{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,2]],"date-time":"2026-10-02T17:18:48Z","timestamp":1790961528694,"version":"4.1.0"},"publisher-location":"Cham","reference-count":44,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031434204","type":"print"},{"value":"9783031434211","type":"electronic"}],"license":[{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2023]]},"DOI":"10.1007\/978-3-031-43421-1_39","type":"book-chapter","created":{"date-parts":[[2023,9,17]],"date-time":"2023-09-17T20:37:24Z","timestamp":1694983044000},"page":"661-676","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":15,"title":["Hypernetworks Build Implicit Neural Representations of\u00a0Sounds"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-8592-2001","authenticated-orcid":false,"given":"Filip","family":"Szatkowski","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6115-0833","authenticated-orcid":false,"given":"Karol J.","family":"Piczak","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0097-5521","authenticated-orcid":false,"given":"Przemys\u0142aw","family":"Spurek","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6652-7727","authenticated-orcid":false,"given":"Jacek","family":"Tabor","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1486-8906","authenticated-orcid":false,"given":"Tomasz","family":"Trzci\u0144ski","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2023,9,18]]},"reference":[{"key":"39_CR1","doi-asserted-by":"crossref","unstructured":"Benbarka, N., et al.: Seeing implicit neural representations as fourier series. In: Proceedings of the IEEE\/CVF Winter Conference on Applications of Computer Vision (WACV), pp. 2041\u20132050 (Jan 2022)","DOI":"10.1109\/WACV51458.2022.00234"},{"key":"39_CR2","unstructured":"Caillon, A., Esling, P.: RAVE: A variational autoencoder for fast and high-quality neural audio synthesis. arXiv: 2111.05011 (2021)"},{"key":"39_CR3","doi-asserted-by":"crossref","unstructured":"Chan, E.R., et al.: PI-GAN: periodic implicit generative adversarial networks for 3d-aware image synthesis. In: Proceedings of the IEEE\/CVF conference on Computer Vision and Pattern Recognition, pp. 5799\u20135809 (2021)","DOI":"10.1109\/CVPR46437.2021.00574"},{"key":"39_CR4","unstructured":"Chang, O., Flokas, L., Lipson, H.: Principled weight initialization for hypernetworks. In: International Conference on Learning Representations (2019)"},{"key":"39_CR5","doi-asserted-by":"publisher","unstructured":"Chen, Y., Wang, X.: Transformers as meta-learners for implicit neural representations. In: Computer Vision-ECCV 2022: 17th European Conference, Tel Aviv, Israel, October 23\u201327, 2022, Proceedings, Part XVII, pp. 170\u2013187. Springer (2022). https:\/\/doi.org\/10.1007\/978-3-031-19790-1_11","DOI":"10.1007\/978-3-031-19790-1_11"},{"key":"39_CR6","unstructured":"Clevert, D.-A., Unterthiner, T., Hochreiter, S.: Fast and Accurate Deep Network Learning by Exponential Linear Units (ELUs). arXiv preprint arXiv:1511.07289 (2015)"},{"key":"39_CR7","unstructured":"D\u00e9fossez, A., et al.: SING: symbol-to-instrument neural generator. In: Advances in Neural Information Processing Systems 31 (2018)"},{"key":"39_CR8","unstructured":"Dupont, E., et al.: From data to functa: Your data point is a function and you should treat it like one. arXiv preprint arXiv:2201.12204 (2022)"},{"key":"39_CR9","unstructured":"Engel, J., et al.: Neural audio synthesis of musical notes with wavenet autoencoders. In: International Conference on Machine Learning, pp. 1068\u20131077. PMLR (2017)"},{"key":"39_CR10","unstructured":"Fons, E., et al.: HyperTime: Implicit Neural Representation for Time Series. arXiv preprint arXiv:2208.05836 (2022)"},{"key":"39_CR11","unstructured":"Glorot, X., Bengio, Y.: Understanding the difficulty of training deep feedforward neural networks. In: Proceedings of the Thirteenth International Conference on Artificial Intelligence and Statistics. JMLR Workshop and Conference Proceedings, pp. 249\u2013256 (2010)"},{"key":"39_CR12","unstructured":"Ha, D., Dai, A., Le, Q.V.: HyperNetworks. arXiv preprint arXiv:1609.09106 (2016)"},{"key":"39_CR13","doi-asserted-by":"crossref","unstructured":"He, K., et al.: Delving deep into rectifiers: surpassing human-level performance on imagenet classification. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 1026\u20131034 (2015)","DOI":"10.1109\/ICCV.2015.123"},{"key":"39_CR14","unstructured":"Kania, A., et al.: Hypernerfgan: Hypernetwork approach to 3d nerf gan. arXiv preprint arXiv:2301.11631 (2023)"},{"key":"39_CR15","unstructured":"Karras, T., et al.: Progressive Growing of GANs for Improved Quality, Stability, And Variation. In: International Conference on Learning Representations (2018)"},{"key":"39_CR16","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"496","DOI":"10.1007\/978-3-030-30493-5_48","volume-title":"Artificial Neural Networks and Machine Learning \u2013 ICANN 2019: Workshop and Special Sessions","author":"S Klocek","year":"2019","unstructured":"Klocek, S., Maziarka, \u0141, Wo\u0142czyk, M., Tabor, J., Nowak, J., \u015amieja, M.: Hypernetwork functional image representation. In: Tetko, I.V., K\u016frkov\u00e1, V., Karpov, P., Theis, F. (eds.) ICANN 2019. LNCS, vol. 11731, pp. 496\u2013510. Springer, Cham (2019). https:\/\/doi.org\/10.1007\/978-3-030-30493-5_48"},{"key":"39_CR17","unstructured":"Kumar, K., et al.: MelGAN: generative adversarial networks for conditional waveform synthesis. In: Advances in Neural Information Processing Systems 32 (2019)"},{"key":"39_CR18","doi-asserted-by":"crossref","unstructured":"Liu, H., et al.: Neural Vocoder is All You Need for Speech Superresolution. arXiv preprint arXiv:2203.14941 (2022)","DOI":"10.21437\/Interspeech.2022-11017"},{"key":"39_CR19","doi-asserted-by":"crossref","unstructured":"Luo, Y., Mesgarani, N.: TasNet: time-domain audio separation network for real-time, single-channel speech separation. In: 2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 696\u2013700. IEEE (2018)","DOI":"10.1109\/ICASSP.2018.8462116"},{"key":"39_CR20","doi-asserted-by":"crossref","unstructured":"Manocha, P., et al.: CDPAM: contrastive learning for perceptual audio similarity. In: ICASSP 2021\u20132021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 196\u2013200. IEEE (2021)","DOI":"10.1109\/ICASSP39728.2021.9413711"},{"key":"39_CR21","unstructured":"Mehri, S., et al.: SampleRNN: An Unconditional End-to-End Neural Audio Generation Model. arXiv preprint arXiv:1612.07837 (2016)"},{"key":"39_CR22","doi-asserted-by":"crossref","unstructured":"Mehta, I., et al.: Modulated periodic activations for generalizable local functional representations. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 14214\u201314223 (2021)","DOI":"10.1109\/ICCV48922.2021.01395"},{"issue":"1","key":"39_CR23","doi-asserted-by":"publisher","first-page":"99","DOI":"10.1145\/3503250","volume":"65","author":"B Mildenhall","year":"2021","unstructured":"Mildenhall, B., et al.: NeRF: representing scenes as neural radiance fields for view synthesis. Commun. ACM 65(1), 99\u2013106 (2021)","journal-title":"Commun. ACM"},{"key":"39_CR24","doi-asserted-by":"crossref","unstructured":"M\u00fcller, N., et al.: DiffRF: Rendering-Guided 3D Radiance Field Diffusion. arXiv preprint arXiv:2212.01206 (2022)","DOI":"10.1109\/CVPR52729.2023.00421"},{"key":"39_CR25","unstructured":"Oord, A., et al.: Parallel WaveNet: fast high-fidelity speech synthesis. In: International Conference on Machine Learning, pp. 3918\u20133926. PMLR (2018)"},{"key":"39_CR26","unstructured":"van den Oord, A., et al.: WaveNet: A Generative Model for Raw Audio. arXiv preprint arXiv:1609.03499 (2016)"},{"issue":"2","key":"39_CR27","doi-asserted-by":"publisher","first-page":"206","DOI":"10.1109\/JSTSP.2019.2908700","volume":"13","author":"H Purwins","year":"2019","unstructured":"Purwins, H., et al.: Deep learning for audio signal processing. IEEE J. Selected Topics Signal Process. 13(2), 206\u2013219 (2019)","journal-title":"IEEE J. Selected Topics Signal Process."