{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,27]],"date-time":"2025-03-27T19:16:16Z","timestamp":1743102976206,"version":"3.40.3"},"publisher-location":"Singapore","reference-count":25,"publisher":"Springer Nature Singapore","isbn-type":[{"type":"print","value":"9789819601240"},{"type":"electronic","value":"9789819601257"}],"license":[{"start":{"date-parts":[[2024,11,12]],"date-time":"2024-11-12T00:00:00Z","timestamp":1731369600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,11,12]],"date-time":"2024-11-12T00:00:00Z","timestamp":1731369600000},"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\/978-981-96-0125-7_30","type":"book-chapter","created":{"date-parts":[[2024,11,17]],"date-time":"2024-11-17T03:06:36Z","timestamp":1731812796000},"page":"359-368","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Expressive Speech Synthesis Enhancement with\u00a0Conditional Embeddings"],"prefix":"10.1007","author":[{"given":"Fanfan","family":"Yan","sequence":"first","affiliation":[]},{"given":"Maoyu","family":"Zhang","sequence":"additional","affiliation":[]},{"given":"Hai","family":"Xu","sequence":"additional","affiliation":[]},{"given":"Haoran","family":"Ding","sequence":"additional","affiliation":[]},{"given":"Meng","family":"Guo","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2024,11,12]]},"reference":[{"key":"30_CR1","doi-asserted-by":"crossref","unstructured":"Cai, X., Dai, D., Wu, Z., Li, X., Li, J., Meng, H.: Emotion controllable speech synthesis using emotion-unlabeled dataset with the assistance of cross-domain speech emotion recognition. In: ICASSP 2021-2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 5734\u20135738. IEEE (2021)","DOI":"10.1109\/ICASSP39728.2021.9413907"},{"key":"30_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":"30_CR3","unstructured":"Kingma, D.P., Welling, M.: Auto-encoding variational Bayes. arXiv preprint arXiv:1312.6114 (2013)"},{"key":"30_CR4","first-page":"17022","volume":"33","author":"J Kong","year":"2020","unstructured":"Kong, J., Kim, J., Bae, J.: HiFi-GAN: generative adversarial networks for efficient and high fidelity speech synthesis. Adv. Neural. Inf. Process. Syst. 33, 17022\u201317033 (2020)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"30_CR5","doi-asserted-by":"crossref","unstructured":"Lee, Y., Kim, T.: Robust and fine-grained prosody control of end-to-end speech synthesis. In: ICASSP 2019-2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 5911\u20135915. IEEE (2019)","DOI":"10.1109\/ICASSP.2019.8683501"},{"key":"30_CR6","unstructured":"Lee, Y., Rabiee, A., Lee, S.Y.: Emotional end-to-end neural speech synthesizer. arXiv preprint arXiv:1711.05447 (2017)"},{"key":"30_CR7","doi-asserted-by":"publisher","first-page":"853","DOI":"10.1109\/TASLP.2022.3145293","volume":"30","author":"Y Lei","year":"2022","unstructured":"Lei, Y., Yang, S., Wang, X., Xie, L.: MsEmotts: multi-scale emotion transfer, prediction, and control for emotional speech synthesis. IEEE\/ACM Trans. Audio, Speech Lang. Process. 30, 853\u2013864 (2022)","journal-title":"IEEE\/ACM Trans. Audio, Speech Lang. Process."},{"key":"30_CR8","doi-asserted-by":"publisher","first-page":"1448","DOI":"10.1109\/TASLP.2022.3164181","volume":"30","author":"T Li","year":"2022","unstructured":"Li, T., Wang, X., Xie, Q., Wang, Z., Xie, L.: Cross-speaker emotion disentangling and transfer for end-to-end speech synthesis. IEEE\/ACM Trans. Audio, Speech, and Lang. Process. 30, 1448\u20131460 (2022)","journal-title":"IEEE\/ACM Trans. Audio, Speech, and Lang. Process."},{"key":"30_CR9","unstructured":"Liu, R., Liu, B., Li, H.: Emotion-aware prosodic phrasing for expressive text-to-speech. arXiv preprint arXiv:2309.11724 (2023)"},{"key":"30_CR10","unstructured":"Liu, Y., et al.: RoBERTa: a robustly optimized BERT pretraining approach. arXiv preprint arXiv:1907.11692 (2019)"},{"key":"30_CR11","unstructured":"Loshchilov, I., Hutter, F.: Decoupled weight decay regularization. arXiv preprint arXiv:1711.05101 (2017)"},{"key":"30_CR12","doi-asserted-by":"crossref","unstructured":"Schneider, S., Baevski, A., Collobert, R., Auli, M.: wav2vec: unsupervised pre-training for speech recognition. arXiv preprint arXiv:1904.05862 (2019)","DOI":"10.21437\/Interspeech.2019-1873"},{"key":"30_CR13","doi-asserted-by":"crossref","unstructured":"Shen, J., et\u00a0al.: 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":"30_CR14","doi-asserted-by":"crossref","unstructured":"Shin, Y., Lee, Y., Jo, S., Hwang, Y., Kim, T.: Text-driven emotional style control and cross-speaker style transfer in neural TTS. arXiv preprint arXiv:2207.06000 (2022)","DOI":"10.21437\/Interspeech.2022-10131"},{"key":"30_CR15","doi-asserted-by":"crossref","unstructured":"Shirahata, Y., Yamamoto, R., Song, E., Terashima, R., Kim, J.M., Tachibana, K.: Period VITS: variational inference with explicit pitch modeling for end-to-end emotional speech synthesis. In: ICASSP 2023-2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp.\u00a01\u20135. IEEE (2023)","DOI":"10.1109\/ICASSP49357.2023.10096480"},{"key":"30_CR16","unstructured":"Skerry-Ryan, R., et al.: Towards end-to-end prosody transfer for expressive speech synthesis with Tacotron. In: International Conference on Machine Learning, pp. 4693\u20134702. PMLR (2018)"},{"key":"30_CR17","doi-asserted-by":"crossref","unstructured":"Um, S.Y., Oh, S., Byun, K., Jang, I., Ahn, C., Kang, H.G.: Emotional speech synthesis with rich and granularized control. In: ICASSP 2020-2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 7254\u20137258. IEEE (2020)","DOI":"10.1109\/ICASSP40776.2020.9053732"},{"key":"30_CR18","unstructured":"Vaswani, A., et al.: Attention is all you need. In: Advances in Neural Information Processing Systems, vol. 30 (2017)"},{"key":"30_CR19","doi-asserted-by":"crossref","unstructured":"Wang, Y., et\u00a0al.: Tacotron: towards end-to-end speech synthesis. arXiv preprint arXiv:1703.10135 (2017)","DOI":"10.21437\/Interspeech.2017-1452"},{"key":"30_CR20","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, pp. 5180\u20135189. PMLR (2018)"},{"key":"30_CR21","doi-asserted-by":"crossref","unstructured":"Wu, P., Ling, Z., Liu, L., Jiang, Y., Wu, H., Dai, L.: End-to-end emotional speech synthesis using style tokens and semi-supervised training. In: 2019 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC), pp. 623\u2013627. IEEE (2019)","DOI":"10.1109\/APSIPAASC47483.2019.9023186"},{"key":"30_CR22","doi-asserted-by":"crossref","unstructured":"Zen, H., Senior, A., Schuster, M.: Statistical parametric speech synthesis using deep neural networks. In: 2013 IEEE International Conference on Acoustics, Speech and Signal Processing, pp. 7962\u20137966. IEEE (2013)","DOI":"10.1109\/ICASSP.2013.6639215"},{"key":"30_CR23","doi-asserted-by":"crossref","unstructured":"Zhang, Y., Cong, J., Xue, H., Xie, L., Zhu, P., Bi, M.: VISinger: variational inference with adversarial learning for end-to-end singing voice synthesis. In: ICASSP 2022-2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 7237\u20137241. IEEE (2022)","DOI":"10.1109\/ICASSP43922.2022.9747664"},{"issue":"4","key":"30_CR24","doi-asserted-by":"publisher","first-page":"2225","DOI":"10.3390\/app13042225","volume":"13","author":"W Zhao","year":"2023","unstructured":"Zhao, W., Yang, Z.: An emotion speech synthesis method based on VITS. Appl. Sci. 13(4), 2225 (2023)","journal-title":"Appl. Sci."},{"key":"30_CR25","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1016\/j.specom.2021.11.006","volume":"137","author":"K Zhou","year":"2022","unstructured":"Zhou, K., Sisman, B., Liu, R., Li, H.: Emotional voice conversion: theory, databases and ESD. Speech Commun. 137, 1\u201318 (2022)","journal-title":"Speech Commun."}],"container-title":["Lecture Notes in Computer Science","PRICAI 2024: Trends in Artificial Intelligence"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-981-96-0125-7_30","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,11,17]],"date-time":"2024-11-17T04:32:00Z","timestamp":1731817920000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-96-0125-7_30"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,11,12]]},"ISBN":["9789819601240","9789819601257"],"references-count":25,"URL":"https:\/\/doi.org\/10.1007\/978-981-96-0125-7_30","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2024,11,12]]},"assertion":[{"value":"12 November 2024","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"PRICAI","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Pacific Rim International Conference on Artificial Intelligence","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Kyoto","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":"2024","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"19 November 2024","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"25 November 2024","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"21","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"pricai2024","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/www.pricai.org\/2024\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}