer

Xulong Zhang, Jianzong Wang, Ning Cheng, Jing Xiao (2022). TDASS: Target Domain Adaptation Speech Synthesis Framework for Multi-speaker Low-Resource TTS. In IJCNN2022 (CCF-C).

Cite arXiv IEEE

Xulong Zhang, Jianzong Wang, Ning Cheng, Jing Xiao (2022). SUSing: SU-net for Singing Voice Synthesis. In IJCNN2022 (CCF-C).

Cite arXiv IEEE

Jian Luo, Jianzong Wang, Ning Cheng, Haobin Tang, Jing Xiao (2022). Speech Augmentation Based Unsupervised Learning for Keyword Spotting. In IJCNN2022 (CCF-C).

Cite arXiv IEEE

Xulong Zhang, Jianzong Wang, Ning Cheng, Jing Xiao (2022). Singer Identification for Metaverse with Timbral and Middle-Level Perceptual Features. In IJCNN2022 (CCF-C).

Cite arXiv IEEE

Xulong Zhang, Jianzong Wang, Ning Cheng, Jing Xiao (2022). MetaSID: Singer Identification with Domain Adaptation for Metaverse. In IJCNN2022 (CCF-C).

Cite arXiv IEEE

Xulong Zhang, Jianzong Wang, Ning Cheng, Jing Xiao (2022). MDCNN-SID: Multi-scale Dilated Convolution Network for Singer Identification. In IJCNN2022 (CCF-C).

Cite arXiv IEEE

Jian Luo, Jianzong Wang, Ning Cheng, Zhenpeng Zheng, Jing Xiao (2022). Adaptive Activation Network for Low Resource Multilingual Speech Recognition. In IJCNN2022 (CCF-C).

Cite arXiv IEEE

Yong Zhang, Zhitao Li, Jianzong Wang, Ning Cheng, Jing Xiao (2022). Self-Attention for Incomplete Utterance Rewriting. In ICASSP2022 (CCF-B).

Cite arXiv IEEE

Botao Zhao, Xulong Zhang, Jianzong Wang, Ning Cheng, Jing Xiao (2022). nnSpeech: Speaker-Guided Conditional Variational Autoencoder for Zero-Shot Multi-speaker text-to-speech. In ICASSP2022 (CCF-B).

Cite arXiv IEEE

Qiqi Wang, Xulong Zhang, Jianzong Wang, Ning Cheng, Jing Xiao (2022). DRVC: A Framework of Any-to-Any Voice Conversion with Self-Supervised Learning. In ICASSP2022 (CCF-B).

Cite Slides arXiv IEEE

Huaizhen Tang, Xulong Zhang, Jianzong Wang, Ning Cheng, Jing Xiao (2022). AVQVC: One-Shot Voice Conversion By Vector Quantization With Applying Contrastive Learning. In ICASSP2022 (CCF-B).

Cite arXiv IEEE

Chenyu Huang, Jianzong Wang, Huangxun Chen, Shijing Si, Zhangcheng Huang, Jing Xiao (2022). zkMLaaS: a Verifiable Scheme for Machine Learning as a Service. In GLOBECOM2022 (CCF-C).

Cite IEEE

Tong Ye, Shijing Si, Jianzong Wang, Rui Wang, Ning Cheng, Jing Xiao (2022). VU-BERT: A Unified Framework for Visual Dialog. In ICASSP2022 (CCF-B).

Cite arXiv IEEE

Shijing Si, Jianzong Wang, Junqing Peng, Jing Xiao (2022). Towards Speaker Age Estimation With Label Distribution Learning. In ICASSP2022 (CCF-B).

Cite arXiv IEEE

Chuanyao Zhang, Jianzong Wang, Zhangcheng Huang, Lingwei Kong, Xiaoyang Qu, Ning Cheng, Jing Xiao (2022). Supervised Contrastive Meta-learning for Few-Shot Classification. In HPCC2022 (CCF-C).

Cite

Wen Wang, Jianzong Wang, Shijing Si, Zhangcheng Huang, Jing Xiao (2022). RL-MD: A Novel Reinforcement Learning Approach for DNA Motif Discovery. In DSAA2022 (CCF-C).

Cite arXiv IEEE

Chendong Zhao, Jianzong Wang, Xiaoyang Qu, Haoqian Wang, Jing Xiao (2022). r-G2P: Evaluating and Enhancing Robustness of Grapheme to Phoneme Conversion by Controlled Noise Introducing and Contextual Information Incorporation. In ICASSP2022 (CCF-B).

Cite

Zhenhou Hong, Jianzong Wang, Xiaoyang Qu, Chendong Zhao, Wei Tao, Jing Xiao (2022). QSpeech: Low-Qubit Quantum Speech Application Toolkit. In IJCNN2022 (CCF-C).

