{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,20]],"date-time":"2026-05-20T18:02:56Z","timestamp":1779300176444,"version":"3.51.4"},"reference-count":34,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Signal Process. Lett."],"published-print":{"date-parts":[[2025]]},"DOI":"10.1109\/lsp.2025.3532218","type":"journal-article","created":{"date-parts":[[2025,1,20]],"date-time":"2025-01-20T19:14:13Z","timestamp":1737400453000},"page":"741-745","source":"Crossref","is-referenced-by-count":6,"title":["Improving Audio Explanations Using Audio Language Models"],"prefix":"10.1109","volume":"32","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-8010-6897","authenticated-orcid":false,"given":"Alican","family":"Akman","sequence":"first","affiliation":[{"name":"GLAM, Department of Computing, Imperial College London, London, U.K."}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-9228-4543","authenticated-orcid":false,"given":"Qiyang","family":"Sun","sequence":"additional","affiliation":[{"name":"GLAM, Department of Computing, Imperial College London, London, U.K."}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6478-8699","authenticated-orcid":false,"given":"Bj\u00f6rn W.","family":"Schuller","sequence":"additional","affiliation":[{"name":"GLAM, Department of Computing, Imperial College London, London, U.K."}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","first-page":"12449","article-title":"wav2vec 2.0: A framework for self-supervised learning of speech representations","volume-title":"Proc. Int. Conf. Adv. Neural Inf. Process. Syst.","volume":"33","author":"Baevski","year":"2020"},{"key":"ref2","first-page":"28492","article-title":"Robust speech recognition via large-scale weak supervision","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Radford","year":"2023"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2021-698"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3122291"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2022.3188113"},{"key":"ref6","article-title":"vq-wav2vec: Self-supervised learning of discrete speech representations","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Baevski","year":"2019"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.findings-acl.931"},{"key":"ref8","article-title":"A fine-tuned wav2vec 2.0\/HuBERT benchmark for speech emotion recognition, speaker verification and spoken language understanding","author":"Wang","year":"2021"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TAFFC.2024.3369726"},{"key":"ref10","article-title":"Llama 2: Open foundation and fine-tuned chat models","author":"Touvron","year":"2023"},{"key":"ref11","first-page":"1877","article-title":"Language models are few-shot learners","volume-title":"Proc. Int. Conf. Adv. Neural Inf. Process. Syst.","volume":"33","author":"Brown","year":"2020"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.5040\/9781501365072.10293"},{"key":"ref13","article-title":"Audiogen: Textually guided audio generation","volume-title":"Proc. 11th Int. Conf. Learn. Representations","author":"Kreuk","year":"2023"},{"key":"ref14","first-page":"56422","article-title":"UniAudio: Towards universal audio generation with large language models","volume-title":"Proc. 41st Int. Conf. Mach. Learn.","volume":"235","author":"Yang","year":"2024"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N16-3020"},{"key":"ref16","article-title":"RISE: Randomized input sampling for explanation of black-box models","volume-title":"Proc. British Mach. Vis. Conf.","author":"Petsiuk","year":"2018"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0130140"},{"key":"ref18","first-page":"3319","article-title":"Axiomatic attribution for deep networks","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Sundararajan","year":"2017"},{"key":"ref19","first-page":"618","article-title":"Grad-cam: Why did you say that? Visual explanations from deep networks via gradient-based localization","volume-title":"Proc. IEEE Int. Conf. Comput. Vis.","author":"Selvaraju","year":"2017"},{"key":"ref20","article-title":"A unified view of gradient-based attribution methods for deep neural networks","author":"Ancona","year":"2017"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/EMBC48229.2022.9871291"},{"key":"ref22","first-page":"35270","article-title":"Listen to interpret: Post-hoc interpretability for audio networks with NMF","volume-title":"Proc. Int. Conf. Adv. Neural Inf. Process. Syst.","volume":"35","author":"Parekh","year":"2022"},{"key":"ref23","first-page":"535","article-title":"Algorithms for non-negative matrix factorization","volume-title":"Proc. Int. Conf. Adv. Neural Inf. Process. Syst.","volume":"13","author":"Lee","year":"2000"},{"key":"ref24","first-page":"2668","article-title":"Interpretability beyond feature attribution: Quantitative testing with concept activation vectors (TCAV)","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Kim","year":"2018"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.354"},{"key":"ref26","article-title":"Audio explanation synthesis with generative foundation models","author":"Akman","year":"2024"},{"key":"ref27","article-title":"Towards audio language modelingAn overview","author":"Wu","year":"2024"},{"key":"ref28","article-title":"High fidelity neural audio compression","author":"Dfossez","year":"2022"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3129994"},{"key":"ref30","article-title":"Soundstorm: Efficient parallel audio generation","author":"Borsos","year":"2023"},{"key":"ref31","article-title":"LauraGPT: Listen, attend, understand, and regenerate audio with GPT","author":"Du","year":"2024"},{"key":"ref32","article-title":"Speech commands: A dataset for limited-vocabulary speech recognition","author":"Warden","year":"2018"},{"key":"ref33","article-title":"Toronto emotional speech set (TESS)","author":"Pichora-Fuller","year":"2020"},{"key":"ref34","article-title":"Simple and controllable music generation","volume-title":"Proc. 37th Conf. Neural Inf. Process. Syst.","author":"Copet","year":"2023"}],"container-title":["IEEE Signal Processing Letters"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/97\/10802935\/10847866.pdf?arnumber=10847866","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,2,7]],"date-time":"2025-02-07T07:10:21Z","timestamp":1738912221000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10847866\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025]]},"references-count":34,"URL":"https:\/\/doi.org\/10.1109\/lsp.2025.3532218","relation":{},"ISSN":["1070-9908","1558-2361"],"issn-type":[{"value":"1070-9908","type":"print"},{"value":"1558-2361","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025]]}}}