{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,7,2]],"date-time":"2025-07-02T04:09:08Z","timestamp":1751429348702,"version":"3.41.0"},"reference-count":38,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2025,7,1]],"date-time":"2025-07-01T00:00:00Z","timestamp":1751328000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0"},{"start":{"date-parts":[[2025,7,1]],"date-time":"2025-07-01T00:00:00Z","timestamp":1751328000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62276076"],"award-info":[{"award-number":["62276076"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62176102"],"award-info":[{"award-number":["62176102"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["J AUDIO SPEECH MUSIC PROC."],"DOI":"10.1186\/s13636-025-00411-8","type":"journal-article","created":{"date-parts":[[2025,7,1]],"date-time":"2025-07-01T08:54:01Z","timestamp":1751360041000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Head information bottleneck (HIB): leveraging information bottleneck for efficient transformer head attribution and pruning"],"prefix":"10.1186","volume":"2025","author":[{"given":"Yukun","family":"Qian","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xuyi","family":"Zhuang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Mingjiang","family":"Wang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2025,7,1]]},"reference":[{"key":"411_CR1","first-page":"12449","volume":"33","author":"A Baevski","year":"2020","unstructured":"A. Baevski, Y. Zhou, A. Mohamed, M. Auli, wav2vec 2.0: A framework for self-supervised learning of speech representations. Adv. Neural Inf. Process. Syst. 33, 12449\u201312460 (2020)","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"411_CR2","doi-asserted-by":"publisher","first-page":"3451","DOI":"10.1109\/TASLP.2021.3122291","volume":"29","author":"WN Hsu","year":"2021","unstructured":"W.N. Hsu, B. Bolte, Y.H.H. Tsai, K. Lakhotia, R. Salakhutdinov, A. Mohamed, Hubert: Self-supervised speech representation learning by masked prediction of hidden units. IEEE\/ACM Trans. Audio Speech Lang. Process. 29, 3451\u20133460 (2021)","journal-title":"IEEE\/ACM Trans. Audio Speech Lang. Process."},{"issue":"6","key":"411_CR3","doi-asserted-by":"publisher","first-page":"1505","DOI":"10.1109\/JSTSP.2022.3188113","volume":"16","author":"S Chen","year":"2022","unstructured":"S. Chen, C. Wang, Z. Chen, Y. Wu, S. Liu, Z. Chen, J. Li, N. Kanda, T. Yoshioka, X. Xiao et al., Wavlm: Large-scale self-supervised pre-training for full stack speech processing. IEEE J. Sel. Top. Signal Process. 16(6), 1505\u20131518 (2022)","journal-title":"IEEE J. Sel. Top. Signal Process."},{"key":"411_CR4","doi-asserted-by":"crossref","unstructured":"S.w. Yang, A.T. Liu, H.y. Lee, in Proceedings of the International Speech Communication Association (Interspeech), Understanding self-attention of self-supervised audio transformers (ISCA, Shanghai, 2020), pp. 785-3789","DOI":"10.21437\/Interspeech.2020-2231"},{"key":"411_CR5","unstructured":"K. Shim, J. Choi, W. Sung, in Proceedings of the International Conference on Learning Representations (ICLR), Understanding the role of self attention for efficient speech recognition (ICLR, Virtual, 2022), pp. 1-19"},{"key":"411_CR6","first-page":"15834","volume":"33","author":"T Chen","year":"2020","unstructured":"T. Chen, J. Frankle, S. Chang, S. Liu, Y. Zhang, Z. Wang, M. Carbin, The lottery ticket hypothesis for pre-trained bert networks. Adv. Neural Inf. Process. Syst. 33, 15834\u201315846 (2020)","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"411_CR7","first-page":"9782","volume":"33","author":"L Hou","year":"2020","unstructured":"L. Hou, Z. Huang, L. Shang, X. Jiang, X. Chen, Q. Liu, Dynabert: Dynamic bert with adaptive width and depth. Adv. Neural Inf. Process. Syst. 33, 9782\u20139793 (2020)","journal-title":"Adv. Neural Inf. Process. Syst."