{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,7,8]],"date-time":"2025-07-08T04:16:10Z","timestamp":1751948170134,"version":"3.41.2"},"publisher-location":"Cham","reference-count":13,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783030008093"},{"type":"electronic","value":"9783030008109"}],"license":[{"start":{"date-parts":[[2018,1,1]],"date-time":"2018-01-01T00:00:00Z","timestamp":1514764800000},"content-version":"unspecified","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":[[2018]]},"DOI":"10.1007\/978-3-030-00810-9_3","type":"book-chapter","created":{"date-parts":[[2018,9,18]],"date-time":"2018-09-18T05:02:57Z","timestamp":1537246977000},"page":"21-31","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":4,"title":["Phone-Level Embeddings for Unit Selection Speech Synthesis"],"prefix":"10.1007","author":[{"given":"Antoine","family":"Perquin","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Gw\u00e9nol\u00e9","family":"Lecorv\u00e9","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Damien","family":"Lolive","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Laurent","family":"Amsaleg","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2018,9,19]]},"reference":[{"key":"3_CR1","doi-asserted-by":"crossref","unstructured":"Black, A.W., Zen, H., Tokuda, K.: Statistical parametric speech synthesis. In: Proceedings of the IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), vol. 4, pp. 1229\u20131232 (2007)","DOI":"10.1109\/ICASSP.2007.367298"},{"key":"3_CR2","doi-asserted-by":"crossref","unstructured":"Hunt, A.J., Black, A.W.: Unit selection in a concatenative speech synthesis system using a large speech database. In: Proceedings of the IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP), vol. 1, pp. 373\u2013376 (1996)","DOI":"10.1109\/ICASSP.1996.541110"},{"key":"3_CR3","unstructured":"Lolive, D., et al.: The IRISA text-to-speech system for the Blizzard challenge 2017. In: Proceedings of the Blizzard Challenge Workshop (2017)"},{"key":"3_CR4","doi-asserted-by":"crossref","unstructured":"Merritt, T., Clark, R.A., Wu, Z., Yamagishi, J., King, S.: Deep neural network-guided unit selection synthesis. In: Proceedings of the IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 5145\u20135149 (2016)","DOI":"10.1109\/ICASSP.2016.7472658"},{"issue":"7","key":"3_CR5","doi-asserted-by":"publisher","first-page":"1877","DOI":"10.1587\/transinf.2015EDP7457","volume":"99","author":"M Morise","year":"2016","unstructured":"Morise, M., Yokomori, F., Ozawa, K.: WORLD: a vocoder-based high-quality speech synthesis system for real-time applications. IEICE Trans. Inf. Syst. 99(7), 1877\u20131884 (2016)","journal-title":"IEICE Trans. Inf. Syst."},{"key":"3_CR6","unstructured":"van den Oord, A., et al.: WaveNet: a generative model for raw audio. In: Proceedings of the ISCA Speech Synthesis Workshop (SSW), pp. 125\u2013125 (2016)"},{"key":"3_CR7","unstructured":"Perquin, A.: Big deep voice: indexation de donn\u00e9es massives de parole gr\u00e2ce \u00e0 des r\u00e9seaux de neurones profonds. Master\u2019s thesis, University of Rennes 1 (2017)"},{"key":"3_CR8","doi-asserted-by":"crossref","unstructured":"Wan, V., Agiomyrgiannakis, Y., Silen, H., Vit, J.: Googles next-generation real-time unit-selection synthesizer using sequence-to-sequence LSTM-based autoencoders. In: Proceedings of the Annual Conference of the International Speech Communication Association (Interspeech), pp. 1143\u20131147 (2017)","DOI":"10.21437\/Interspeech.2017-1107"},{"key":"3_CR9","doi-asserted-by":"crossref","unstructured":"Wang, Y., et al.: Tacotron: towards end-to-end speech synthesis. In: Proceedings of the Annual Conference of the International Speech Communication Association (Interspeech), pp. 4006\u20134010 (2017)","DOI":"10.21437\/Interspeech.2017-1452"},{"issue":"7","key":"3_CR10","doi-asserted-by":"publisher","first-page":"1255","DOI":"10.1109\/TASLP.2016.2551865","volume":"24","author":"Z Wu","year":"2016","unstructured":"Wu, Z., King, S.: Improving trajectory modelling for DNN-based speech synthesis by using stacked bottleneck features and minimum generation error training. IEEE\/ACM Trans. Audio Speech Lang. Process. (TASLP) 24(7), 1255\u20131265 (2016)","journal-title":"IEEE\/ACM Trans. Audio Speech Lang. Process. (TASLP)"},{"key":"3_CR11","doi-asserted-by":"crossref","unstructured":"Wu, Z., Watts, O., King, S.: Merlin: an open source neural network speech synthesis system. In: Proceedings of the ISCA Speech Synthesis Workshop (SSW), pp. 218\u2013223 (2016)","DOI":"10.21437\/SSW.2016-33"},{"key":"3_CR12","doi-asserted-by":"crossref","unstructured":"Yan, Z.J., Qian, Y., Soong, F.K.: Rich-context unit selection (RUS) approach to high quality TTS. In: IEEE International Conference on Acoustics Speech and Signal Processing (ICASSP), pp. 4798\u20134801 (2010)","DOI":"10.1109\/ICASSP.2010.5495150"},{"key":"3_CR13","doi-asserted-by":"crossref","unstructured":"Ze, H., Senior, A., Schuster, M.: Statistical parametric speech synthesis using deep neural networks. In: Proceedings of the IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 7962\u20137966 (2013)","DOI":"10.1109\/ICASSP.2013.6639215"}],"container-title":["Lecture Notes in Computer Science","Statistical Language and Speech Processing"],"original-title":[],"link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-030-00810-9_3","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,7,7]],"date-time":"2025-07-07T17:52:48Z","timestamp":1751910768000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-030-00810-9_3"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018]]},"ISBN":["9783030008093","9783030008109"],"references-count":13,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-00810-9_3","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2018]]},"assertion":[{"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":"Mons","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Belgium","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2018","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"15 October 2018","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"16 October 2018","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"6","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"slsp2018","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/slsp2018.irdta.eu\/","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"}},{"value":"EasyChair","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information"}},{"value":"40","order":3,"name":"number_of_submissions_sent_for_review","label":"Number of Submissions Sent for Review","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information"}},{"value":"15","order":4,"name":"number_of_full_papers_accepted","label":"Number of Full Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information"}},{"value":"0","order":5,"name":"number_of_short_papers_accepted","label":"Number of Short Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information"}},{"value":"38% - 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"}},{"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"}},{"value":"3-4","order":8,"name":"average_number_of_papers_per_reviewer","label":"Average Number of Papers per Reviewer","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information"}},{"value":"Yes","order":9,"name":"external_reviewers_involved","label":"External Reviewers Involved","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information"}},{"order":10,"name":"additional_info_on_review_process","label":"Additional Info on Review Process","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information"}}]}}