{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,2]],"date-time":"2026-06-02T16:33:56Z","timestamp":1780418036012,"version":"3.54.1"},"publisher-location":"New York, NY, USA","reference-count":52,"publisher":"ACM","funder":[{"name":"National Center of Science (Poland)","award":["2023\/50\/E\/ST6\/00169"],"award-info":[{"award-number":["2023\/50\/E\/ST6\/00169"]}]},{"name":"Department of Artificial Intelligence, Wroc\u0142aw University of Science and Technology"},{"name":"National Center of Science (Poland)","award":["2023\/50\/E\/ST6\/00068"],"award-info":[{"award-number":["2023\/50\/E\/ST6\/00068"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2025,11,10]]},"DOI":"10.1145\/3746252.3761405","type":"proceedings-article","created":{"date-parts":[[2025,11,8]],"date-time":"2025-11-08T00:52:37Z","timestamp":1762563157000},"page":"2063-2073","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":2,"title":["As Good as It KAN Get: High-Fidelity Audio Representation"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0008-7695-7905","authenticated-orcid":false,"given":"Patryk","family":"Marsza\u0142ek","sequence":"first","affiliation":[{"name":"Jagiellonian University, Krakow, Poland"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0009-9637-6128","authenticated-orcid":false,"given":"Maciej","family":"Rut","sequence":"additional","affiliation":[{"name":"Jagiellonian University, Krakow, Poland"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2025-0547","authenticated-orcid":false,"given":"Piotr","family":"Kawa","sequence":"additional","affiliation":[{"name":"Wroclaw University of Science and Technology, Wroclaw, Poland"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0097-5521","authenticated-orcid":false,"given":"Przemys\u0142aw","family":"Spurek","sequence":"additional","affiliation":[{"name":"Jagiellonian University, Krakow, Poland and IDEAS Research Institute, Warszawa, Poland"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0266-5802","authenticated-orcid":false,"given":"Piotr","family":"Syga","sequence":"additional","affiliation":[{"name":"Wroclaw University of Science and Technology, Wroclaw, Poland"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2025,11,10]]},"reference":[{"key":"e_1_3_2_1_1_1","volume-title":"wav2vec 2.0: A framework for self-supervised learning of speech representations. Advances in neural information processing systems","author":"Baevski Alexei","year":"2020","unstructured":"Alexei Baevski, Yuhao Zhou, Abdelrahman Mohamed, and Michael Auli. 2020. wav2vec 2.0: A framework for self-supervised learning of speech representations. Advances in neural information processing systems, Vol. 33 (2020), 12449-12460."},{"key":"e_1_3_2_1_2_1","volume-title":"HyperPlanes: Hypernetwork Approach to Rapid NeRF Adaptation. arXiv preprint arXiv:2402.01524","author":"Batorski Pawel","year":"2024","unstructured":"Pawel Batorski, Dawid Malarz, Marcin Przewiezlikowski, Marcin Mazur, S\u0142awomir Tadeja, and Przemys\u0142aw Spurek. 2024. HyperPlanes: Hypernetwork Approach to Rapid NeRF Adaptation. arXiv preprint arXiv:2402.01524 (2024)."},{"key":"e_1_3_2_1_3_1","volume-title":"International Conference on Learning Representations.","author":"Chen Wei-Yu","year":"2019","unstructured":"Wei-Yu Chen, Yen-Cheng Liu, Zsolt Kira, Yu-Chiang Frank Wang, and Jia-Bin Huang. 2019. A Closer Look at Few-shot Classification. In International Conference on Learning Representations."