{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,31]],"date-time":"2025-12-31T12:18:08Z","timestamp":1767183488397,"version":"3.40.3"},"publisher-location":"Cham","reference-count":58,"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_1","type":"book-chapter","created":{"date-parts":[[2020,9,25]],"date-time":"2020-09-25T08:04:59Z","timestamp":1601021099000},"page":"3-19","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":11,"title":["Grapheme-to-Phoneme Transduction for Cross-Language ASR"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-5631-2893","authenticated-orcid":false,"given":"Mark","family":"Hasegawa-Johnson","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Leanne","family":"Rolston","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3530-8577","authenticated-orcid":false,"given":"Camille","family":"Goudeseune","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Gina-Anne","family":"Levow","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6645-6030","authenticated-orcid":false,"given":"Katrin","family":"Kirchhoff","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2020,9,26]]},"reference":[{"key":"1_CR1","unstructured":"Adda, G., et al.: Breaking the unwritten language barrier: the BULB project. In: Proceedings of the SLTU-2016 5th Workshop on Spoken Language Technologies for Under-resourced Languages (2016)"},{"key":"1_CR2","unstructured":"Aker, A., Paramita, M.L., Pinnis, M., Gaizauskas, R.J.: Bilingual dictionaries for all EU languages. In: Proceedings of the Conference on Language Resources and Evaluation (LREC), pp. 2839\u20132845 (2014)"},{"key":"1_CR3","doi-asserted-by":"crossref","unstructured":"Allauzen, C., Mohri, M., Roark, B.: Generalized algorithms for constructing statistical language models. In: Proceedings of the Annual Meeting of the Association for Computational Linguistics, pp. 40\u201347 (2003)","DOI":"10.3115\/1075096.1075102"},{"key":"1_CR4","unstructured":"Baayen, R., Piepenbrock, R., Gulikers, L.: CELEX2. Technical report, LDC96L14, Linguistic Data Consortium (1996)"},{"key":"1_CR5","unstructured":"Bahl, L.R., Brown, P.F., de Souza, P.V., Picheny, M.A.: Acoustic Markov models used in the Tangora speech recognition system. In: Proceedings ICASSP, pp. 497\u2013500 (1988)"},{"issue":"5","key":"1_CR6","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":"1_CR7","unstructured":"Blench, R., Nebel, A.: Dinka-English and English-Dinka dictionary (2005)"},{"issue":"4","key":"1_CR8","first-page":"5","volume":"8","author":"F Bond","year":"2012","unstructured":"Bond, F., Paik, K.: A survey of wordnets and their licenses. Small 8(4), 5 (2012)","journal-title":"Small"},{"issue":"6097","key":"1_CR9","doi-asserted-by":"publisher","first-page":"957","DOI":"10.1126\/science.1219669","volume":"337","author":"R Bouckaert","year":"2012","unstructured":"Bouckaert, R., et al.: Mapping the origins and expansion of the Indo-European language family. Science 337(6097), 957\u2013960 (2012)","journal-title":"Science"},{"key":"1_CR10","doi-asserted-by":"publisher","unstructured":"Chan, W., Jaitly, N., Le, Q., Vinyals, O.: Listen, attend and spell: a neural network for large vocabulary conversational speech recognition. In: Proceedings ICASSP, pp. 4960\u20134964 (2016). https:\/\/doi.org\/10.1109\/ICASSP.2016.7472621","DOI":"10.1109\/ICASSP.2016.7472621"},{"key":"1_CR11","unstructured":"D\u00e2na, A.: S\u00f6zl\u00fck (2006). www.denizyuret.com\/2006\/11\/turkish-resources.html. Accessed 20 July 2020"},{"issue":"6","key":"1_CR12","doi-asserted-by":"publisher","first-page":"637","DOI":"10.1121\/1.1906946","volume":"24","author":"K Davis","year":"1952","unstructured":"Davis, K., Biddulph, R., Balashek, S.: Automatic recognition of spoken digits. J. Acoust. Soc. Am. 24(6), 637\u2013642 (1952)","journal-title":"J. Acoust. Soc. Am."