{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,11]],"date-time":"2026-04-11T20:38:24Z","timestamp":1775939904594,"version":"3.50.1"},"publisher-location":"Cham","reference-count":36,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031466731","type":"print"},{"value":"9783031466748","type":"electronic"}],"license":[{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"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":[[2023]]},"DOI":"10.1007\/978-3-031-46674-8_11","type":"book-chapter","created":{"date-parts":[[2023,11,4]],"date-time":"2023-11-04T13:02:29Z","timestamp":1699102949000},"page":"154-167","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":9,"title":["Voice Conversion with\u00a0Denoising Diffusion Probabilistic GAN Models"],"prefix":"10.1007","author":[{"given":"Xulong","family":"Zhang","sequence":"first","affiliation":[]},{"given":"Jianzong","family":"Wang","sequence":"additional","affiliation":[]},{"given":"Ning","family":"Cheng","sequence":"additional","affiliation":[]},{"given":"Jing","family":"Xiao","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2023,11,5]]},"reference":[{"key":"11_CR1","unstructured":"Chen, N., Zhang, Y., Zen, H., Weiss, R.J., Norouzi, M., Chan, W.: Wavegrad: estimating gradients for waveform generation. In: 9th International Conference on Learning Representations. OpenReview.net (2021)"},{"key":"11_CR2","doi-asserted-by":"crossref","unstructured":"Deng, C., Yu, C., Lu, H., Weng, C., Yu, D.: Pitchnet: unsupervised singing voice conversion with pitch adversarial network. In: 2020 IEEE International Conference on Acoustics, Speech and Signal Processing, pp. 7749\u20137753. IEEE (2020)","DOI":"10.1109\/ICASSP40776.2020.9054199"},{"key":"11_CR3","doi-asserted-by":"crossref","unstructured":"Ding, S., Gutierrez-Osuna, R.: Group latent embedding for vector quantized variational autoencoder in non-parallel voice conversion. In: Kubin, G., Kacic, Z. (eds.) 20th Annual Conference of the International Speech Communication Association, pp. 724\u2013728. ISCA (2019)","DOI":"10.21437\/Interspeech.2019-1198"},{"issue":"11","key":"11_CR4","doi-asserted-by":"publisher","first-page":"139","DOI":"10.1145\/3422622","volume":"63","author":"IJ Goodfellow","year":"2020","unstructured":"Goodfellow, I.J., et al.: Generative adversarial networks. Commun. ACM 63(11), 139\u2013144 (2020)","journal-title":"Commun. ACM"},{"key":"11_CR5","doi-asserted-by":"crossref","unstructured":"Helander, E., Schwarz, J., Nurminen, J., Sil\u00e9n, H., Gabbouj, M.: On the impact of alignment on voice conversion performance. In: 9th Annual Conference of the International Speech Communication Association, pp. 1453\u20131456. ISCA (2008)","DOI":"10.21437\/Interspeech.2008-419"},{"key":"11_CR6","unstructured":"Ho, J., Jain, A., Abbeel, P.: Denoising diffusion probabilistic models. In: Larochelle, H., Ranzato, M., Hadsell, R., Balcan, M., Lin, H. (eds.) Advances in Neural Information Processing Systems 33: Annual Conference on Neural Information Processing Systems 2020 (2020)"},{"issue":"4","key":"11_CR7","doi-asserted-by":"publisher","first-page":"468","DOI":"10.1109\/TETCI.2020.2977678","volume":"4","author":"W Huang","year":"2020","unstructured":"Huang, W., et al.: Unsupervised representation disentanglement using cross domain features and adversarial learning in variational autoencoder based voice conversion. IEEE Trans. Emerg. Top. Comput. Intell. 4(4), 468\u2013479 (2020)","journal-title":"IEEE Trans. Emerg. Top. Comput. Intell."