},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00209"},{"key":"e_1_3_2_1_5_1","volume-title":"Qwen-audio: Advancing universal audio understanding via unified large-scale audio-language models. arXiv preprint arXiv:2311.07919","author":"Chu Yunfei","year":"2023","unstructured":"Yunfei Chu, Jin Xu, Xiaohuan Zhou, Qian Yang, Shiliang Zhang, Zhijie Yan, Chang Zhou, and Jingren Zhou. 2023. Qwen-audio: Advancing universal audio understanding via unified large-scale audio-language models. arXiv preprint arXiv:2311.07919 (2023)."},{"key":"e_1_3_2_1_6_1","volume-title":"WhisperSpeech GitHub repository. https:\/\/github.com\/collabora\/WhisperSpeech [Online","year":"2024","unstructured":"Collabora. 2024. WhisperSpeech GitHub repository. https:\/\/github.com\/collabora\/WhisperSpeech [Online; accessed 3. Mar. 2024]."},{"key":"e_1_3_2_1_7_1","volume-title":"High Fidelity Neural Audio Compression. Transactions on Machine Learning Research","author":"D\u00e9fossez Alexandre","year":"2023","unstructured":"Alexandre D\u00e9fossez, Jade Copet, Gabriel Synnaeve, and Yossi Adi. 2023. High Fidelity Neural Audio Compression. Transactions on Machine Learning Research (2023)."},{"key":"e_1_3_2_1_8_1","volume-title":"International conference on machine learning. PMLR, 1126-1135","author":"Finn Chelsea","year":"2017","unstructured":"Chelsea Finn, Pieter Abbeel, and Sergey Levine. 2017. Model-agnostic meta-learning for fast adaptation of deep networks. In International conference on machine learning. PMLR, 1126-1135."},{"key":"e_1_3_2_1_9_1","unstructured":"Ali Gorji Andisheh Amrollahi and Andreas Krause. 2023. A Scalable Walsh-Hadamard Regularizer to Overcome the Low-degree Spectral Bias of Neural Networks. arXiv:2305.09779 [cs.LG] https:\/\/arxiv.org\/abs\/2305.09779"},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU57964.2023.10389651"},{"key":"e_1_3_2_1_11_1","volume-title":"arXiv preprint arXiv:1609.09106","author":"Ha David","year":"2016","unstructured":"David Ha, Andrew Dai, and Quoc V Le. 2016. Hypernetworks. arXiv preprint arXiv:1609.09106 (2016)."},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1016\/0021-9045(76)90040-X"},{"key":"e_1_3_2_1_13_1","volume-title":"Kushal Lakhotia","author":"Hsu Wei-Ning","year":"2021","unstructured":"Wei-Ning Hsu, Benjamin Bolte, Yao-Hung Hubert Tsai, Kushal Lakhotia, Ruslan Salakhutdinov, and Abdelrahman Mohamed. 2021. Hubert: Self-supervised speech representation learning by masked prediction of hidden units. IEEE\/ACM transactions on audio, speech, and language processing, Vol. 29 (2021), 3451-3460."},{"key":"e_1_3_2_1_14_1","volume-title":"LoRA: Low-Rank Adaptation of Large Language Models. In International Conference on Learning Representations. https:\/\/openreview.net\/forum?id=nZeVKeeFYf9","author":"Hu Edward J","year":"2022","unstructured":"Edward J Hu, Yelong Shen, Phillip Wallis, Zeyuan Allen-Zhu, Yuanzhi Li, Shean Wang, Lu Wang, and Weizhu Chen. 2022. LoRA: Low-Rank Adaptation of Large Language Models. In International Conference on Learning Representations. https:\/\/openreview.net\/forum?id=nZeVKeeFYf9"},{"key":"e_1_3_2_1_15_1","unstructured":"Keith Ito and Linda Johnson. 2017. The LJ Speech Dataset. https:\/\/keithito.com\/LJ-Speech-Dataset\/."},{"key":"e_1_3_2_1_16_1","unstructured":"Adam Kania Marko Mihajlovic Sergey Prokudin Jacek Tabor and Przemyslaw Spurek. 