{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,27]],"date-time":"2025-03-27T23:05:35Z","timestamp":1743116735133,"version":"3.40.3"},"publisher-location":"Singapore","reference-count":20,"publisher":"Springer Nature Singapore","isbn-type":[{"type":"print","value":"9789819620630"},{"type":"electronic","value":"9789819620647"}],"license":[{"start":{"date-parts":[[2024,12,28]],"date-time":"2024-12-28T00:00:00Z","timestamp":1735344000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,12,28]],"date-time":"2024-12-28T00:00:00Z","timestamp":1735344000000},"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":[[2025]]},"DOI":"10.1007\/978-981-96-2064-7_12","type":"book-chapter","created":{"date-parts":[[2024,12,27]],"date-time":"2024-12-27T19:24:32Z","timestamp":1735327472000},"page":"157-170","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Operatic Singing Voice Synthesis From Inexperienced Voice Considering Tempo and\u00a0Vowel Change"],"prefix":"10.1007","author":[{"given":"Aoto","family":"Sugahara","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Soma","family":"Kishimoto","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yuji","family":"Adachi","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Kiyoto","family":"Tai","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ryoichi","family":"Takashima","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Tetsuya","family":"Takiguchi","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2024,12,28]]},"reference":[{"key":"12_CR1","unstructured":"Chen, J., Tan, X., Luan, J., Qin, T., Liu, T.Y.: HiFiSinger: Towards High-Fidelity Neural Singing Voice Synthesis. CoRR (2020)"},{"key":"12_CR2","unstructured":"Devlin, J., Chang, M.W., Lee, K., Toutanova, K.: BERT: pre-training of Deep Bidirectional Transformers for Language Understanding. In: North American Chapter of the Association for Computational Linguistics (2019)"},{"key":"12_CR3","doi-asserted-by":"publisher","first-page":"1735","DOI":"10.1162\/neco.1997.9.8.1735","volume":"9","author":"S Hochreiter","year":"1997","unstructured":"Hochreiter, S., Schmidhuber, J.: Long short-term memory. Neural Comput. 9, 1735\u20131780 (1997). https:\/\/doi.org\/10.1162\/neco.1997.9.8.1735","journal-title":"Neural Comput."},{"key":"12_CR4","doi-asserted-by":"publisher","first-page":"3451","DOI":"10.1109\/TASLP.2021.3122291","volume":"29","author":"WN Hsu","year":"2021","unstructured":"Hsu, W.N., Bolte, B., Tsai, Y.H.H., Lakhotia, K., Salakhutdinov, R., Mohamed, A.: HuBERT: self-supervised speech representation learning by masked prediction of hidden units. IEEE\/ACM Trans. Audio Speech Lang. Proc. 29, 3451\u20133460 (2021)","journal-title":"IEEE\/ACM Trans. Audio Speech Lang. Proc."},{"key":"12_CR5","doi-asserted-by":"crossref","unstructured":"Isola, P., Zhu, J.Y., Zhou, T., Efros, A.: Image-to-image translation with conditional adversarial networks. In: CVPR, pp. 5967\u20135976 (2017)","DOI":"10.1109\/CVPR.2017.632"},{"key":"12_CR6","doi-asserted-by":"crossref","unstructured":"Katahira, K., Adachi, Y., Tai, K., Takashima, R., Takiguchi, T.: Opera singing voice synthesis considering vowel variations. In: IEEE Global Conference on Consumer Electronics (GCCE), pp. 663\u2013664 (2020)","DOI":"10.1109\/GCCE50665.2020.9291895"},{"key":"12_CR7","unstructured":"Kong, J., Kim, J., Bae, J.: HiFi-GAN: generative adversarial networks for efficient and high fidelity speech synthesis. In: Proceedings of NeurIPS, pp. 17022\u201317033 (2020)"},{"key":"12_CR8","unstructured":"Kumar, K., Kumar, R., de\u00a0Boissi\u00e8re, T., Gestin, L., Teoh, W.Z., et\u00a0al.: MelGAN: generative adversarial networks for conditional waveform synthesis. In: Neural Information Processing Systems (2019)"},{"key":"12_CR9","doi-asserted-by":"publisher","first-page":"92","DOI":"10.3342\/ceo.2008.1.2.92","volume":"1","author":"SH Lee","year":"2008","unstructured":"Lee, S.H., Kwon, H.J., Choi, H.J., Lee, N.H., Lee, S.J., Jin, S.M.: The singer\u2019s formant and speaker\u2019s ring resonance: a long-term average spectrum analysis. Clin. Exp. Otorhinolaryngol. 1, 92\u201396 (2008)","journal-title":"Clin. Exp. Otorhinolaryngol."