},{"key":"39_CR28","unstructured":"Rahaman, N., et al.: On the spectral bias of neural networks. In: International Conference on Machine Learning, pp. 5301\u20135310. PMLR (2019)"},{"key":"39_CR29","doi-asserted-by":"crossref","unstructured":"Rix, A.W., et al.: Perceptual evaluation of speech quality (PESQ)-a new method for speech quality assessment of telephone networks and codecs. In: 2001 IEEE International Conference on Acoustics, Speech, and Signal Processing, Proceedings (Cat. No. 01CH37221), vol. 2, pp. 749\u2013752. IEEE (2001)","DOI":"10.1109\/ICASSP.2001.941023"},{"key":"39_CR30","first-page":"7462","volume":"33","author":"V Sitzmann","year":"2020","unstructured":"Sitzmann, V., et al.: Implicit neural representations with periodic activation functions. Adv. Neural. Inf. Process. Syst. 33, 7462\u20137473 (2020)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"39_CR31","first-page":"10136","volume":"33","author":"V Sitzmann","year":"2020","unstructured":"Sitzmann, V., et al.: Metasdf: Meta-learning signed distance functions. Adv. Neural. Inf. Process. Syst. 33, 10136\u201310147 (2020)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"39_CR32","doi-asserted-by":"crossref","unstructured":"Smith, L.N., Topin, N.: Super-convergence: very fast training of neural networks using large learning rates. In: Artificial Intelligence and Machine Learning for Multi-domain Operations Applications, vol. 11006, pp. 369\u2013386. SPIE (2019)","DOI":"10.1117\/12.2520589"},{"key":"39_CR33","unstructured":"Spurek, P., et al.: Hypernetwork approach to generating point clouds. In: Proceedings of Machine Learning Research, vol. 119 (2020)"},{"key":"39_CR34","doi-asserted-by":"publisher","unstructured":"Str\u00fcmpler, Y., et al.: Implicit neural representations for image compression. In: Computer Vision-ECCV 2022: 17th European Conference, Tel Aviv, Israel, 23\u201327 October 2022, Proceedings, Part XXVI, pp. 74\u201391. Springer (2022). https:\/\/doi.org\/10.1007\/978-3-031-19809-0_5","DOI":"10.1007\/978-3-031-19809-0_5"},{"key":"39_CR35","doi-asserted-by":"crossref","unstructured":"Taal, C.H., et al.: A short-time objective intelligibility measure for time frequency weighted noisy speech. In: 2010 IEEE International Conference on Acoustics, Speech and Signal Processing, pp. 4214\u20134217. IEEE (2010)","DOI":"10.1109\/ICASSP.2010.5495701"},{"key":"39_CR36","doi-asserted-by":"crossref","unstructured":"Tabor, J., Trzci\u0144ski, T., et al.: Hyperpocket: generative point cloud completion. In: 2022 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS), pp. 6848\u20136853. IEEE (2022)","DOI":"10.1109\/IROS47612.2022.9981829"},{"key":"39_CR37","first-page":"7537","volume":"33","author":"M Tancik","year":"2020","unstructured":"Tancik, M., et al.: Fourier features let networks learn high frequency functions in low dimensional domains. Adv. Neural. Inf. Process. Syst. 33, 7537\u20137547 (2020)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"39_CR38","unstructured":"Van der Maaten, L., Hinton, G.: Visualizing data using t-SNE. J. Mach. Learn. Res. 9(11) (2008)"},{"key":"39_CR39","unstructured":"Von Oswald, J., et al.: Continual learning with hypernetworks. arXiv preprint arXiv:1906.00695 (2019)"},{"key":"39_CR40","doi-asserted-by":"crossref","unstructured":"Yamamoto, R., Song, E., Kim, J.-M.: Parallel WaveGAN: a fast waveform generation model based on generative adversarial networks with multi-resolution spectrogram. In: ICASSP 2020\u20132020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 6199\u20136203. IEEE (2020)","DOI":"10.1109\/ICASSP40776.2020.9053795"},{"key":"39_CR41","doi-asserted-by":"publisher","first-page":"495","DOI":"10.1109\/TASLP.2021.3129994","volume":"30","author":"N Zeghidour","year":"2021","unstructured":"Zeghidour, N., et al.: SoundStream: an end-to-end neural audio codec. IEEE\/ACM Trans. Audio, Speech Lang. Process, 30, 495\u2013507 (2021)","journal-title":"IEEE\/ACM Trans. Audio, Speech Lang. Process,"},{"key":"39_CR42","unstructured":"Zhao, D., et al.: Meta-Learning via Hypernetworks (2020)"},{"key":"39_CR43","unstructured":"Zimny, D., Trzci\u0144ski, T., Spurek, P.: Points2NeRF: Generating Neural Radiance Fields from 3D point cloud. arXiv preprint arXiv:2206.01290 (2022)"},{"key":"39_CR44","unstructured":"Zuiderveld, J., Federici, M., Bekkers, E.J.: Towards