Not all generalisation failures can be bought back: four boundaries in affective audio modelling

[2608.27674] Not all generalisation failures can be bought back: four boundaries in affective audio modelling Skip to main content Search Submit Donate Log in Electrical Engineering and Systems Science > Audio and Speech Processing arXiv:2608.27674 (eess) [Submitted on 27 Aug 2026] Title: Not all generalisation failures can be bought back: four boundaries in affective audio modelling Authors: Jingyi Zhang , Xiaotong Yao View PDF HTML (experimental) Abstract: Models mapping acoustic properties onto affective response underpin applications from music recommendation to sound design, yet are evaluated almost entirely within the corpus they were fitted on. When one fails outside it, the standard response -- more data, or a larger model -- assumes every failure is a shortage of resources. We show it is not, and that the alternative calls for the opposite remedy. Using four corpora of rated sound, four pretrained representations and three corpora of physiological recording, we pushed one mapping across four boundaries an application must cross: to new material, to edited audio, to a sensor in place of a self-report, and to an individual listener. At each we report the ceiling the target permits, the fraction surviving the crossing, and the price in target-side observations of closing the gap. Within a corpus, prediction reaches 84% of the ceiling set by inter-listener agreement. A same-domain corpus swap costs a fifth of that, and a hundred target labels return two-thirds of the loss. Crossing between music and environmental sound costs four-fifths to all of it, and four pretrained representations recover none of it. Against physiological response no information source we constructed exceeds a third of the attainable ceiling. "The model does not generalise" is therefore two diagnoses, not one, with mutually exclusive remedies; treating the second as the first is the more expensive mistake. Comments: 40 pages, 8 figures. Supplementary Information (25 pages, 8 Extended Data figures) included as an ancillary file. Code, run records and per-panel source data: this https URL Subjects: Audio and Speech Processing (eess.AS) ACM classes: H.5.5; I.2.6 Cite as: arXiv:2608.27674 [eess.AS] (or arXiv:2608.27674v1 [eess.AS] for this version) https://doi.org/10.48550/arXiv.2608.27674 Focus to learn more arXiv-issued DOI via DataCite Submission history From: Jingyi Zhang [ view email ] [v1] Thu, 27 Aug 2026 20:00:59 UTC (1,136 KB) Full-text links: Access Paper: View PDF HTML (experimental) TeX Source view license Ancillary-file links: Ancillary files ( details ) : supplementary.pdf Current browse context: eess.AS < prev | next > new | recent | 2026-08 Change to browse by: eess References & Citations SciX Google Scholar Semantic Scholar export BibTeX citation Bookmark Bibliographic Tools Bibliographic and Citation Tools Bibliographic Explorer Toggle Bibliographic Explorer ( What is the Explorer? ) Connected Papers Toggle Connected Papers ( What is Connected Papers? ) Litmaps Toggle Litmaps ( What is Litmaps? ) scite.ai Toggle scite Smart Citations ( What are Smart Citations? ) Code, Data, Media Code, Data and Media Associated with this Article alphaXiv Toggle alphaXiv ( What is alphaXiv? ) Links to Code Toggle CatalyzeX Code Finder for Papers ( What is CatalyzeX? ) DagsHub Toggle DagsHub ( What is DagsHub? ) GotitPub Toggle Gotit.pub ( What is GotitPub? ) Huggingface Toggle Hugging Face ( What is Huggingface? ) ScienceCast Toggle ScienceCast ( What is ScienceCast? ) Demos Demos Replicate Toggle Replicate ( What is Replicate? ) Spaces Toggle Hugging Face Spaces ( What is Spaces? ) Spaces Toggle TXYZ.AI ( What is TXYZ.AI? ) Related Papers Recommenders and Search Tools Link to Influence Flower Influence Flower ( What are Influence Flowers? ) Core recommender toggle CORE Recommender ( What is CORE? ) Author Venue Institution Topic About arXivLabs arXivLabs: experimental projects with community collaborators arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website. Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them. Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs . Which authors of this paper are endorsers? | Disable MathJax ( What is MathJax? ) We gratefully acknowledge support from our major funders , member institutions , and all contributors. About · Help · Contact · Subscribe · Copyright · Privacy · Accessibility · Operational Status (opens in new tab) Major funding support from (opens in new tab) (opens in new tab) (opens in new tab)

Related documents

• Not all generalisation failures can be bought back: four boundaries in affective audio modelling#779598
• The Effect of Emotional Context on Large Language Models' Endorsement of Premature Decisions: Comparing Emotional Vulnerability Across Six Commercial Models#780783
• The Effect of Emotional Context on Large Language Models' Endorsement of Premature Decisions: Comparing Emotional Vulnerability Across Six Commercial Models#779408
• Apparent Psychological Profiles of Large Language Models are Largely a Measurement Artifact#290636
• "Mirror" Large Language Model Evaluations of Depression are Criterion Contaminated#999166