About me

I am a final year Ph. D. student at Centre for Vision, Speech and Signal processing (CVSSP), University of Surrey under the superviosion of Profesor Mark. D. Plumbley. My research interests include sound understanding and audio processing with artificial intelligence. My research topics include audio tagging, sound event detection, source separation of real-world sounds, general audio processing and music signal processing. I obtained my bachelor and master degree at South China University of Technology in 2012 and 2015. My CV can be downloaded and Google scholar can be viewed.

Contact: q.kong [at] surrey.ac.uk

Selected Publications

  • Cross-task learning for audio tagging, sound event detection and spatial localization: DCASE 2019 baseline systems [pdf] [code]
    Qiuqiang Kong, Yin Cao, Turab Iqbal, Yong Xu, Wenwu Wang, Mark D. Plumbley
    arXiv preprint arXiv:1904.03476, 2019
  • Weakly labelled audioset tagging with attention neural networks [pdf] [code]
    Qiuqiang Kong, Changsong Yu, Yong Xu, Turab Iqbal, Wenwu Wang, Mark D. Plumbley
    IEEE/ACM Transactions on Audio, Speech, and Language Processing, 2019
  • Single-Channel Signal Separation and Deconvolution with Generative Adversarial Networks [pdf] [code]
    Kong, Qiuqiang, Yong Xu, Wenwu Wang, Philip J. B. Jackson, Mark D. Plumbley
    IJCAI 2019
  • Polyphonic Sound Event Detection and Localization using a Two-Stage Strategy [pdf] [code] Best reproducible award
    Yin Cao*, Qiuqiang Kong*, Turab Iqbal, Fengyan An, Wenwu Wang, Mark D. Plumbley
    DCASE Workshop 2019
  • Divergence Based Weighting for Information Channels in Deep Convolutional Neural Networks for Bird Audio Detection [pdf]
    Cemre Zor, Muhammad Awais, Josef Kittler, Miroslaw Bober, Sameed Husain, Qiuqiang Kong, Christian Kroos
    ICASSP 2019
  • Acoustic Scene Generation with Conditional Samplernn [pdf] [code]
    Qiuqiang Kong, Yong Xu, Turab Iqbal, Yin Cao, Wenwu Wang, Mark D. Plumbley
    ICASSP 2019
  • Attention-based Atrous Convolutional Neural Networks: Visualisation and Understanding Perspectives of Acoustic Scenes [pdf]
    Zhao Ren, Qiuqiang Kong, Jing Han, Mark D. Plumbley, Björn W. Schuller
    ICASSP 2019
  • Sound Event Detection with Sequentially Labelled Data Based on Connectionist Temporal Classification and Unsupervised Clustering [pdf] [code]
    Yuanbo Hou, Qiuqiang Kong, Shengchen Li, and Mark D. Plumbley
    ICASSP 2019
  • Sound Event Detection and Time–Frequency Segmentation from Weakly Labelled Data [pdf] [code]
    Qiuqiang Kong, Yong Xu, Iwona Sobieraj, Wenwu Wang, Mark D. Plumbley
    IEEE/ACM Transactions on Audio, Speech and Language Processing (TASLP), 2019
  • Capsule routing for sound event detection [pdf] [code]
    Turab Iqbal, Yong Xu, Qiuqiang Kong, Wenwu Wang
    EUSIPCO 2018
  • DCASE 2018 Challenge baseline with convolutional neural networks [pdf] [code]
    Qiuqiang Kong, Turab Iqbal, Yong Xu, Wenwu Wang, Mark D. Plumbley
    DCASE Workshop 2018
  • Multi-level attention model for weakly supervised audio classification [pdf] [code]
    Changsong Yu, Karim Said Barsim, Qiuqiang Kong, Bin Yang
    DCASE Workshop 2018
  • A joint separation-classification model for sound event detection of weakly labelled data [pdf] [code]
    Qiuqiang Kong, Yong Xu, Wenwu Wang, Mark D. Plumbley
    ICASSP 2018
  • Audio set classification with attention model: A probabilistic perspective [pdf] [code]
    Qiuqiang Kong, Yong Xu, Wenwu Wang, and Mark D. Plumbley
    ICASSP 2018
  • Large-scale weakly supervised audio classification using gated convolutional neural network [pdf] [code]
    Xu, Yong*, Qiuqiang Kong*, Wenwu Wang, and Mark D. Plumbley
    ICASSP 2018
  • Convolutional gated recurrent neural network incorporating spatial features for audio tagging [pdf]
    Yong Xu, Qiuqiang Kong, Qiang Huang, Wenwu Wang, Mark D. Plumbley
    IJCNN 2017
  • Attention and localization based on a deep convolutional recurrent model for weakly supervised audio tagging [pdf] [code]
    Yong Xu, Qiuqiang Kong, Qiang Huang, Wenwu Wang, and Mark D. Plumbley
    INTERSPEECH 2017
  • A joint detection-classification model for audio tagging of weakly labelled data [pdf] [code]
    Qiuqiang Kong, Yong Xu, Wenwu Wang, Mark D. Plumbley
    ICASSP 2017
  • Deep neural network baseline for DCASE challenge 2016 [pdf] [code]
    Qiuqiang Kong, Iwona Sobieraj, Wenwu Wang, Mark Plumbley
    DCASE Workshop 2016

Patents

  • Large scale music fingerprint and retrieval (CN103853836), bought by KUGOU, 2014.