{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,2]],"date-time":"2026-06-02T09:28:02Z","timestamp":1780392482354,"version":"3.54.1"},"publisher-location":"Cham","reference-count":27,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031483080","type":"print"},{"value":"9783031483097","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\/978-3-031-48309-7_20","type":"book-chapter","created":{"date-parts":[[2023,11,21]],"date-time":"2023-11-21T20:03:21Z","timestamp":1700597001000},"page":"233-244","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":13,"title":["Region Normalized Capsule Network Based Generative Adversarial Network for\u00a0Non-parallel Voice Conversion"],"prefix":"10.1007","author":[{"given":"Md. Tousin","family":"Akhter","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Padmanabha","family":"Banerjee","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Sandipan","family":"Dhar","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Subhayu","family":"Ghosh","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Nanda Dulal","family":"Jana","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2023,11,22]]},"reference":[{"key":"20_CR1","doi-asserted-by":"publisher","unstructured":"Abe, M., Nakamura, S., Shikano, K., Kuwabara, H.: Voice conversion through vector quantization. In: International Conference on Acoustics, Speech, and Signal Processing, ICASSP 1988, vol. 1, pp. 655\u2013658 (1988). https:\/\/doi.org\/10.1109\/ICASSP.1988.196671","DOI":"10.1109\/ICASSP.1988.196671"},{"key":"20_CR2","doi-asserted-by":"publisher","unstructured":"Chen, Y.N., Liu, L.J., Hu, Y.J., Jiang, Y., Ling, Z.H.: Improving recognition-synthesis based any-to-one voice conversion with cyclic training. In: ICASSP 2022, pp. 7007\u20137011 (2022). https:\/\/doi.org\/10.1109\/ICASSP43922.2022.9747140","DOI":"10.1109\/ICASSP43922.2022.9747140"},{"key":"20_CR3","series-title":"Lecture Notes in Computer Science (Lecture Notes in Artificial Intelligence)","doi-asserted-by":"publisher","first-page":"368","DOI":"10.1007\/978-3-319-11581-8_46","volume-title":"Speech and Computer","author":"M Coto-Jim\u00e9nez","year":"2014","unstructured":"Coto-Jim\u00e9nez, M., Goddard-Close, J., Mart\u00ednez-Licona, F.M.: Quality assessment of HMM-based speech synthesis using acoustical vowel analysis. In: Ronzhin, A., Potapova, R., Delic, V. (eds.) SPECOM 2014. LNCS (LNAI), vol. 8773, pp. 368\u2013375. Springer, Cham (2014). https:\/\/doi.org\/10.1007\/978-3-319-11581-8_46"},{"key":"20_CR4","doi-asserted-by":"publisher","first-page":"92","DOI":"10.1109\/TAI.2022.3149858","volume":"4","author":"S Dhar","year":"2022","unstructured":"Dhar, S., Jana, N.D., Das, S.: An adaptive learning based generative adversarial network for one-to-one voice conversion. IEEE Trans. Artif. Intell. 4, 92\u2013106 (2022). https:\/\/doi.org\/10.1109\/TAI.2022.3149858","journal-title":"IEEE Trans. Artif. Intell."},{"key":"20_CR5","doi-asserted-by":"publisher","unstructured":"Du, H., Tian, X., Xie, L., Li, H.: Optimizing voice conversion network with cycle consistency loss of speaker identity. In: 2021 IEEE SLT, pp. 507\u2013513 (2021). https:\/\/doi.org\/10.1109\/SLT48900.2021.9383567","DOI":"10.1109\/SLT48900.2021.9383567"},{"key":"20_CR6","unstructured":"Goodfellow, I., et al.: Generative adversarial nets. In: Advances in NIPS, vol. 27. Curran Associates, Inc. (2014)"},{"key":"20_CR7","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"526","DOI":"10.1007\/978-3-030-11015-4_38","volume-title":"Computer Vision \u2013 ECCV 2018 Workshops","author":"A Jaiswal","year":"2019","unstructured":"Jaiswal, A., AbdAlmageed, W., Wu, Y., Natarajan, P.: CapsuleGAN: generative adversarial