{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,11]],"date-time":"2026-06-11T11:00:12Z","timestamp":1781175612163,"version":"3.54.1"},"publisher-location":"Singapore","reference-count":17,"publisher":"Springer Nature Singapore","isbn-type":[{"value":"9789819200702","type":"print"},{"value":"9789819200719","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\/978-981-92-0071-9_32","type":"book-chapter","created":{"date-parts":[[2026,6,11]],"date-time":"2026-06-11T10:35:54Z","timestamp":1781174154000},"page":"476-486","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Adapting Emotional Expressiveness in\u00a0Text-to-Speech for\u00a0Low-Resource Languages"],"prefix":"10.1007","author":[{"given":"Luong","family":"Ho","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hao","family":"Do","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Minh","family":"Nguyen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Duc","family":"Chau","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,6,1]]},"reference":[{"key":"32_CR1","unstructured":"Casanova, E., Weber, J., Shulby, C.D., J\u00fanior, A.C., G\u00f6lge, E., Ponti, M.A.: Yourtts: towards zero-shot multi-speaker tts and zero-shot voice conversion for everyone. In: International Conference on Machine Learning (2021). https:\/\/api.semanticscholar.org\/CorpusID:244908340"},{"key":"32_CR2","doi-asserted-by":"crossref","unstructured":"Chandra, S.S., Du, Z., Sisman, B.: Exploring speech style spaces with language models: Emotional tts without emotion labels. ArXiv arXiv:2405.11413 (2024). https:\/\/api.semanticscholar.org\/CorpusID:269921953","DOI":"10.21437\/odyssey.2024-28"},{"key":"32_CR3","unstructured":"Jia, Y., et al.: Transfer learning from speaker verification to multispeaker text-to-speech synthesis. ArXiv arXiv:1806.04558 (2018). https:\/\/api.semanticscholar.org\/CorpusID:48363067"},{"key":"32_CR4","unstructured":"Jung, W., Lee, J.: E3-vits: emotional end-to-end tts with cross-speaker style transfer"},{"key":"32_CR5","unstructured":"Kim, J., Kong, J., Son, J.: Conditional variational autoencoder with adversarial learning for end-to-end text-to-speech. ArXiv arXiv:2106.06103. https:\/\/api.semanticscholar.org\/CorpusID:235417304"},{"key":"32_CR6","unstructured":"Kong, J., Kim, J., Bae, J.: Hifi-gan: generative adversarial networks for efficient and high fidelity speech synthesis. ArXiv arXiv:2010.05646 (2020). https:\/\/api.semanticscholar.org\/CorpusID:222291664"},{"key":"32_CR7","doi-asserted-by":"crossref","unstructured":"Kong, J., Park, J., Kim, B., Kim, J., Kong, D., Kim, S.: Vits2: improving quality and efficiency of single-stage text-to-speech with adversarial learning and architecture design. ArXiv arXiv:2307.16430 (2023). https:\/\/api.semanticscholar.org\/CorpusID:260334571","DOI":"10.21437\/Interspeech.2023-534"},{"key":"32_CR8","unstructured":"Le, T., [c\u00e1c t\u00e1c gi nu c\u00f3\u00a0trong README]: vivoice: enabling vietnamese multi-speaker speech synthesis. https:\/\/github.com\/thinhlpg\/viVoice (2024). Accessed 01 Sep 2025"},{"key":"32_CR9","doi-asserted-by":"crossref","unstructured":"Li, T., et al.: Diclet-tts: diffusion model based cross-lingual emotion transfer for text-to-speech \u2014 a study between english and mandarin. IEEE\/ACM Trans. Audio Speech Lang. Process. 31, 3418\u20133430 (2023). https:\/\/api.semanticscholar.org\/CorpusID:261529948","DOI":"10.1109\/TASLP.2023.3313413"},{"key":"32_CR10","doi-asserted-by":"crossref","unstructured":"Liu, S., Cao, Y., Wang, D., Wu, X., Liu, X., Meng, H.M.: Any-to-many voice conversion with location-relative sequence-to-sequence modeling. IEEE\/ACM Trans. Audio Speech Lang. Process. 29, 1717\u20131728 (2020). https:\/\/api.semanticscholar.org\/CorpusID:221516317","DOI":"10.1109\/TASLP.2021.3076867"},{"key":"32_CR11","doi-asserted-by":"crossref","unstructured":"Nekvinda, T., Dusek, O.: One model, many languages: meta-learning for multilingual text-to-speech. In: Interspeech (2020). https:\/\/api.semanticscholar.org\/CorpusID:220935720","DOI":"10.21437\/Interspeech.2020-2679"},{"key":"32_CR12","unstructured":"Wang, Y., et al.: Style tokens: Unsupervised style modeling, control and transfer in end-to-end speech synthesis. In: International Conference on Machine Learning (2018). https:\/\/api.semanticscholar.org\/CorpusID:4349820"},{"key":"32_CR13","unstructured":"Wu, P., et al.: Cross-speaker emotion transfer based on speaker condition layer normalization and semi-supervised training in text-to-speech. ArXiv arXiv:2110.04153 (2021). https:\/\/api.semanticscholar.org\/CorpusID:238531605"},{"key":"32_CR14","unstructured":"Zhang, B., et al.: Wenet: production first and production ready end-to-end speech recognition toolkit. ArXiv arXiv:2102.01547 (2021). https:\/\/api.semanticscholar.org\/CorpusID:231749822"},{"key":"32_CR15","doi-asserted-by":"crossref","unstructured":"Zhang, Y., et al.: Learning to speak fluently in a foreign language: multilingual speech synthesis and cross-language voice cloning. ArXiv arXiv:1907.04448 (2019). https:\/\/api.semanticscholar.org\/CorpusID:195873975","DOI":"10.21437\/Interspeech.2019-2668"},{"key":"32_CR16","doi-asserted-by":"crossref","unstructured":"Zhou, K., Sisman, B., Liu, R., Li, H.: Seen and unseen emotional style transfer for voice conversion with a new emotional speech dataset. In: ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 920\u2013924 (2020). https:\/\/api.semanticscholar.org\/CorpusID:225094190","DOI":"10.1109\/ICASSP39728.2021.9413391"},{"key":"32_CR17","doi-asserted-by":"crossref","unstructured":"Zhu, X., et al.: Metts: multilingual emotional text-to-speech by cross-speaker and cross-lingual emotion transfer. IEEE\/ACM Trans. Audio Speech Lang. Process. 32, 1506\u20131518 (2023). https:\/\/api.semanticscholar.org\/CorpusID:260334233","DOI":"10.1109\/TASLP.2024.3363444"}],"container-title":["Lecture Notes in Computer Science","Intelligent Information and Database Systems"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-981-92-0071-9_32","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,6,11]],"date-time":"2026-06-11T10:36:03Z","timestamp":1781174163000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-92-0071-9_32"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"ISBN":["9789819200702","9789819200719"],"references-count":17,"URL":"https:\/\/doi.org\/10.1007\/978-981-92-0071-9_32","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026]]},"assertion":[{"value":"1 June 2026","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ACIIDS","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Asian Conference on Intelligent Information and Database Systems","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Kaohsiung","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Taiwan","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":"13 April 2026","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"15 April 2026","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"18","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"aciids2026","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/aciids.pwr.edu.pl\/2026\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}