{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,2]],"date-time":"2026-03-02T15:22:57Z","timestamp":1772464977061,"version":"3.50.1"},"reference-count":64,"publisher":"Ubiquity Press, Ltd.","issue":"1","license":[{"start":{"date-parts":[[2026,3,2]],"date-time":"2026-03-02T00:00:00Z","timestamp":1772409600000},"content-version":"unspecified","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["TISMIR"],"abstract":"<jats:p>Functional sounds\u2014typically brief, nonverbal audio cues used in the interfaces of electronic devices\u2014play a critical role in human\u2013machine interaction but remain largely unexplored within music information retrieval (MIR). This study proposes a data-driven framework that uses musically informed audio features to predict the perceived semantic expression of functional sounds. Our three-stage pipeline first uses unsupervised feature extraction to transform 805 functional sounds into high-level topic distributions for timbre, chroma, and loudness using Gaussian mixture models and latent Dirichlet allocation. Second, these features train multi-output regression models to predict 19 perceptual dimensions from the FBMUX framework, with a random forest regressor achieving the best performance. Finally, a listening experiment assesses how well the model predictions align with user perceptions. Interpretability analyses further reveal how individual features contribute to model predictions. This work contributes to MIR by expanding its scope to the domain of functional, non-musical audio. It presents a novel application of MIR techniques, demonstrating that structured, musically informed descriptors can support perceptual modeling in domains with limited data and high subjective variance. It contributes a transferable approach and highlights the potential of MIR to inform human\u2013machine interaction and sound design.<\/jats:p>","DOI":"10.5334\/tismir.290","type":"journal-article","created":{"date-parts":[[2026,3,2]],"date-time":"2026-03-02T13:43:32Z","timestamp":1772459012000},"page":"50-65","source":"Crossref","is-referenced-by-count":0,"title":["Predicting Perceived Semantic Expression of Functional Sounds Using Unsupervised Feature Extraction and Ensemble Learning"],"prefix":"10.5334","volume":"9","author":[{"ORCID":"https:\/\/orcid.org\/0009-0008-3600-1028","authenticated-orcid":false,"given":"Annika","family":"Frommholz","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2540-3661","authenticated-orcid":false,"given":"Steffen","family":"Lepa","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-8629-5242","authenticated-orcid":false,"given":"Tom","family":"Virkus","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9427-9932","authenticated-orcid":false,"given":"Stefan","family":"Weinzierl","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-0914-1008","authenticated-orcid":false,"given":"Johannes","family":"Helberger","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"3285","published-online":{"date-parts":[[2026,3,2]]},"reference":[{"key":"key20260302134327_r1","volume-title":"Musikpsychologie. Jahrbuch der Deutschen Gesellschaft f\u00fcr Musikpsychologie. Band 27: Akustik und musikalische H\u00f6rwahrnehmung","year":"2017"},{"issue":"15","key":"key20260302134327_r2","doi-asserted-by":"crossref","first-page":"2051","DOI":"10.1016\/j.cub.2015.06.043","article-title":"Human screams occupy a privileged niche in the communication soundscape","volume":"25","year":"2015","journal-title":"Current Biology"},{"key":"key20260302134327_r3","article-title":"Tools and architecture for the evaluation of similarity measures: Case study of timbre similarity","year":"2004"},{"key":"key20260302134327_r4","first-page":"282","article-title":"Der sensorische wohlklang als funktion psychoakustischer empfindungsgr\u00f6\u00dfen","volume":"58","year":"1985","journal-title":"Acustica"},{"issue":"2","key":"key20260302134327_r5","doi-asserted-by":"crossref","first-page":"124","DOI":"10.1037\/pmu0000087","article-title":"Both acoustic intensity and loudness contribute to time\u2011series models of perceived affect in response to music","volume":"25","year":"2015","journal-title":"Psychomusicology: Music, Mind & Brain"},{"key":"key20260302134327_r6","unstructured":"Bian, W. (2018). Convolutional neural networks for music mood classification tasks. Submitted to the MIREX Challenge 2018. https:\/\/www.music-ir.org\/mirex\/abstracts\/ 2018\/WB1.pdf."