{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,14]],"date-time":"2026-01-14T12:30:55Z","timestamp":1768393855449,"version":"3.49.0"},"reference-count":53,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,7,2]],"date-time":"2025-07-02T00:00:00Z","timestamp":1751414400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,7,2]],"date-time":"2025-07-02T00:00:00Z","timestamp":1751414400000},"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":[[2025,7,2]]},"DOI":"10.1109\/iscc65549.2025.11326439","type":"proceedings-article","created":{"date-parts":[[2026,1,13]],"date-time":"2026-01-13T20:56:15Z","timestamp":1768337775000},"page":"1-6","source":"Crossref","is-referenced-by-count":0,"title":["Design and Deployment of a Standard Framework for Audio Neural Networks Embedding Models"],"prefix":"10.1109","author":[{"given":"Stefano","family":"Giacomelli","sequence":"first","affiliation":[{"name":"University of L’Aquila (UnivAQ),Department of Information Engineering, Computer Science and Mathematics (DISIM),L’Aquila,Italy"}]},{"given":"Carlo","family":"Centofanti","sequence":"additional","affiliation":[{"name":"University of L’Aquila (UnivAQ),Department of Information Engineering, Computer Science and Mathematics (DISIM),L’Aquila,Italy"}]},{"given":"Fabio","family":"Graziosi","sequence":"additional","affiliation":[{"name":"University of L’Aquila (UnivAQ),Department of Information Engineering, Computer Science and Mathematics (DISIM),L’Aquila,Italy"}]},{"given":"Claudia","family":"Rinaldi","sequence":"additional","affiliation":[{"name":"University of L’Aquila (UnivAQ),Department of Information Engineering, Computer Science and Mathematics (DISIM),L’Aquila,Italy"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"crossref","first-page":"121902","DOI":"10.1016\/j.eswa.2023.121902","article-title":"Acoustic scene classification: A comprehensive survey","volume":"238","author":"Ding","year":"2024","journal-title":"Expert Systems with Applications"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2021.3090678"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2010.2098858"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1007\/s11042-020-10073-7"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2021.3068045"},{"key":"ref6","article-title":"Visualization of deep audio embeddings for music exploration and rediscovery","volume-title":"Proceedings of the 19th Sound and Music Computing Conference (SMC).","author":"Tovstogan"},{"issue":"7","key":"ref7","first-page":"4244","article-title":"Optimization and acceleration of convolutional neural networks: A survey","volume-title":"Journal of King Saud University - Computer and Information Sciences","volume":"34","author":"Habib"},{"key":"ref8","doi-asserted-by":"crossref","first-page":"102990","DOI":"10.1016\/j.sysarc.2023.102990","article-title":"A survey of techniques for optimizing transformer inference","volume":"144","author":"Chitty-Venkata","year":"2023","journal-title":"Journal of Systems Architecture"},{"issue":"6","key":"ref9","doi-asserted-by":"crossref","first-page":"945","DOI":"10.3390\/electronics11060945","article-title":"A Survey on Efficient Convolutional Neural Networks and Hardware Acceleration","volume":"11","author":"Ghimire","year":"2022","journal-title":"Electronics"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1145\/3530811"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.33682\/w13e-5v06"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2023.3293032"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-347"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053160"},{"issue":"6","key":"ref15","article-title":"A review of deep learning based methods for acoustic scene classification","volume":"10","author":"Abe\u03b2er","year":"2020","journal-title":"Applied Sciences"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1145\/3322240"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1186\/s13636-022-00251-w"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2023.3328283"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2014.6854950"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICOT.2017.8336092"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2023.3283982"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/TAFFC.2021.3114365"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2023.3318015"},{"key":"ref24","doi-asserted-by":"crossref","first-page":"104956","DOI":"10.1016\/j.dsp.2024.104956","article-title":"Transformers and audio detection tasks: An overview","volume":"158","year":"2025","journal-title":"Digital Signal Processing"},{"issue":"12","key":"ref25","doi-asserted-by":"crossref","first-page":"100616","DOI":"10.1016\/j.patter.2022.100616","article-title":"Audio self-supervised learning: A