capsule network. In: Leal-Taix\u00e9, L., Roth, S. (eds.) ECCV 2018. LNCS, vol. 11131, pp. 526\u2013535. Springer, Cham (2019). https:\/\/doi.org\/10.1007\/978-3-030-11015-4_38"},{"key":"20_CR8","unstructured":"Jolicoeur-Martineau, A.: The relativistic discriminator: a key element missing from standard GAN. arXiv arXiv:1807.00734 (2019)"},{"key":"20_CR9","doi-asserted-by":"crossref","unstructured":"Kaneko, T., Kameoka, H., Tanaka, K., Hojo, N.: CycleGAN-VC2: improved cycleGAN-based non-parallel voice conversion. In: ICASSP, vol. 2019, pp. 6820\u20136824 (2019)","DOI":"10.1109\/ICASSP.2019.8682897"},{"key":"20_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, pp. 5919\u20135923 (2021)","DOI":"10.1109\/ICASSP39728.2021.9414851"},{"key":"20_CR11","doi-asserted-by":"publisher","unstructured":"Kaneko, T., Kameoka, H.: CycleGAN-VC: non-parallel voice conversion using cycle-consistent adversarial networks. In: 2018, 26th EUSIPCO, pp. 2100\u20132104 (2018). https:\/\/doi.org\/10.23919\/EUSIPCO.2018.8553236","DOI":"10.23919\/EUSIPCO.2018.8553236"},{"key":"20_CR12","unstructured":"Kingma, D.P., Ba, J.: Adam: a method for stochastic optimization. arXiv preprint arXiv:1412.6980 (2014)"},{"key":"20_CR13","doi-asserted-by":"publisher","unstructured":"Kishida, T., Nakashika, T.: Non-parallel voice conversion based on free-energy minimization of speaker-conditional restricted Boltzmann machine. In: 2022 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC), pp. 251\u2013255 (2022). https:\/\/doi.org\/10.23919\/APSIPAASC55919.2022.9980151","DOI":"10.23919\/APSIPAASC55919.2022.9980151"},{"key":"20_CR14","unstructured":"Kominek, J., Black, A.W.: The CMU arctic speech databases. In: SSW (2004)"},{"key":"20_CR15","unstructured":"Kumar, K., et al.: MelGAN: generative adversarial networks for conditional waveform synthesis. In: NeurIPS (2019)"},{"key":"20_CR16","doi-asserted-by":"crossref","unstructured":"Lorenzo-Trueba, J., et al.: The voice conversion challenge 2018: promoting development of parallel and nonparallel methods. In: Odyssey (2018)","DOI":"10.21437\/Odyssey.2018-28"},{"issue":"1","key":"20_CR17","doi-asserted-by":"publisher","first-page":"14634","DOI":"10.1038\/s41598-021-93977-0","volume":"11","author":"V Mazzia","year":"2021","unstructured":"Mazzia, V., Salvetti, F., Chiaberge, M.: Efficient-CapsNet: capsule network with self-attention routing. Sci. Rep. 11(1), 14634 (2021)","journal-title":"Sci. Rep."},{"key":"20_CR18","doi-asserted-by":"crossref","unstructured":"Mazzia, V., Salvetti, F., Chiaberge, M.: Efficient-CapsNet: capsule network with self-attention routing. CoRR abs\/2101.12491 (2021). https:\/\/arxiv.org\/abs\/2101.12491","DOI":"10.1038\/s41598-021-93977-0"},{"key":"20_CR19","unstructured":"Sabour, S., Frosst, N., Hinton, G.E.: Dynamic routing between capsules. arXiv arXiv:1710.09829 (2017)"},{"key":"20_CR20","doi-asserted-by":"publisher","first-page":"132","DOI":"10.1109\/TASLP.2020.3038524","volume":"29","author":"B Sisman","year":"2021","unstructured":"Sisman, B., Yamagishi, J., King, S., Li, H.: An overview of voice conversion and its challenges: from statistical modeling to deep learning. IEEE\/ACM Trans. Audio Speech Lang. Process. 29, 132\u2013157 (2021)","journal-title":"IEEE\/ACM Trans. Audio Speech Lang. Process."