Deep learning meets measurement error: the hidden challenge in binaural sound source localisation

Reed-Jones, J orcid iconORCID: 0000-0002-6398-1980, Fergus, P, Ellis, D and Jones, K Deep learning meets measurement error: the hidden challenge in binaural sound source localisation. In: Faculty Research Conference 2025. (Accepted)

[thumbnail of Jago_Reed_Jones__FET_Conference_2025 (1).pdf] Text
Jago_Reed_Jones__FET_Conference_2025 (1).pdf - Published Version
Access Restricted

Download (299kB)

Abstract

In the field of binaural sound source localisation, deep learning is often used to make predictions of a sound source’s direction. Typically, models are trained and evaluated using data synthesised from head related transfer function measurements, with the same set of measurements being used in the training and testing datasets. This work verifies whether it is valid to do so by training and testing convolutional neural networks on binaural audio made from nine different sets of measurements of the same head simulator. It is found that there is very poor cross-performance, and the models do not generalise well to unseen measurement datasets, leading to the conclusion that this approach to evaluating deep binaural sound source localisation models is not valid.

Item Type: Conference or Workshop Item (Paper)
Subjects: Q Science > QA Mathematics > QA75 Electronic computers. Computer science
T Technology > TA Engineering (General). Civil engineering (General)
Divisions: Computer Science and Mathematics
Engineering
Date of acceptance: 7 May 2025
Date Deposited: 08 Jul 2025 12:18
Last Modified: 08 Jul 2025 12:18
URI: https://researchonline.ljmu.ac.uk/id/eprint/26710
View Item View Item