Aaron Nicolson

I am a Postdoc at CSIRO, stationed at the Australian e-Health Research Centre in Brisbane, Australia. I am also a part of CSIRO's Machine Learning & Artificial Intelligence Future Science Platform. My research focus is multimodal deep learning for medical image analysis.

In 2020, I completed my PhD at the Signal Processing Laboratory of Griffith University, under the supervision of Kuldip K. Paliwal. There, I investigated deep learning for robust speech processing with projects such as Deep Xi.

Email / Google Scholar / Twitter / Github

Selected Publications

	Improving Chest X-Ray Report Generation by Leveraging Warm-Starting Aaron Nicolson, Jason Dowling, Bevan Koopman, arXiv, 2022 github / arXiv
	On Training Targets for Deep Learning Approaches to Clean Speech Magnitude Spectrum Estimation Aaron Nicolson, Kuldip K. Paliwal The Journal of the Acoustical Society of America, 2021
	Masked multi-head self-attention for causal speech enhancement Aaron Nicolson, Kuldip K. Paliwal Speech Communication, 2020
	Spectral distortion level resulting in a just-noticeable difference between an a priori signal-to-noise ratio estimate and its instantaneous case Aaron Nicolson, Kuldip K. Paliwal The Journal of the Acoustical Society of America, 2020
	Sum-product networks for robust automatic speaker identification Aaron Nicolson, Kuldip K. Paliwal INTERSPEECH, 2020 github
	DeepMMSE: A Deep Learning Approach to MMSE-Based Noise Power Spectral Density Estimation Qiquan Zhang, Aaron Nicolson, Mingjiang Wang, Kuldip K. Paliwal, Chenxu Wang IEEE/ACM Transactions on Audio, Speech, and Language Processing, 2020
	Deep residual-dense lattice network for speech enhancement Mohammad Nikzad, Aaron Nicolson, Yongsheng Gao, Jun Zhou, Kuldip K Paliwal, Fanhua Shang Proceedings of the AAAI Conference on Artificial Intelligence, 2020
	Deep learning for minimum mean-square error approaches to speech enhancement Aaron Nicolson, Kuldip K. Paliwal Speech Communication, 2019 github

Based on Jon Barron's page.