2024. FreSh: Frequency Shifting for Accelerated Neural Representation Learning. arXiv:2410.05050 [cs.LG] https:\/\/arxiv.org\/abs\/2410.05050"},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2023-1537"},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-30493-5_48"},{"key":"e_1_3_2_1_19_1","volume-title":"Siamese SIREN: Audio Compression with Implicit Neural Representations. In ICML 2023 Workshop Neural Compression: From Information Theory to Applications. https:\/\/openreview.net\/forum?id=AgkMFYcOmM","author":"Lanzend\u00f6rfer Luca A","year":"2023","unstructured":"Luca A Lanzend\u00f6rfer and Roger Wattenhofer. 2023. Siamese SIREN: Audio Compression with Implicit Neural Representations. In ICML 2023 Workshop Neural Compression: From Information Theory to Applications. https:\/\/openreview.net\/forum?id=AgkMFYcOmM"},{"key":"e_1_3_2_1_20_1","volume-title":"Kan: Kolmogorov-arnold networks. arXiv preprint arXiv:2404.19756","author":"Liu Ziming","year":"2024","unstructured":"Ziming Liu, Yixuan Wang, Sachin Vaidya, Fabian Ruehle, James Halverson, Marin Solja\u010di\u0107, Thomas Y Hou, and Max Tegmark. 2024a. Kan: Kolmogorov-arnold networks. arXiv preprint arXiv:2404.19756 (2024)."},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00262"},{"key":"e_1_3_2_1_22_1","unstructured":"Ilya Loshchilov and Frank Hutter. 2019. Decoupled Weight Decay Regularization. arXiv:1711.05101 [cs.LG] https:\/\/arxiv.org\/abs\/1711.05101"},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9413711"},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"crossref","unstructured":"Ben Mildenhall Pratul P. Srinivasan Matthew Tancik Jonathan T. Barron Ravi Ramamoorthi and Ren Ng. 2020. NeRF: Representing Scenes as Neural Radiance Fields for View Synthesis. In ECCV.","DOI":"10.1007\/978-3-030-58452-8_24"},{"key":"e_1_3_2_1_25_1","volume-title":"Instant neural graphics primitives with a multiresolution hash encoding. ACM transactions on graphics (TOG)","author":"M\u00fcller Thomas","year":"2022","unstructured":"Thomas M\u00fcller, Alex Evans, Christoph Schied, and Alexander Keller. 2022. Instant neural graphics primitives with a multiresolution hash encoding. ACM transactions on graphics (TOG), Vol. 41, 4 (2022), 1-15."},{"key":"e_1_3_2_1_26_1","unstructured":"Patrick O'Reilly Andreas Bugler Keshav Bhandari Max Morrison and Bryan Pardo. 2022. VoiceBlock: Privacy through Real-Time Adversarial Attacks with Audio-to-Audio Models. In Neural Information Processing Systems."},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178964"},{"key":"e_1_3_2_1_28_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2024.128179"},{"key":"e_1_3_2_1_29_1","volume-title":"International conference on machine learning. PMLR, 28492-28518","author":"Radford Alec","year":"2023","unstructured":"Alec Radford, Jong Wook Kim, Tao Xu, Greg Brockman, Christine McLeavey, and Ilya Sutskever. 2023. Robust speech recognition via large-scale weak supervision. In International conference on machine learning. PMLR, 28492-28518."},{"key":"e_1_3_2_1_30_1","unstructured":"Nasim Rahaman Aristide Baratin Devansh Arpit Felix Draxler Min Lin Fred A. Hamprecht Yoshua Bengio and Aaron Courville. 2019. On the Spectral Bias of Neural Networks. arXiv:1806.08734 [stat.ML] https:\/\/arxiv.org\/abs\/1806.08734"},{"key":"e_1_3_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2001.941023"},{"key":"e_1_3_2_1_32_1","doi-asserted-by":"publisher","DOI":"10.1145\/2647868.2655045"},{"key":"e_1_3_2_1_33_1","volume-title":"Baraniuk","author":"Saragadam Vishwanath","year":"2023","unstructured":"Vishwanath Saragadam, Daniel LeJeune, Jasper Tan, Guha Balakrishnan, Ashok Veeraraghavan, and Richard G. Baraniuk. 