Enea Ceolini

Position:
PhD Student -- ended Mar 2020
Email:
Work phone:
Location:
The brain is really efficient in dealing with real-time streams of information. It can process it in such a way that is both robust and efficient. In my work I focus on trying to understand what are the principles of this computations. All this in order to translate this principles into algorithms that can run paired with dynamical sensors such as silicon cochlea an silicon retina. These sensor are spiking systems. Computationally this introduces many advantages such as speed, low power consumption and compressed information. Specifically I am interested in developing a robust and fast algorithm that can extract single sources from a mixture collect by a sensor in an auditory scene. I believe that spiking computation can not only help us reaching goals that traditional methods can not achieve, but also that it can bring us insights on how the brain might be solving many difficult tasks.

Supervisor

Shih-Chii Liu

Publications

2020

  • Ceolini, E. , Hjortkjaer, J., Wong, D. E., O'Sullivan, J., Raghavan, V. ,Herrero, J. , Mehta, A., Liu, S-C., and Mesgarani, N. Brain-informed speech separation (BISS) for enhancement of target speaker in multitalker speech perception, NeuroImage, 223: 117282, 2020
  • Ceolini, E., Kiselev, I., and Liu, S-C. Evaluating multi-channel multi-device speech separation algorithms in the wild: a hardware-software solution, IEEE Transactions on Audio, Language and Speech Processing, 28: 1428-1439, 2020
  • Enea Ceolini, Charlotte Frenkel, Sumit Bam Shrestha, Gemma Taverni, Lyes Khacef, Melika Payvand, Elisa Donati Hand-gesture recognition based on EMG and event-based camera sensor fusion: a benchmark in neuromorphic computing, Frontiers in Neuroscience, 2020 pdf

2019

  • Braun, S., Neil, D., Anumula, J.,. Ceolini, E., and Liu, S-C. Attention-driven multi-sensor selection, 2019 IEEE International Joint Conference on Neural Networks (IJCNN), 2019
  • Ceolini, E. and Liu, S-C. Combining deep neural networks and beamforming for real-time multi-channel speech enhancement using a wireless acoustic sensor network, IEEE International Workshop on Machine Learning for Speech Processing (MLSP 2019), 2019
  • Ceolini, E., Anumula, J.,. Braun, S., and Liu, S-C. Event-driven pipeline for low latency low compute keyword spotting and speaker verification system, 2019 International Conference on Acoustics, Speech and Signal Processing, 2019
  • Ceolini, E., Kiselev, I., and Liu, S-C. Audio classification systems using deep neural networks and an event-driven auditory sensor, 2019 Proceedings of IEEE Sensors Conference, 2019
  • Enea Ceolini, Gemma Taverni, Lyes Khacef, Melika Payvand, Elisa Donati Sensor fusion using EMG and vision for hand gesture classification in mobile applications, 2019 IEEE Biomedical Circuits and Systems Conference (BioCAS) 1-4, 2019
  • Liu, Shih-Chii and Rueckauer, Bodo and Ceolini, Enea and Huber, Adrian and Delbruck, Tobi Event-Driven Sensing for Efficient Perception: Vision and Audition Algorithms, IEEE Signal Processing Magazine 29-37, 2019
  • Lou, Y., Ceolini, E., Han, C., Liu, S-C., and Mesgarani, N. FaSNet: Low-latency adaptive beamforming for multi-microphone audio processing, 2019 IEEE Automatic Speech Recognition and Understanding (ASRU) Workshop, 2019

2018

  • Anumula, J., Ceolini, E., He, Z., Huber, A., and Liu, S-C. An event-driven probabilistic model of sound source localization using cochlea spikes, 2018 IEEE International Symposium on Circuits and Systems, 2018
  • Braun, S. and Neil, D. and Anumula, J. and Ceolini, E. and Liu, S-C. Multi-channel attention for end-to-end speech recognition, 2018 Interspeech, 2018
  • Ceolini, E. and Anumula, J. and Huber, A and Kiselev, I. and Liu, S-C. Speaker activity detection and minimum variance beamforming for source separation, 2018 Interspeech, 2018
  • Daniel DE Wong, Soren A Fuglsang, Jens Hjortkjær, Enea Ceolini, Malcolm Slaney, Alain De Cheveigne A comparison of regularization methods in forward and backward models for auditory attention decoding, Frontiers in neuroscience, 12:, 2018
  • Gao, C., Neil, D., Ceolini, E., Liu, S-C., Delbruck, T. DeltaRNN: A Power-efficient Recurrent Neural Network Accelerator, Proceedings of the 2018 ACM/SIGDA International Symposium on Field-Programmable Gate Arrays (FPGA 2018) 21-30, 2018
  • M Ancona, E Ceolini, C Oztireli, M Gross Towards better understanding of gradient-based attribution methods for Deep Neural Networks, 6th International Conference on Learning Representations (ICLR), 2018

2017

2016