Cite arXiv IEEE

Jianhan Wu, Shijing Si, Jianzong Wang, Xiaoyang Qu, Xiao Jing (2022). Pose Guided Human Image Synthesis with Partially Decoupled GAN. In ACML2022 (CCF-C).

Cite

Yanxin Song, Jianzong Wang, Tianbo Wu, Zhangcheng Huang, Jing Xiao (2022). Micro-Expression Recognition Based on Attribute Information Embedding and Cross-modal Contrastive Learning. In IJCNN2022 (CCF-C).

Cite

Zihao Cao, Jianzong Wang, Shijing Si, Zhangcheng Huang, Jing Xiao (2022). Machine Unlearning Method Based On Projection Residual. In DSAA2022 (CCF-C).

Cite

Jianzong Wang, Shijing Si, Zhitao Zhu, Xiaoyang Qu, Zhenhou Hong, Jing Xiao (2022). Leveraging Causal Inference for Explainable Automatic Program Repair. In IJCNN2022 (CCF-C).

Cite

Chendong Zhao, Jianzong Wang, Xiaoyang Qu, Haoqian Wang, Jing Xiao (2022). Learning Invariant Representation and Risk Minimized for Unsupervised Accent Domain Adaptation. In SLT2022.

Cite

Jianhan Wu, Shijing Si, Jianzong Wang, Jing Xiao (2022). Improving Human Image Synthesis with Residual Fast Fourier Transformation and Wasserstein Distance. In IJCNN2022 (CCF-C).

Cite

Zhengyang Li, Shijing Si, Jianzong Wang, Jing Xiao (2022). Federated Split BERT for Heterogeneous Text Classification. In IJCNN2022 (CCF-C).

Cite arXiv IEEE

Shijing Si, Jianzong Wang, Ruiyi Zhang, Qinliang Su, Jing Xiao (2022). Federated Non-negative Matrix Factorization for Short Texts Topic Modeling with Mutual Information. In IJCNN2022 (CCF-C).

Cite arXiv IEEE

Liyao Xiong, Zoe Lin Jiang, Yi Huang, Jianzong Wang, Jing Xiao, Weizhe Zhang, Xuan Wang (2022). Efficient Private Set Intersection Based on Functional Encryption. In ICDIS2022.

Cite

Nan Zhang, Jianzong Wang, Zhenhou Hong, Chendong Zhao, Xiaoyang Qu, Jing Xiao (2022). DT-SV: A Transformer-based Time-domain Approach for Speaker Verification. In IJCNN2022 (CCF-C).

Cite arXiv IEEE

Haibo Yang, Shengjie Zhang, Xiaoyang Han, Botao Zhao, Yan Ren, Yaru Sheng, Xiao-Yong Zhang (2022). Denoising of 3D MR Images Using a Voxel-Wise Hybrid Residual MLP-CNN Model to Improve Small Lesion Diagnostic Confidence. In MICCAI2022 (CCF-B).

PDF Cite

Zhitao Zhu, Shijing Si, Jianzong Wang, Yaodong Yang, Jing Xiao (2022). Debias the Black-Box: A Fair Ranking Framework via Knowledge Distillation. In WISE2022 (CCF-C).

Cite

Zhitao Zhu, Shijing Si, Jianzong Wang, Jing Xiao (2022). Cali3F: Calibrated Fast Fair Federated Recommendation System. In IJCNN2022 (CCF-C).

Cite arXiv IEEE

Denghao Li, Yuqiao Zeng, Jianzong Wang, Lingwei Kong, Zhangcheng Huang, Ning Cheng, Xiaoyang Qu, Jing Xiao (2022). Blur the Linguistic Boundary: Interpreting Chinese Buddhist Sutra in English via Neural Machine Translation. In ICTAI2022 (CCF-C).

Cite

Jianhan Wu, Shijing Si, Jianzong Wang, Jing Xiao (2022). Augmentation-induced Consistency Regularization for Classification. In IJCNN2022 (CCF-C).

Cite

Chendong Zhao, Jianzong Wang, Wenqi Wei, Xiaoyang Qu, Haoqian Wang, Jing Xiao (2022). Adaptive Sparse and Monotonic Attention for Transformer-based Automatic Speech Recognition. In DSAA2022 (CCF-C).

Cite arXiv IEEE

Chendong Zhao, Jianzong Wang, Leilai Li, Xiaoyang Qu, Jing Xiao (2022). Adaptive Few-Shot Learning Algorithm for Rare Sound Event Detection. In IJCNN2022 (CCF-C).

