{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,3]],"date-time":"2026-07-03T18:24:11Z","timestamp":1783103051535,"version":"3.54.6"},"publisher-location":"Singapore","reference-count":20,"publisher":"Springer Nature Singapore","isbn-type":[{"value":"9789819698042","type":"print"},{"value":"9789819698059","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\/978-981-96-9805-9_36","type":"book-chapter","created":{"date-parts":[[2025,7,25]],"date-time":"2025-07-25T05:53:51Z","timestamp":1753422831000},"page":"437-448","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["DynFusion-VC: Zero-Shot Voice Conversion via Optimized Fusion of Features"],"prefix":"10.1007","author":[{"given":"Chenghuan","family":"Xie","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Aimin","family":"Zhou","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2025,7,26]]},"reference":[{"key":"36_CR1","doi-asserted-by":"publisher","first-page":"1717","DOI":"10.1109\/TASLP.2021.3076867","volume":"29","author":"S Liu","year":"2021","unstructured":"Liu, S., Cao, Y., Wang, D., Wu, X., Liu, X., Meng, H.: Any-to-many voice conversion with location-relative sequence-to-sequence modeling. IEEE\/ACM Trans. Audio Speech Lang. Process. 29, 1717\u20131728 (2021)","journal-title":"IEEE\/ACM Trans. Audio Speech Lang. Process."},{"key":"36_CR2","doi-asserted-by":"crossref","unstructured":"Okamoto, T., Ohtani, Y., Toda, T., Kawai, H.: Convnext-TTS and convnext-VC: Convnext-based fast end-to-end sequence-to-sequence text-to-speech and voice conversion. In: ICASSP 2024\u20132024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 12456\u201312460. IEEE (2024)","DOI":"10.1109\/ICASSP48485.2024.10446890"},{"key":"36_CR3","doi-asserted-by":"crossref","unstructured":"Wang, Z., et al.: Multilevel temporal-channel speaker retrieval for zero-shot voice conversion. IEEE\/ACM Trans. Audio Speech Lang. Process. (2024)","DOI":"10.1109\/TASLP.2024.3407577"},{"key":"36_CR4","doi-asserted-by":"crossref","unstructured":"Li, J., Guo, Y., Chen, X., Yu, K.: Sef-VC: speaker embedding free zero-shot voice conversion with cross attention. In: ICASSP 2024\u20132024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 12296\u201312300. IEEE (2024)","DOI":"10.1109\/ICASSP48485.2024.10446160"},{"key":"36_CR5","doi-asserted-by":"crossref","unstructured":"Lu, H., Wu, X., Guo, H., Liu, S., Wu, Z., Meng, H.: Unifying one-shot voice conversion and cloning with disentangled speech representations. In: ICASSP 2024-2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 11141\u201311145. IEEE (2024)","DOI":"10.1109\/ICASSP48485.2024.10446296"},{"key":"36_CR6","unstructured":"Zhao, Y., et al.: Voice conversion challenge 2020: intra-lingual semi-parallel and cross-lingual voice conversion. arXiv preprint arXiv:2008.12527 (2020)"},{"key":"36_CR7","doi-asserted-by":"crossref","unstructured":"Baas, M., van Niekerk, B., Kamper, H.: Voice conversion with just nearest neighbors. In: Interspeech 2023, pp. 2053\u20132057. ISCA (2023)","DOI":"10.21437\/Interspeech.2023-419"},{"key":"36_CR8","doi-asserted-by":"crossref","unstructured":"Li, J., Tu, W., Xiao, L.: FreeVC: towards high-quality text-free one-shot voice conversion. In: ICASSP 2023\u20132023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 1\u20135. IEEE (2023)","DOI":"10.1109\/ICASSP49357.2023.10095191"},{"key":"36_CR9","doi-asserted-by":"crossref","unstructured":"Wang, D., Deng, L., Yeung, Y.T., Chen, X., Liu, X., Meng, H.: VQMIVC: vector quantization and mutual information-based unsupervised speech representation disentanglement for one-shot voice conversion. In: Interspeech 2021, pp. 1344\u20131348. ISCA (2021)","DOI":"10.21437\/Interspeech.2021-283"},{"issue":"6","key":"36_CR10","doi-asserted-by":"publisher","first-page":"1505","DOI":"10.1109\/JSTSP.2022.3188113","volume":"16","author":"S Chen","year":"2022","unstructured":"Chen, S., et al.: WavLM: large-scale self-supervised pre-training for full stack speech processing. IEEE J. Sel. Top. Signal Process. 