{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,22]],"date-time":"2025-11-22T05:53:50Z","timestamp":1763790830732,"version":"3.45.0"},"publisher-location":"Singapore","reference-count":19,"publisher":"Springer Nature Singapore","isbn-type":[{"value":"9789819533459","type":"print"},{"value":"9789819533466","type":"electronic"}],"license":[{"start":{"date-parts":[[2025,11,23]],"date-time":"2025-11-23T00:00:00Z","timestamp":1763856000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,11,23]],"date-time":"2025-11-23T00:00:00Z","timestamp":1763856000000},"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\/978-981-95-3346-6_9","type":"book-chapter","created":{"date-parts":[[2025,11,22]],"date-time":"2025-11-22T05:49:38Z","timestamp":1763790578000},"page":"115-127","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Fine-Grained Prosody-Controllable Lao Speech Synthesis Guided by\u00a0Natural Language"],"prefix":"10.1007","author":[{"given":"Na","family":"Wang","sequence":"first","affiliation":[]},{"given":"Zhenbei","family":"Guo","sequence":"additional","affiliation":[]},{"given":"Cunli","family":"Mao","sequence":"additional","affiliation":[]},{"given":"Linqin","family":"Wang","sequence":"additional","affiliation":[]},{"given":"Zhengtao","family":"Yu","sequence":"additional","affiliation":[]},{"given":"Shengxiang","family":"Gao","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2025,11,23]]},"reference":[{"key":"9_CR1","doi-asserted-by":"crossref","unstructured":"Xie, T., Rong, Y., Zhang, P., Liu, L.: Towards controllable speech synthesis in the era of large language models: a survey. arXiv preprint arXiv:2412.06602 (2024)","DOI":"10.18653\/v1\/2025.emnlp-main.40"},{"key":"9_CR2","doi-asserted-by":"crossref","unstructured":"Guo, Z., Leng, Y., Wu, Y., Zhao, S., Tan, X.: Prompttts: controllable text-to-speech with text descriptions. In: ICASSP 2023-2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 1\u20135. IEEE (2023)","DOI":"10.1109\/ICASSP49357.2023.10096285"},{"key":"9_CR3","doi-asserted-by":"crossref","unstructured":"Ji, S., et\u00a0al.: Controlspeech: towards simultaneous zero-shot speaker cloning and zero-shot language style control with decoupled codec. arXiv preprint arXiv:2406.01205 (2024)","DOI":"10.18653\/v1\/2025.acl-long.346"},{"key":"9_CR4","doi-asserted-by":"crossref","unstructured":"Jin, Z., et al.: Speechcraft: a fine-grained expressive speech dataset with natural language description. In: Proceedings of the 32nd ACM International Conference on Multimedia, pp. 1255\u20131264 (2024)","DOI":"10.1145\/3664647.3681674"},{"key":"9_CR5","doi-asserted-by":"crossref","unstructured":"Ji, S., et al.: Textrolspeech: a text style control speech corpus with codec language text-to-speech models. In: ICASSP 2024-2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 10301\u201310305. IEEE (2024)","DOI":"10.1109\/ICASSP48485.2024.10445879"},{"key":"9_CR6","doi-asserted-by":"crossref","unstructured":"Chen, S., et al.: Neural codec language models are zero-shot text to speech synthesizers. IEEE Trans. Audio Speech Lang. Process. (2025)","DOI":"10.1109\/TASLPRO.2025.3530270"},{"key":"9_CR7","unstructured":"Lyth, D., King, S.: Natural language guidance of high-fidelity text-to-speech with synthetic annotations. arXiv preprint arXiv:2402.01912 (2024)"},{"key":"9_CR8","doi-asserted-by":"crossref","unstructured":"Yang, D., Liu, S., Huang, R., Weng, C., Meng, H.: Instructtts: modelling expressive tts in discrete latent space with natural language style prompt. IEEE\/ACM Trans. Audio Speech Lang. Process. (2024)","DOI":"10.1109\/TASLP.2024.3402088"},{"key":"9_CR9","doi-asserted-by":"crossref","unstructured":"Yamamoto, R., Shirahata, Y., Kawamura, M., Tachibana, K.: Description-based controllable text-to-speech with cross-lingual voice control. In: ICASSP 2025-2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 1\u20135. IEEE (2025)","DOI":"10.1109\/ICASSP49660.2025.10887783"},{"key":"9_CR10","doi-asserted-by":"crossref","unstructured":"Sun, G., Zhang, Y., Weiss, R.J., Cao, Y., Zen, H., Wu, Y.: Fully-hierarchical