},{"key":"11_CR8","doi-asserted-by":"crossref","unstructured":"Jeong, M., Kim, H., Cheon, S.J., Choi, B.J., Kim, N.S.: Diff-TTS: a denoising diffusion model for text-to-speech. In: Hermansky, H., Cernock\u00fd, H., Burget, L., Lamel, L., Scharenborg, O., Motl\u00edcek, P. (eds.) 22nd Annual Conference of the International Speech Communication Association, pp. 3605\u20133609. ISCA (2021)","DOI":"10.21437\/Interspeech.2021-469"},{"key":"11_CR9","doi-asserted-by":"crossref","unstructured":"Kameoka, H., Kaneko, T., Tanaka, K., Hojo, N.: StarGAN-VC: non-parallel many-to-many voice conversion using star generative adversarial networks. In: 2018 IEEE Spoken Language Technology Workshop, pp. 266\u2013273. IEEE (2018)","DOI":"10.1109\/SLT.2018.8639535"},{"issue":"9","key":"11_CR10","doi-asserted-by":"publisher","first-page":"1432","DOI":"10.1109\/TASLP.2019.2917232","volume":"27","author":"H Kameoka","year":"2019","unstructured":"Kameoka, H., Kaneko, T., Tanaka, K., Hojo, N.: ACVAE-VC: non-parallel voice conversion with auxiliary classifier variational autoencoder. IEEE\/ACM Trans. Audio Speech Lang. Process. 27(9), 1432\u20131443 (2019)","journal-title":"IEEE\/ACM Trans. Audio Speech Lang. Process."},{"key":"11_CR11","doi-asserted-by":"crossref","unstructured":"Kaneko, T., Kameoka, H.: CycleGAN-VC: non-parallel voice conversion using cycle-consistent adversarial networks. In: 26th European Signal Processing Conference, pp. 2100\u20132104. IEEE (2018)","DOI":"10.23919\/EUSIPCO.2018.8553236"},{"key":"11_CR12","doi-asserted-by":"crossref","unstructured":"Kaneko, T., Kameoka, H.: CycleGAN-VC3: examining and improving CycleGAN-VCs for mel-spectrogram conversion. In: Meng, H., Xu, B., Zheng, T.F. (eds.) 21st Annual Conference of the International Speech Communication Association, pp. 2017\u20132021. ISCA (2020)","DOI":"10.21437\/Interspeech.2020-2280"},{"key":"11_CR13","doi-asserted-by":"crossref","unstructured":"Kaneko, T., Kameoka, H., Hiramatsu, K., Kashino, K.: Sequence-to-sequence voice conversion with similarity metric learned using generative adversarial networks. In: Lacerda, F. (ed.) 18th Annual Conference of the International Speech Communication Association, pp. 1283\u20131287. ISCA (2017)","DOI":"10.21437\/Interspeech.2017-970"},{"key":"11_CR14","doi-asserted-by":"crossref","unstructured":"Kaneko, T., Kameoka, H., Tanaka, K., Hojo, N.: CycleGAN-VC2: improved CycleGAN-based non-parallel voice conversion. In: IEEE International Conference on Acoustics, Speech and Signal Processing, pp. 6820\u20136824. IEEE (2019)","DOI":"10.1109\/ICASSP.2019.8682897"},{"key":"11_CR15","doi-asserted-by":"crossref","unstructured":"Kaneko, T., Kameoka, H., Tanaka, K., Hojo, N.: StarGAN-VC2: rethinking conditional methods for StarGAN-based voice conversion. In: Kubin, G., Kacic, Z. (eds.) 20th Annual Conference of the International Speech Communication Association, pp. 679\u2013683. ISCA (2019)","DOI":"10.21437\/Interspeech.2019-2236"},{"key":"11_CR16","unstructured":"Kingma, D.P., Welling, M.: Auto-encoding variational bayes. In: Bengio, Y., LeCun, Y. (eds.) 2nd International Conference on Learning Representations (2014)"},{"key":"11_CR17","unstructured":"Kong, Z., Ping, W., Huang, J., Zhao, K., Catanzaro, B.: Diffwave: a versatile diffusion model for audio synthesis. In: 9th International Conference on Learning Representations (2021)"},{"key":"11_CR18","doi-asserted-by":"crossref","unstructured":"Liu, J., Li, C., Ren, Y., Chen, F., Zhao, Z.: Diffsinger: singing voice synthesis via shallow diffusion mechanism. In: Thirty-Sixth AAAI Conference on Artificial Intelligence, pp. 11020\u201311028. AAAI Press (2022)","DOI":"10.1609\/aaai.v36i10.21350"},{"key":"11_CR19","doi-asserted-by":"crossref","unstructured":"Lu, Y., Wang, Z., Watanabe, S., Richard, A., Yu, C., Tsao, Y.: Conditional diffusion probabilistic model for speech enhancement. In: IEEE International Conference on Acoustics, Speech and Signal Processing, pp. 7402\u20137406. IEEE (2022)","DOI":"10.1109\/ICASSP43922.2022.9746901"},{"key":"11_CR20","doi-asserted-by":"crossref","unstructured":"Lugmayr, A., Danelljan, M., Romero, A., Yu, F., Timofte, R., Gool, L.V.: Repaint: inpainting using denoising diffusion probabilistic models. In: IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 11451\u201311461. IEEE (2022)","DOI":"10.1109\/CVPR52688.2022.01117"},{"key":"11_CR21","doi-asserted-by":"crossref","unstructured":"Mohammadi, S.H., Kain, A.: Voice conversion using deep neural networks with speaker-independent pre-training. In: 2014 IEEE Spoken Language Technology Workshop, pp. 19\u201323. IEEE (2014)","DOI":"10.1109\/SLT.2014.7078543"},{"issue":"1","key":"11_CR22","doi-asserted-by":"publisher","first-page":"134","DOI":"10.1016\/j.specom.2011.07.007","volume":"54","author":"K Nakamura","year":"2012","unstructured":"Nakamura, K., Toda, T., Saruwatari, H., Shikano, K.: Speaking-aid systems using GMM-based voice conversion for electrolaryngeal speech. Speech Commun. 54(1), 134\u2013146 (2012)","journal-title":"Speech Commun."},{"key":"11_CR23","doi-asserted-by":"crossref","unstructured":"Qian, K., Jin, Z., Hasegawa-Johnson, M., Mysore, G.J.: F0-consistent many-to-many non-parallel voice conversion via conditional autoencoder. In: 2020 IEEE International Conference on Acoustics, Speech and Signal Processing, pp. 6284\u20136288. IEEE (2020)","DOI":"10.1109\/ICASSP40776.2020.9054734"},{"key":"11_CR24","unstructured":"Qian, K., Zhang, Y., Chang, S., Yang, X., Hasegawa-Johnson, M.: Autovc: zero-shot voice style transfer with only autoencoder loss. In: Chaudhuri, K., Salakhutdinov, R. (eds.) Proceedings of the 36th International Conference on Machine Learning. Proceedings of Machine Learning Research, vol. 97, pp. 5210\u20135219. PMLR (2019)"},{"key":"11_CR25","doi-asserted-by":"crossref","unstructured":"Saharia, C., et al.: Palette: image-to-image diffusion models. In: Nandigjav, M., Mitra, N.J., Hertzmann, A. (eds.) SIGGRAPH 2022: Special Interest Group on Computer Graphics and Interactive Techniques Conference, pp. 15:1\u201315:10. ACM (2022)","DOI":"10.1145\/3528233.3530757"},{"key":"11_CR26","doi-asserted-by":"crossref","unstructured":"Si, S., Wang, J., Zhang, X., Qu, X., Cheng, N., Xiao, J.: Boosting StarGANs for voice conversion with contrastive discriminator, pp. 355\u2013366 (2023)","DOI":"10.1007\/978-3-031-30108-7_30"},{"key":"11_CR27","doi-asserted-by":"crossref","unstructured":"Sun, L., Kang, S., Li, K., Meng, H.M.: Voice conversion using deep bidirectional long short-term memory based recurrent neural networks. In: 2015 IEEE International Conference on Acoustics, Speech and Signal Processing, pp. 4869\u20134873. IEEE (2015)","DOI":"10.1109\/ICASSP.2015.7178896"},{"key":"11_CR28","doi-asserted-by":"crossref","unstructured":"Kaneko, T., Kameoka, H.: Maskcyclegan-VC: learning non-parallel voice conversion with filling in frames. In: IEEE International Conference on Acoustics, Speech and Signal Processing, pp. 5919\u20135923. IEEE (2021)","DOI":"10.1109\/ICASSP39728.2021.9414851"},{"key":"11_CR29","doi-asserted-by":"crossref","unstructured":"Tang, H., Zhang, X., Wang, J., Cheng, N., Xiao, J.: Emomix: emotion mixing via diffusion models for emotional speech synthesis (2023)","DOI":"10.21437\/Interspeech.2023-1317"},{"key":"11_CR30","doi-asserted-by":"crossref","unstructured":"Tang, H., Zhang, X., Wang, J., Cheng, N., Xiao, J.: QI-TTS: questioning intonation control for emotional speech synthesis. In: 2023 IEEE International Conference on Acoustics, Speech and Signal Processing, pp. 1\u20135 (2023)","DOI":"10.1109\/ICASSP49357.2023.10095623"},{"key":"11_CR31","doi-asserted-by":"crossref","unstructured":"Tang, H., Zhang, X., Wang, J., Cheng, N., Xiao, J.: Learning speech representations with flexible hidden feature dimensions. In: 2023 IEEE International Conference on