{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,5,29]],"date-time":"2025-05-29T05:23:27Z","timestamp":1748496207418,"version":"3.40.3"},"publisher-location":"Cham","reference-count":16,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783031209796"},{"type":"electronic","value":"9783031209802"}],"license":[{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2022]]},"DOI":"10.1007\/978-3-031-20980-2_23","type":"book-chapter","created":{"date-parts":[[2022,11,12]],"date-time":"2022-11-12T19:03:09Z","timestamp":1668279789000},"page":"265-278","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":2,"title":["Comparing NLP Solutions for the Disambiguation of French Heterophonic Homographs for End-to-End TTS Systems"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-2405-1713","authenticated-orcid":false,"given":"Maria-Loulou","family":"Hajj","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3359-6846","authenticated-orcid":false,"given":"Martin","family":"Lenglet","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9909-6078","authenticated-orcid":false,"given":"Olivier","family":"Perrotin","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4598-9206","authenticated-orcid":false,"given":"G\u00e9rard","family":"Bailly","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2022,11,10]]},"reference":[{"issue":"5","key":"23_CR1","doi-asserted-by":"publisher","first-page":"434","DOI":"10.1016\/j.specom.2008.01.002","volume":"50","author":"M Bisani","year":"2008","unstructured":"Bisani, M., Ney, H.: Joint-sequence models for grapheme-to-phoneme conversion. Speech Commun. 50(5), 434\u2013451 (2008)","journal-title":"Speech Commun."},{"key":"23_CR2","unstructured":"Black, A.W., Lenzo, K., Pagel, V.: Issues in building general letter to sound rules. In: The Third ESCA\/COCOSDA Workshop (ETRW) on Speech Synthesis. Jenolan Caves House, Blue Mountains, Australia (1998)"},{"issue":"2","key":"23_CR3","doi-asserted-by":"publisher","first-page":"198","DOI":"10.1016\/j.cognition.2006.05.009","volume":"104","author":"ML Bosse","year":"2007","unstructured":"Bosse, M.L., Tainturier, M.J., Valdois, S.: Developmental dyslexia: the visual attention span deficit hypothesis. Cognition 104(2), 198\u2013230 (2007)","journal-title":"Cognition"},{"key":"23_CR4","unstructured":"Goldman, J.P., Laenzlinger, C., Wehrli, E.: La phon\u00e9tisation de plus, tous et de certains nombres: une analyse phono-syntaxique. Actes de TALN99, Cargese, Corse, pp. 165\u2013174 (1999)"},{"key":"23_CR5","unstructured":"Gorman, K., Mazovetskiy, G., Nikolaev, V.: Improving homograph disambiguation with supervised machine learning. In: Proceedings of the Eleventh International Conference on Language Resources and Evaluation (LREC 2018) (2018)"},{"key":"23_CR6","doi-asserted-by":"crossref","unstructured":"Kastner, K., Santos, J.F., Bengio, Y., Courville, A.: Representation mixing for TTS synthesis. In: ICASSP 2019\u20132019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 5906\u20135910. IEEE (2019)","DOI":"10.1109\/ICASSP.2019.8682880"},{"key":"23_CR7","unstructured":"Kumar, A.: NLP pre-trained models explained with examples (2021)"},{"key":"23_CR8","unstructured":"Le, H., et al.: Flaubert: unsupervised language model pre-training for French (2019). https:\/\/arxiv.org\/abs\/1912.05372"},{"key":"23_CR9","doi-asserted-by":"crossref","unstructured":"Lenglet, M., Perrotin, O., Bailly, G.: Mod\u00e9lisation de la parole avec tacotron2: analyse acoustique et phon\u00e9tique des plongements de caract\u00e8re. In: 34$$^{e}$$ Journ\u00e9es d\u2019\u00c9tudes sur la Parole (JEP), pp. 845\u2013854. Noirmoutier, France (2022)","DOI":"10.21437\/JEP.2022-83"},{"key":"23_CR10","doi-asserted-by":"publisher","unstructured":"Nicolis, M., Klimkov, V.: Homograph disambiguation with contextual word embeddings for TTS systems. In: ISCA Speech Synthesis Workshop (SSW), pp. 222\u2013226 (2021). https:\/\/doi.org\/10.21437\/SSW.2021-39","DOI":"10.21437\/SSW.2021-39"},{"key":"23_CR11","unstructured":"Ping, W., et al.: Deep voice 3: scaling text-to-speech with convolutional sequence learning. arXiv preprint arXiv:1710.07654 (2017)"},{"key":"23_CR12","unstructured":"Ren, Y., et al.: Fastspeech: fast, robust and controllable text to speech. Adv. Neural Inf. Process. Syst. 32 (2019)"},{"key":"23_CR13","doi-asserted-by":"crossref","unstructured":"Shen, J., et al.: Natural TTS synthesis by conditioning wavenet on mel spectrogram predictions (2018). https:\/\/arxiv.org\/abs\/1712.05884","DOI":"10.1109\/ICASSP.2018.8461368"},{"key":"23_CR14","doi-asserted-by":"crossref","unstructured":"Sun, M., Bellegarda, J.R.: Improved pos tagging for text-to-speech synthesis. In: 2011 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 5384\u20135387. IEEE (2011)","DOI":"10.1109\/ICASSP.2011.5947575"},{"key":"23_CR15","doi-asserted-by":"crossref","unstructured":"Taylor, J., Richmond, K.: Analysis of pronunciation learning in end-to-end speech synthesis. In: INTERSPEECH, pp. 2070\u20132074 (2019)","DOI":"10.21437\/Interspeech.2019-2830"},{"key":"23_CR16","doi-asserted-by":"crossref","unstructured":"Yao, K., Zweig, G.: Sequence-to-sequence neural net models for grapheme-to-phoneme conversion. arXiv preprint arXiv:1506.00196 (2015)","DOI":"10.21437\/Interspeech.2015-134"}],"container-title":["Lecture Notes in Computer Science","Speech and Computer"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-20980-2_23","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,3,11]],"date-time":"2023-03-11T22:50:29Z","timestamp":1678575029000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-20980-2_23"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022]]},"ISBN":["9783031209796","9783031209802"],"references-count":16,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-20980-2_23","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2022]]},"assertion":[{"value":"10 November 2022","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":"Gurugram","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":"2022","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"14 November 2022","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"16 November 2022","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"24","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"specom2022","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/www.specom.co.in","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":"99","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":"60","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":"61% - 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)"}}]}}