Cite

Yeqing Qiu, Chenyu Huang, Jianzong Wang, Zhangcheng Huang, Jing Xiao (2022). A Privacy-Preserving Subgraph-Level Federated Graph Neural Network via Differential Privacy. In KSEM2022 (CCF-C).

Cite arXiv Springer

Denghao Li, Jianzong Wang, Lingwei Kong, Shijing Si, Zhangcheng Huang, Chenyu Huang, Jing Xiao (2022). A Nearest Neighbor Under-sampling Strategy for Vertical Federated Learning in Financial Domain. In IH&MMSec2022 (CCF-C).

Cite ACM

Yaqi Sun, Shijing Si, Jianzong Wang, Yuhan Dong, Zhitao Zhu, Jing Xiao (2022). A Fair Federated Learning Framework With Reinforcement Learning. In IJCNN2022 (CCF-C).

Cite arXiv IEEE

Huaizhen Tang, Xulong Zhang, Jianzong Wang, Ning Cheng, Zhen Zeng, Edward Xiao, Jing Xiao (2021). TGAVC: Improving Autoencoder Voice Conversion with Text-Guided and Adversarial Training. In ASRU2021.

Cite arXiv IEEE

Aolan Sun, Jianzong Wang, Ning Cheng, Methawee Tantrawenith, Zhiyong Wu, Helen Meng, Edward Xiao, Jing Xiao (2021). Reconstructing Dual Learning for Neural Voice Conversion Using Relatively Few Samples. In ASRU2021.

Cite IEEE

Xulong Zhang, Jianzong Wang, Ning Cheng, Edward Xiao, Jing Xiao (2021). CycleGEAN: Cycle Generative Enhanced Adversarial Network for Voice Conversion. In ASRU2021.

PDF Cite IEEE

Shijing Si, Jianzong Wang, Huiming Sun, Jianhan Wu, Chuanyao Zhang, Xiaoyang Qu, Ning Cheng, Lei Chen, Jing Xiao (2021). Variational Information Bottleneck for Effective Low-Resource Audio Classification. In INTERSPEECH2021 (CCF-C).

PDF Cite arXiv ISCA

Shijing Si, Jianzong Wang, Xiaoyang Qu, Ning Cheng, Wenqi Wei, Xinghua Zhu, Jing Xiao (2021). Speech2Video: Cross-Modal Distillation for Speech to Video Generation. In INTERSPEECH2021 (CCF-C).

PDF Cite arXiv ISCA

Jian Luo, Jianzong Wang, Ning Cheng, Jing Xiao (2021). Dropout Regularization for Self-Supervised Learning of Transformer Encoder Speech Representation. In INTERSPEECH2021 (CCF-C).

PDF Cite arXiv ISCA

Cheng Yi, Jianzong Wang, Ning Cheng, Shiyu Zhou, Bo Xu (2021). Transfer Ability of Monolingual Wav2vec2.0 for Low-resource Speech Recognition. In IJCNN2021 (CCF-C).

Cite IEEE

Jian Luo, Jianzong Wang, Ning Cheng, Jing Xiao (2021). Loss Prediction: End-to-End Active Learning Approach For Speech Recognition. In IJCNN2021 (CCF-C).

Cite arXiv IEEE

Nan Zhang, Jianzong Wang, Wenqi Wei, Xiaoyang Qu, Ning Cheng, Jing Xiao (2021). CACnet: Cube Attentional CNN for Automatic Speech Recognition. In IJCNN2021 (CCF-C).

Cite IEEE

Cheng Yi, Jianzong Wang, Ning Cheng, Shiyu Zhou, Bo Xu (2021). A Language Model Based Pseudo-Sample Deliberation for Semi-supervised Speech Recognition. In IJCNN2021 (CCF-C).

Cite IEEE

Jian Luo, Jianzong Wang, Ning Cheng, Edward Xiao, Jing Xiao, Georg Kucsko, Patrick O’Neill, Jagadeesh Balam, Slyne Deng, Adriana Flores, Boris Ginsburg, Jocelyn Huang, Oleksii Kuchaiev, Vitaly Lavrukhin, Jason Li (2021). Cross-Language Transfer Learning and Domain Adaptation for End-to-End Automatic Speech Recognition. In ICME2021 (CCF-B).

Cite IEEE

Jian Luo, Jianzong Wang, Ning Cheng, Jing Xiao (2021). Unidirectional Memory-Self-Attention Transducer for Online Speech Recognition. In ICASSP2021 (CCF-B).

Cite arXiv IEEE

Xulong Zhang, Jiale Qian, Yi Yu, Yifu Sun, Wei Li (2021). Singer Identification Using Deep Timbre Feature Learning with KNN-NET. In ICASSP2021 (CCF-B).