Lightweight Controllable Audio Synthesis with Conditional Implicit Neural Representations. arXiv preprint arXiv:2111.08462 (2021)"}],"container-title":["Lecture Notes in Computer Science","Machine Learning and Knowledge Discovery in Databases: Research Track"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-43421-1_39","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,10,28]],"date-time":"2024-10-28T06:59:44Z","timestamp":1730098784000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-43421-1_39"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023]]},"ISBN":["9783031434204","9783031434211"],"references-count":44,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-43421-1_39","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023]]},"assertion":[{"value":"18 September 2023","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"This paper belongs to the line of fundamental research and all the experiments in this paper were performed using publicly available data. However, we acknowledge that there are potential ethical implications of our work that need to be considered.As with all machine learning models, biases from the training data can be encoded into the model, leading to inaccurate or discriminatory behavior towards underrepresented groups.Furthermore, the data reconstructed with Implicit Neural Representations always contains some degree of error, and models trained with different hyperparameters can produce varying representations. These properties make INRs a potential tool to evade copyright detection, and current detection algorithms are not equipped to work on data stored as INR weights, further compounding the issue.","order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Ethical Statement"}},{"value":"ECML PKDD","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Joint European Conference on Machine Learning and Knowledge Discovery in Databases","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Turin","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Italy","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2023","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"18 September 2023","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"22 September 2023","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"23","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"ecml2023","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/2023.ecmlpkdd.org\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Double-blind","order":1,"name":"type","label":"Type","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"CMT","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"829","order":3,"name":"number_of_submissions_sent_for_review","label":"Number of Submissions Sent for Review","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"196","order":4,"name":"number_of_full_papers_accepted","label":"Number of Full Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"0","order":5,"name":"number_of_short_papers_accepted","label":"Number of Short Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"24% - The value is computed by the equation \"Number of Full Papers Accepted \/ Number of Submissions Sent for Review * 100\" and then rounded to a whole number.","order":6,"name":"acceptance_rate_of_full_papers","label":"Acceptance Rate of Full Papers","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"3.63","order":7,"name":"average_number_of_reviews_per_paper","label":"Average Number of Reviews per Paper","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"4.5","order":8,"name":"average_number_of_papers_per_reviewer","label":"Average Number of Papers per Reviewer","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"Yes","order":9,"name":"external_reviewers_involved","label":"External Reviewers Involved","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"Applied Data Science Track: 239 submissions, 58 accepted papers; Demo Track: 31 submissions, 16 accepted papers.","order":10,"name":"additional_info_on_review_process","label":"Additional Info on Review Process","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}}]}}