{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,15]],"date-time":"2026-04-15T23:02:24Z","timestamp":1776294144931,"version":"3.50.1"},"publisher-location":"Cham","reference-count":17,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783032168078","type":"print"},{"value":"9783032168085","type":"electronic"}],"license":[{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"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\/978-3-032-16808-5_5","type":"book-chapter","created":{"date-parts":[[2026,4,15]],"date-time":"2026-04-15T22:07:02Z","timestamp":1776290822000},"page":"55-69","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Emotional Speech Synthesis Approach Using Prosody-Based Clustering"],"prefix":"10.1007","author":[{"given":"Arnas","family":"Radzevi\u010dius","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"\u017dygimantas","family":"Girdauskas","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Rokas","family":"Sabaitis","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Aistis","family":"Raudys","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2026,4,1]]},"reference":[{"issue":"6","key":"5_CR1","doi-asserted-by":"publisher","first-page":"4234","DOI":"10.1109\/TPAMI.2024.3356232","volume":"46","author":"X Tan","year":"2024","unstructured":"Tan, X., et al.: Naturalspeech: end-to-end text-to-speech synthesis with human-level quality. IEEE Trans. Pattern Anal. Mach. Intell. 46(6), 4234\u20134245 (2024)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"5_CR2","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. PMLR, (2021)"},{"key":"5_CR3","doi-asserted-by":"crossref","unstructured":"Li, Y.A., Han, C., Raghavan, V., Mischler, G. and Mesgarani, N.: Styletts 2: towards human-level text-to-speech through style diffusion and adversarial training with large speech language models. Adv. Neural Inform. Process. Syst. 36 19594\u201319621 (2023)","DOI":"10.52202\/075280-0860"},{"key":"5_CR4","unstructured":"Peng, J., et al.: A survey on speech large language models. arXiv preprint arXiv:2410.18908 (2024)"},{"key":"5_CR5","doi-asserted-by":"crossref","unstructured":"Zeng, Z., Wang, J., Cheng, N., Xiao, J.: Prosody learning mechanism for speech synthesis system without text length limit. arXiv preprint arXiv:2008.05656, 2020","DOI":"10.21437\/Interspeech.2020-2053"},{"key":"5_CR6","doi-asserted-by":"publisher","first-page":"3418","DOI":"10.1109\/TASLP.2023.3313413","volume":"31","author":"T Li","year":"2023","unstructured":"Li, T., et al.: DiCLET-TTS: diffusion model based cross-lingual emotion transfer for text-to-speech\u2013a study between English and mandarin. IEEE\/ACM Trans. Audio, Speech, Lang. Process. 31, 3418\u20133430 (2023)","journal-title":"IEEE\/ACM Trans. Audio, Speech, Lang. Process."},{"key":"5_CR7","doi-asserted-by":"crossref","unstructured":"Lameris, H., Mehta, S., Henter, G.E., Gustafson, J., va Sz\u00e9kely, \u00c9.: Prosody-controllable spontaneous TTS with neural HMMS. In: ICASSP 2023\u20132023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 1\u20135. IEEE (2023)","DOI":"10.1109\/ICASSP49357.2023.10097200"},{"key":"5_CR8","doi-asserted-by":"crossref","unstructured":"Shen, J., et al.: Natural TTS synthesis by conditioning wavenet on mel spectrogram predictions. In: 2018 IEEE international conference on acoustics, speech and signal processing (ICASSP), pp. 4779\u20134783. IEEE, (2018)","DOI":"10.1109\/ICASSP.2018.8461368"},{"key":"5_CR9","doi-asserted-by":"crossref","unstructured":"Cho, D.-H., Oh, H.-S., Kim, S.-B., Lee, S.-H., Lee, S.-W.: Emosphere-TTS: Emotional style and intensity modeling via spherical emotion vector for controllable emotional text-to-speech. arXiv preprint arXiv:2406.07803 (2024)","DOI":"10.21437\/Interspeech.2024-398"},{"key":"5_CR10","doi-asserted-by":"crossref","unstructured":"Latif, S., Shahid, A., Qadir, J., et al.: Emotional speech cloning using gans. In: 2021 International Conference on Recent Trends on Electronics, Information, Communication & Technology (RTEICT), pp. 824\u2013828. IEEE (2021)","DOI":"10.1109\/RTEICT52294.2021.9573848"},{"issue":"7","key":"5_CR11","doi-asserted-by":"publisher","first-page":"5837","DOI":"10.1007\/s10462-022-10315-0","volume":"56","author":"N Kaur","year":"2023","unstructured":"Kaur, N., Singh, P.: Conventional and contemporary approaches used in text to speech synthesis: a review. Artif. Intell. Rev. 56(7), 5837\u20135880 (2023)","journal-title":"Artif. Intell. Rev."},{"key":"5_CR12","doi-asserted-by":"crossref","unstructured":"Werchniak, A.: Exploring the application of synthetic audio in training keyword spotters. In: ICASSP 2021\u20132021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 7993\u20137996. IEEE, (2021)","DOI":"10.1109\/ICASSP39728.2021.9413448"},{"issue":"11","key":"5_CR13","doi-asserted-by":"publisher","first-page":"205","DOI":"10.21105\/joss.00205","volume":"2","author":"L McInnes","year":"2017","unstructured":"McInnes, L., Healy, J., Astels, S., et al.: hdbscan: hierarchical density based clustering. J. Open Source Softw. 2(11), 205 (2017)","journal-title":"J. Open Source Softw."},{"key":"5_CR14","doi-asserted-by":"crossref","unstructured":"Ma, Z., et al.: emotion2vec: self-supervised pre-training for speech emotion representation. arXiv preprint arXiv:2312.15185 (2023)","DOI":"10.18653\/v1\/2024.findings-acl.931"},{"issue":"1\u20133","key":"5_CR15","doi-asserted-by":"publisher","first-page":"37","DOI":"10.1016\/0169-7439(87)80084-9","volume":"2","author":"S Wold","year":"1987","unstructured":"Wold, S., Esbensen, K., Geladi, P.: Principal component analysis. Chemom. Intell. Lab. Syst. 2(1\u20133), 37\u201352 (1987)","journal-title":"Chemom. Intell. Lab. Syst."},{"key":"5_CR16","doi-asserted-by":"crossref","unstructured":"McInnes, L., Healy, J., Melville, J.: Umap: uniform manifold approximation and projection for dimension reduction. arxiv. arXiv preprint arXiv:1802.03426, 10, (2018)","DOI":"10.21105\/joss.00861"},{"key":"5_CR17","doi-asserted-by":"crossref","unstructured":"Bakhturina, E., Lavrukhin, V., Ginsburg, B., Zhang, Y.: Hi-fi multi-speaker english TTS dataset. arXiv preprint arXiv:2104.01497 (2021)","DOI":"10.21437\/Interspeech.2021-1599"}],"container-title":["Communications in Computer and Information Science","Information and Software Technologies"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-032-16808-5_5","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,15]],"date-time":"2026-04-15T22:07:04Z","timestamp":1776290824000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-032-16808-5_5"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"ISBN":["9783032168078","9783032168085"],"references-count":17,"URL":"https:\/\/doi.org\/10.1007\/978-3-032-16808-5_5","relation":{},"ISSN":["1865-0929","1865-0937"],"issn-type":[{"value":"1865-0929","type":"print"},{"value":"1865-0937","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026]]},"assertion":[{"value":"1 April 2026","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ICIST","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Information and Software Technologies","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Kaunas","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Lithuania","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":"16 October 2025","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"17 October 2025","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"31","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"icist2025","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/icist.ktu.edu\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}