Dr Calum Heggan

Hi i’m Calum, I completed my PhD in late 2024, which focused on few-shot and self-supervised leanring for audio classification tasks. During this time I worked with both the IPAB and IDCOM groups under the supervsion of Mehrdad Yaghoobi (Singal Processing), Timothy Hospedales (Informatics) and Sam Budgett (Thales UK).

I now work at Telesemica, researching and developing ML-based solutions to facilitate audio intelligence in noisy environments.

Other VIVA Passed and thesis publicly available! (December 2014)
Conferences “From Pixels to Waveforms: Evaluating Pre-trained Image Models for Few-Shot Audio Classification” accepted at IJCNN24. Paper and code coming soon.
Other Started writing Thesis
Conferences “On the Transferability of Large-Scale Self-Supervision to Few-Shot Audio Classification” is accepted to ICASSP SASB. Code to be released soon, and formally presented in Seoul April 2024
Conference Presentations MT-SLVR presented at INTERSPEECH 23
Publications MT-SLVR and its relevant code are officially released
Conferences MT-SLVR (A new multi-task representation learning approach) is accepted to INTERSPEECH23. To be released soon, and formally presented in August 2023
Workshops Co-hosted an international Few-Shot Learning workshop for Thales UK’s “FoundAItion” (5/5/23)
Conference Presentations MetaAudio presented at ICANN22 Session 2 (6/9/22)
Conferences MetaAudio accepted to ICANN22. To be presented in early September
Publications MetaAudio, the first few-shot audio classification benchmark is now live on arXiv and submitted to ICANN22