{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T18:20:03Z","timestamp":1777486803713,"version":"3.51.4"},"reference-count":41,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,6,30]],"date-time":"2025-06-30T00:00:00Z","timestamp":1751241600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,6,30]],"date-time":"2025-06-30T00:00:00Z","timestamp":1751241600000},"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":[],"published-print":{"date-parts":[[2025,6,30]]},"DOI":"10.1109\/ijcnn64981.2025.11229318","type":"proceedings-article","created":{"date-parts":[[2025,11,14]],"date-time":"2025-11-14T18:46:15Z","timestamp":1763145975000},"page":"1-8","source":"Crossref","is-referenced-by-count":1,"title":["Transformation of audio embeddings into interpretable, concept-based representations"],"prefix":"10.1109","author":[{"given":"Alice","family":"Zhang","sequence":"first","affiliation":[{"name":"Univ. of Texas at Austin,Dept. of Electrical and Computer Engineering,Austin,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Edison","family":"Thomaz","sequence":"additional","affiliation":[{"name":"Univ. of Texas at Austin,Dept. of Electrical and Computer Engineering,Austin,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Lie","family":"Lu","sequence":"additional","affiliation":[{"name":"Dolby Laboratories,San Francisco,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2020.3030497"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746312"},{"key":"ref3","first-page":"18 090","article-title":"Pengi: An audio language model for audio tasks","volume":"36","author":"Deshmukh","year":"2023","journal-title":"NeurIPS"},{"key":"ref4","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"ICML","author":"Radford"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10095889"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10095969"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10448504"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1609\/aimag.v38i3.2741"},{"key":"ref9","article-title":"Interpreting CLIP\u2019s image representation via text-based decomposition","volume-title":"ICLR 2024","author":"Gandelsman"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.52202\/079017-2678"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01592"},{"key":"ref12","article-title":"Toward interpretable music tagging with self-attention","author":"Won","year":"2019"},{"key":"ref13","article-title":"Interpreting and explaining deep neural networks for classification of audio signals","author":"Becker","year":"2018"},{"issue":"2","key":"ref14","first-page":"127","article-title":"Why are speech spectrograms hard to read?","volume":"113","author":"Liberman","year":"1968","journal-title":"American annals of the deaf"},{"key":"ref15","article-title":"SPES: Spectrogram perturbation for explainable speech-to-text generation","author":"Fucci","year":"2024"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N16-3020"},{"key":"ref17","article-title":"Local interpretable model-agnostic explanations for music content analysis","volume-title":"ISMIR","author":"Mishra"},{"key":"ref18","article-title":"audioLIME: Listenable Explanations Using Source Separation","volume-title":"13th International Workshop on Machine Learning and Music","author":"Haunschmid"},{"key":"ref19","first-page":"35 270","article-title":"Listen to interpret: Post-hoc interpretability for audio networks with NMF","volume":"35","author":"Parekh","year":"2022","journal-title":"NeurIPS"},{"key":"ref20","first-page":"9273","article-title":"Towards automatic concept-based explanations","author":"Ghorbani","year":"2019","journal-title":"NeurIPS 2019"},{"key":"ref21","first-page":"5338","article-title":"Concept bottleneck models","volume":"119","author":"Koh","year":"2020","journal-title":"ICML 2020"},{"key":"ref22","article-title":"Label-free concept bottleneck models","author":"Oikarinen","year":"2023","journal-title":"ICLR 2023"},{"key":"ref23","article-title":"Post-hoc concept bottleneck models","volume-title":"ICLR 2023","author":"Yuksekgonul"},{"key":"ref24","article-title":"Information maximization perspective of orthogonal matching pursuit with applications to explainable AI","volume-title":"NeurIPS 2023","author":"Chattopadhyay"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW60793.2023.00292"},{"key":"ref26","article-title":"CLIP-Dissect: Automatic description of neuron representations in deep vision networks","volume-title":"ICLR 2023","author":"Oikarinen"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3133208"},{"key":"ref28","article-title":"Concept-based explanations using non-negative concept activation vectors and decision tree for CNN models","author":"Mutahar","year":"2022"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i13.17389"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1145\/2647868.2655045"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2019.2907016"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1145\/2733373.2806390"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7952261"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746828"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2024.3419446"},{"key":"ref36","article-title":"LanguageBind: Extending video-language pretraining to n-modality by language-based semantic alignment","author":"Zhu","year":"2024"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.naacl-long.266"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9052990"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747631"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02588"},{"key":"ref41","article-title":"Qwen-audio: Advancing universal audio understanding via unified large-scale audio-language models","author":"Chu","year":"2023"}],"event":{"name":"2025 International Joint Conference on Neural Networks (IJCNN)","location":"Rome, Italy","start":{"date-parts":[[2025,6,30]]},"end":{"date-parts":[[2025,7,5]]}},"container-title":["2025 International Joint Conference on Neural Networks (IJCNN)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11227166\/11227148\/11229318.pdf?arnumber=11229318","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,11,15]],"date-time":"2025-11-15T07:30:27Z","timestamp":1763191827000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11229318\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,6,30]]},"references-count":41,"URL":"https:\/\/doi.org\/10.1109\/ijcnn64981.2025.11229318","relation":{},"subject":[],"published":{"date-parts":[[2025,6,30]]}}}