Cite Code Dataset arXiv IEEE

Zhen Zeng, Jianzong Wang, Ning Cheng, Jing Xiao (2021). LVCNet: Efficient Condition-Dependent Modeling Network for Waveform Generation. In ICASSP2021 (CCF-B).

Cite arXiv IEEE

Yongwei Gao, Xulong Zhang, Wei Li (2021). Vocal Melody Extraction via HRNet-Based Singing Voice Separation and Encoder-Decoder-Based F0 Estimation. In [J],Electronics2021 (IF=2.69).

Cite Electronics

Jian Luo, Jianzong Wang, Ning Cheng, Guilin Jiang, Jing Xiao (2021). Multi-Quartznet: Multi-Resolution Convolution for Speech Recognition with Multi-Layer Feature Fusion. In SLT2021.

Cite arXiv IEEE

Zhen Zeng, Jianzong Wang, Ning Cheng, Jing Xiao (2021). MelGlow: Efficient Waveform Generative Network Based On Location-Variable Convolution. In SLT2021.

Cite arXiv IEEE

Aolan Sun, Jianzong Wang, Ning Cheng, Huayi Peng, Zhen Zeng, Lingwei Kong, Jing Xiao (2021). GraphPB: Graphical Representations of Prosody Boundary in Speech Synthesis. In SLT2021.

Cite arXiv IEEE

Jian Luo, Jianzong Wang, Ning Cheng, Guilin Jiang, Jing Xiao (2021). End-To-End Silent Speech Recognition with Acoustic Sensing. In SLT2021.

Cite arXiv IEEE

Zhenhou Hong, Jianzong Wang, Wenqi Wei, Jie Liu, Xiaoyang Qu, Bo Chen, Zihang Wei, Jing Xiao (2021). When Hearing the Voice, Who Will Come to Your Mind. In IJCNN2021 (CCF-C).

Cite IEEE

Fengying Yu, Dewei Tao, Jianzong Wang, Yanfei Hui, Ning Cheng, Jing Xiao (2021). Semantic Extraction for Sentence Representation via Reinforcement Learning. In IJCNN2021 (CCF-C).

Cite IEEE

Zhitao Li, Jianzong Wang, Ning Cheng, Jing Xiao (2021). Semantic Embedding Graph Convolutional Networks for Multi-label Video Segment Classification. In PAAP2021.

Cite

Fengying Yu, Jianzong Wang, Dewei Tao, Ning Cheng, Jing Xiao (2021). Self-supervised Learning for Semantic Sentence Matching with Dense Transformer Inference Network. In APWeb-WAIM2021 (CCF-C).

Cite Springer

Zhenhou Hong, Jianzong Wang, Xiaoyang Qu, Xinghua Zhu, Jie Liu, Jing Xiao (2021). Quantum Convolutional Neural Network on Protein Distance Prediction. In IJCNN2021 (CCF-C).

Cite

Zhenhou Hong, Jianzong Wang, Xiaoyang Qu, Chendong Zhao, Jie Liu, Jing Xiao (2021). Neural Architecture Search as Self-assessor in Semi-supervised Learning. In BigData2021 (CCF-C).

Cite

Jianzong Wang, Zhangcheng Huang, Lingwei Kong, Denghao Li, Jing Xiao (2021). Modeling Without Sharing Privacy: Federated Neural Machine Translation. In WISE2021 (CCF-C).

PDF Cite Springer

Yanfei Hui, Jianzong Wang, Ning Cheng, Fengying Yu, Tianbo Wu, Jing Xiao (2021). Joint Intent Detection and Slot Filling Based on Continual Learning Model. In ICASSP2021 (CCF-B).

Cite

Junyi Peng, Xiaoyang Qu, Jianzong Wang, Rongzhi Gu, Jing Xiao, Lukás Burget, Jan Cernocký (2021). ICSpk: Interpretable Complex Speaker Embedding Extractor from Raw Waveform. In INTERSPEECH2021 (CCF-C).

PDF Cite ISCA

Pengyu Wang, Jing Wang, Chao Li, Jianzong Wang, Haojin Zhu, Minyi Guo (2021). Grus: Toward Unified-memory-efficient High-performance Graph Processing on GPU. In TACO2021 (CCF-B).

Cite

Zhenhou Hong, Jianzong Wang, Xiaoyang Qu, Jie Liu, Chendong Zhao, Jing Xiao (2021). Federated Learning with Dynamic Transformer for Text to Speech. In INTERSPEECH2021 (CCF-C).

PDF Cite arXiv ISCA

Xiaoyang Qu, Jianzong Wang, Jie Liu, Jing Xiao (2021). Enhancing Neural Architecture Search by Upgrading Weak Components. In IJCNN2021 (CCF-C).

