{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,5,14]],"date-time":"2025-05-14T06:10:08Z","timestamp":1747203008173,"version":"3.40.5"},"reference-count":21,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,3,6]],"date-time":"2025-03-06T00:00:00Z","timestamp":1741219200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,3,6]],"date-time":"2025-03-06T00:00:00Z","timestamp":1741219200000},"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":[[2025,3,6]]},"DOI":"10.1109\/ncc63735.2025.10983860","type":"proceedings-article","created":{"date-parts":[[2025,5,13]],"date-time":"2025-05-13T17:43:35Z","timestamp":1747158215000},"page":"1-5","source":"Crossref","is-referenced-by-count":0,"title":["Development of Resource Efficient Direct Speech to Speech Translation System using Transformer, Reformer, and Linformer"],"prefix":"10.1109","author":[{"given":"Lalaram","family":"Arya","sequence":"first","affiliation":[{"name":"Indian Institute of Technology Dharwad,Department of Electrical, Electronics and Communication Engineering,Dharwad,India,580011"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"S. R.","family":"Mahadeva Prasanna","sequence":"additional","affiliation":[{"name":"Indian Institute of Technology Dharwad,Department of Electrical, Electronics and Communication Engineering,Dharwad,India,580011"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"volume-title":"Vanimedia","key":"ref1"},{"key":"ref2","first-page":"12449","article-title":"wav2vec 2.0: A framework for self-supervised learning of speech representations","volume-title":"Advances in Neural Information Processing Systems","volume":"33","author":"Baevski","year":"2020"},{"key":"ref3","article-title":"The reversible residual network: Backpropagation without storing activations","volume-title":"CoRR abs\/1707.04585","author":"Gomez","year":"2017"},{"key":"ref4","first-page":"10120","article-title":"Translatotron 2: High-quality direct speech-to-speech translation with voice preservation","volume-title":"Proceedings of the 39th International Conference on Machine Learning","volume":"162","author":"Jia"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1951"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/SLT48900.2021.9383496"},{"article-title":"Glow-tts: A generative flow for text-to-speech via monotonic alignment search","volume-title":"Proceedings of the 34th International Conference on Neural Information Processing Systems. NIPS\u201920","author":"Kim","key":"ref7"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1406.3269"},{"key":"ref9","article-title":"Reformer: The efficient transformer","author":"Kitaev","year":"2020","journal-title":"CoRR abs\/2001.04451"},{"article-title":"Hifi-gan: Generative adversarial networks for efficient and high fidelity speech synthesis","volume-title":"Proceedings of the 34th International Conference on Neural Information Processing Systems. NIPS\u201920","author":"Kong","key":"ref10"},{"key":"ref11","first-page":"255","volume-title":"Convolutional Networks for Images, Speech, and Time Series","author":"Le Cun","year":"1998"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.acl-long.235"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33016706"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10448426"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.iwslt-1.4"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/W18-6319"},{"key":"ref17","first-page":"24","article-title":"Prabhupa-davani: A code-mixed speech translation data for 25 languages","author":"Sandhan","year":"2022","journal-title":"LaTeCH-C LtL"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461368"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref21","volume":"CoRR abs\/2006.04768","author":"Wang","year":"2020","journal-title":"Linformer: Self-attention with linear complexity"}],"event":{"name":"2025 National Conference on Communications (NCC)","start":{"date-parts":[[2025,3,6]]},"location":"New Delhi, India","end":{"date-parts":[[2025,3,9]]}},"container-title":["2025 National Conference on Communications (NCC)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10982528\/10982694\/10983860.pdf?arnumber=10983860","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,5,14]],"date-time":"2025-05-14T05:33:35Z","timestamp":1747200815000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10983860\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,3,6]]},"references-count":21,"URL":"https:\/\/doi.org\/10.1109\/ncc63735.2025.10983860","relation":{},"subject":[],"published":{"date-parts":[[2025,3,6]]}}}