{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,26]],"date-time":"2025-03-26T09:30:00Z","timestamp":1742981400374,"version":"3.40.3"},"publisher-location":"Cham","reference-count":27,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783030594299"},{"type":"electronic","value":"9783030594305"}],"license":[{"start":{"date-parts":[[2020,1,1]],"date-time":"2020-01-01T00:00:00Z","timestamp":1577836800000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2020,1,1]],"date-time":"2020-01-01T00:00:00Z","timestamp":1577836800000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2020]]},"DOI":"10.1007\/978-3-030-59430-5_13","type":"book-chapter","created":{"date-parts":[[2020,9,25]],"date-time":"2020-09-25T08:04:59Z","timestamp":1601021099000},"page":"157-168","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":3,"title":["Deep Variational Metric Learning for Transfer of Expressivity in Multispeaker Text to Speech"],"prefix":"10.1007","author":[{"given":"Ajinkya","family":"Kulkarni","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Vincent","family":"Colotte","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Denis","family":"Jouvet","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2020,9,26]]},"reference":[{"key":"13_CR1","unstructured":"Wang, Y.: Tacotron: a fully end-to-end text-to-speech synthesis model. J. CoRR, arxiv.org, vol. abs\/1703.10135 (2017)"},{"key":"13_CR2","unstructured":"Ping, W., et al.: Deep Voice 3: 2000-speaker neural text-to-speech, CoRR, arxiv.org, volume abs\/1710.07654 (2017)"},{"key":"13_CR3","unstructured":"Sotelo, J., et al.: Char2Wav: end-to-end speech synthesis. In: ICLR (2017)"},{"key":"13_CR4","unstructured":"Taigman, Y., Wolf, L., Polyak, A., Nachmani, E.: VoiceLoop: voice fitting and synthesis via a phonological loop. In: ICLR (2017)"},{"key":"13_CR5","doi-asserted-by":"crossref","unstructured":"Zhang, Y.-J., Pan, S., He, L., Ling, Z.-H.: Learning latent representations for style control and transfer in end-to-end speech synthesis. In: ICASSP (2018)","DOI":"10.1109\/ICASSP.2019.8683623"},{"key":"13_CR6","doi-asserted-by":"crossref","unstructured":"Akuzawa, K., Yusuke, I., Yutaka, M.: Expressive speech synthesis via modeling expressions with variational autoencoder. In: Interspeech (2018)","DOI":"10.21437\/Interspeech.2018-1113"},{"key":"13_CR7","unstructured":"Hsu, W.N., et al.: Hierarchical generative modeling for controllable speech synthesis. In: ICLR (2019)"},{"key":"13_CR8","unstructured":"Wang, Y., et al.: Style tokens: unsupervised style modeling, control and transfer in end-to-end speech synthesis. In: ICML (2018)"},{"key":"13_CR9","unstructured":"Skerry-Ryan, R.J., et al.: Towards end-to-end prosody transfer for expressive speech synthesis with tacotron. In: ICML (2018)"},{"key":"13_CR10","doi-asserted-by":"crossref","unstructured":"Lee, Y., Kim, T.: Robust and fine-grained prosody control of end-to-end speech synthesis. In: ICASSP (2019)","DOI":"10.1109\/ICASSP.2019.8683501"},{"key":"13_CR11","doi-asserted-by":"crossref","unstructured":"Parker, J., Stylianou, Y., Cipolla, R.: Adaptation of an expressive single speaker deep neural network speech synthesis system. In: ICASSP (2018)","DOI":"10.1109\/ICASSP.2018.8461888"},{"key":"13_CR12","unstructured":"Kulkarni, A., Colotte, V., Jouvet, D.: Layer adaptation for transfer of expressivity in speech synthesis. In: Language & Technology Conference (LTC) (2019)"},{"key":"13_CR13","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"714","DOI":"10.1007\/978-3-030-01267-0_42","volume-title":"Computer Vision \u2013 ECCV 2018","author":"X Lin","year":"2018","unstructured":"Lin, X., Duan, Y., Dong, Q., Lu, J., Zhou, J.: Deep variational metric learning. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) ECCV 2018. LNCS, vol. 11219, pp. 714\u2013729. Springer, Cham (2018). https:\/\/doi.org\/10.1007\/978-3-030-01267-0_42"},{"key":"13_CR14","doi-asserted-by":"crossref","unstructured":"Kaya, M., Bilge, H.