Cite

Xiaoyang Qu, Jianzong Wang, Jing Xiao (2021). Enhancing Data-Free Adversarial Distillation with Activation Regularization and Virtual Interpolation. In ICASSP2021 (CCF-B).

Cite

Jie Zhao, Xinghua Zhu, Jianzong Wang, Jing Xiao (2021). Efficient Client Contribution Evaluation for Horizontal Federated Learning. In ICASSP2021 (CCF-B).

Cite arXiv IEEE

Junyi Peng, Xiaoyang Qu, Rongzhi Gu, Jianzong Wang, Jing Xiao, Lukás Burget, Jan Cernocký (2021). Effective Phase Encoding for End-To-End Speaker Verification. In INTERSPEECH2021 (CCF-C) (Best Student Paper Award).

Cite ISCA Best Student Paper Award

Anshun Xue, Xinghua Zhu, Jianzong Wang, Jing Xiao (2021). Diversified Point Cloud Classification Using Personalized Federated Learning. In IJCNN2021 (CCF-C).

Cite IEEE

Yanxi Tang, Jianzong Wang, Xiaoyang Qu, Jing Xiao (2021). Contrastive Learning for improving End-to-end Speaker Verification. In IJCNN2021 (CCF-C).

Cite IEEE

Leilai Li, Jianzong Wang, Xiaoyang Qu, Jing Xiao (2021). Communication-Memory-Efficient Decentralized Learning For Audio Representation. In IJCNN2021 (CCF-C).

Cite IEEE

Jianzong Wang, Shijing Si, Zhenhou Hong, Xiaoyang Qu, Xinghua Zhu, Jing Xiao (2021). Case Study of Few-Shot Learning in Text Recognition Models. In WISE2021 (CCF-C).

Cite

Jie Liu, Jianzong Wang, Xiaoyang Qu, Bo Chen, Zihang Wei, Jing Xiao (2021). Automatic Joint Optimization of Algorithm-Level Compression and Compiler-Based Acceleration with Reinforcement Learning for DNN in Edge Devices. In IJCNN2021 (CCF-C).

Cite

Botao Zhao, Yan Ren, Ziqi Yu, Jinhua Yu, Tingying Peng, Xiao-Yong Zhang (2021). AUCseg: An Automatically Unsupervised Clustering Toolbox for 3D-Segmentation of High-Grade Gliomas in Multi-Parametric MR Images. In Front. Oncol. (IF=5.74).

Cite

Guanyu Lin, Xinghua Zhu, Jianzong Wang, Jing Xiao (2021). Anomaly Removal for Vehicle Energy Consumption in Federated Learning. In IJCNN2021 (CCF-C).

Cite IEEE

Yong Liu, Xinghua Zhu, Jianzong Wang, Jing Xiao (2021). A Quantitative Metric for Privacy Leakage in Federated Learning. In ICASSP2021 (CCF-B).

Cite arXiv IEEE

Chao Sun, Jianzong Wang, Fengying Yu, Ning Cheng, Jing Xiao (2021). A Novel Capsule Aggregation Framework for Natural Language Inference. In APWeb-WAIM2021 (CCF-C).

Cite

Lingwei Kong, Jianzong Wang, Zhangcheng Huang, Jing Xiao (2021). A Competition of Shape and Texture Bias by Multi-view Image Representation. In PRCV2021 (CCF-C).

Cite

Zhen Zeng, Jianzong Wang, Ning Cheng, Jing Xiao (2020). Prosody Learning Mechanism for Speech Synthesis System Without Text Length Limit. In INTERSPEECH2020 (CCF-C).

PDF Cite arXiv ISCA

Zhenpeng Zheng, Jianzong Wang, Ning Cheng, Jian Luo, Jing Xiao (2020). MLNET: An Adaptive Multiple Receptive-Field Attention Neural Network for Voice Activity Detection. In INTERSPEECH2020 (CCF-C).

PDF Cite arXiv ISCA

Xueli Jia, Jianzong Wang, Zhiyong Zhang, Ning Cheng, Jing Xiao (2020). Large-Scale Transfer Learning for Low-Resource Spoken Language Understanding. In INTERSPEECH2020 (CCF-C).

PDF Cite arXiv ISCA

Wenqi Wei, Jianzong Wang, Jiteng Ma, Ning Cheng, Jing Xiao (2020). A Real-Time Robot-Based Auxiliary System for Risk Evaluation of COVID-19 Infection. In INTERSPEECH2020 (CCF-C).

