Mogridge, R. orcid.org/0000-0002-5686-070X and Ragni, A. orcid.org/0000-0003-0634-4456 (2026) Minerva 2 for speech and language tasks. Computer Speech & Language, 95. 101843. ISSN: 0885-2308
Abstract
Most artificial neural networks do not directly incorporate a memory of previous experiences, instead using training data to parameterise a model, and then discarding the training data prior to inference. While some recent models have included a memory, this has typically been added to an already highly parameterised model. An alternative option is to use a purely memory-based model, and then add parameters. This has been shown to work for Minerva 2, a simple, non-parametric, memory-based model which has been widely used in the field of human psychology. We revisit the use of Minerva 2 for speech and language tasks, drawing comparisons between Minerva 2 and other architectures, and showing that an iterative process that Minerva 2 uses for inference is a close relative of deep equilibrium models. We assess parameterised models based on Minerva 2, including a sequence model inspired by Minerva 2’s similarity to the transformer architecture, which shows promising results.
Metadata
Item Type: | Article |
---|---|
Authors/Creators: |
|
Copyright, Publisher and Additional Information: | © 2025 The Authors. Except as otherwise noted, this author-accepted version of a journal article published in Computer Speech & Language is made available via the University of Sheffield Research Publications and Copyright Policy under the terms of the Creative Commons Attribution 4.0 International License (CC-BY 4.0), which permits unrestricted use, distribution and reproduction in any medium, provided the original work is properly cited. To view a copy of this licence, visit http://creativecommons.org/licenses/by/4.0/ |
Keywords: | Exemplars; Minerva 2Phone recognition; Emotion classification; Speech intelligibility |
Dates: |
|
Institution: | The University of Sheffield |
Academic Units: | The University of Sheffield > Faculty of Engineering (Sheffield) > Department of Computer Science (Sheffield) |
Funding Information: | Funder Grant number Engineering and Physical Sciences Research Council 2431591 |
Date Deposited: | 30 Sep 2025 10:27 |
Last Modified: | 30 Sep 2025 13:56 |
Status: | Published |
Publisher: | Elsevier BV |
Refereed: | Yes |
Identification Number: | 10.1016/j.csl.2025.101843 |
Related URLs: | |
Open Archives Initiative ID (OAI ID): | oai:eprints.whiterose.ac.uk:232360 |