{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,13]],"date-time":"2026-07-13T20:07:11Z","timestamp":1783973231656,"version":"3.55.0"},"publisher-location":"Singapore","reference-count":13,"publisher":"Springer Nature Singapore","isbn-type":[{"value":"9789819234912","type":"print"},{"value":"9789819234929","type":"electronic"}],"license":[{"start":{"date-parts":[[2026,7,14]],"date-time":"2026-07-14T00:00:00Z","timestamp":1783987200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2026,7,14]],"date-time":"2026-07-14T00:00:00Z","timestamp":1783987200000},"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":[[2027]]},"DOI":"10.1007\/978-981-92-3492-9_5","type":"book-chapter","created":{"date-parts":[[2026,7,13]],"date-time":"2026-07-13T19:39:44Z","timestamp":1783971584000},"page":"51-61","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["ManchuTTS: Towards High-Quality Manchu Speech Synthesis via Flow Matching and Hierarchical Text Representation"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-3450-0826","authenticated-orcid":false,"given":"Suhua","family":"Wang","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0002-0438-2969","authenticated-orcid":false,"given":"Zifan","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5463-8171","authenticated-orcid":false,"given":"Xiaoxin","family":"Sun","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6724-5537","authenticated-orcid":false,"given":"Meiqi","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-8243-608X","authenticated-orcid":false,"given":"Yun","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4415-5365","authenticated-orcid":false,"given":"Xin","family":"Li","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,7,14]]},"reference":[{"key":"5_CR1","unstructured":"Shu, P., et al.: Transcending language boundaries: harnessing LLMs for low-resource language translation. arXiv preprint arXiv:2411.11295 (2024)"},{"key":"5_CR2","doi-asserted-by":"publisher","first-page":"6246","DOI":"10.52202\/079017-0202","volume":"37","author":"F Shen","year":"2024","unstructured":"Shen, F., Tang, J.: Imagpose: a unified conditional framework for pose-guided person generation. Adv. Neural. Inf. Process. Syst. 37, 6246\u20136266 (2024)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"5_CR3","unstructured":"Shen, F., et al.: Long-term talking face generation via motion-prior conditional diffusion model. arXiv preprint arXiv:2502.09533 (2025)"},{"issue":"10","key":"5_CR4","doi-asserted-by":"publisher","first-page":"258","DOI":"10.1007\/s10462-024-10891-3","volume":"57","author":"Y Wang","year":"2024","unstructured":"Wang, Y., Wang, Z., Yu, H., Wang, G., Lei, D.: The interactive fusion of characters and lexical information for Chinese named entity recognition. Artif. Intell. Rev. 57(10), 258 (2024)","journal-title":"Artif. Intell. Rev."},{"key":"5_CR5","doi-asserted-by":"crossref","unstructured":"Lee, Y., Kim, C.: Wave-u-mamba: an end-to-end framework for high-quality and efficient speech super resolution. In: ICASSP 2025\u20132025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 1\u20135. IEEE (2025)","DOI":"10.1109\/ICASSP49660.2025.10890511"},{"key":"5_CR6","doi-asserted-by":"crossref","unstructured":"Chen, Y., et al.: F5-TTS: a fairytaler that fakes fluent and faithful speech with flow matching. arXiv preprint arXiv:2410.06885 (2024)","DOI":"10.18653\/v1\/2025.acl-long.313"},{"key":"5_CR7","doi-asserted-by":"crossref","unstructured":"Wang, K., Guan, W., Lu, S., Yao, J., Li, L., Hong, Q.: Slimspeech: lightweight and efficient text-to-speech with slim rectified flow. In: ICASSP 2025\u20132025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 1\u20135. IEEE (2025)","DOI":"10.1109\/ICASSP49660.2025.10889258"},{"key":"5_CR8","doi-asserted-by":"crossref","unstructured":"McAuliffe, M., Socolof, M., Mihuc, S., Wagner, M., Sonderegger, M.: Montreal forced aligner: trainable text-speech alignment using kaldi. In: Interspeech, vol. 2017, pp. 498\u2013502 (2017)","DOI":"10.21437\/Interspeech.2017-1386"},{"key":"5_CR9","doi-asserted-by":"crossref","unstructured":"Aziz, A.F.A., Tiun, S., Ruslan, N.: End to end text to speech synthesis for Malay language using Tacotron and Tacotron 2. Int. J. Adv. Comput. Sci. Appl. 14(6) (2023)","DOI":"10.14569\/IJACSA.2023.0140644"},{"key":"5_CR10","doi-asserted-by":"crossref","unstructured":"Gopalakrishnan, T., Imam, S.A., Aggarwal, A.: Fine tuning and comparing Tacotron 2, deep voice 3, and fastspeech 2 TTS models in a low resource environment. In: 2022 IEEE International Conference on Data Science and Information System (ICDSIS), pp. 1\u20136. IEEE (2022)","DOI":"10.1109\/ICDSIS55133.2022.9915932"},{"key":"5_CR11","first-page":"8067","volume":"33","author":"J Kim","year":"2020","unstructured":"Kim, J., Kim, S., Kong, J., Yoon, S.: Glow-TTS: a generative flow for text-to-speech via monotonic alignment search. Adv. Neural. Inf. Process. Syst. 33, 8067\u20138077 (2020)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"5_CR12","doi-asserted-by":"crossref","unstructured":"Xing, Z., Xiong, B., Wen, W.: Low-resource VITS-based emotion speech synthesis using KNN algorithm. In: Pacific Rim International Conference on Artificial Intelligence, pp. 333\u2013345. Springer (2024)","DOI":"10.1007\/978-981-96-0125-7_28"},{"key":"5_CR13","doi-asserted-by":"crossref","unstructured":"Wei, C.C., Hung, L.C., Gao, S.Y., Chen, Y.C., Tseng, S.P.: Personalized audiobook generation using voice cloning and text-to-speech synthesis. In: 2024 International Conference on Orange Technology (ICOT), pp. 1\u20134. IEEE (2024)","DOI":"10.1109\/ICOT64290.2024.10936951"}],"container-title":["Lecture Notes in Computer Science","Advanced Intelligent Computing Technology and Applications"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-981-92-3492-9_5","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,7,13]],"date-time":"2026-07-13T19:39:46Z","timestamp":1783971586000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-92-3492-9_5"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,7,14]]},"ISBN":["9789819234912","9789819234929"],"references-count":13,"URL":"https:\/\/doi.org\/10.1007\/978-981-92-3492-9_5","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,7,14]]},"assertion":[{"value":"14 July 2026","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"The authors declare no conflicts of interest.","order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Disclosure of Interests"}},{"value":"ICIC","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Intelligent Computing","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Toronto","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Canada","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2026","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"22 July 2026","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"26 July 2026","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"22","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"icic2026a","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/www.ic-icc.cn\/2026\/index.htm","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}