2023. WIRE: Wavelet Implicit Neural Representations. 18507-18516 pages. https:\/\/openaccess.thecvf.com\/content\/CVPR2023\/html\/Saragadam_WIRE_Wavelet_Implicit_Neural_Representations_CVPR_2023_paper.html [Online; accessed 3. Mar. 2024]."},{"key":"e_1_3_2_1_34_1","volume-title":"Stochastic maximum likelihood optimization via hypernetworks. arXiv preprint arXiv:1712.01141","author":"Sheikh Abdul-Saboor","year":"2017","unstructured":"Abdul-Saboor Sheikh, Kashif Rasul, Andreas Merentitis, and Urs Bergmann. 2017. Stochastic maximum likelihood optimization via hypernetworks. arXiv preprint arXiv:1712.01141 (2017)."},{"key":"e_1_3_2_1_35_1","first-page":"7462","volume-title":"Lin (Eds.)","volume":"33","author":"Sitzmann Vincent","year":"2020","unstructured":"Vincent Sitzmann, Julien Martel, Alexander Bergman, David Lindell, and Gordon Wetzstein. 2020. Implicit Neural Representations with Periodic Activation Functions. In Advances in Neural Information Processing Systems, H. Larochelle, M. Ranzato, R. Hadsell, M.F. Balcan, and H. Lin (Eds.), Vol. 33. Curran Associates, Inc., 7462-7473. https:\/\/proceedings.neurips.cc\/paper_files\/paper\/2020\/file\/53c04118df112c13a8c34b38343b9c10-Paper.pdf"},{"key":"e_1_3_2_1_36_1","volume-title":"SNAC: Multi-Scale Neural Audio Codec. In Audio Imagination: NeurIPS 2024 Workshop AI-Driven Speech, Music, and Sound Generation.","author":"Siuzdak Hubert","year":"2024","unstructured":"Hubert Siuzdak, Florian Gr\u00f6tschla, and Luca A Lanzend\u00f6rfer. 2024. SNAC: Multi-Scale Neural Audio Codec. In Audio Imagination: NeurIPS 2024 Workshop AI-Driven Speech, Music, and Sound Generation."},{"key":"e_1_3_2_1_37_1","volume-title":"Smith and Nicholay Topin","author":"Leslie","year":"2018","unstructured":"Leslie N. Smith and Nicholay Topin. 2018a. Super-Convergence: Very Fast Training of Neural Networks Using Large Learning Rates. arXiv:1708.07120 [cs.LG] https:\/\/arxiv.org\/abs\/1708.07120"},{"key":"e_1_3_2_1_38_1","volume-title":"Smith and Nicholay Topin","author":"Leslie","year":"2018","unstructured":"Leslie N. Smith and Nicholay Topin. 2018b. Super-Convergence: Very Fast Training of Neural Networks Using Large Learning Rates. arXiv:1708.07120 [cs.LG] https:\/\/arxiv.org\/abs\/1708.07120"},{"key":"e_1_3_2_1_39_1","volume-title":"Proceedings of the 37th International Conference on Machine Learning. 9099-9108","author":"Spurek Przemys\u0142aw","year":"2020","unstructured":"Przemys\u0142aw Spurek, Sebastian Winczowski, Jacek Tabor, Maciej Zamorski, Maciej Zieba, and Tomasz Trzci'nski. 2020. Hypernetwork approach to generating point clouds. In Proceedings of the 37th International Conference on Machine Learning. 9099-9108."},{"key":"e_1_3_2_1_40_1","volume-title":"Luc Van Gool, and Federico Tombari","author":"Str\u00fcmpler Yannick","year":"2022","unstructured":"Yannick Str\u00fcmpler, Janis Postels, Ren Yang, Luc Van Gool, and Federico Tombari. 2022. Implicit Neural Representations for Image Compression. In ECCV."},{"key":"e_1_3_2_1_41_1","first-page":"8144","volume-title":"Oh (Eds.)","volume":"35","author":"Su Kun","year":"2022","unstructured":"Kun Su, Mingfei Chen, and Eli Shlizerman. 2022. INRAS: Implicit Neural Representation for Audio Scenes. In Advances in Neural Information Processing Systems, S. Koyejo, S. Mohamed, A. Agarwal, D. Belgrave, K. Cho, and A. Oh (Eds.), Vol. 35. Curran Associates, Inc., 8144-8158."