survey","volume":"3","author":"Shuo","year":"2022","journal-title":"Patterns"},{"key":"ref26","article-title":"EVAR - Evaluation package for Audio Representations","author":"Laboratory","year":"2025"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747348"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2021-1775"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2023-1087"},{"key":"ref30","first-page":"125","article-title":"HEAR: Holistic Evaluation of Audio Representations","volume-title":"Proceedings of the NeurIPS 2021 Competitions and Demonstrations Track","volume":"176","author":"Turian"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746790"},{"key":"ref32","article-title":"DCASE Benchmarks","year":"2025","journal-title":"Detection and Classification of Acoustic Scenes and Events"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSPW62465.2024.10625960"},{"key":"ref34","article-title":"MIR Evaluation eXchange","year":"2025","journal-title":"International Society for Music Information Retrieval"},{"key":"ref35","article-title":"MARBLE: Music audio representation benchmark for universal evaluation","volume-title":"37th Conference on Neural Information Processing Systems (NEURIPS) - Datasets and Benchmarks Track","author":"Ruibin"},{"key":"ref36","first-page":"10330","article-title":"Codec-SUPERB: An in-depth analysis of sound codec models","volume-title":"Findings of the Association for Computational Linguistics: ACL 2024","author":"Wu"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2019.2908700"},{"key":"ref38","article-title":"The Northwestern University Source Separation Library","volume-title":"Proceedings of the 19th International Society for Music Information Retrieval Conference, ISMIR 2018","author":"Manilow"},{"key":"ref39","first-page":"2637","article-title":"Asteroid: The PyTorch-Based Audio Source Separation Toolkit for Researchers","volume-title":"Proceedings of the International Speech Communication Association Conference, Interspeech 2020","author":"Pariente"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.21105\/joss.01667"},{"key":"ref41","article-title":"Onssen: an open-source speech separation and enhancement library","author":"Ni","year":"2019","journal-title":"arXiv:1911.00982"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1111\/2041-210x.14196"},{"key":"ref43","article-title":"SpeechBrain: A General-Purpose Speech Toolkit","author":"Ravanelli","year":"2021","journal-title":"arXiv:2106.04624"},{"key":"ref44","article-title":"ESPnet: End-to-End Speech Processing Toolkit","author":"Watanabe","year":"2018","journal-title":"arXiv:1804.00015"},{"key":"ref45","article-title":"Torchbench: Benchmarking pytorch with high api surface coverage","author":"Yueming"},{"key":"ref46","article-title":"PyTorch: an imperative style, high-performance deep learning library","volume-title":"Curran Associates Inc","author":"Paszke"},{"key":"ref47","first-page":"265","article-title":"Tensorflow: a system for large-scale machine learning","volume-title":"Proceedings of the 12th USENIX Conference on Operating Systems Design and Implementation, ser. OSDI\u201916. USA: USENIX Association","author":"Abadi"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1145\/3368089.3417051"},{"key":"ref49","article-title":"mlco2\/codecarbon: v2.8.5","author":"Courty","year":"2025"},{"key":"ref50","first-page":"220","article-title":"Model cards for model reporting","volume-title":"Proceedings of the Conference on Fairness, Accountability, and Transparency, ser. FAT* \u201819.","author":"Mitchell"},{"key":"ref51","article-title":"ONNX About"},{"key":"ref52","first-page":"2011","article-title":"Exploring TensorRT to Improve Real-Time Inference for Deep Learning","volume-title":"2022 IEEE 24th Int Conf on High Performance Computing & Communications; 8th Int Conf on Data Science & Systems; 20th Int Conf on Smart City; 8th Int Conf on Dependability in Sensor, Cloud & Big Data Systems & Application (HPCC\/DSS\/SmartCity\/DependSys)","author":"Zhou"},{"key":"ref53","article-title":"TorchScript: Optimized Execution of PyTorch Programs","author":"DeVito"}],"event":{"name":"2025 IEEE Symposium on Computers and Communications (ISCC)","location":"Bologna, Italy","start":{"date-parts":[[2025,7,2]]},"end":{"date-parts":[[2025,7,5]]}},"container-title":["2025 IEEE Symposium on Computers and Communications (ISCC)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11325745\/11324448\/11326439.pdf?arnumber=11326439","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,1,14]],"date-time":"2026-01-14T07:02:47Z","timestamp":1768374167000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11326439\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,7,2]]},"references-count":53,"URL":"https:\/\/doi.org\/10.1109\/iscc65549.2025.11326439","relation":{},"subject":[],"published":{"date-parts":[[2025,7,2]]}}}