{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,27]],"date-time":"2025-03-27T19:37:34Z","timestamp":1743104254479,"version":"3.40.3"},"publisher-location":"Cham","reference-count":27,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783030279462"},{"type":"electronic","value":"9783030279479"}],"license":[{"start":{"date-parts":[[2019,1,1]],"date-time":"2019-01-01T00:00:00Z","timestamp":1546300800000},"content-version":"tdm","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":[[2019]]},"DOI":"10.1007\/978-3-030-27947-9_8","type":"book-chapter","created":{"date-parts":[[2019,9,1]],"date-time":"2019-09-01T23:02:43Z","timestamp":1567378963000},"page":"91-102","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["Using Auto-Encoder BiLSTM Neural Network for Czech Grapheme-to-Phoneme Conversion"],"prefix":"10.1007","author":[{"given":"Mark\u00e9ta","family":"J\u016fzov\u00e1","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jakub","family":"V\u00edt","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2019,8,6]]},"reference":[{"key":"8_CR1","doi-asserted-by":"publisher","first-page":"153","DOI":"10.1524\/slaw.2011.0013","volume":"56","author":"A Bi\u010dan","year":"2011","unstructured":"Bi\u010dan, A.: Distribution and combinations of Czech consonants. Zeitschrift f\u00fcr Slawistik 56, 153\u2013171 (2011)","journal-title":"Zeitschrift f\u00fcr Slawistik"},{"issue":"5","key":"8_CR2","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":"8_CR3","doi-asserted-by":"crossref","unstructured":"Cho, K., et al.: Learning phrase representations using RNN encoder-decoder for statistical machine translation. In: Moschitti, A., Pang, B., Daelemans, W. (eds.) EMNLP, pp. 1724\u20131734. ACL (2014)","DOI":"10.3115\/v1\/D14-1179"},{"key":"8_CR4","first-page":"361","volume-title":"TSD 2019","author":"Z Hanzl\u00ed\u010dek","year":"2019","unstructured":"Hanzl\u00ed\u010dek, Z., V\u00edt, J., Tihelka, D.: LSTM-based speech segmentation for TTS synthesis. In: Ek\u0161tein, K. (ed.) TSD 2019. LNAI, vol. 11697, pp. 361\u2013372. Springer, Heidelberg (2019)"},{"issue":"8","key":"8_CR5","doi-asserted-by":"publisher","first-page":"1735","DOI":"10.1162\/neco.1997.9.8.1735","volume":"9","author":"S Hochreiter","year":"1997","unstructured":"Hochreiter, S., Schmidhuber, J.: Long short-term memory. Neural Comput. 9(8), 1735\u20131780 (1997)","journal-title":"Neural Comput."},{"key":"8_CR6","unstructured":"Jiampojamarn, S., Cherry, C., Kondrak, G.: Joint processing and discriminative training for letter-to-phoneme conversion. In: Proceedings of ACL-08: HLT, pp. 905\u2013913. Association for Computational Linguistics, Columbus (2008)"},{"key":"8_CR7","unstructured":"Ku\u010dera, H.: The phonology of Czech, Slavistic printings and reprintings, vol. 30, \u2019s-Gravenhage, Mouton (1961)"},{"key":"8_CR8","unstructured":"Macha\u010d, P., Skarnitzl, R.: Principles of phonetic segmentation. Edition erudica, Epocha (2009)"},{"key":"8_CR9","series-title":"Lecture Notes in Computer Science (Lecture Notes in Artificial Intelligence)","doi-asserted-by":"publisher","first-page":"223","DOI":"10.1007\/3-540-45323-7_38","volume-title":"Text, Speech and Dialogue","author":"J Matou\u0161ek","year":"2000","unstructured":"Matou\u0161ek, J.: Building a New Czech text-to-speech system using triphone-based speech units. In: Sojka, P., Kope\u010dek, I., Pala, K. (eds.) TSD 2000. LNCS (LNAI), vol. 1902, pp. 223\u2013228. Springer, Heidelberg (2000). https:\/\/doi.org\/10.1007\/3-540-45323-7_38"},{"key":"8_CR10","doi-asserted-by":"crossref","unstructured":"Matou\u0161ek, J., Tihelka, D.: Annotation errors detection in TTS corpora. In: Proceedings of INTERSPEECH 2013, Lyon, France, pp. 1511\u20131515 (2013)","DOI":"10.21437\/Interspeech.2013-305"},{"key":"8_CR11","series-title":"Lecture Notes in Computer Science (Lecture Notes in Artificial Intelligence)","doi-asserted-by":"publisher","first-page":"456","DOI":"10.1007\/978-3-642-32790-2_55","volume-title":"Text, Speech and Dialogue","author":"J