{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,30]],"date-time":"2025-12-30T23:55:21Z","timestamp":1767138921804,"version":"build-2238731810"},"publisher-location":"Singapore","reference-count":21,"publisher":"Springer Nature Singapore","isbn-type":[{"value":"9789819628810","type":"print"},{"value":"9789819628827","type":"electronic"}],"license":[{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"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\/978-981-96-2882-7_4","type":"book-chapter","created":{"date-parts":[[2025,3,8]],"date-time":"2025-03-08T01:59:45Z","timestamp":1741399185000},"page":"30-40","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Intensity Controllable Emotional Speech Synthesis Based on Valence-Arousal-Dominance"],"prefix":"10.1007","author":[{"given":"Guoping","family":"Li","sequence":"first","affiliation":[]},{"given":"Yanxiang","family":"Chen","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2025,3,9]]},"reference":[{"key":"4_CR1","unstructured":"Lee, Y., Rabiee, A., Lee, S.-Y.: Emotional end-to-end neural speech synthesizer. arxiv preprint arxiv:1711.05447 (2017)"},{"key":"4_CR2","unstructured":"Wang, Y., Stanton, D., Zhang, Y., et al.: Style tokens: unsupervised style modeling, control and transfer in end-to-end speech synthesis. In: International Conference on Machine Learning, PMLR, pp. 5180\u20135189 (2018)"},{"key":"4_CR3","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, November 2019","DOI":"10.1109\/APSIPAASC47483.2019.9023186"},{"key":"4_CR4","doi-asserted-by":"crossref","unstructured":"Tang, H., Zhang, X., Wang, J., Cheng, N.: Emomix: emotion mixing via diffusion models for emotional speech synthesis. arxiv preprint arxiv:2306.00648 (2023)","DOI":"10.21437\/Interspeech.2023-1317"},{"key":"4_CR5","doi-asserted-by":"crossref","unstructured":"Li, T., et al.: Cross-speaker emotion transfer based on prosody compensation for end-to-end speech synthesis. arxiv preprint arxiv:2207.01198 (2022)","DOI":"10.21437\/Interspeech.2022-610"},{"key":"4_CR6","doi-asserted-by":"crossref","unstructured":"Zhu, X., et al.: Controlling emotion strength with relative attribute for end-to-end speech synthesis. In: 2019 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU), IEEE (2019)","DOI":"10.1109\/ASRU46091.2019.9003829"},{"key":"4_CR7","doi-asserted-by":"crossref","unstructured":"Zhou, K., et al.: Emotion intensity and its control for emotional voice conversion. IEEE Trans. Affect. Comput. 14(1), 31\u201348 (2022)","DOI":"10.1109\/TAFFC.2022.3175578"},{"key":"4_CR8","doi-asserted-by":"crossref","unstructured":"Um, S.Y., Oh, S., Byun, K., et al.: Emotional speech synthesis with rich and granularized control. In: ICASSP 2020\u20132020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), IEEE (2020)","DOI":"10.1109\/ICASSP40776.2020.9053732"},{"key":"4_CR9","doi-asserted-by":"crossref","unstructured":"Ma, Z., et al.: emotion2vec: Self-supervised pre-training for speech emotion representation. arxiv preprint arxiv:2312.15185 (2023)","DOI":"10.18653\/v1\/2024.findings-acl.931"},{"key":"4_CR10","doi-asserted-by":"crossref","unstructured":"Nandini, D., et al.: Design of subject independent 3D VAD emotion detection system using EEG signals and machine learning algorithms. Biomed. Sig. Process. Control 85, 104894 (2023)","DOI":"10.1016\/j.bspc.2023.104894"},{"key":"4_CR11","unstructured":"Baevski, A., et al.: wav2vec 2.0: a framework for self-supervised learning of speech representations. Adv. Neural Inf. Process. Syst. 33, 12449\u201312460 (2020)"},{"key":"4_CR12","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, PMLR (2021)"},{"issue":"4","key":"4_CR13","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":"4_CR14","doi-asserted-by":"publisher","first-page":"132306","DOI":"10.1016\/j.physd.2019.132306","volume":"404","author":"A Sherstinsky","year":"2020","unstructured":"Sherstinsky, A.: Fundamentals of recurrent neural network (RNN) and long short-term memory (LSTM) network. Physica D 404, 132306 (2020)","journal-title":"Physica D"},{"key":"4_CR15","doi-asserted-by":"crossref","unstructured":"Vielzeuf, V., et al.: Centralnet: a multilayer approach for multimodal fusion. In: Proceedings of the European Conference on Computer Vision (ECCV) Workshops (2018)","DOI":"10.1007\/978-3-030-11024-6_44"},{"key":"4_CR16","doi-asserted-by":"crossref","unstructured":"Zhou, K., et al.: Seen and unseen emotional style transfer for voice conversion with a new emotional speech dataset. In: ICASSP 2021\u20132021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), IEEE (2021)","DOI":"10.1109\/ICASSP39728.2021.9413391"},{"key":"4_CR17","unstructured":"Ilya, L., Frank, H.: Decoupled weight decay regularization. arxiv preprint arxiv:1711.05101 (2017)"},{"key":"4_CR18","unstructured":"Robert, K.: Mel-cepstral distance measure for objective speech quality assessment. In: Proceedings of IEEE pacific Rim Conference on Communications Computers and Signal Processing, vol. 1, IEEE (1993)"},{"key":"4_CR19","doi-asserted-by":"publisher","first-page":"79861","DOI":"10.1109\/ACCESS.2020.2990405","volume":"8","author":"M Sajjad","year":"2020","unstructured":"Sajjad, M., Kwon, S.: Clustering-based speech emotion recognition by incorporating learned features and deep BiLSTM. IEEE Access 8, 79861\u201379875 (2020)","journal-title":"IEEE Access"},{"issue":"2","key":"4_CR20","doi-asserted-by":"publisher","first-page":"213","DOI":"10.1007\/s00530-014-0446-1","volume":"22","author":"RC Streijl","year":"2016","unstructured":"Streijl, R.C., Winkler, S., Hands, D.S.: Mean opinion score (MOS) revisited: methods and applications, limitations and alternatives. Multimedia Syst. 22(2), 213\u2013227 (2016)","journal-title":"Multimedia Syst."},{"key":"4_CR21","unstructured":"Svetlana, K., Mohammad, S.M.: Best-worst scaling more reliable than rating scales: a case study on sentiment intensity annotation. arxiv preprint arxiv:1712.01765 (2017)"}],"updated-by":[{"DOI":"10.1007\/978-981-96-2882-7_29","type":"correction","label":"Correction","source":"publisher","updated":{"date-parts":[[2025,5,14]],"date-time":"2025-05-14T00:00:00Z","timestamp":1747180800000}}],"container-title":["Lecture Notes in Computer Science","Advances in Brain Inspired Cognitive Systems"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-981-96-2882-7_4","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,5,13]],"date-time":"2025-05-13T01:37:29Z","timestamp":1747100249000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-96-2882-7_4"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025]]},"ISBN":["9789819628810","9789819628827"],"references-count":21,"URL":"https:\/\/doi.org\/10.1007\/978-981-96-2882-7_4","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025]]},"assertion":[{"value":"9 March 2025","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"14 May 2025","order":2,"name":"change_date","label":"Change Date","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"Correction","order":3,"name":"change_type","label":"Change Type","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"A correction has been published.","order":4,"name":"change_details","label":"Change Details","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"BICS","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Brain Inspired Cognitive Systems","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Hefei","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":"2024","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"7 December 2024","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"9 December 2024","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":"bics2024","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/bics2024.dobell.me\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}