学者信息

洪青阳 (QingYang Hong)

信息学院

合作者

已发表成果:

WOK 论文 83 篇;中文核心 12 篇;其它论文 1 篇;专利发明 6 个;

  • REFLOW-TTS: A RECTIFIED FLOW MODEL FOR HIGH-FIDELITY TEXT-TO-SPEECH

    arXiv,,2023-09-29.
    Guan, Wenhao (1); Su, Qi (2); Zhou, Haodong (2); Miao, Shiyu (2); Xie, Xingjia (2); Li, Lin (2); Ho...
    EI:20230369796   10.48550/arXiv.2309.17056
    收录情况:EI
  • COMMUNITY DETECTION GRAPH CONVOLUTIONAL NETWORK FOR OVERLAP-AWARE SPEAKER DIARIZATION

    arXiv,,2023-06-26.
    Wang, Jie (1); Chen, Zhicong (1); Zhou, Haodong (1); Li, Lin (1); Hong, Qingyang (2)
    EI:20230238375  
    收录情况:EI
  • Interpretable Style Transfer for Text-to-Speech with ControlVAE and Diffusion Bridge

    arXiv,,2023-06-07.
    Guan, Wenhao (1); Li, Tao (1); Li, Yishuang (2); Huang, Hukai (1); Hong, Qingyang (1); Li, Lin (2, ...
    EI:20230242699  
    收录情况:EI
  • Interpretable Style Transfer for Text-to-Speech with ControlVAE and Diffusion Bridge

    Proceedings of the Annual Conference of the International Speech Communication Association, INTERSPEECH,2308-457X,2023.
    Guan, Wenhao; Li, Tao; Li, Yishuang; Huang, Hukai; Hong, Qingyang; Li, Lin
    WOS:001186650304092   EI:20233814759957   10.21437/Interspeech.2023-1151
    收录情况:EI、CPCI-S
  • Cross-Modal Semantic Alignment before Fusion for Two-Pass End-to-End Spoken Language Understanding

    Proceedings of the Annual Conference of the International Speech Communication Association, INTERSPEECH,2308-457X,2023.
    Huang, Lingyan; Li, Tao; Zhou, Haodong; Hong, Qingyang; Li, Lin
    WOS:001186650301056   EI:20233814760197   10.21437/Interspeech.2023-758
    收录情况:EI、CPCI-S
  • Conformer-based Language Embedding with Self-Knowledge Distillation for Spoken Language Identification

    Proceedings of the Annual Conference of the International Speech Communication Association, INTERSPEECH,2308-457X,2023.
    Wang, Feng; Huang, Lingyan; Li, Tao; Hong, Qingyang; Li, Lin
    WOS:001186650305095   EI:20233814760860   10.21437/Interspeech.2023-1557
    收录情况:EI、CPCI-S
  • Meta Learning with Adaptive Loss Weight for Low-Resource Speech Recognition

    ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings,1520-6149,2023.
    Wang, Qiulin (1); Hu, Wenxuan (1); Li, Lin (2); Hong, Qingyang (1)
    EI:20234715105776   10.1109/ICASSP49357.2023.10094936
    收录情况:EI
  • Unsupervised Speaker Verification Using Pre-Trained Model and Label Correction

    ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings,1520-6149,2023.
    Chen, Zhicong (1); Wang, Jie (1); Hu, Wenxuan (2); Li, Lin (1); Hong, Qingyang (2)
    EI:20234715104602   10.1109/ICASSP49357.2023.10094610
    收录情况:EI
  • Community Detection Graph Convolutional Network for Overlap-Aware Speaker Diarization

    ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings,1520-6149,2023.
    Wang, Jie (1); Chen, Zhicong (1); Zhou, Haodong (1); Li, Lin (1); Hong, Qingyang (2)
    EI:20234715105681   10.1109/ICASSP49357.2023.10095143
    收录情况:EI
  • The XMU System for Audio-Visual Diarization and Recognition in MISP Challenge 2022

    ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings,1520-6149,2023.
    Li, Tao (1); Zhou, Haodong (2); Wang, Jie (2); Hong, Qingyang (1); Li, Lin (2)
    EI:20234715105627   10.1109/ICASSP49357.2023.10095693
    收录情况:EI
  • Towards A Unified Conformer Structure: from ASR to ASV Task

    ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings,1520-6149,2023.
    Liao, Dexin (1); Jiang, Tao (2); Wang, Feng (1); Li, Lin (3); Hong, Qingyang (1)
    EI:20234715105218   10.1109/ICASSP49357.2023.10095433
    收录情况:EI
  • CASA-Net: Cross-attention and Self-attention for End-to-End Audio-visual Speaker Diarization

    2023 Asia Pacific Signal and Information Processing Association Annual Summit and Conference, APSIPA ASC 2023,2309-9402,2023.
    Zhou, Haodong; Li, Tao; Wang, Jie; Li, Lin; Hong, Qingyang
    WOS:001108741800017   EI:20235115256915   10.1109/APSIPAASC58517.2023.10317320
    收录情况:EI、CPCI-S
  • A Pipelined Framework with?Serialized Output Training for?Overlapping Speech Recognition

    Communications in Computer and Information Science,1865-0929,2023.
    Li, Tao (1); Huang, Lingyan (1); Wang, Feng (1); Li, Song (2); Hong, Qingyang (1); Li, Lin (2)
    EI:20232414230147   10.1007/978-981-99-2401-1_10
    收录情况:EI