fine-grained prosody modeling for interpretable speech synthesis. In: ICASSP 2020-2020 IEEE international conference on acoustics, speech and signal processing (ICASSP), pp. 6264\u20136268. IEEE (2020)","DOI":"10.1109\/ICASSP40776.2020.9053520"},{"key":"9_CR11","unstructured":"Liu, Z., et al.: Controllable and lossless non-autoregressive end-to-end text-to-speech. arXiv preprint arXiv:2207.06088 (2022)"},{"issue":"1","key":"9_CR12","doi-asserted-by":"publisher","first-page":"361","DOI":"10.1007\/s00034-022-02126-z","volume":"42","author":"G Pamisetty","year":"2023","unstructured":"Pamisetty, G., Murty, K.S.R.: Prosody-tts: an end-to-end speech synthesis system with prosody control. Circ. Syst. Signal Process. 42(1), 361\u2013384 (2023)","journal-title":"Circ. Syst. Signal Process."},{"key":"9_CR13","doi-asserted-by":"crossref","unstructured":"Guo, Y., Du, C., Yu, K.: Unsupervised word-level prosody tagging for controllable speech synthesis. In: ICASSP 2022-2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 7597\u20137601. IEEE (2022)","DOI":"10.1109\/ICASSP43922.2022.9746323"},{"key":"9_CR14","doi-asserted-by":"crossref","unstructured":"Korotkova, Y., Kalinovskiy, I., Vakhrusheva, T.: Word-level text markup for prosody control in speech synthesis. In: Proceedings of Interspeech 2024, pp. 2280\u20132284 (2024)","DOI":"10.21437\/Interspeech.2024-715"},{"key":"9_CR15","doi-asserted-by":"crossref","unstructured":"Xue, L., et al.: mt5: a massively multilingual pre-trained text-to-text transformer. arXiv preprint arXiv:2010.11934 (2020)","DOI":"10.18653\/v1\/2021.naacl-main.41"},{"key":"9_CR16","unstructured":"Yi, C., Wang, J., Cheng, N., Zhou, S., Xu, B.: Applying wav2vec2. 0 to speech recognition in various low-resource languages. arXiv preprint arXiv:2012.12121 (2020)"},{"key":"9_CR17","doi-asserted-by":"crossref","unstructured":"Conneau, A., et al.: Unsupervised cross-lingual representation learning at scale. arXiv preprint arXiv:1911.02116 (2019)","DOI":"10.18653\/v1\/2020.acl-main.747"},{"key":"9_CR18","unstructured":"Mortensen, D.R., Dalmia, S., Littell, P.: Epitran: precision G2P for many languages. In: Calzolari, N. et al. (eds.) Proceedings of the Eleventh International Conference on Language Resources and Evaluation (LREC 2018), Paris, France, May 2018. European Language Resources Association (ELRA) (2018)"},{"key":"9_CR19","first-page":"27980","volume":"36","author":"R Kumar","year":"2023","unstructured":"Kumar, R., Seetharaman, P., Luebs, A., Kumar, I., Kumar, K.: High-fidelity audio compression with improved rvqgan. Adv. Neural. Inf. Process. Syst. 36, 27980\u201327993 (2023)","journal-title":"Adv. Neural. Inf. Process. Syst."}],"container-title":["Lecture Notes in Computer Science","Natural Language Processing and Chinese Computing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-981-95-3346-6_9","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,11,22]],"date-time":"2025-11-22T05:49:44Z","timestamp":1763790584000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-95-3346-6_9"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,11,23]]},"ISBN":["9789819533459","9789819533466"],"references-count":19,"URL":"https:\/\/doi.org\/10.1007\/978-981-95-3346-6_9","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,11,23]]},"assertion":[{"value":"23 November 2025","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"NLPCC","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"CCF International Conference on Natural Language Processing and Chinese Computing","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Urumqi","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"China","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":"7 August 2025","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"9 August 2025","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"14","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"nlpcc2025","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/tcci.ccf.org.cn\/conference\/2025\/index.php","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}