Matou\u0161ek","year":"2012","unstructured":"Matou\u0161ek, J., Tihelka, D., \u0160m\u00eddl, L.: On the impact of annotation errors on\u00a0unit-selection\u00a0speech\u00a0synthesis. In: Sojka, P., Hor\u00e1k, A., Kope\u010dek, I., Pala, K. (eds.) TSD 2012. LNCS (LNAI), vol. 7499, pp. 456\u2013463. Springer, Heidelberg (2012). https:\/\/doi.org\/10.1007\/978-3-642-32790-2_55"},{"key":"8_CR12","series-title":"Lecture Notes in Computer Science (Lecture Notes in Artificial Intelligence)","doi-asserted-by":"publisher","first-page":"287","DOI":"10.1007\/978-3-540-39398-6_41","volume-title":"Text, Speech and Dialogue","author":"J Matou\u0161ek","year":"2003","unstructured":"Matou\u0161ek, J., Tihelka, D., Psutka, J.: Experiments with automatic segmentation for Czech speech synthesis. In: Matou\u0161ek, V., Mautner, P. (eds.) TSD 2003. LNCS (LNAI), vol. 2807, pp. 287\u2013294. Springer, Heidelberg (2003). https:\/\/doi.org\/10.1007\/978-3-540-39398-6_41"},{"key":"8_CR13","first-page":"147","volume":"39","author":"J Matou\u0161ek","year":"2012","unstructured":"Matou\u0161ek, J., Tihelka, D., Romportl, J., Psutka, J.: Slovak unit-selection speech synthesis: creating a new Slovak voice within a Czech TTS system ARTIC. IAENG Int. J. Comput. Sci. 39, 147\u2013154 (2012)","journal-title":"IAENG Int. J. Comput. Sci."},{"key":"8_CR14","series-title":"Lecture Notes in Computer Science (Lecture Notes in Artificial Intelligence)","doi-asserted-by":"publisher","first-page":"257","DOI":"10.1007\/11551874_33","volume-title":"Text, Speech and Dialogue","author":"J Matou\u0161ek","year":"2005","unstructured":"Matou\u0161ek, J., Kala, J.: On modelling glottal stop in Czech text-to-speech synthesis. In: Matou\u0161ek, V., Mautner, P., Pavelka, T. (eds.) TSD 2005. LNCS (LNAI), vol. 3658, pp. 257\u2013264. Springer, Heidelberg (2005). https:\/\/doi.org\/10.1007\/11551874_33"},{"key":"8_CR15","doi-asserted-by":"crossref","unstructured":"Matou\u0161ek, J., Psutka, J.: ARTIC: a new czech text-to-speech system using statistical approach to speech segment database construction. In: Interspeech 2000 - ICSLP, Beijing, China, vol. 4, pp. 612\u2013615 (2000)","DOI":"10.21437\/ICSLP.2000-886"},{"key":"8_CR16","series-title":"Lecture Notes in Computer Science (Lecture Notes in Artificial Intelligence)","doi-asserted-by":"publisher","first-page":"155","DOI":"10.1007\/978-3-540-30120-2_20","volume-title":"Text, Speech and Dialogue","author":"J Matou\u0161ek","year":"2004","unstructured":"Matou\u0161ek, J., Tihelka, D.: Slovak text-to-speech synthesis in ARTIC system. In: Sojka, P., Kope\u010dek, I., Pala, K. (eds.) TSD 2004. LNCS (LNAI), vol. 3206, pp. 155\u2013162. Springer, Heidelberg (2004). https:\/\/doi.org\/10.1007\/978-3-540-30120-2_20"},{"issue":"6","key":"8_CR17","doi-asserted-by":"publisher","first-page":"907","DOI":"10.1017\/S1351324915000315","volume":"22","author":"JR Novak","year":"2016","unstructured":"Novak, J.R., Minamatsu, N., Hirose, K.: Phonetisaurus: exploring grapheme-to-phoneme conversion with joint n-gram models in the WFST framework. Natural Lang. Eng. 22(6), 907\u2013938 (2016)","journal-title":"Natural Lang. Eng."},{"key":"8_CR18","unstructured":"Palkov\u00e1, Z.: Fonetika a fonologie \u010de\u0161tiny [Phonetics and phonology of Czech], 1st edn. Univerzita Karlova, Nakladatelstv\u00ed Karolinum, Praha (1994)"},{"key":"8_CR19","volume-title":"Mluv\u00edme s po\u010d\u00edta\u010dem \u010desky [Talking with Computer in Czech]","author":"J Psutka","year":"2006","unstructured":"Psutka, J., M\u00fcller, L., Matou\u0161ek, J., Radov\u00e1, V.: Mluv\u00edme s po\u010d\u00edta\u010dem \u010desky [Talking with Computer in Czech]. Academia, Praha (2006)"},{"key":"8_CR20","doi-asserted-by":"crossref","unstructured":"Rao, K., Peng, F., Sak, H., Beaufays, F.: Grapheme-to-phoneme conversion using long short-term memory recurrent neural networks. In: 2015 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 4225\u20134229 (2015)","DOI":"10.1109\/ICASSP.2015.7178767"},{"key":"8_CR21","unstructured":"Sutskever, I., Vinyals, O., Le, Q.V.: Sequence to sequence learning with neural networks. In: Proceedings NIPS, Montreal, Canada, pp. 3104\u20133112 (2014)"},{"key":"8_CR22","series-title":"Lecture Notes in Computer Science (Lecture Notes in Artificial Intelligence)","doi-asserted-by":"publisher","first-page":"369","DOI":"10.1007\/978-3-030-00794-2_40","volume-title":"Text, Speech, and Dialogue","author":"D Tihelka","year":"2018","unstructured":"Tihelka, D., Hanzl\u00ed\u010dek, Z., J\u016fzov\u00e1, M., V\u00edt, J., Matou\u0161ek, J., Gr\u016fber, M.: Current state of text-to-speech system ARTIC: a\u00a0decade of research on the field of speech technologies. In: Sojka, P., Hor\u00e1k, A., Kope\u010dek, I., Pala, K. (eds.) TSD 2018. LNCS (LNAI), vol. 11107, pp. 369\u2013378. Springer, Cham (2018). https:\/\/doi.org\/10.1007\/978-3-030-00794-2_40"},{"issue":"2","key":"8_CR23","doi-asserted-by":"publisher","first-page":"122","DOI":"10.1109\/LSP.2010.2098440","volume":"18","author":"D Wang","year":"2011","unstructured":"Wang, D., King, S.: Letter-to-sound pronunciation prediction using conditional random fields. IEEE Signal Process. Lett. 18(2), 122\u2013125 (2011)","journal-title":"IEEE Signal Process. Lett."},{"key":"8_CR24","doi-asserted-by":"crossref","unstructured":"Wang, Y., et al.: Tacotron: towards end-to-end speech synthesis (2017). https:\/\/arxiv.org\/abs\/1703.10135","DOI":"10.21437\/Interspeech.2017-1452"},{"key":"8_CR25","volume-title":"Handbook of Standards and Resources for Spoken Language Systems","author":"JC Wells","year":"1997","unstructured":"Wells, J.C.: SAMPA computer readable phonetic alphabet. In: Gibbon, D., Moore, R., Winski, R. (eds.) Handbook of Standards and Resources for Spoken Language Systems. Mouton de Gruyter, Berlin (1997)"},{"key":"8_CR26","unstructured":"Wu, Y., et al.: Google\u2019s neural machine translation system: bridging the gap between human and machine translation. CoRR abs\/1609.08144 (2016). http:\/\/arxiv.org\/abs\/1609.08144"},{"key":"8_CR27","doi-asserted-by":"crossref","unstructured":"Yao, K., Zweig, G.: Sequence-to-sequence neural net models for grapheme-to-phoneme conversion. CoRR abs\/1506.00196 (2015)","DOI":"10.21437\/Interspeech.2015-134"}],"container-title":["Lecture Notes in Computer Science","Text, Speech, and Dialogue"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-030-27947-9_8","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,3,13]],"date-time":"2024-03-13T16:39:40Z","timestamp":1710347980000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-030-27947-9_8"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019]]},"ISBN":["9783030279462","9783030279479"],"references-count":27,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-27947-9_8","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2019]]},"assertion":[{"value":"6 August 2019","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"TSD","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Text, Speech, and Dialogue","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Ljubljana","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Slovenia","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2019","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"10 September 2019","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"13 September 2019","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"22","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"tsd2019","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/www.kiv.zcu.cz\/tsd2019\/","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":"inhouse TSD Web App 3.1","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"73","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":"33","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":"45% - 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":"2-4","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":"2,42","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)"}},{"value":"1 full invited talk","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)"}}]}}