{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,14]],"date-time":"2026-02-14T10:22:33Z","timestamp":1771064553050,"version":"3.50.1"},"publisher-location":"Singapore","reference-count":24,"publisher":"Springer Nature Singapore","isbn-type":[{"value":"9789819981441","type":"print"},{"value":"9789819981458","type":"electronic"}],"license":[{"start":{"date-parts":[[2023,11,27]],"date-time":"2023-11-27T00:00:00Z","timestamp":1701043200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2023,11,27]],"date-time":"2023-11-27T00:00:00Z","timestamp":1701043200000},"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":[[2024]]},"DOI":"10.1007\/978-981-99-8145-8_37","type":"book-chapter","created":{"date-parts":[[2023,11,26]],"date-time":"2023-11-26T23:02:30Z","timestamp":1701039750000},"page":"482-494","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["MelMAE-VC: Extending Masked Autoencoders to\u00a0Voice Conversion"],"prefix":"10.1007","author":[{"given":"Yuhao","family":"Wang","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yuantao","family":"Gu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2023,11,27]]},"reference":[{"key":"37_CR1","unstructured":"Baevski, A., Zhou, Y., Mohamed, A., Auli, M.: wav2vec 2.0: a framework for self-supervised learning of speech representations. In: Advances in Neural Information Processing Systems, vol. 33, pp. 12449\u201312460 (2020)"},{"key":"37_CR2","doi-asserted-by":"crossref","unstructured":"Chung, J.S., Nagrani, A., Zisserman, A.: Voxceleb2: deep speaker recognition. arXiv preprint arXiv:1806.05622 (2018)","DOI":"10.21437\/Interspeech.2018-1929"},{"key":"37_CR3","unstructured":"Devlin, J., Chang, M.W., Lee, K., Toutanova, K.: Bert: pre-training of deep bidirectional transformers for language understanding. arXiv preprint arXiv:1810.04805 (2018)"},{"key":"37_CR4","doi-asserted-by":"crossref","unstructured":"He, K., Chen, X., Xie, S., Li, Y., Doll\u00e1r, P., Girshick, R.: Masked autoencoders are scalable vision learners. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 16000\u201316009 (2022)","DOI":"10.1109\/CVPR52688.2022.01553"},{"key":"37_CR5","first-page":"28708","volume":"35","author":"PY Huang","year":"2022","unstructured":"Huang, P.Y., et al.: Masked autoencoders that listen. Adv. Neural. Inf. Process. Syst. 35, 28708\u201328720 (2022)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"37_CR6","unstructured":"Kahn, J.D., et al.: Flashlight: enabling innovation in tools for machine learning. In: International Conference on Machine Learning, pp. 10557\u201310574. PMLR (2022)"},{"key":"37_CR7","doi-asserted-by":"crossref","unstructured":"Kaneko, T., Kameoka, H.: CycleGAN-VC: non-parallel voice conversion using cycle-consistent adversarial networks. In: 2018 26th European Signal Processing Conference (EUSIPCO), pp. 2100\u20132104. IEEE (2018)","DOI":"10.23919\/EUSIPCO.2018.8553236"},{"key":"37_CR8","doi-asserted-by":"crossref","unstructured":"Kaneko, T., Kameoka, H., Tanaka, K., Hojo, N.: CycleGAN-VC2: improved cycleGAN-based non-parallel voice conversion. In: ICASSP 2019\u20132019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 6820\u20136824. IEEE (2019)","DOI":"10.1109\/ICASSP.2019.8682897"},{"key":"37_CR9","doi-asserted-by":"crossref","unstructured":"Kaneko, T., Kameoka, H., Tanaka, K., Hojo, N.: CycleGAN-VC3: examining and improving CycleGAN-VCs for mel-spectrogram conversion. arXiv preprint arXiv:2010.11672 (2020)","DOI":"10.21437\/Interspeech.2020-2280"},{"key":"37_CR10","doi-asserted-by":"crossref","unstructured":"Kaneko, T., Kameoka, H., Tanaka, K., Hojo, N.: MaskcycleGAN-VC: learning non-parallel voice conversion with filling in frames. In: ICASSP 2021\u20132021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 5919\u20135923. IEEE (2021)","DOI":"10.1109\/ICASSP39728.2021.9414851"},{"key":"37_CR11","doi-asserted-by":"crossref","unstructured":"Kashkin, A., Karpukhin, I., Shishkin, S.: Hifi-VC: high quality ASR-based voice conversion. arXiv preprint arXiv:2203.16937 (2022)","DOI":"10.21437\/SSW.2023-16"},{"key":"37_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, pp. 5530\u20135540. PMLR (2021)"},{"key":"37_CR13","unstructured":"Kingma, D.P., Ba, J.: Adam: a method for stochastic optimization. arXiv preprint arXiv:1412.6980 (2014)"},{"key":"37_CR14","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":"37_CR15","unstructured":"Loshchilov, I., Hutter, F.: Decoupled weight decay regularization. arXiv preprint arXiv:1711.05101 (2017)"},{"key":"37_CR16","doi-asserted-by":"crossref","unstructured":"Nagrani, A., Chung, J.S., Zisserman, A.: VoxCeleb: a large-scale speaker identification dataset. arXiv preprint arXiv:1706.08612 (2017)","DOI":"10.21437\/Interspeech.2017-950"},{"key":"37_CR17","doi-asserted-by":"crossref","unstructured":"Nguyen, B., Cardinaux, F.: