{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,25]],"date-time":"2026-04-25T05:33:28Z","timestamp":1777095208867,"version":"3.51.4"},"reference-count":71,"publisher":"IEEE","license":[{"start":{"date-parts":[[2026,2,2]],"date-time":"2026-02-02T00:00:00Z","timestamp":1769990400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,2,2]],"date-time":"2026-02-02T00:00:00Z","timestamp":1769990400000},"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":[[2026,2,2]]},"DOI":"10.1109\/icsc67292.2026.00053","type":"proceedings-article","created":{"date-parts":[[2026,4,24]],"date-time":"2026-04-24T19:44:40Z","timestamp":1777059880000},"page":"320-327","source":"Crossref","is-referenced-by-count":0,"title":["Explainability in Speech AI: Challenges and Future Directions"],"prefix":"10.1109","author":[{"given":"Xiaoliang","family":"Wu","sequence":"first","affiliation":[{"name":"University of Southampton,Electronics and Computer Science,Southampton,United Kingdom"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Sarah","family":"Kiden","sequence":"additional","affiliation":[{"name":"University of Southampton,Electronics and Computer Science,Southampton,United Kingdom"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Rui","family":"Chu","sequence":"additional","affiliation":[{"name":"Tufts University,Electrical and Computer Engineering,Medford,MA,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jennifer","family":"Williams","sequence":"additional","affiliation":[{"name":"University of Southampton,Electronics and Computer Science,Southampton,United Kingdom"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shuo","family":"Zhang","sequence":"additional","affiliation":[{"name":"Tufts University,Data Analytics,Medford,MA,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Alice Mello","family":"Da Fonseca","sequence":"additional","affiliation":[{"name":"Tufts University,Data Analytics,Medford,MA,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2012.2205597"},{"key":"ref2","article-title":"Deep speech 2: End-to-end speech recognition in english and mandarin","volume-title":"Proceedings of the 33rd International Conference on Machine Learning (ICML)","author":"Amodei"},{"key":"ref3","article-title":"Robust speech recognition via large-scale weak supervision","volume-title":"Proceedings of the 40th International Conference on Machine Learning (ICML)","author":"Radford"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2009.08.009"},{"key":"ref5","article-title":"Xvectors: Robust dnn embeddings for speaker recognition","author":"Snyder","year":"2018","journal-title":"ICASSP"},{"issue":"1","key":"ref6","first-page":"116","article-title":"Speech emotion recognition: Two decades in a nutshell","volume":"35","author":"Schuller","year":"2018","journal-title":"IEEE Signal Processing Magazine"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1159\/000515346"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-3015"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1016\/j.dsp.2017.10.011"},{"key":"ref10","article-title":"Interpretability techniques for speech models (tutorial materials)","author":"Lentz","year":"2025","journal-title":"Tutorial website \/ materials"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2025-288"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.34133\/icomputing.0074"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1016\/j.jfranklin.2023.11.038"},{"key":"ref14","first-page":"1878","article-title":"Unsupervised learning of disentangled and interpretable representations from sequential data","author":"Hsu","year":"2017","journal-title":"Advances in Neural Information Processing Systems (NeurIPS)"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1097"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/SLT.2018.8639650"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.aacl-main.46"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-1002"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10590-1_53"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.74"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.354"},{"key":"ref22","article-title":"Deep inside convolutional networks: Visualising image classification models and saliency maps","volume-title":"International Conference on Learning Representations (ICLR)","author":"Simonyan"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0130140"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N16-3020"},{"key":"ref25","article-title":"Axiomatic attribution for deep networks","volume-title":"Proceedings of the 34th International Conference on Machine Learning (ICML)","author":"Sundararajan"},{"key":"ref26","first-page":"1","article-title":"Explaining predictions of nonlinear classifiers in nlp","volume-title":"Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing (EMNLP) Workshops","author":"Arras"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2020\/746"},{"key":"ref28","doi-asserted-by":"crossref","first-page":"1947","DOI":"10.1038\/s41467-025-56779-w","article-title":"Cortical processing of discrete prosodic patterns in continuous speech","volume":"16","author":"Gnanateja","year":"2025","journal-title":"Nat Commun"},{"key":"ref29","first-page":"1764","article-title":"Towards end-to-end speech recognition with recurrent neural networks","volume-title":"Proceedings of the 31st International Conference on Machine Learning (ICML)","author":"Graves"},{"key":"ref30","article-title":"Deep speech: Scaling up end-to-end speech recognition","author":"Hannun","year":"2014","journal-title":"arXiv preprint