- Speaker Retrieval in the Wild: Challenges, Effectiveness and Robustness
- BBC Broadcasting House, April 2024
- University of Cambridge, March 2024
-
Phonetic Error Analysis beyond Phone Error Rate, University of Edinburgh, 2023 Slides
-
Speech Acoustic Modelling from Raw Signal Representations, Edinburgh Napier University, 2022 Slides
-
On the Robustness and Training Dynamics of Raw Waveform Models, University of Edinburgh, 2021 Slides
-
Raw Sign and Magnitude Spectra for Multi-head Acoustic Modelling, University of Edinburgh, 2020 Slides
-
DNN Statistical Interpretation and Normalisation for ASR, University of Edinburgh, 2019 Slides
-
Understanding and Interpreting DNNs for
Speech Recognition, Qatar Computing Research Institute (QCRI), 2019 Slides Video
-
Speech Phase Spectrum: Love It or Leave It?, University of Edinburgh, 2018
-
Channel Compensation in the Generalised VTS Approach to Robust ASR, UKSpeech (University of Cambridge), 2017 Slides Video
- Source-filter Separation of Speech Signal in the Phase Domain, UKSpeech (University of East Anglia), 2015 Slides
-
From Priors to Transformers: How CSTR Encoded my Career Path, CSTR’s 40th Anniversary, Endinburgh, 2024
-
Genie in the mike! The Science of Talking (with) Machines, A Pint of Science Festival, Sheffield, 2017 Teaser
-
Signal Processing is Dead(?)! Long Live DNN!, Machine Intelligence for Natural Interfaces (MINI) workshop, Sheffield, 2016
-
Deep Learning, The End of History and The Last Computer Scientist, A Pint of Science Festival, Sheffield, 2016
-
Ethics in Data Modelling; Love it or Leave it?, Research Ethics and Integrity module, University of Sheffield, Sheffield, 2014
-
Why do a PhD?, Department of Computer Science, University of Sheffield, Sheffield, 2014 Slides