},{"issue":"1","key":"key20260302134327_r7","doi-asserted-by":"crossref","first-page":"5","DOI":"10.1023\/A:1010933404324","article-title":"Random forests","volume":"45","year":"2001","journal-title":"Machine Learning"},{"key":"key20260302134327_r8","first-page":"471","volume-title":"Santa Fe Institute Studies in the Sciences of Complexity\u2011Proceedings","year":"1994"},{"key":"key20260302134327_r9","doi-asserted-by":"crossref","first-page":"3247","DOI":"10.1121\/1.2933513","article-title":"Psysound3: A program for the analysis of sound recordings","volume":"123","year":"2008","journal-title":"The Journal of the Acoustical Society of America"},{"key":"key20260302134327_r10","doi-asserted-by":"crossref","first-page":"09","DOI":"10.5121\/csit.2022.122302","volume-title":"Artificial Intelligence, Soft Computing and Applications","year":"2022"},{"key":"key20260302134327_r11","unstructured":"Cao, C., and Li, M. (2009). Thinkit\u2019s submissions for mirex2009 audio music classification and similarity tasks. Submitted to the MIREX Challenge 2009. https:\/\/www.music-ir.org\/mirex\/abstracts\/2009\/CL.pdf."},{"key":"key20260302134327_r12","doi-asserted-by":"crossref","first-page":"273","DOI":"10.1016\/j.plrev.2022.10.004","article-title":"Consonance and dissonance perception: A critical review of the historical sources, multidisciplinary findings, and main hypotheses","volume":"43","year":"2022","journal-title":"Physics of Life Reviews"},{"key":"key20260302134327_r13","first-page":"559","article-title":"Untersuchungen zur aufschreckenden wirkung (startling) synthetischer ger\u00e4usche","year":"2007"},{"key":"key20260302134327_r14","first-page":"245","article-title":"On inter\u2011rater agreement in audio music similarity","year":"2014"},{"issue":"1","key":"key20260302134327_r15","doi-asserted-by":"crossref","first-page":"182","DOI":"10.5334\/tismir.107","article-title":"On evaluation of inter\u2011 and intra\u2011rater agreement in music recommendation","volume":"4","year":"2021","journal-title":"Transactions of the International Society for Music Information Retrieval"},{"issue":"4","key":"key20260302134327_r16","doi-asserted-by":"crossref","first-page":"1951","DOI":"10.1121\/1.4892767","article-title":"Using listener\u2011based perceptual features as intermediate representations in music information retrieval","volume":"136","year":"2014","journal-title":"The Journal of the Acoustical Society of America"},{"key":"key20260302134327_r17","volume-title":"SoundInnovationLab\/somunicate\u2011model\u2011selection: Stable release with data","year":"2026"},{"key":"key20260302134327_r18","unstructured":"Goodfellow, I., Bengio, Y., and Courville, A. (2016). Deep Learning. MIT Press. https:\/\/www.deeplearningbook.org."},{"issue":"7\/8","key":"key20260302134327_r19","doi-asserted-by":"crossref","first-page":"1505","DOI":"10.1108\/EJM-09-2017-0609","article-title":"Non\u2011musical sound branding \u2013 a conceptualization and research overview","volume":"52","year":"2018","journal-title":"European Journal of Marketing"},{"key":"key20260302134327_r20","volume-title":"Mosqito","author":"Green Forge Coop","year":"2024"},{"key":"key20260302134327_r21","doi-asserted-by":"crossref","first-page":"357","DOI":"10.1038\/s41586-020-2649-2","article-title":"Array programming with NumPy","volume":"585","year":"2020","journal-title":"Nature"},{"key":"key20260302134327_r22","volume-title":"The Sonification Handbook","year":"2011"},{"key":"key20260302134327_r23","article-title":"Towards automatic music recommendation for audio branding scenarios","year":"2016"},{"key":"key20260302134327_r24","volume-title":"Proceedings of NIPS","year":"2009"},{"key":"key20260302134327_r25","volume-title":"Speech and Language Processing: An Introduction to Natural Language Processing, Computational Linguistics, and Speech Recognition With Language Models","year":"2025"},{"issue":"1","key":"key20260302134327_r26","doi-asserted-by":"crossref","first-page":"141","DOI":"10.1177\/001316446002000116","article-title":"The application of electronic computers to factor analysis","volume":"20","year":"1960","journal-title":"Educational and Psychological Measurement"},{"key":"key20260302134327_r27","article-title":"Are we there yet? A brief survey of music emotion prediction datasets, models and outstanding challenges","volume-title":"arXiv preprint arXiv:2406.08809","year":"2024"},{"issue":"1","key":"key20260302134327_r28","first-page":"e6","article-title":"Latent acoustic topic models for unstructured