},{"key":"12_CR10","doi-asserted-by":"crossref","unstructured":"Liu, J., Li, C., Ren, Y., Chen, F., Zhao, Z.: DiffSinger: singing voice synthesis via shallow diffusion mechanism. In: AAAI Conference on Artificial Intelligence (2021)","DOI":"10.1609\/aaai.v36i10.21350"},{"key":"12_CR11","unstructured":"Mathieu, M., Couprie, C., LeCun, Y.: Deep multi-scale video prediction beyond mean square error. In: 4th International Conference on Learning Representations (ICLR) (2016)"},{"key":"12_CR12","doi-asserted-by":"crossref","unstructured":"Morise, M., Yokomori, F., Ozawa, K.: WORLD: a vocoder-based high-quality speech synthesis system for real-time applications (2016). 2016 The Institute of Electronics, Information and Communication Engineers","DOI":"10.1587\/transinf.2015EDP7457"},{"key":"12_CR13","doi-asserted-by":"crossref","unstructured":"Nanzaka, R., Kitamura, T., Takiguchi, T., Adachi, Y., Tai, K.: Spectrum enhancement of singing voice using deep learning. In: 2018 IEEE International Symposium on Multimedia (ISM), pp. 167\u2013170 (2018)","DOI":"10.1109\/ISM.2018.00-18"},{"key":"12_CR14","doi-asserted-by":"crossref","unstructured":"van Niekerk, B., Carbonneau, M.A., Za\u00efdi, J., Baas, M., Seut\u00e9, H., Kamper, H.: A comparison of discrete and soft speech units for improved voice conversion. In: ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 6562\u20136566 (2022)","DOI":"10.1109\/ICASSP43922.2022.9746484"},{"key":"12_CR15","doi-asserted-by":"crossref","unstructured":"Panayotov, V., Chen, G., Povey, D., Khudanpur, S.: Librispeech: an ASR corpus based on public domain audio books. In: 2015 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 5206\u20135210 (2015)","DOI":"10.1109\/ICASSP.2015.7178964"},{"key":"12_CR16","unstructured":"Ren, Y., Hu, C., Tan, X., Qin, T., Zhao, S., et\u00a0al.: FastSpeech 2: fast and high-quality end-to-end text to speech. In: International Conference on Learning Representations (2021)"},{"key":"12_CR17","unstructured":"Sonobe, R., Takamichi, S., Saruwatari, H.: JSUT corpus: free large-scale Japanese speech corpus for end-to-end speech synthesis. arXiv preprint 1711.00354 (2017)"},{"key":"12_CR18","doi-asserted-by":"publisher","unstructured":"Sugahara, A., Kishimoto, S., Adachi, Y., Tai, K., Takashima, R., Takiguchi, T.: Operatic singing voice synthesis using diff-SVC. In: IEEE Global Conference on Consumer Electronics (GCCE), pp. 776\u2013777 (2023). https:\/\/doi.org\/10.1109\/GCCE59613.2023.10315526","DOI":"10.1109\/GCCE59613.2023.10315526"},{"key":"12_CR19","unstructured":"Sundberg, J.: The Science of the Singing Voice, pp. 85\u201390, 115\u2013130. Northern Illinois University Press (1987)"},{"key":"12_CR20","doi-asserted-by":"publisher","unstructured":"Wu, X., Kumar, V., Quinlan, R., Ghosh, J., Yang, Q., et\u00a0al.: Top 10 algorithms in data mining. Knowl. Inf. Syst. 14 (2007). https:\/\/doi.org\/10.1007\/s10115-007-0114-2","DOI":"10.1007\/s10115-007-0114-2"}],"container-title":["Lecture Notes in Computer Science","MultiMedia Modeling"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-981-96-2064-7_12","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,12,27]],"date-time":"2024-12-27T20:03:39Z","timestamp":1735329819000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-96-2064-7_12"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,12,28]]},"ISBN":["9789819620630","9789819620647"],"references-count":20,"URL":"https:\/\/doi.org\/10.1007\/978-981-96-2064-7_12","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2024,12,28]]},"assertion":[{"value":"28 December 2024","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"MMM","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Multimedia Modeling","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Nara","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Japan","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":"9 January 2025","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"11 January 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":"mmm2025","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/mmm2025.net\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}