{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,25]],"date-time":"2026-08-25T05:37:20Z","timestamp":1787636240966,"version":"build-2736575974"},"reference-count":49,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,4,6]],"date-time":"2025-04-06T00:00:00Z","timestamp":1743897600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,4,6]],"date-time":"2025-04-06T00:00:00Z","timestamp":1743897600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100000781","name":"European Research Council","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100000781","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,4,6]]},"DOI":"10.1109\/icassp49660.2025.10890619","type":"proceedings-article","created":{"date-parts":[[2025,3,12]],"date-time":"2025-03-12T17:15:02Z","timestamp":1741799702000},"page":"1-5","source":"Crossref","is-referenced-by-count":1,"title":["Estimating Musical Surprisal in Audio"],"prefix":"10.1109","author":[{"given":"Mathias Rose","family":"Bjare","sequence":"first","affiliation":[{"name":"Johannes Kepler University (JKU),Institute of Computational Perception,Linz,Austria"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Giorgia","family":"Cantisani","sequence":"additional","affiliation":[{"name":"ENS, PSL University, CNRS,Laboratoire des Systèmes Perceptifs,Paris,France"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Stefan","family":"Lattner","sequence":"additional","affiliation":[{"name":"Sony Computer Science Laboratories (CSL),Paris,France"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Gerhard","family":"Widmer","sequence":"additional","affiliation":[{"name":"Johannes Kepler University (JKU),Institute of Computational Perception,Linz,Austria"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.2307\/427154"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1080\/09298219508570672"},{"key":"ref3","article-title":"The construction and evaluation of statistical models of melodic structure in music perception and composition","volume-title":"Ph.D. dissertation","author":"Pearce","year":"2005"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1111\/j.1756-8765.2012.01214.x"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1525\/mp.2019.37.2.165"},{"key":"ref6","first-page":"810","article-title":"Exploring sampling techniques for generating melodies with a transformer language model","volume-title":"ISMIR","author":"Bjare"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1523\/jneurosci.0428-19.2019"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1609\/aiide.v10i5.12767"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1017\/S0890060414000687"},{"key":"ref10","article-title":"Controlling surprisal in music generation via information content curve matching","volume-title":"ISMIR","author":"Bjare"},{"key":"ref11","first-page":"224","article-title":"Audio oracle: A new algorithm for fast learning of audio structures","volume-title":"ICMC","author":"Dubnov"},{"key":"ref12","article-title":"Deep generative models of music expectation","volume-title":"NeurIPS ML for Audio Workshop 2023","author":"Masclef"},{"key":"ref13","first-page":"160","article-title":"Retrieving musical information from neural data: how cognitive features enrich acoustic ones","volume-title":"ISMIR","author":"Abrams"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.5334\/tismir.123"},{"key":"ref15","article-title":"On the typicality of musical sequences","volume-title":"ISMIR Late Breaking and Demo Papers","author":"Bjare","year":"2022"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref17","article-title":"Long-form music generation with latent diffusion","volume-title":"ISMIR","author":"Evans"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72998-0_17"},{"key":"ref19","article-title":"Music2latent: Consistency autoencoders for latent audio compression","volume-title":"ISMIR","author":"Pasini"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1016\/j.neuroimage.2009.12.019"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.7554\/eLife.51784"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.3389\/fpsyg.2014.01052"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1016\/j.bandc.2019.103621"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1162\/jocn_a_01181"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pcbi.1006162"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.3813\/aaa.919279"},{"key":"ref27","first-page":"32211","article-title":"Consistency models","volume-title":"ICML","volume":"202","author":"Song"},{"key":"ref28","first-page":"12449","article-title":"wav2vec 2.0: A framework for self-supervised learning of speech representations","volume-title":"NeurIPS","author":"Baevski"},{"key":"ref29","first-page":"673","article-title":"Contrastive learning of musical representations","volume-title":"ISMIR","author":"Spijkervet"},{"key":"ref30","article-title":"Jukebox: A generative model for music","author":"Dhariwal","year":"2020","journal-title":"CoRR"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3129994"},{"key":"ref32","article-title":"High fidelity neural audio compression","volume":"2023","author":"D\u00e9fossez","year":"2023","journal-title":"Trans. Mach. Learn. Res."},{"key":"ref33","article-title":"High-fidelity audio compression with improved RVQGAN","volume-title":"NeurIPS","author":"Kumar"},{"key":"ref34","article-title":"Language models are unsupervised multitask learners","author":"Radford","year":"2019"},{"key":"ref35","article-title":"Medleydb 2.0: New data and a system for sustainable data collection","volume":"36","author":"Bittner","year":"2016","journal-title":"ISMIR Late Breaking and Demo Papers"},{"key":"ref36","article-title":"The MUSDB18 corpus for music separation","author":"Rafii","year":"2017"},{"key":"ref37","article-title":"Deep12","author":"Kishi"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2023.127063"},{"key":"ref39","article-title":"FlashAttention: Fast and memory-efficient exact attention with io-awareness","author":"Dao","year":"2022","journal-title":"CoRR"},{"key":"ref40","article-title":"Adam: A method for stochastic optimization","volume-title":"ICLR (Poster)","author":"Kingma"},{"key":"ref41","first-page":"71","article-title":"Conchord: an application for generating musical harmony by navigating in a perceptually motivated tonal interval space","volume-title":"CMMR","author":"Bernardes"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1080\/09298215.2016.1182192"},{"key":"ref43","volume-title":"Information theory and esthetic perception","author":"Moles","year":"1966"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1007\/BF00419633"},{"key":"ref45","first-page":"4","article-title":"Maximum filter vibrato suppression for onset detection","volume-title":"DAFx","volume":"7","author":"B\u00f6ck"},{"key":"ref46","article-title":"ITUR BS.1770-4"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2023-1949"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.3389\/fnhum.2016.00604"},{"key":"ref49","article-title":"Neural signatures of musical and linguistic interactions during natural song listening","author":"Cantisani","year":"2024","journal-title":"Hal preprint"}],"event":{"name":"ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","location":"Hyderabad, India","start":{"date-parts":[[2025,4,6]]},"end":{"date-parts":[[2025,4,11]]}},"container-title":["ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10887540\/10887541\/10890619.pdf?arnumber=10890619","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,25]],"date-time":"2026-03-25T05:24:23Z","timestamp":1774416263000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10890619\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,4,6]]},"references-count":49,"URL":"https:\/\/doi.org\/10.1109\/icassp49660.2025.10890619","relation":{},"subject":[],"published":{"date-parts":[[2025,4,6]]}}}