},{"issue":"1","key":"411_CR8","doi-asserted-by":"publisher","first-page":"45","DOI":"10.1007\/s12559-023-10179-8","volume":"16","author":"V Hassija","year":"2024","unstructured":"V. Hassija, V. Chamola, A. Mahapatra, A. Singal, D. Goel, K. Huang, S. Scardapane, I. Spinelli, M. Mahmud, A. Hussain, Interpreting black-box models: a review on explainable artificial intelligence. Cogn. Comput. 16(1), 45\u201374 (2024)","journal-title":"Cogn. Comput."},{"issue":"1","key":"411_CR9","doi-asserted-by":"publisher","first-page":"68","DOI":"10.1145\/3359786","volume":"63","author":"M Du","year":"2019","unstructured":"M. Du, N. Liu, X. Hu, Techniques for interpretable machine learning. Commun. ACM 63(1), 68\u201377 (2019)","journal-title":"Commun. ACM"},{"key":"411_CR10","doi-asserted-by":"crossref","unstructured":"A. Pasad, J.C. Chou, K. Livescu, in Proceedings of the 2021 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU). Layer-wise analysis of a self-supervised speech representation model (IEEE, Virtual, 2021), pp. 914\u2013921","DOI":"10.1109\/ASRU51503.2021.9688093"},{"key":"411_CR11","doi-asserted-by":"publisher","unstructured":"S. Wen\u00a0Yang, P.H. Chi, Y.S. Chuang, C.I.J. Lai, K. Lakhotia, Y.Y. Lin, A.T. Liu, J. Shi, X. Chang, G.T. Lin, T.H. Huang, W.C. Tseng, K. Tik\u00a0Lee, D.R. Liu, Z. Huang, S. Dong, S.W. Li, S. Watanabe, A. Mohamed, H. Yi\u00a0Lee, in Interspeech 2021. Superb: Speech processing universal performance benchmark (2021), pp. 1194\u20131198. https:\/\/doi.org\/10.21437\/Interspeech.2021-1775","DOI":"10.21437\/Interspeech.2021-1775"},{"key":"411_CR12","doi-asserted-by":"crossref","unstructured":"R.R. Selvaraju, M. Cogswell, A. Das, R. Vedantam, D. Parikh, D. Batra, in Proceedings of the IEEE International Conference on Computer Vision (ICCV), Grad-cam: Visual explanations from deep networks via gradient-based localization (IEEE, Venice, 2017), pp. 618\u2013626","DOI":"10.1109\/ICCV.2017.74"},{"key":"411_CR13","doi-asserted-by":"crossref","unstructured":"M.D. Zeiler, R. Fergus, in Proceedings of the European Conference on Computer Vision (ECCV). Visualizing and understanding convolutional networks (Springer, Zurich, 2014), pp. 818\u2013833","DOI":"10.1007\/978-3-319-10590-1_53"},{"issue":"7","key":"411_CR14","doi-asserted-by":"publisher","first-page":"4625","DOI":"10.1109\/TPAMI.2024.3358410","volume":"46","author":"H Deng","year":"2024","unstructured":"H. Deng, N. Zou, M. Du, W. Chen, G. Feng, Z. Yang, Z. Li, Q. Zhang, Unifying fourteen post-hoc attribution methods with taylor interactions. IEEE Trans. Pattern. Anal. Mach. Intell. 46(7), 4625\u20134640 (2024). https:\/\/doi.org\/10.1109\/TPAMI.2024.3358410","journal-title":"IEEE Trans. Pattern. Anal. Mach. Intell."},{"key":"411_CR15","doi-asserted-by":"crossref","unstructured":"A. Zhmoginov, I. Fischer, M. Sandler, in Proceedings of the European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases (ECML PKDD). Information-bottleneck approach to salient region discovery (Springer, Ghent, 2021), pp. 531\u2013546","DOI":"10.1007\/978-3-030-67664-3_32"},{"issue":"1","key":"411_CR16","doi-asserted-by":"publisher","first-page":"976","DOI":"10.1109\/TVCG.2021.3114683","volume":"28","author":"T Jaunet","year":"2021","unstructured":"T. Jaunet, C. Kervadec, R. Vuillemot, G. Antipov, M. Baccouche, C. Wolf, Visqa: X-raying vision and language reasoning in transformers. IEEE Trans. Vis. Comput. Graph. 28(1), 976\u2013986 (2021)","journal-title":"IEEE Trans. Vis. Comput. Graph."