{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,28]],"date-time":"2025-11-28T12:00:13Z","timestamp":1764331213096,"version":"3.28.0"},"reference-count":53,"publisher":"IEEE","license":[{"start":{"date-parts":[[2023,10,25]],"date-time":"2023-10-25T00:00:00Z","timestamp":1698192000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,10,25]],"date-time":"2023-10-25T00:00:00Z","timestamp":1698192000000},"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":[[2023,10,25]]},"DOI":"10.1109\/metroxraine58569.2023.10405705","type":"proceedings-article","created":{"date-parts":[[2024,2,1]],"date-time":"2024-02-01T18:26:36Z","timestamp":1706811996000},"page":"537-542","source":"Crossref","is-referenced-by-count":1,"title":["Deep Audio Analyzer: A Framework to Industrialize the Research on Audio Forensics"],"prefix":"10.1109","author":[{"given":"Valerio Francesco","family":"Puglisi","sequence":"first","affiliation":[{"name":"University of Catania,Department of Mathematics and Computer Science,Catania,Sicily,Italy,95123"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Oliver","family":"Giudice","sequence":"additional","affiliation":[{"name":"University of Catania,Department of Mathematics and Computer Science,Catania,Sicily,Italy,95123"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Sebastiano","family":"Battiato","sequence":"additional","affiliation":[{"name":"University of Catania,Department of Mathematics and Computer Science,Catania,Sicily,Italy,95123"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1145\/2983468.2983470"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP.2019.8803502"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.3390\/jimaging7080126"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.3390\/jimaging8100263"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1016\/j.jvcir.2022.103635"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP40778.2020.9191094"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP.2019.8803619"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1007\/s11042-016-4277-2"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-11756-5_6"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2008.931080"},{"volume-title":"The HTK Book. Entropic Cambridge Research Labo-ratory","year":"2002","author":"Young","key":"ref11"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2006.1659988"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.21437\/eurospeech.2001-396"},{"key":"ref14","article-title":"RASR - The RWTH Aachen University Open Source Speech Recognition Toolkit","author":"Rybach","year":"2011","journal-title":"Proc. of ASRU"},{"key":"ref15","article-title":"The Kaldi Speech Recognition Toolkit","author":"Povey","year":"2011","journal-title":"Proc. of ASRU"},{"key":"ref16","first-page":"10","article-title":"Tensorflow: A system for largescale machine learning","volume-title":"Proc. of. USENIX Symposium on Operating Systems Design and Implementation","author":"Abadi","year":"2016"},{"key":"ref17","article-title":"Pytorch: An imperative style, high-performance deep learning library","author":"Paszke","year":"2019","journal-title":"Proc. of NeurIPS"},{"key":"ref18","article-title":"Deep speech: Scaling up end-to-end speech recognition","author":"Hannun","year":"2014","journal-title":"arXiv"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P18-4022"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683713"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU46091.2019.9003968"},{"key":"ref22","article-title":"Lingvo: A modular and scalable framework for sequence-to-sequence modeling","author":"Shen","year":"2019","journal-title":"arXiv"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N19-4009"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1456"},{"key":"ref25","article-title":"NeMo: a toolkit for building AI applications using Neural Modules","author":"Kuchaiev","year":"2019","journal-title":"arXiv"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2020-1673"},{"key":"ref27","article-title":"SpeechBrain: A general-purpose speech toolkit","author":"Ravanelli","year":"2021","journal-title":"arXiv preprint"},{"volume-title":"The AI community building the future","year":"2021","author":"Hugging","key":"ref28"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.25080\/majora-7b98e3ed-003"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/MSPEC.1970.5213512"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1121\/1.400476"},{"volume-title":"Chroma feature analysis and synthesis","year":"2007","author":"Ellis","key":"ref32"},{"key":"ref33","article-title":"Chroma Toolbox: MATLAB implementations for extracting variants of chroma-based audio features","volume-title":"Proceedings of the International Conference on Music Information Retrieval (ISMIR)","author":"Muller","year":"2011"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1007\/0-387-32845-9"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/ICME.2002.1035731"},{"key":"ref36","first-page":"12449","article-title":"wav2vec 2.0: A framework for self-supervised learning of speech representations","volume":"33","author":"Baevski","year":"2020","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref37","article-title":"Free English and Czech telephone speech corpus shared under the CC-BY-SA 3.0 license","volume-title":"Proceedings of the Ninth Inter-national Conference on Language Resources and Evaluation (LREC14)","author":"Korvas","year":"2014"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.6028\/nist.ir.4930"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746316"},{"key":"ref40","article-title":"Common voice: A massively-multilingual speech corpus","author":"Ardila","year":"2019","journal-title":"arXiv preprint"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/ICSDA.2017.8384449"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9413901"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1550"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2821"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053327"},{"key":"ref46","article-title":"Librimix: An open-source dataset for generalizable speech separation","author":"Cosentino","year":"2020","journal-title":"arXiv preprint"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2650"},{"volume-title":"LibriParty","key":"ref48"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1007\/s10579-008-9076-6"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1097\/01.JAA.0000723972.94123.e8"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.21105\/joss.04101"},{"article-title":"An information theoretic measure of speech recognition performance","volume-title":"Workshop on standardisation for speech I\/O technology, Naval Air Development Center","author":"Woodard","key":"ref52"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2004-668"}],"event":{"name":"2023 IEEE International Conference on Metrology for eXtended Reality, Artificial Intelligence and Neural Engineering (MetroXRAINE)","start":{"date-parts":[[2023,10,25]]},"location":"Milano, Italy","end":{"date-parts":[[2023,10,27]]}},"container-title":["2023 IEEE International Conference on Metrology for eXtended Reality, Artificial Intelligence and Neural Engineering (MetroXRAINE)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10405419\/10405547\/10405705.pdf?arnumber=10405705","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,2,2]],"date-time":"2024-02-02T00:51:34Z","timestamp":1706835094000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10405705\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,10,25]]},"references-count":53,"URL":"https:\/\/doi.org\/10.1109\/metroxraine58569.2023.10405705","relation":{},"subject":[],"published":{"date-parts":[[2023,10,25]]}}}