},{"key":"1_CR13","doi-asserted-by":"publisher","unstructured":"Deng, L.: Integrated-multilingual speech recognition using universal phonological features in a functional speech production model. In: Proceedings ICASSP (1997). https:\/\/doi.org\/10.1109\/ICASSP.1997.596110","DOI":"10.1109\/ICASSP.1997.596110"},{"key":"1_CR14","doi-asserted-by":"publisher","unstructured":"Deri, A., Knight, K.: Grapheme-to-phoneme models for (almost) any language. In: Proceedings 54th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pp. 399\u2013408 (2016). https:\/\/doi.org\/10.18653\/v1\/P16-1038","DOI":"10.18653\/v1\/P16-1038"},{"key":"1_CR15","volume-title":"Pattern Classification","author":"RO Duda","year":"2001","unstructured":"Duda, R.O., Hart, P.E., Stork, D.G.: Pattern Classification. Wiley, New York (2001)"},{"key":"1_CR16","doi-asserted-by":"publisher","first-page":"721","DOI":"10.1121\/1.1909742","volume":"30","author":"H Dudley","year":"1958","unstructured":"Dudley, H., Balashek, S.: Automatic recognition of phonetic patterns in speech. J. Acoust. Soc. Am. 30, 721\u2013732 (1958)","journal-title":"J. Acoust. Soc. Am."},{"key":"1_CR17","unstructured":"Eberhard, D.M., Simons, G.F., Fennig, C.D. (eds.): Ethnologue: Languages of the World. 23rd edn. SIL International, Dallas (2020). www.ethnologue.com"},{"key":"1_CR18","unstructured":"Elmahdy, M., Hasegawa-Johnson, M., Mustafawi, E.: Development of a TV broadcasts speech recognition system for Qatari Arabic. In: Proceedings of the Conference on Language Resources and Evaluation (LREC), pp. 3057\u20133061 (2014)"},{"key":"1_CR19","unstructured":"Garrett, J., Lastowka, G., et al.: Turkmen-English dictionary: a SPA project of Peace Corps Turkmenistan (1996)"},{"key":"1_CR20","doi-asserted-by":"crossref","unstructured":"Gilloux, M.: Automatic learning of word transducers from examples. In: Proceedings EUROSPEECH, pp. 107\u2013112 (1991)","DOI":"10.3115\/977180.977199"},{"key":"1_CR21","doi-asserted-by":"crossref","unstructured":"Gr\u00e9zl, F., Karafia\u00e1t, M., Vesel\u00fd, K.: Adaptation of multilingual stacked bottle-neck neural network structure for new language. In: Proceedings ICASSP, pp. 7704\u20137708 (2014)","DOI":"10.1109\/ICASSP.2014.6855089"},{"key":"1_CR22","unstructured":"Hasegawa-Johnson, M., Goudeseune, C., Levow, G.A.: Fast transcription of speech in low-resource languages (2019). https:\/\/arxiv.org\/abs\/1909.07285"},{"key":"1_CR23","doi-asserted-by":"publisher","DOI":"10.1515\/9783110219135","volume-title":"Principles of Historical Linguistics","author":"HH Hock","year":"1991","unstructured":"Hock, H.H.: Principles of Historical Linguistics. Mouton de Gruyter, Berlin (1991)"},{"key":"1_CR24","doi-asserted-by":"crossref","DOI":"10.5040\/9798400665639","volume-title":"The History of Turkey","author":"DA Howard","year":"2016","unstructured":"Howard, D.A.: The History of Turkey. Greenwood, Santa Barbara (2016)"},{"key":"1_CR25","doi-asserted-by":"crossref","unstructured":"Hughes, G.W.: The Recognition of Speech by Machine. Ph.D. Thesis, MIT (1961)","DOI":"10.21236\/AD0268489"},{"key":"1_CR26","doi-asserted-by":"crossref","unstructured":"Hwang, M.Y., Huang, X.: Subphonetic modeling for speech recognition. In: Human Language Technology (HLT), pp. 174\u2013179 (1992)","DOI":"10.3115\/1075527.1075566"},{"key":"1_CR27","unstructured":"IATE: Interactive terminology for Europe (2020). https:\/\/iate.europa.eu. Accessed 26 July 2020"},{"key":"1_CR28","doi-asserted-by":"crossref","unstructured":"International Phonetic Association: Handbook of the International Phonetic Association, Cambridge (1999)","DOI":"10.1017\/9780511807954"},{"key":"1_CR29","unstructured":"Kamholz, D., Pool, J., Colowick, S.M.: PanLex: building a resource for panlingual lexical translation. In: Proceedings of the Conference on Language Resources and Evaluation (LREC), pp. 3145\u20133150 (2014)"},{"key":"1_CR30","doi-asserted-by":"crossref","unstructured":"Kneser, R., Ney, H.: Improved backing-off for M-gram language modeling. In: Proc. ICASSP, pp. 181\u2013184 (1995)","DOI":"10.1109\/ICASSP.1995.479394"},{"key":"1_CR31","unstructured":"K\u00f6hler, J.: Comparing three methods to create multilingual phone models for vocabulary independent speech recognition tasks. In: Multi-Lingual Interoperability in Speech Technology (1999)"},{"key":"1_CR32","unstructured":"Kroeber, P.D.: The Salish Language Family: Reconstructing Syntax. University of Nebraska Press (1999)"},{"key":"1_CR33","first-page":"36","volume":"6","author":"H Ku\u010dera","year":"1963","unstructured":"Ku\u010dera, H.: Mechanical phonemic transcription and phoneme frequency count in Czech. Int. J. Slavic Linguist. Poetics 6, 36\u201350 (1963)","journal-title":"Int. J. Slavic Linguist. Poetics"},{"issue":"3","key":"1_CR34","doi-asserted-by":"publisher","first-page":"550","DOI":"10.2307\/414611","volume":"66","author":"P Ladefoged","year":"1990","unstructured":"Ladefoged, P.: The revised international phonetic alphabet. Language 66(3), 550\u2013552 (1990)","journal-title":"Language"},{"issue":"6","key":"1_CR35","doi-asserted-by":"publisher","first-page":"1594","DOI":"10.1121\/1.2143635","volume":"41","author":"FF Lee","year":"1969","unstructured":"Lee, F.F.: Automatic grapheme-to-phoneme translation of English. J. Acoust. Soc. Am. 41(6), 1594 (1969). https:\/\/doi.org\/10.1121\/1.2143635","journal-title":"J. Acoust. Soc. Am."