{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,12]],"date-time":"2025-10-12T07:46:51Z","timestamp":1760255211579,"version":"build-2065373602"},"publisher-location":"Cham","reference-count":15,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783032079558","type":"print"},{"value":"9783032079565","type":"electronic"}],"license":[{"start":{"date-parts":[[2025,10,13]],"date-time":"2025-10-13T00:00:00Z","timestamp":1760313600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,10,13]],"date-time":"2025-10-13T00:00:00Z","timestamp":1760313600000},"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":[[2026]]},"DOI":"10.1007\/978-3-032-07956-5_6","type":"book-chapter","created":{"date-parts":[[2025,10,12]],"date-time":"2025-10-12T07:19:36Z","timestamp":1760253576000},"page":"83-98","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Enhancing Sinhala Text-to-Speech with\u00a0End-to-End VITS Architecture"],"prefix":"10.1007","author":[{"given":"Sasangi","family":"Nayanathara","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Inuri","family":"Harischandra","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Thamira","family":"Weerakoon","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Randil","family":"Pushpananda","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2025,10,13]]},"reference":[{"key":"6_CR1","unstructured":"Tan, X., Qin, T., Soong, F., Liu, T.-Y.: A survey on neural speech synthesis (2021)"},{"key":"6_CR2","unstructured":"Arik, S \u00d6., et al.: Deep voice: real-time neural text-to-speech, CoRR, vol. abs\/1702.07825 (2017)"},{"key":"6_CR3","doi-asserted-by":"crossref","unstructured":"Wang, Y., et al.: Tacotron: towards end-to-end speech synthesis, arXiv [cs.CL] (2017)","DOI":"10.21437\/Interspeech.2017-1452"},{"key":"6_CR4","unstructured":"Van den Oord, A., et al.: WaveNet: a generative model for raw audio, CoRR, vol. abs\/1609.03499 (2016)"},{"key":"6_CR5","doi-asserted-by":"crossref","unstructured":"Shen, J., et al.: Natural TTS synthesis by conditioning WaveNet on mel spectrogram predictions, arXiv [cs.CL] (2018)","DOI":"10.1109\/ICASSP.2018.8461368"},{"key":"6_CR6","unstructured":"Ren, Y., et al.: FastSpeech: fast, robust and controllable text to speech, arXiv [cs.CL] (2019)"},{"key":"6_CR7","unstructured":"Ren, Y., et al.: FastSpeech 2: fast and high-quality end-to-end text to speech, arXiv [eess.AS] (2022)"},{"key":"6_CR8","unstructured":"Kim, J., Kong, J., Son, J.: Conditional variational autoencoder with adversarial learning for end-to-end text-to-speech. In: International Conference on Machine Learning, pp. 5530\u20135540 (2021)"},{"key":"6_CR9","unstructured":"Wang, C., et al.: Neural codec language models are zero-shot text to speech synthesizers, arXiv [cs.CL] (2023)"},{"key":"6_CR10","unstructured":"Nishimura, Y., Hirose, T., Ohi, M., Nakayama, H., Inoue, N.: HALL-E: hierarchical neural codec language model for minute-long zero-shot text-to-speech synthesis, arXiv [eess.AS] (2024)"},{"key":"6_CR11","series-title":"Lecture Notes in Computer Science (Lecture Notes in Artificial Intelligence)","doi-asserted-by":"publisher","first-page":"472","DOI":"10.1007\/978-3-540-74628-7_61","volume-title":"Text, Speech and Dialogue","author":"R Weerasinghe","year":"2007","unstructured":"Weerasinghe, R., Wasala, A., Welgama, V., Gamage, K.: Festival-si: a sinhala text-to-speech system. In: Matou\u0161ek, V., Mautner, P. (eds.) TSD 2007. LNCS (LNAI), vol. 4629, pp. 472\u2013479. Springer, Heidelberg (2007). https:\/\/doi.org\/10.1007\/978-3-540-74628-7_61"},{"key":"6_CR12","doi-asserted-by":"crossref","unstructured":"Nanayakkara, L., Liyanage, C., Viswakula, P.T., Nagungodage, T., Pushpananda, R., Weerasinghe, R.: A human quality text to speech system for Sinhala, in SLTU, pp. 157\u2013161 (2018)","DOI":"10.21437\/SLTU.2018-33"},{"key":"6_CR13","doi-asserted-by":"crossref","unstructured":"Arachchige, T.K., Weerasinghe, R.: TacoSi: a Sinhala text to speech system with neural networks (2023)","DOI":"10.1109\/ICARC57651.2023.10145749"},{"key":"6_CR14","unstructured":"PathNirvana: Path Nirvana Sinhala TTS Dataset (2023). https:\/\/github.com\/pnfo\/sinhala-tts-dataset"},{"key":"6_CR15","unstructured":"Ito, K., Johnson, L.: The LJ speech dataset (2017). https:\/\/keithito.com\/LJ-Speech-Dataset\/"}],"container-title":["Lecture Notes in Computer Science","Speech and Computer"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-032-07956-5_6","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,12]],"date-time":"2025-10-12T07:19:40Z","timestamp":1760253580000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-032-07956-5_6"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,13]]},"ISBN":["9783032079558","9783032079565"],"references-count":15,"URL":"https:\/\/doi.org\/10.1007\/978-3-032-07956-5_6","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,10,13]]},"assertion":[{"value":"13 October 2025","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"SPECOM","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Speech and Computer","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Szeged","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Hungary","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2025","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"13 October 2025","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"15 October 2025","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"27","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"specom2025","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/specom.inf.u-szeged.hu\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}