PDF Cite ISCA

Xulong Zhang, Yi Yu, Yongwei Gao, Xi Chen, Wei Li (2020). Research on Singing Voice Detection Based on a Long-Term Recurrent Convolutional Network with Vocal Separation and Temporal Smoothing. In [J],Electronics2020 (IF=2.69).

Cite Electronics

Aolan Sun, Jianzong Wang, Ning Cheng, Huayi Peng, Zhen Zeng, Jing Xiao (2020). GraphTTS: Graph-to-Sequence Modelling in Neural Text-to-Speech. In ICASSP2020 (CCF-B).

Cite arXiv IEEE

Zhen Zeng, Jianzong Wang, Ning Cheng, Tian Xia, Jing Xiao (2020). Aligntts: Efficient Feed-Forward Text-to-Speech System Without Explicit Alignment. In ICASSP2020 (CCF-B).

Cite arXiv IEEE

Xiaoyang Qu, Jianzong Wang, Jing Xiao (2020). Quantization and Knowledge Distillation for Efficient Federated Learning on Edge Devices. In HPCC2020 (CCF-C).

Cite IEEE

Xiaoyang Qu, Jianzong Wang, Jing Xiao (2020). ParallelNAS: A Parallel and Distributed System for Neural Architecture Search. In HPCC2020 (CCF-C).

Cite

Lingwei Kong, Hengtao Tao, Jianzong Wang, Zhangcheng Huang, Jing Xiao (2020). Network Coding for Federated Learning Systems. In ICONIP2020 (CCF-C).

Cite Springer

Nan Zhang, Jianzong Wang, Jian Yang, Xiaoyang Qu, Jing Xiao (2020). Multi-objective Cuckoo Algorithm for Mobile Devices Network Architecture Search. In ICANN2020 (CCF-C).

Cite

Nan Zhang, Jianzong Wang, Xiaoyang Qu, Jing Xiao (2020). Image Compressed Sensing Using Neural Architecture Search. In BigData2020.

Cite

Anxun He, Jianzong Wang, Zhangcheng Huang, Jing Xiao (2020). FedSmart: An Auto Updating Federated Learning Optimization Mechanism. In APWeb-WAIM2020 (CCF-C).

Cite arXiv Springer

Xiaoyang Qu, Jianzong Wang, Jing Xiao (2020). Evolutionary Algorithm Enhanced Neural Architecture Search for Text-Independent Speaker Verification. In INTERSPEECH2020 (CCF-C).

PDF Cite arXiv ISCA

Wenqi Wei, Jianzong Wang, Ning Cheng, Yuanxu Chen, Bao Zhou, Jing Xiao (2020). Epidemic Guard: A COVID-19 Detection System for Elderly People. In APWeb-WAIM2020 (CCF-C).

Cite Springer

Xinghua Zhu, Jianzong Wang, Zhenhou Hong, Jing Xiao (2020). Empirical Studies of Institutional Federated Learning For Natural Language Processing. In EMNLP2020 (CCF-B).

PDF Cite ACL

Yanxi Tang, Jianzong Wang, Xiaoyang Qu, Nan Zhang, Jing Xiao (2020). D-GHNAS for Joint Intent Classification and Slot Filling. In APWeb-WAIM2020 (CCF-C).

Cite

Zelong Yan, Jianzong Wang, Ning Cheng, Tianbo Wu, Jing Xiao (2020). Chinese Punctuation Prediction with Adaptive Attention and Dependency Tree. In CCKS2020.

Cite

Linjie Chen, Jianzong Wang, Zhangcheng Huang, Jing Xiao (2020). An Approach for Neural Machine Translation with Graph Attention Network. In ICCPR2020.

Cite

Chen Feng, Jianzong Wang, Tongxu Li, Junqing Peng, Jing Xiao (2020). A Robust Speaker Clustering Method Based on Discrete Tied Variational Autoencoder. In ICASSP2020 (CCF-B).

Cite IEEE

Zeyuan Li, Jianzong Wang, Xiaoyang Qu, Jing Xiao (2020). 3D Point Cloud Segmentation for Complex Structure Based on PointSIFT. In PRCV2020 (CCF-C).

Cite

Lei Wang, Hongning Zhu, Xulong Zhang, Shengchen Li, Wei Li (2019). Transfer Learning for Music Classification and Regression Tasks Using Artist Tags. In CSMT2019.

Cite Springer

Xulong Zhang, Shengchen Li, Zijin Li, Shizhe Chen, Yongwei Gao, Wei Li (2019). Singing Voice Detection Using Multi-Feature Deep Fusion with CNN. In CSMT2019.

PDF Cite Springer

Yuliang Ma, Ye Yuan, Feida Zhu, Guoren Wang, Jing Xiao, Jianzong Wang (2019). Who Should Be Invited to My Party: A Size-Constrained k-Core Problem in Social Networks. In JCST2019.