arXiv:1412.5567"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2010.2064307"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1145\/1873951.1874246"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1016\/j.csl.2012.02.005"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9413543"},{"key":"ref35","article-title":"Hierarchical generative modeling for controllable speech synthesis","author":"Hsu","year":"2018","journal-title":"arXiv preprint arXiv:1810.07217"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.3321\/j.issn:0529-6579.2007.z1.029"},{"issue":"1","key":"ref37","doi-asserted-by":"crossref","first-page":"81","DOI":"10.1038\/s43586-022-00172-0","article-title":"Why black box machine learning should be avoided for highstakes decisions, in brief","volume":"2","author":"Rudin","year":"2022","journal-title":"Nat Rev Methods Primers"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10094635"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10445989"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/EMBC48229.2022.9871291"},{"key":"ref41","article-title":"Audiolime: Listenable explanations using source separation","author":"Haunschmid","year":"2020","journal-title":"arXiv preprint arXiv:2008.00582"},{"key":"ref42","article-title":"On the veracity of local, model-agnostic explanations in audio classification: Targeted investigations with adversarial examples","author":"Praher","year":"2021","journal-title":"arXiv preprint arXiv:2107.09045"},{"key":"ref43","article-title":"Reliable local explanations for machine listening","author":"Mishra","year":"2020","journal-title":"arXiv preprint arXiv:2007.07682"},{"key":"ref44","article-title":"Understanding global feature contributions with additive importance measures","author":"Covert","year":"2020","journal-title":"Advances in Neural Information Processing Systems (NeurIPS)"},{"key":"ref45","article-title":"Vocal tract length perturbation (vtlp) improves speech recognition","volume-title":"Proceedings of the International Conference on Machine Learning (ICML)","author":"Jaitly"},{"key":"ref46","article-title":"Towards better understanding of gradient-based attribution methods for deep neural networks","volume-title":"International Conference on Learning Representations (ICLR)","author":"Ancona"},{"key":"ref47","article-title":"Smoothgrad: Removing noise by adding noise","author":"Smilkov","year":"2017","journal-title":"arXiv preprint arXiv:1706.03825"},{"key":"ref48","article-title":"Striving for simplicity: The all convolutional net","volume-title":"International Conference on Learning Representations (ICLR)","author":"Springenberg"},{"key":"ref49","article-title":"Learning important features through propagating activation differences","volume-title":"Proceedings of the International Conference on Machine Learning (ICML)","author":"Shrikumar"},{"key":"ref50","article-title":"Interpreting and explaining deep neural networks for classification of audio signals","volume":"abs\/1807.03418","author":"Becker","year":"2018","journal-title":"ArXiv"},{"key":"ref51","article-title":"Xai-based comparison of input representations for audio event classification","author":"Frommholz","year":"2023"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2650"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2016.7472621"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1145\/1143844.1143891"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2017.2763455"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/icassp.2018.8462682"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/ISSPIT.2018.8642691"},{"key":"ref58","article-title":"Visualizing automatic speech recognition","author":"Markert","year":"2021","journal-title":"Speech Processing for Safety-Critical Transportation (SPSC)"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-993"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-926"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1037\/0022-3514.70.3.614"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1037\/0033-2909.129.5.770"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1121\/1.2208451"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1016\/j.jvoice.2010.04.002"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1016\/j.protcy.2013.12.124"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1186\/s13636-024-00329-7"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.7551\/mitpress\/1072.001.0001"},{"key":"ref68","article-title":"The Phonetic Description of Voice Quality","author":"Laver","year":"1980"},{"key":"ref69","article-title":"Explainability for speech models: On the challenges of xai for speech","volume-title":"Proceedings of the 10th Italian Conference on Computational Linguistics (CLiC-it). CEUR Workshop Proceedings","author":"Fucci"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1017\/CBO9781139166621"},{"key":"ref71","article-title":"Towards a rigorous science of interpretable machine learning","author":"Doshi-Velez","year":"2017","journal-title":"arXiv preprint arXiv:1702.08608"}],"event":{"name":"2026 International Conference on Semantic Computing (ICSC)","location":"Laguna Hills, CA, USA","start":{"date-parts":[[2026,2,2]]},"end":{"date-parts":[[2026,2,4]]}},"container-title":["2026 International Conference on Semantic Computing (ICSC)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11484077\/11486285\/11486457.pdf?arnumber=11486457","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,25]],"date-time":"2026-04-25T04:33:35Z","timestamp":1777091615000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11486457\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,2,2]]},"references-count":71,"URL":"https:\/\/doi.org\/10.1109\/icsc67292.2026.00053","relation":{},"subject":[],"published":{"date-parts":[[2026,2,2]]}}}