16(6), 1505\u20131518 (2022)","journal-title":"IEEE J. Sel. Top. Signal Process."},{"key":"36_CR11","doi-asserted-by":"crossref","unstructured":"Lin, G.T., et al.: On the utility of self-supervised models for prosody-related tasks. In: 2022 IEEE Spoken Language Technology Workshop (SLT), pp. 1104\u20131111. IEEE (2023)","DOI":"10.1109\/SLT54892.2023.10023234"},{"key":"36_CR12","doi-asserted-by":"crossref","unstructured":"Sha, B., Li, X., Wu, Z., Shan, Y., Meng, H.: neural concatenative singing voice conversion: rethinking concatenation-based approach for one-shot singing voice conversion. In: ICASSP 2024\u20132024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 12577\u201312581. IEEE (2024)","DOI":"10.1109\/ICASSP48485.2024.10446066"},{"key":"36_CR13","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":"36_CR14","doi-asserted-by":"crossref","unstructured":"Jang, W., Lim, D., Yoon, J., Kim, B., Kim, J.: UnivNet: a neural vocoder with multi-resolution spectrogram discriminators for high-fidelity waveform generation. arXiv preprint arXiv:2106.07889 (2021)","DOI":"10.21437\/Interspeech.2021-1016"},{"key":"36_CR15","unstructured":"Lee, S.G., Ping, W., Ginsburg, B., Catanzaro, B., Yoon, S.: BigVGAN: a universal neural vocoder with large-scale training. arXiv preprint arXiv:2206.04658 (2022)"},{"key":"36_CR16","doi-asserted-by":"crossref","unstructured":"Wang, C., Zeng, C., Chen, J., Xue, O.: Hifi-wavegan: generative adversarial network with auxiliary spectrogram-phase loss for high-fidelity singing voice generation. In: International Symposium on Neural Networks, pp. 80\u201392. Springer (2024)","DOI":"10.1007\/978-981-97-4399-5_8"},{"key":"36_CR17","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. IEEE (2015)","DOI":"10.1109\/ICASSP.2015.7178964"},{"key":"36_CR18","unstructured":"Casanova, E., Weber, J., Shulby, C.D., Junior, 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, pp. 2709\u20132720. PMLR (2022)"},{"key":"36_CR19","unstructured":"Radford, A., Kim, J.W., Xu, T., Brockman, G., McLeavey, C., Sutskever, I.: Robust speech recognition via large-scale weak supervision. In: International Conference on Machine Learning, pp. 28492\u201328518. PMLR (2023)"},{"key":"36_CR20","doi-asserted-by":"crossref","unstructured":"David, S., Daniel, G.R., Gregory, S., Daniel, P., Sanjeev, K.: X-vectors: robust DNN embeddings for speaker recognition. In: 2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 5329\u20135333. IEEE (2018)","DOI":"10.1109\/ICASSP.2018.8461375"}],"container-title":["Lecture Notes in Computer Science","Advanced Intelligent Computing Technology and Applications"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-981-96-9805-9_36","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,7,3]],"date-time":"2026-07-03T17:59:57Z","timestamp":1783101597000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-96-9805-9_36"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025]]},"ISBN":["9789819698042","9789819698059"],"references-count":20,"URL":"https:\/\/doi.org\/10.1007\/978-981-96-9805-9_36","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":"26 July 2025","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ICIC","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Intelligent Computing","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Ningbo","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":"26 July 2025","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"29 July 2025","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":"icic2025","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/www.ic-icc.cn\/icg\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}