\u015e.: Deep metric learning: a survey. In: Symmetry, vol. 11 (2019). ISSN 2073\u20138994","DOI":"10.3390\/sym11091066"},{"key":"13_CR15","unstructured":"Sohn, K.: Improved deep metric learning with multi-class N-pair loss objective. In: NIPS (2016)"},{"key":"13_CR16","doi-asserted-by":"crossref","unstructured":"Snyder, D., Garcia-Romero, D., Sell, G., Povey, D., Khudanpur, S.: X-Vectors: robust DNN embeddings for speaker recognition. In: ICASSP (2018)","DOI":"10.1109\/ICASSP.2018.8461375"},{"key":"13_CR17","unstructured":"Kingma, D.P., Max, W.: Auto-encoding variational bayes. CoRR, arxiv.org, abs\/1312.6114 (2013)"},{"key":"13_CR18","unstructured":"Rezende, D.J., Mohamed, S., Wierstra, D.: Stochastic backpropagation and approximate inference in deep generative models. In: ICML (2014)"},{"key":"13_CR19","doi-asserted-by":"crossref","unstructured":"Bowman, S.R., Vilnis, L., Vinyals, O., Dai, A.M., Jozefowicz, R., Bengio, S.: Generating sentences from a continuous space. In: SIGNLL Conference on Computational Natural Language Learning (2016)","DOI":"10.18653\/v1\/K16-1002"},{"key":"13_CR20","doi-asserted-by":"crossref","unstructured":"Chung, J.S., Nagrani, A., Zisserman, A.: VoxCeleb2: deep speaker recognition. In: Interspeech (2018)","DOI":"10.21437\/Interspeech.2018-1929"},{"key":"13_CR21","unstructured":"Povey, D., et al.: The Kaldi speech recognition toolkit. In: ASRU Conference (2011)"},{"key":"13_CR22","doi-asserted-by":"crossref","unstructured":"Morise, M., Yokomori, F., Ozawa, K.: WORLD: a vocoder-based high-quality speech synthesis system for real-time applications. In: IEICE Transactions (2016)","DOI":"10.1587\/transinf.2015EDP7457"},{"key":"13_CR23","unstructured":"Yamagishi, J., Honnet, P.E., Garner, P., Lazaridis, A.: The SIWIS French Speech Synthesis Database (2017)"},{"key":"13_CR24","doi-asserted-by":"crossref","unstructured":"Stan, A., et al.: TUNDRA: a multilingual corpus of found data for TTS research created with light supervision. In: Interspeech (2013)","DOI":"10.21437\/Interspeech.2013-545"},{"issue":"2","key":"13_CR25","doi-asserted-by":"publisher","first-page":"213","DOI":"10.1007\/s00530-014-0446-1","volume":"22","author":"RC Streijl","year":"2014","unstructured":"Streijl, R.C., Winkler, S., Hands, D.S.: Mean opinion score (MOS) revisited: methods and applications, limitations and alternatives. Multimed. Syst. 22(2), 213\u2013227 (2014). https:\/\/doi.org\/10.1007\/s00530-014-0446-1","journal-title":"Multimed. Syst."},{"key":"13_CR26","doi-asserted-by":"crossref","unstructured":"Dahmani, S., Colotte, V., Girard, V., Ouni, S.: Conditional variational auto-encoder for text-driven expressive audiovisual speech synthesis. In: Interspeech (2019)","DOI":"10.21437\/Interspeech.2019-2848"},{"key":"13_CR27","doi-asserted-by":"crossref","unstructured":"Wu, Z., Watts, O., King, S.: Merlin: an open source neural network speech synthesis system. In: ISCA Speech Synthesis Workshop (SSW9) (2016)","DOI":"10.21437\/SSW.2016-33"}],"container-title":["Lecture Notes in Computer Science","Statistical Language and Speech Processing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-030-59430-5_13","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,11,20]],"date-time":"2022-11-20T11:34:17Z","timestamp":1668944057000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-030-59430-5_13"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020]]},"ISBN":["9783030594299","9783030594305"],"references-count":27,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-59430-5_13","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2020]]},"assertion":[{"value":"26 September 2020","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"SLSP","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Statistical Language and Speech Processing","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Cardiff","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"United Kingdom","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2020","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"14 October 2020","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"16 October 2020","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"8","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"slsp2020","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/irdta.eu\/slsp2020\/","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":"25","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":"13","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":"52% - 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":"2","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)"}},{"value":"Due to COVID-19 pandemic the conference was held virtually.","order":10,"name":"additional_info_on_review_process","label":"Additional Info on Review Process","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}}]}}