},{"key":"20_CR21","doi-asserted-by":"crossref","unstructured":"Sun, L., Li, K., Wang, H., Kang, S., Meng, H.M.: Phonetic posteriorgrams for many-to-one voice conversion without parallel data training. In: 2016 IEEE International Conference on Multimedia and Expo (ICME), pp. 1\u20136 (2016)","DOI":"10.1109\/ICME.2016.7552917"},{"key":"20_CR22","doi-asserted-by":"publisher","unstructured":"Uchida, H., Saito, D., Minematsu, N., Hirose, K.: Statistical acoustic-to-articulatory mapping unified with speaker normalization based on voice conversion. In: Proceedings of the INTERSPEECH 2015, pp. 588\u2013592 (2015). https:\/\/doi.org\/10.21437\/Interspeech.2015-209","DOI":"10.21437\/Interspeech.2015-209"},{"key":"20_CR23","unstructured":"Vaswani, A., et al.: Attention is all you need. In: NIPS (2017)"},{"key":"20_CR24","doi-asserted-by":"publisher","unstructured":"Wu, J., Polyak, A., Taigman, Y., Fong, J., Agrawal, P., He, Q.: Multilingual text-to-speech training using cross language voice conversion and self-supervised learning of speech representations. In: ICASSP 2022, pp. 8017\u20138021 (2022). https:\/\/doi.org\/10.1109\/ICASSP43922.2022.9746282","DOI":"10.1109\/ICASSP43922.2022.9746282"},{"key":"20_CR25","doi-asserted-by":"crossref","unstructured":"Yu, T., et al.: Region normalization for image inpainting. In: AAAI (2020)","DOI":"10.1609\/aaai.v34i07.6967"},{"key":"20_CR26","series-title":"Lecture Notes in Computer Science (Lecture Notes in Artificial Intelligence)","doi-asserted-by":"publisher","first-page":"463","DOI":"10.1007\/978-3-319-23132-7_57","volume-title":"Speech and Computer","author":"Y-S Yun","year":"2015","unstructured":"Yun, Y.-S., Jung, J., Eun, S.: Voice conversion between synthesized bilingual voices using line spectral frequencies. In: Ronzhin, A., Potapova, R., Fakotakis, N. (eds.) SPECOM 2015. LNCS (LNAI), vol. 9319, pp. 463\u2013471. Springer, Cham (2015). https:\/\/doi.org\/10.1007\/978-3-319-23132-7_57"},{"key":"20_CR27","series-title":"Lecture Notes in Computer Science (Lecture Notes in Artificial Intelligence)","doi-asserted-by":"publisher","first-page":"788","DOI":"10.1007\/978-3-319-66429-3_79","volume-title":"Speech and Computer","author":"V Zahariev","year":"2017","unstructured":"Zahariev, V., Azarov, E., Petrovsky, A.: Voice conversion for TTS systems with tuning on the target speaker based on GMM. In: Karpov, A., Potapova, R., Mporas, I. (eds.) SPECOM 2017. LNCS (LNAI), vol. 10458, pp. 788\u2013798. Springer, Cham (2017). https:\/\/doi.org\/10.1007\/978-3-319-66429-3_79"}],"container-title":["Lecture Notes in Computer Science","Speech and Computer"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-48309-7_20","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,11,21]],"date-time":"2023-11-21T20:11:39Z","timestamp":1700597499000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-48309-7_20"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023]]},"ISBN":["9783031483080","9783031483097"],"references-count":27,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-48309-7_20","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":"22 November 2023","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"SPECOM","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Speech and Computer","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Dharwad","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"India","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":"29 November 2023","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2 December 2023","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"25","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"specom2023","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/www.iitdh.ac.in\/specom-2023\/","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":"174","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":"94","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":"54% - 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":"3","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":"4","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)"}}]}}