},{"key":"411_CR17","doi-asserted-by":"crossref","unstructured":"C. Park, I. Na, Y. Jo, S. Shin, J. Yoo, B.C. Kwon, J. Zhao, H. Noh, Y. Lee, J. Choo, in  Proceedings of the 2019 IEEE Visualization Conference (VIS). Sanvis: Visual analytics for understanding self-attention networks (IEEE, Vancouver, 2019), pp. 146\u2013150","DOI":"10.1109\/VISUAL.2019.8933677"},{"key":"411_CR18","doi-asserted-by":"publisher","unstructured":"B. Hoover, H. Strobelt, S. Gehrmann, in Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics: System Demonstrations, ed. by A. Celikyilmaz, T.H. Wen. exBERT: A Visual Analysis Tool to Explore Learned Representations in Transformer Models (Association for Computational Linguistics, Online, 2020), pp. 187\u2013196. https:\/\/doi.org\/10.18653\/v1\/2020.acl-demos.22","DOI":"10.18653\/v1\/2020.acl-demos.22"},{"issue":"01","key":"411_CR19","doi-asserted-by":"publisher","first-page":"262","DOI":"10.1109\/TVCG.2023.3327163","volume":"30","author":"C Yeh","year":"2024","unstructured":"C. Yeh, Y. Chen, A. Wu, C. Chen, F. Viegas, M. Wattenberg, AttentionViz: A Global View of Transformer Attention. IEEE Trans. Vis. Comput. Graph. 30(01), 262\u2013272 (2024). https:\/\/doi.org\/10.1109\/TVCG.2023.3327163","journal-title":"IEEE Trans. Vis. Comput. Graph."},{"issue":"2","key":"411_CR20","doi-asserted-by":"publisher","first-page":"1160","DOI":"10.1109\/TVCG.2020.3028976","volume":"27","author":"JF DeRose","year":"2020","unstructured":"J.F. DeRose, J. Wang, M. Berger, Attention flows: Analyzing and comparing attention mechanisms in language models. IEEE Trans. Vis. Comput. Graph. 27(2), 1160\u20131170 (2020)","journal-title":"IEEE Trans. Vis. Comput. Graph."},{"key":"411_CR21","doi-asserted-by":"crossref","unstructured":"O. Barkan, E. Hauon, A. Caciularu, O. Katz, I. Malkiel, O. Armstrong, N. Koenigstein, in Proceedings of the 30th ACM International Conference on Information & Knowledge Management CIKM), Grad-sam: Explaining transformers via gradient self-attention maps (ACM, Queensland, 2021), pp. 2882\u20132887","DOI":"10.1145\/3459637.3482126"},{"key":"411_CR22","doi-asserted-by":"crossref","unstructured":"Y. Hao, L. Dong, F. Wei, K. Xu, in Proceedings of the AAAI Conference on Artificial Intelligence (AAAI), Self-attention attribution: Interpreting information interactions inside transformer (AAAI, Virtual, 2021), pp. 12963\u201312971","DOI":"10.1609\/aaai.v35i14.17533"},{"key":"411_CR23","doi-asserted-by":"crossref","unstructured":"Y. Peng, K. Kim, F. Wu, P. Sridhar, S. Watanabe, in ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), Structured pruning of self-supervised pre-trained models for speech recognition and understanding (IEEE, Rhodes Island, 2023), pp. 1\u20135","DOI":"10.1109\/ICASSP49357.2023.10095335"},{"key":"411_CR24","first-page":"21256","volume":"34","author":"CIJ Lai","year":"2021","unstructured":"C.I.J. Lai, Y. Zhang, A.H. Liu, S. Chang, Y.L. Liao, Y.S. Chuang, K. Qian, S. Khurana, D. Cox, J. Glass, Parp: Prune, adjust and re-prune for self-supervised speech recognition. Adv. Neural Inf. Process. Syst. 34, 21256\u201321272 (2021)","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"411_CR25","unstructured":"A. Baevski, W.N. Hsu, Q. Xu, A. Babu, J. Gu, M. Auli, in Proceedings of the International Conference on Machine Learning (ICML). Data2vec: A general framework for self-supervised learning in speech, vision and language (ACM, Baltimore, 2022), pp. 1298\u20131312"},{"issue":"6","key":"411_CR26","doi-asserted-by":"publisher","first-page":"1179","DOI":"10.1109\/JSTSP.2022.3207050","volume":"16","author":"A Mohamed","year":"2022","unstructured":"A. Mohamed, H.Y. Lee, L. Borgholt, J.D. Havtorn, J. Edin, C. Igel, K. Kirchhoff, S.W. Li, K. Livescu, L. Maal\u00f8e, T.N. Sainath, S. Watanabe, Self-supervised speech representation learning: A review. IEEE J. Sel. Top. Signal Process. 16(6), 1179\u20131210 (2022). https:\/\/doi.org\/10.1109\/JSTSP.2022.3207050","journal-title":"IEEE J. Sel. Top. Signal Process."