audio classification","volume":"1","year":"2012","journal-title":"APSIPA Transactions on Signal and Information Processing"},{"key":"key20260302134327_r29","doi-asserted-by":"crossref","first-page":"47","DOI":"10.1007\/s11621-012-0124-7","article-title":"Using customer insights to improve product sound design","volume":"29","year":"2012","journal-title":"Marketing Review St. Gallen"},{"key":"key20260302134327_r30","doi-asserted-by":"crossref","first-page":"261","DOI":"10.1007\/978-3-540-78246-9_31","volume-title":"Data Analysis, Machine Learning and Applications","year":"2008"},{"issue":"4","key":"key20260302134327_r31","doi-asserted-by":"crossref","first-page":"387","DOI":"10.1080\/09298215.2020.1778041","article-title":"A computational model for predicting perceived musical expression in branding scenarios","volume":"49","year":"2020","journal-title":"Journal of New Music Research"},{"issue":"3","key":"key20260302134327_r32","doi-asserted-by":"crossref","first-page":"191","DOI":"10.17645\/mac.v8i3.3153","article-title":"Popular music as entertainment communication: How perceived semantic expression explains liking of previously unknown music","volume":"8","year":"2020","journal-title":"Media and Communication"},{"key":"key20260302134327_r33","volume-title":"Advances in Neural Information Processing Systems","year":"2017"},{"issue":"1","key":"key20260302134327_r34","first-page":"2522","article-title":"From local explanations to global understanding with explainable ai for trees","volume":"2","year":"2020","journal-title":"Nature Machine Intelligence"},{"key":"key20260302134327_r35","first-page":"1","article-title":"On the generalised distance in statistics","volume":"80","year":"1936","journal-title":"Sankhya A"},{"issue":"5","key":"key20260302134327_r36","doi-asserted-by":"crossref","first-page":"740","DOI":"10.1108\/JPBM-05-2019-2370","article-title":"The impact of the sonic logo\u2019s acoustic features on orienting responses, emotions and brand personality transmission","volume":"30","year":"2021","journal-title":"Journal of Product & Brand Management"},{"issue":"5","key":"key20260302134327_r37","volume":"2","year":"2015","journal-title":"The evolution of popular music: USA 1960\u20132010. Royal Society Open Science"},{"key":"key20260302134327_r38","volume-title":"Test Theory: A Unified Treatment","year":"1999","edition":"1st"},{"key":"key20260302134327_r39","article-title":"librosa: Audio and music signal analysis in Python","year":"2015"},{"key":"key20260302134327_r40","first-page":"51","article-title":"Data structures for statistical computing in Python","year":"2010"},{"key":"key20260302134327_r41","first-page":"583","article-title":"Psychoacoustic experiments on feasible sound levels of possible warning signals for quiet vehicles","year":"2011"},{"key":"key20260302134327_r42","first-page":"41","article-title":"Basic semantics of product sounds","volume":"6","year":"2012","journal-title":"International Journal of Design"},{"key":"key20260302134327_r43","first-page":"8024","volume-title":"Advances in Neural Information Processing Systems 32","year":"2019"},{"issue":"3","key":"key20260302134327_r44","doi-asserted-by":"crossref","first-page":"466","DOI":"10.3390\/app9030466","article-title":"Modelling timbral hardness","volume":"9","year":"2019","journal-title":"Applied Sciences"},{"key":"key20260302134327_r45","first-page":"2825","article-title":"Scikit\u2011learn: Machine learning in Python","volume":"12","year":"2011","journal-title":"Journal of Machine Learning Research"},{"key":"key20260302134327_r46","unstructured":"Peeters, G. (2008). A generic training and classification system for mirex08 classification tasks: Audio music mood, audio genre, audio artist and audio tag. Submitted to the MIREX Challenge 2008. https:\/\/www.music-ir.org\/mirex\/abstracts\/2008\/Peeters_2008_ISMIR_MIREX.pdf."