Cite

Anxun He, Jianzong Wang, Zhangcheng Huang, Linjie Chen, Lingwei Kong, Man Zhang, Mei Han, Ruei-Sung Lin, Jing Xiao (2019). Two Proposed Vehicle Insurance Pricing Frameworks Based on Federated Machine Learning. In SDBD2019.

Cite ACM

Jianzong Wang, Zhangcheng Huang, Lingwei Kong, Jing Xiao, Pengyu Wang, Lu Zhang, Chao Li (2019). Performance of Training Sparse Deep Neural Networks on GPUs. In HPEC2019.

Cite

Xinghua Zhu, Jianzong Wang, Zhenhou Hong, Junxiong Guo, Jing Xiao (2019). On Probability Calibration of Recurrent Text Recognition Network. In ICONIP2019 (CCF-C).

Cite

Xinghua Zhu, Jianzong Wang, Zhenhou Hong, Tian Xia, Jing Xiao (2019). Federated Learning of Unsegmented Chinese Text Recognition Model. In ICTAI2019 (CCF-C).

Cite IEEE

Sein Minn, Michel C. Desmarais, Feida Zhu, Jing Xiao, Jianzong Wang (2019). Dynamic Student Classiffication on Memory Networks for Knowledge Tracing. In PAKDD2019.

Cite

Aozhi Liu, Jianzong Wang, Junqing Peng, Yiwen Wang, Yaqi Mei, Xiaojing Liang, Zimin Xia, Jing Xiao (2019). Composer4Everyone: Automatic Music Generation with Audio Motif. In MIPR2019.

Cite IEEE

Lingwei Kong, Jianzong Wang, Zhangcheng Huang, Anxun He, Linjie Chen, Man Zhang, Jing Xiao (2019). A Federated Learning Schema with Additive Homomorphic Encrytion. In FL-IJCAI2019.

Cite FL-IJCAI

Jianzong Wang, Xinhui Liu, Aozhi Liu, Jing Xiao (2019). A Deep Learning-Based Method for Vehicle License Plate Recognition in Natural Scene. In APSIPA Transactions on Signal and Information Processing.

Cite APSIPA Transactions on Signal and Information Processing

Yongwei Gao, Yichun Shen, Xulong Zhang, Shuai Yu, Wei Li (2018). Music Summary Detection with State Space Embedding and Recurrence Plot. In CSMT2018.

Cite Springer

Zhigao Chen, Xulong Zhang, Jin Deng, Juanjuan Li, Yiliang Jiang, Wei Li (2018). A Practical Singing Voice Detection System Based on GRU-RNN. In CSMT2018 (Best Paper Award).

PDF Cite Springer

Xulong Zhang, Yiliang Jiang, Jin Deng, Juanjuan Li, Mi Tian, Wei Li (2018). A Novel Singer Identification Method Using GMM-UBM. In CSMT2018.

Cite Springer

Jianzong Wang, Aozhi Liu, Jing Xiao (2018). Video-Based Pig Recognition with Feature-Integrated Transfer Learning. In CCBR2018.

Cite

Wei Xie, Feida Zhu, Jing Xiao, Jianzong Wang (2018). Social Network Monitoring for Bursty Cascade Detection. In TKDD2018 (CCF-B).

Cite

Lihong Liu, Jin Ma, Jianzong Wang, Jing Xiao (2018). Automated Full Quantification of Left Ventricle with Deep Neural Networks. In STACOM2018.

Cite

Siqi Zheng, Jianzong Wang, Jing Xiao, Wei-Ning Hsu, James R. Glass (2018). A Noise-Robust Self-Adaptive Multitarget Speaker Detection System. In ICPR2018 (CCF-C).

Cite

Jianzong Wang, Hui Guo, Jing Xiao (2017). Prioritized Grid Highway Long Short-Term Memory-Based Universal Background Model for Speaker Verification. In CCBR2017.

Cite Springer

Jianzong Wang, Yiwen Wang, Aozhi Liu, Jing Xiao (2017). Assistance of Speech Recognition in Noisy Environment with Sentence Level Lip-Reading. In CCBR2017.

Cite Springer

Xin Mu, Feida Zhu, Ee-Peng Lim, Jing Xiao, Jianzong Wang, Zhi-Hua Zhou (2016). User Identity Linkage by Latent User Space Modelling. In SIGKDD2016 (CCF-A).

Cite

Jianzong Wang, Lianglun Cheng (2015). qSDS: A QoS-Aware I/O Scheduling Framework towards Software Defined Storage. In ANCS2015 (CCF-C).