NVC-Net: End-to-end adversarial voice conversion. In: ICASSP 2022\u20132022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 7012\u20137016. IEEE (2022)","DOI":"10.1109\/ICASSP43922.2022.9747020"},{"key":"37_CR18","unstructured":"Oord, A.v.d., et al.: WaveNet: a generative model for raw audio. arXiv preprint arXiv:1609.03499 (2016)"},{"key":"37_CR19","doi-asserted-by":"crossref","unstructured":"Prenger, R., Valle, R., Catanzaro, B.: WaveGlow: a flow-based generative network for speech synthesis. In: ICASSP 2019\u20132019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 3617\u20133621. IEEE (2019)","DOI":"10.1109\/ICASSP.2019.8683143"},{"key":"37_CR20","unstructured":"Qian, K., Zhang, Y., Chang, S., Yang, X., Hasegawa-Johnson, M.: AutoVC: zero-shot voice style transfer with only autoencoder loss. In: International Conference on Machine Learning, pp. 5210\u20135219. PMLR (2019)"},{"key":"37_CR21","unstructured":"Radford, A., Narasimhan, K., Salimans, T., Sutskever, I., et al.: Improving language understanding by generative pre-training (2018)"},{"issue":"9","key":"37_CR22","doi-asserted-by":"publisher","first-page":"2505","DOI":"10.1109\/TASL.2012.2205241","volume":"20","author":"T Toda","year":"2012","unstructured":"Toda, T., Nakagiri, M., Shikano, K.: Statistical voice conversion techniques for body-conducted unvoiced speech enhancement. IEEE Trans. Audio Speech Lang. Process. 20(9), 2505\u20132517 (2012)","journal-title":"IEEE Trans. Audio Speech Lang. Process."},{"key":"37_CR23","doi-asserted-by":"crossref","unstructured":"Wan, L., Wang, Q., Papir, A., Moreno, I.L.: Generalized end-to-end loss for speaker verification. In: 2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 4879\u20134883. IEEE (2018)","DOI":"10.1109\/ICASSP.2018.8462665"},{"key":"37_CR24","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\u20132022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 7237\u20137241. IEEE (2022)","DOI":"10.1109\/ICASSP43922.2022.9747664"}],"container-title":["Communications in Computer and Information Science","Neural Information Processing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-981-99-8145-8_37","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,3,13]],"date-time":"2024-03-13T19:01:13Z","timestamp":1710356473000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-99-8145-8_37"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,11,27]]},"ISBN":["9789819981441","9789819981458"],"references-count":24,"URL":"https:\/\/doi.org\/10.1007\/978-981-99-8145-8_37","relation":{},"ISSN":["1865-0929","1865-0937"],"issn-type":[{"value":"1865-0929","type":"print"},{"value":"1865-0937","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,11,27]]},"assertion":[{"value":"27 November 2023","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ICONIP","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Neural Information Processing","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Changsha","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":"2023","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"20 November 2023","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"23 November 2023","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"30","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"iconip2023","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/iconip2023.org\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Single-blind","order":1,"name":"type","label":"Type","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"EasyChair","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"1274","order":3,"name":"number_of_submissions_sent_for_review","label":"Number of Submissions Sent for Review","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"650","order":4,"name":"number_of_full_papers_accepted","label":"Number of Full Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"0","order":5,"name":"number_of_short_papers_accepted","label":"Number of Short Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"51% - The value is computed by the equation \"Number of Full Papers Accepted \/ Number of Submissions Sent for Review * 100\" and then rounded to a whole number.","order":6,"name":"acceptance_rate_of_full_papers","label":"Acceptance Rate of Full Papers","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"4.14","order":7,"name":"average_number_of_reviews_per_paper","label":"Average Number of Reviews per Paper","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"2.46","order":8,"name":"average_number_of_papers_per_reviewer","label":"Average Number of Papers per Reviewer","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"Yes","order":9,"name":"external_reviewers_involved","label":"External Reviewers Involved","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}}]}}