},{"key":"411_CR27","unstructured":"A. Vaswani, N. Shazeer, N. Parmar et al., in Proceedings of the Neural Information Processing Systems (NeurIPS), Attention is all you need. (MIT Press, Long Beach, 2017), pp. 6000 - 6010"},{"key":"411_CR28","doi-asserted-by":"crossref","unstructured":"A. Gulati, J. Qin, C.C. Chiu et al., in Proceedings of the International Speech Communication Association (Interspeech), Conformer: Convolution-augmented transformer for speech recognition (ISCA, Shanghai, 2020), pp.5036-5040","DOI":"10.21437\/Interspeech.2020-3015"},{"key":"411_CR29","doi-asserted-by":"publisher","unstructured":"N. Tishby, N. Zaslavsky, in 2015 IEEE Information Theory Workshop (ITW). Deep learning and the information bottleneck principle (2015), pp. 1\u20135. https:\/\/doi.org\/10.1109\/ITW.2015.7133169","DOI":"10.1109\/ITW.2015.7133169"},{"key":"411_CR30","unstructured":"G. Klambauer, T. Unterthiner, A. Mayr, S. Hochreiter, in Proceedings of the Neural Information Processing Systems (NeurIPS), Self-normalizing neural networks. (MIT Press, Long Beach, 2017), pp. 972-981"},{"key":"411_CR31","unstructured":"K. Schulz, L. Sixt, F. Tombari, T. Landgraf, in Proceedings of the International Conference on Learning Representations (ICLR). Restricting the flow: Information bottlenecks for attribution (ICLR, Virtual, 2020), pp. 1-18"},{"key":"411_CR32","unstructured":"A.A. Alemi, I. Fischer, J.V. Dillon, K. Murphy, in Proceedings of the International Conference on Learning Representations (ICLR). Deep variational information bottleneck (ICLR, Toulon, 2017), pp. 1-19"},{"key":"411_CR33","unstructured":"K.P. Murphy, Probabilistic machine learning: Advanced topics (MIT Press, 2023)"},{"key":"411_CR34","doi-asserted-by":"crossref","unstructured":"V. Panayotov, G. Chen, D. Povey, S. Khudanpur, in Proceedings of the 2015 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). Librispeech: An asr corpus based on public domain audio books (IEEE, Brisbane, 2015), pp. 5206\u20135210","DOI":"10.1109\/ICASSP.2015.7178964"},{"key":"411_CR35","doi-asserted-by":"crossref","unstructured":"A. Nagrani, J.S. Chung, A. Zisserman, in Proceedings of the International Speech Communication Association (Interspeech), Voxceleb: A large-scale speaker identification dataset (ISCA, Stockholm, 2017), pp. 2616-2620","DOI":"10.21437\/Interspeech.2017-950"},{"key":"411_CR36","unstructured":"P. Warden, Speech Commands: A Dataset for Limited-Vocabulary Speech Recognition.\u00a0ArXiv\u00a0e-prints\u00a0(2018).\u00a01804.03209"},{"key":"411_CR37","doi-asserted-by":"crossref","unstructured":"L. Lugosch, M. Ravanelli, P. Ignoto, V.S. Tomar, Y. Bengio, in Proceedings of  the International Speech Communication Association (Interspeech). Speech model pretraining for end-to-end spoken language understanding (ISCA, Graz, 2019), pp. 814\u2013818","DOI":"10.21437\/Interspeech.2019-2396"},{"key":"411_CR38","unstructured":"P. Michel, O. Levy, G. Neubig, in Proceedings of the Neural Information Processing Systems (NeurIPS), Are sixteen heads really better than one? (MIT Press, Vancouver, 2019), pp. 14037-14047"}],"container-title":["EURASIP Journal on Audio, Speech, and Music Processing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1186\/s13636-025-00411-8.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1186\/s13636-025-00411-8\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1186\/s13636-025-00411-8.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,7,1]],"date-time":"2025-07-01T08:54:16Z","timestamp":1751360056000},"score":1,"resource":{"primary":{"URL":"https:\/\/asmp-eurasipjournals.springeropen.com\/articles\/10.1186\/s13636-025-00411-8"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,7,1]]},"references-count":38,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2025,12]]}},"alternative-id":["411"],"URL":"https:\/\/doi.org\/10.1186\/s13636-025-00411-8","relation":{},"ISSN":["1687-4722"],"issn-type":[{"value":"1687-4722","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,7,1]]},"assertion":[{"value":"8 January 2025","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"11 June 2025","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"1 July 2025","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"The authors declare that they have no competing interests.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Competing interests"}}],"article-number":"25"}}