Acoustics, Speech and Signal Processing, pp. 1\u20135 (2023)","DOI":"10.1109\/ICASSP49357.2023.10094969"},{"key":"11_CR32","doi-asserted-by":"crossref","unstructured":"Tang, H., Zhang, X., Wang, J., Cheng, N., Xiao, J.: VQ-CL: learning disentangled speech representations with contrastive learning and vector quantization. In: 2023 IEEE International Conference on Acoustics, Speech and Signal Processing, pp. 1\u20135 (2023)","DOI":"10.1109\/ICASSP49357.2023.10095654"},{"key":"11_CR33","doi-asserted-by":"crossref","unstructured":"Tobing, P.L., Wu, Y., Hayashi, T., Kobayashi, K., Toda, T.: Non-parallel voice conversion with cyclic variational autoencoder. In: Kubin, G., Kacic, Z. (eds.) 20th Annual Conference of the International Speech Communication Association, pp. 674\u2013678. ISCA (2019)","DOI":"10.21437\/Interspeech.2019-2307"},{"issue":"8","key":"11_CR34","doi-asserted-by":"publisher","first-page":"2222","DOI":"10.1109\/TASL.2007.907344","volume":"15","author":"T Toda","year":"2007","unstructured":"Toda, T., Black, A.W., Tokuda, K.: Voice conversion based on maximum-likelihood estimation of spectral parameter trajectory. IEEE Trans. Audio Speech Lang. Process. 15(8), 2222\u20132235 (2007)","journal-title":"IEEE Trans. Audio Speech Lang. Process."},{"issue":"9","key":"11_CR35","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. Speech Audio Process. 20(9), 2505\u20132517 (2012)","journal-title":"IEEE Trans. Speech Audio Process."},{"issue":"10","key":"11_CR36","doi-asserted-by":"publisher","first-page":"1506","DOI":"10.1109\/TASLP.2014.2333242","volume":"22","author":"Z Wu","year":"2014","unstructured":"Wu, Z., Virtanen, T., Chng, E., Li, H.: Exemplar-based sparse representation with residual compensation for voice conversion. IEEE\/ACM Trans. Audio Speech Lang. Process. 22(10), 1506\u20131521 (2014)","journal-title":"IEEE\/ACM Trans. Audio Speech Lang. Process."}],"container-title":["Lecture Notes in Computer Science","Advanced Data Mining and Applications"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-46674-8_11","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,11,4]],"date-time":"2023-11-04T13:16:26Z","timestamp":1699103786000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-46674-8_11"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023]]},"ISBN":["9783031466731","9783031466748"],"references-count":36,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-46674-8_11","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023]]},"assertion":[{"value":"5 November 2023","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ADMA","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Advanced Data Mining and Applications","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Shenyang","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":"27 August 2023","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"29 August 2023","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"9","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"adma2023","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/adma2023.uqcloud.net\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Double-blind","order":1,"name":"type","label":"Type","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"Yes. Microsoft CMT","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"503","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":"216","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":"43% - 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":"2.97","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":"3.77","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":"No","order":9,"name":"external_reviewers_involved","label":"External Reviewers Involved","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}}]}}