Huy Phan

PhD opportunity in deep learning for joint audio and ear-EEG processing, working with Preben Kidmose, Kaare Mikkelsen and myself. This position is based in Aarhus University. More detail can be found HERE. * The position has been filled. *

I am a Lecturer (roughly equivalent to Assistant Professor) in Artificial Intelligence at the School of Electronic Engineering and Computer Science, Queen Mary University of London (UK). Before I was a Lecturer at the School of Computing, University of Kent (UK) and a postdoctoral researcher in the CIBIM lab at the Department of Engineering Science, University of Oxford (UK), working with Prof. Maarten De Vos. I obtained my PhD (Dr.-Ing. in German system) with summa cum laude in the Institute for Signal Processing, University of Lübeck (Germany) under the supervision of Prof. Alfred Mertins. I received University of Lübeck’s Doctoral Scholarship for my PhD studies and the Bernd Fischer award for the best PhD thesis.

I investigate topics in the fields of machine learning/deep learning and signal processing. I am particularly interested in speech analysis, environmental sound analysis, and biosignal analysis, and healthcare applications.

My CV is available here.


  • 17 June 2019: (New) Two papers accepted for Interspeech 2019
  • 4 June 2019: (New) Two papers accepted for EUSIPCO 2019
  • 10 April 2019: (New) Two papers accepted for EMBC 2019
  • 3 April 2019: (New) Two papers accepted for 2019 AES Conf. Audio Forensics
  • 11 February 2019: Work on “Resting-state brain information flow predicts cognitive flexibility in humans” accepted for Nature Scientific Reports. Congrat~ O. Y. Chén
  • 1 February 2019: Two papers accepted for ICASSP 2019
  • 28 January 2019: Our work SeqSleepNet accepted to be published in IEEE Trans. Neural Systems and Rehabilitation Engineering (TNSRE). Source code available here
  • January 2019: I am now a Lecturer in the School of Computing, University of Kent (UK)
  • 14 November 2018: Received the Bernd Fischer award. News about the University of Lübeck’s 2018 Awards online here and here
  • 6 November 2018: New preprint on Unifying Isolated and Overlapping Audio Event Detection available on arXiv.
  • 6 November 2018: New preprint, Beyond Equal-Length Snippets: How Long is Sufficient to Recognize an Audio Scene?, available on arXiv.
  • 1 October 2018: Our work, SeqSleepNet: End-to-End Hierarchical Recurrent Neural Network for Sequence-to-Sequence Automatic Sleep Staging, available on arXiv. Source code will be available shortly here
  • 22 September 2018: Our preprint on automatic sleep staging accepted to be published in IEEE Trans. Biomedical Engineering (TBME).
  • 31 August 2018: Awarded the Bernd Fisher award, University of Lübeck, for best PhD thesis
  • 31 August 2018: MultitaskSleepNet source code for automatic sleep staging available
  • 31 August 2018: New version of our recent work on automatic sleep staging available
  • 16 May 2018: Preprint of our recent work on automatic sleep staging available in arXiv
  • 04 May 2018: My PhD thesis approved for “summa cum laude”
  • 03 May 2018: I will serve as a session co-chair at EMBC 2018
  • 08 April 2018: Four papers accepted for EMBC 2018
  • 31 Jan 2018: Giving a talk on “Temporal Structure Modelling for Audio Event Detection” at Univesity of Kent (Medway)
  • 29 Jan 2018: Two papers accepted for ICASSP 2018
  • 16 Oct 2017: Joining the University of Oxford as a postdoctoral researcher
  • 23 Aug 2017: Successfully defending my PhD thesis, entitled “Audio Event Detection, Classification, and Beyond”
  • 02 Dec 2016: Giving a talk on “Some Perspectives on Audio Event Detection” at TU Dortmund
  • 18 Jul 2016: Released Matlab code for random regression forests