},{"key":"key20260302134327_r47","first-page":"45","article-title":"Software framework for topic modelling with large corpora","year":"2010"},{"key":"key20260302134327_r48","first-page":"152","article-title":"50 years of the International Journal of Human\u2011Computer Studies. Reflections on the past, present and future of human\u2011centred technologies","volume":"131","year":"2019","journal-title":"International Journal of Human\u2011Computer Studies"},{"key":"key20260302134327_r49","doi-asserted-by":"crossref","first-page":"1161","DOI":"10.1037\/h0077714","article-title":"A circumplex model of affect","volume":"39","year":"1980","journal-title":"Journal of Personality and Social Psychology"},{"issue":"3","key":"key20260302134327_r50","doi-asserted-by":"crossref","first-page":"523","DOI":"10.1007\/s10844-013-0247-6","article-title":"The neglected user in music information retrieval research","volume":"41","year":"2013","journal-title":"Journal of Intelligent Information Systems"},{"key":"key20260302134327_r51","volume-title":"Miteinander Reden 1: St\u00f6rungen und Kl\u00e4rungen: Allgemeine Psychologie der Kommunikation","year":"1981","edition":"48th"},{"issue":"2","key":"key20260302134327_r52","first-page":"461","article-title":"Estimating the dimension of a model","volume":"6","year":"1978","journal-title":"The Annals of Statistics"},{"key":"key20260302134327_r53","volume-title":"Auditory Interfaces","year":"2022","edition":"1st"},{"key":"key20260302134327_r54","unstructured":"Song, G., Ding, S., and Wang, Z. (2018). Audio classification tasks using recurrent neural network. Submitted to the MIREX Challenge 2018. https:\/\/www.music-ir.org\/ mirex\/abstracts\/2018\/GS1.pdf."},{"key":"key20260302134327_r55","unstructured":"Tardieu, D., Charbuillet, C., Cornu, F., and Peeters, G. (2011). Mirex\u20112011 single\u2011label and multi\u2011label classification tasks: Ircamclassification2011 submission. Submitted to the MIREX Challenge 2011. https:\/\/www.music-ir.org\/mirex\/ abstracts\/2011\/TCCP4.pdf."},{"key":"key20260302134327_r56","doi-asserted-by":"crossref","first-page":"114169","DOI":"10.1016\/j.jbusres.2023.114169","article-title":"Influencing brand personality with sonic logos: The role of musical timbre","volume":"168","year":"2023","journal-title":"Journal of Business Research"},{"issue":"3","key":"key20260302134327_r57","doi-asserted-by":"crossref","first-page":"169","DOI":"10.1017\/S1355771800003071","article-title":"Marsyas: A framework for audio analysis","volume":"4","year":"2000","journal-title":"Organised Sound"},{"issue":"5","key":"key20260302134327_r58","doi-asserted-by":"crossref","first-page":"293","DOI":"10.1109\/TSA.2002.800560","article-title":"Musical genre classification of audio signals","volume":"10","year":"2002","journal-title":"IEEE Transactions on Speech and Audio Processing"},{"key":"key20260302134327_r59","volume-title":"Validation of the FBMUX questionnaire for measuring communicative expression of UX sounds on 3 levels","year":"2025"},{"key":"key20260302134327_r60","volume-title":"The semantic expression space of UX sounds on the functional level of product communication: An exploratory study with sound designers and consumers.","year":"2025"},{"key":"key20260302134327_r61","volume-title":"Mensch und Computer 2025 \u2011 Workshopband","year":"2025"},{"key":"key20260302134327_r62","first-page":"146","article-title":"Timbre of steady sounds: A factorial investigation of its verbal attributes","volume":"30","year":"1974","journal-title":"Acustica"},{"key":"key20260302134327_r63","first-page":"89","article-title":"The acoustic emotion Gaussians model for emotion\u2011based music annotation and retrieval","year":"2012"},{"issue":"2","key":"key20260302134327_r64","doi-asserted-by":"crossref","first-page":"448","DOI":"10.1109\/TASL.2007.911513","article-title":"A regression approach to music emotion recognition","volume":"16","year":"2008","journal-title":"IEEE Transactions on Audio, Speech, and Language Processing"}],"container-title":["Transactions of the International Society for Music Information Retrieval"],"original-title":[],"link":[{"URL":"https:\/\/account.transactions.ismir.net\/index.php\/up-j-tismir\/article\/download\/290\/359","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/account.transactions.ismir.net\/index.php\/up-j-tismir\/article\/download\/290\/360","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/account.transactions.ismir.net\/index.php\/up-j-tismir\/article\/download\/290\/359","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,2]],"date-time":"2026-03-02T14:08:49Z","timestamp":1772460529000},"score":1,"resource":{"primary":{"URL":"https:\/\/account.transactions.ismir.net\/index.php\/up-j-tismir\/article\/view\/290"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,3,2]]},"references-count":64,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2026,1,7]]}},"URL":"https:\/\/doi.org\/10.5334\/tismir.290","relation":{},"ISSN":["2514-3298"],"issn-type":[{"value":"2514-3298","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,3,2]]}}}