},{"key":"e_1_3_2_1_42_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-43421-1_39"},{"key":"e_1_3_2_1_43_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2010.5495701"},{"key":"e_1_3_2_1_44_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00287"},{"key":"e_1_3_2_1_45_1","first-page":"7537","volume-title":"Lin (Eds.)","volume":"33","author":"Tancik Matthew","year":"2020","unstructured":"Matthew Tancik, Pratul Srinivasan, Ben Mildenhall, Sara Fridovich-Keil, Nithin Raghavan, Utkarsh Singhal, Ravi Ramamoorthi, Jonathan Barron, and Ren Ng. 2020. Fourier Features Let Networks Learn High Frequency Functions in Low Dimensional Domains. In Advances in Neural Information Processing Systems, H. Larochelle, M. Ranzato, R. Hadsell, M.F. Balcan, and H. Lin (Eds.), Vol. 33. Curran Associates, Inc., 7537-7547. https:\/\/proceedings.neurips.cc\/paper_files\/paper\/2020\/file\/55053683268957697aa39fba6f231c68-Paper.pdf"},{"key":"e_1_3_2_1_46_1","doi-asserted-by":"publisher","DOI":"10.1109\/TSA.2002.800560"},{"key":"e_1_3_2_1_47_1","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2016-159"},{"key":"e_1_3_2_1_48_1","volume-title":"Advances in Neural Information Processing Systems","author":"Vaswani Ashish","year":"2017","unstructured":"Ashish Vaswani, Noam Shazeer, Niki Parmar, Jakob Uszkoreit, Llion Jones, Aidan N Gomez, Lukasz Kaiser, and Illia Polosukhin. 2017. Attention is All you Need. In Advances in Neural Information Processing Systems, I. Guyon, U. Von Luxburg, S. Bengio, H. Wallach, R. Fergus, S. Vishwanathan, and R. Garnett (Eds.), Vol. 30. Curran Associates, Inc. https:\/\/proceedings.neurips.cc\/paper_files\/paper\/2017\/file\/3f5ee243547dee91fbd053c1c4a845aa-Paper.pdf"},{"key":"e_1_3_2_1_49_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICSDA.2013.6709856"},{"key":"e_1_3_2_1_50_1","volume-title":"Generalizing from a few examples: A survey on few-shot learning. ACM computing surveys (csur)","author":"Wang Yaqing","year":"2020","unstructured":"Yaqing Wang, Quanming Yao, James T Kwok, and Lionel M Ni. 2020. Generalizing from a few examples: A survey on few-shot learning. ACM computing surveys (csur), Vol. 53, 3 (2020), 1-34."},{"key":"e_1_3_2_1_51_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053795"},{"key":"e_1_3_2_1_52_1","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3129994"}],"event":{"name":"CIKM '25: The 34th ACM International Conference on Information and Knowledge Management","location":"Seoul Republic of Korea","acronym":"CIKM '25","sponsor":["SIGIR ACM Special Interest Group on Information Retrieval","SIGWEB ACM Special Interest Group on Hypertext, Hypermedia, and Web"]},"container-title":["Proceedings of the 34th ACM International Conference on Information and Knowledge Management"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3746252.3761405","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,12]],"date-time":"2025-12-12T02:25:42Z","timestamp":1765506342000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3746252.3761405"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,11,10]]},"references-count":52,"alternative-id":["10.1145\/3746252.3761405","10.1145\/3746252"],"URL":"https:\/\/doi.org\/10.1145\/3746252.3761405","relation":{},"subject":[],"published":{"date-parts":[[2025,11,10]]},"assertion":[{"value":"2025-11-10","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}