{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,10,29]],"date-time":"2024-10-29T13:39:49Z","timestamp":1730209189531,"version":"3.28.0"},"reference-count":17,"publisher":"IEEE","license":[{"start":{"date-parts":[[2023,11,1]],"date-time":"2023-11-01T00:00:00Z","timestamp":1698796800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,11,1]],"date-time":"2023-11-01T00:00:00Z","timestamp":1698796800000},"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":[[2023,11,1]]},"DOI":"10.1109\/comnet60156.2023.10366659","type":"proceedings-article","created":{"date-parts":[[2023,12,25]],"date-time":"2023-12-25T14:41:28Z","timestamp":1703515288000},"page":"1-8","source":"Crossref","is-referenced-by-count":0,"title":["Exploring the Impact of Speech AI: A Comparative Analysis of ML Models on Arabic Dataset"],"prefix":"10.1109","author":[{"given":"Mohamed Khaled Ben","family":"Mna","sequence":"first","affiliation":[{"name":"University of Carthage,Mediatron Research Lab SUPCOM,Tunis,Tunisia"}]},{"given":"Asma Ben","family":"Letaifa","sequence":"additional","affiliation":[{"name":"University of Carthage,Mediatron Research Lab SUPCOM,Tunis,Tunisia"}]}],"member":"263","reference":[{"article-title":"FASTSPEECH 2: FAST AND HIGH-QUALITY END-TOEND TEXT TO SPEECH","year":"2022","author":"Ren","key":"ref1"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461368"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-1452"},{"key":"ref4","first-page":"6265","article-title":"Fast-Speech: Fast, robust and controllable text to speech","volume-title":"In ICASSP 2019-2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","author":"Ren"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-1452"},{"key":"ref6","first-page":"471","article-title":"Deep voice 3: Scaling text-to-speech with convolutional sequence learning","volume-title":"In Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics","volume":"1","author":"Ping"},{"key":"ref7","article-title":"Char2wav: End-to-end speech synthesis","author":"Sotelo","year":"2017","journal-title":"arXiv preprint arXiv:1707.01655"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461368"},{"key":"ref9","first-page":"1870","article-title":"Style tokens: Unsupervised style modeling, control and transfer in end-to-end speech synthesis","volume-title":"In Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics","volume":"1","author":"Wang"},{"key":"ref10","first-page":"1930","article-title":"Parallel data-free voice conversion with non-parallel data","volume-title":"In Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics","volume":"1","author":"Yamamoto"},{"key":"ref11","article-title":"Listening while speaking: Speech chain by deep learning","author":"Hayashi","year":"2017","journal-title":"arXiv preprint arXiv:1707.04879"},{"key":"ref12","article-title":"Adaptive fastspeech: Efficient text-to-speech with transformer","author":"Fan","year":"2019","journal-title":"arXiv preprint arXiv:1905.09263"},{"key":"ref13","article-title":"Melnet: A generative model for audio in the frequency domain","author":"Wang","year":"2019","journal-title":"arXiv preprint arXiv:1906.01083"},{"key":"ref14","article-title":"Ernie: Enhanced representation through informative embedding","author":"Zhou","year":"2018","journal-title":"arXiv preprint arXiv:1904.09223"},{"key":"ref15","article-title":"LPCNet: Improving Neural Speech Synthesis Through Linear Prediction","author":"Liu","year":"2020","journal-title":"arXiv preprint arXiv:1910.11895"},{"key":"ref16","first-page":"481","article-title":"Neural speech synthesis with transformer network","volume-title":"In 2019 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","author":"Wang"},{"key":"ref17","first-page":"233","article-title":"Deep voice 2: Multi-speaker neural text-to-speech","volume-title":"In 2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","author":"Ping"}],"event":{"name":"2023 IEEE Tenth International Conference on Communications and Networking (ComNet)","start":{"date-parts":[[2023,11,1]]},"location":"Hammamet, Tunisia","end":{"date-parts":[[2023,11,3]]}},"container-title":["2023 IEEE Tenth International Conference on Communications and Networking (ComNet)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10366461\/10366462\/10366659.pdf?arnumber=10366659","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,1,12]],"date-time":"2024-01-12T19:07:03Z","timestamp":1705086423000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10366659\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,11,1]]},"references-count":17,"URL":"https:\/\/doi.org\/10.1109\/comnet60156.2023.10366659","relation":{},"subject":[],"published":{"date-parts":[[2023,11,1]]}}}