Cite

Chao Yin, Jianzong Wang, Haitao Lv, Zongmin Cui, Lianglun Cheng, Qin Zhan, Tongfang Li (2015). OptRS: An Optimized Algorithm Based on CRS Codes in Big Data Storage Systems. In ICA3PP2015 (CCF-C).

Cite

Jianzong Wang, Lianglun Cheng (2015). DistDL: A Distributed Deep Learning Service Schema with GPU Accelerating. In APWeb2015 (CCF-C).

Cite

Qingtao Wu, Xulong Zhang, Mingchuan Zhang, Ying Lou, Ruijuan Zheng, Wangyang Wei (2014). Reputation revision method for selecting cloud services based on prior knowledge and a market mechanism. In TSWJ2014 (IF=0.44).

Cite

Chao Yin, Jianzong Wang, Changsheng Xie, Jiguang Wan, Changlin Long, Wenjuan Bi (2013). Robot: An Efficient Model for Big Data Storage Systems Based on Erasure Coding. In BigData2013 (CCF-C).

Cite

Qingtao Wu, Xulong Zhang, Ruijuan Zheng, Mingchuan Zhang (2013). Probability-Symmetric Storage Allocation for Distributed Storage Systems based on Network Coding. In iJOE2013.

Cite

Qingtao Wu, Xulong Zhang, Ruijuan Zheng, Mingchuan Zhang (2013). An Autonomic Intrusion Detection Model with Multi-Attribute Auction Mechanism. In IJCSI2013.

Cite

Jianzong Wang, Rui Hua, Yifeng Zhu, Jiguang Wan, Changsheng Xie, Yanjun Chen (2012). RO-BURST: A Robust Virtualization Cost Model for Workload Consolidation over Clouds. In CCGrid2012 (CCF-C).

Cite IEEE

Jianzong Wang, Weijiao Gong, Peter J. Varman, Changsheng Xie (2012). Reducing Storage Overhead with Small Write Bottleneck Avoiding in Cloud RAID System. In GRID2012.

Cite IEEE

Jianzong Wang, Yanjun Chen, Daniel Gmach, Changsheng Xie, Jiguang Wan, Rui Hua (2012). pCloud: An Adaptive I/O Resource Allocation Algorithm with Revenue Consideration over Public Clouds. In GPC2012.

Cite Springer

Jiguang Wan, Jibin Wang, Yan Liu, Qing Yang, Jianzong Wang, Changsheng Xie (2012). Enhancing Shared RAID Performance Through Online Profiling. In MSST2012 (CCF-B).

Cite IEEE

Jianzong Wang, Weijiao Gong, Changsheng Xie (2012). A Quantitative Evaluation Model for Choosing Efficient Redundancy Strategies over Clouds. In NAS2012 (Best Paper Award).

Cite IEEE

Jianzong Wang, Hao Huang, Jia Fu, Peng Wang, Jun Liu, Yaodong Yang (2011). Performance analysis of data deduplication technology for storage. In POEM2009.

Cite SPIE

Jianzong Wang, Peter J. Varman, Changsheng Xie (2011). Optimizing Storage Performance in Public Cloud Platforms. In JZUS-C2011 (IF=0.308).

PDF Cite Springer

Jianzong Wang, Yanjun Chen, Rui Hua, Peng Wang, Jia Fu (2011). A Distributed Big Data Storage and Data Mining Framework for Solar-Generated Electricity Quantity Forecasting. In POEM2011.

Cite SPIE

Zhuo Liu, Fei Wu, Xiao Qin, Changsheng Xie, Jian Zhou, Jianzong Wang (2010). TRACER: A Trace Replay Tool to Evaluate Energy-Efficiency of Mass Storage Systems. In CLUSTER2010 (CCF-B).

Cite IEEE

Jianzong Wang, Peter J. Varman, Changsheng Xie (2010). Middleware Enabled Data Sharing on Cloud Storage Services. In MW4SOC2010.

Cite ACM

Jianzong Wang, Jiguang Wan, Zhuo Liu, Peng Wang (2010). Data Mining of Mass Storage Based on Cloud Computing. In GCC2010.

Cite IEEE

Jianzong Wang, Peter J. Varman, Changsheng Xie (2010). Avoiding Performance Fluctuation in Cloud Storage. In HiPC2010 (CCF-C).

Cite IEEE

Peng Wang, Diqing Hu, Changsheng Xie, Jianzong Wang, Xiao Qin (2010). A Fine-Grained Data Reconstruction Algorithm for Solid-State Disks. In NAS2010.

Cite IEEE

Jianzong Wang, Huaixiang Hu, Jiguang Wan, Peng Wang (2008). A Virtual Network Computer's Optical Storage Virtualization Scheme. In ISOS2008.

Cite SPIE