},{"key":"1_CR36","doi-asserted-by":"crossref","unstructured":"Li, J., Hasegawa-Johnson, M.: Autosegmental neural nets: should phones and tones be synchronous or asynchronous? In: Proceedings Interspeech (2020)","DOI":"10.21437\/Interspeech.2020-1834"},{"key":"1_CR37","unstructured":"Marcantonio, A.: The Uralic language family: facts, myths and statistics. Sapienza Universit\u00e0 di Roma (2002)"},{"key":"1_CR38","unstructured":"Millward, J.: Eurasian Crossroads: A History of Xinjiang. Columbia University Press (1982)"},{"key":"1_CR39","unstructured":"Moran, S., McCloy, D. (eds.): PHOIBLE 2.0. Jena: Max Planck Institute for the Science of Human History (2019)"},{"key":"1_CR40","unstructured":"Mortensen, D.R., Dalmia, S., Littell, P.: Epitran: precision G2P for many languages. In: Proceedings of the Conference on Language Resources and Evaluation (LREC), pp. 2710\u20132714 (2018)"},{"key":"1_CR41","unstructured":"Neubig, G., et al.: DyNet: the dynamic neural network toolkit (2017). https:\/\/arxiv.org\/pdf\/1701.03980.pdf. Accessed 14 Sept 2017"},{"issue":"6","key":"1_CR42","doi-asserted-by":"publisher","first-page":"907","DOI":"10.1017\/S1351324915000315","volume":"22","author":"JR Novak","year":"2015","unstructured":"Novak, J.R., Minematsu, 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 (2015)","journal-title":"Natural Lang. Eng."},{"issue":"2","key":"1_CR43","first-page":"9","volume":"1989","author":"AH Omar","year":"1989","unstructured":"Omar, A.H.: The Malay spelling reform. J. Simplified Spelling Soc. 1989(2), 9\u201313 (1989)","journal-title":"J. Simplified Spelling Soc."},{"key":"1_CR44","doi-asserted-by":"crossref","unstructured":"Peters, B., Dehdari, J., van Genabith, J.: Massively multilingual neural grapheme-to-phoneme conversion. In: EMNLP 2017 Workshop on Building Linguisically Generalizable NLP Systems (2017)","DOI":"10.18653\/v1\/W17-5403"},{"issue":"4","key":"1_CR45","doi-asserted-by":"publisher","first-page":"200","DOI":"10.1177\/002383096100400403","volume":"4","author":"GE Peterson","year":"1961","unstructured":"Peterson, G.E.: Automatic speech recognition procedures. Lang. Speech 4(4), 200\u2013219 (1961). https:\/\/doi.org\/10.1177\/002383096100400403","journal-title":"Lang. Speech"},{"key":"1_CR46","unstructured":"Povey, D., et al.: The Kaldi speech recognition toolkit. In: IEEE 2011 Workshop on Automatic Speech Recognition and Understanding. IEEE Signal Processing Society, December 2011. IEEE Catalog No.: CFP11SRW-USB"},{"issue":"3","key":"1_CR47","first-page":"351","volume":"22","author":"PA Rentzepopoulos","year":"1996","unstructured":"Rentzepopoulos, P.A., Kokkinakis, G.K.: Efficient multilingual phoneme-to-grapheme conversion based on HMM. Comput. Linguist. 22(3), 351\u2013376 (1996)","journal-title":"Comput. Linguist."},{"key":"1_CR48","unstructured":"Ritchie, M., Comrie, B. (eds.): The Intercontinental Dictionary Series. Max Planck Institute for Evolutionary Anthropology, Leipzig (2015). http:\/\/ids.clld.org. Accessed 26 July 2020"},{"key":"1_CR49","unstructured":"Rolston, L., Kirchhoff, K.: Collection of bilingual data for lexicon transfer learning. Technical report, UWEETR-2016-0000, University of Washington Department of Electrical Engineering (2016)"},{"key":"1_CR50","doi-asserted-by":"crossref","unstructured":"Schultz, T.: GlobalPhone: a multilingual speech and text database developed at Karlsruhe University. In: Seventh International Conference on Spoken Language Processing (2002)","DOI":"10.21437\/ICSLP.2002-151"},{"key":"1_CR51","unstructured":"Schultz, T., Waibel, A.: Multilingual and crosslingual speech recognition. In: Proceedings International Conference Spoken Language Processing (ICSLP), pp. 0577:1\u20134 (1998)"},{"issue":"1","key":"1_CR52","first-page":"49","volume":"20","author":"M Uzman","year":"2010","unstructured":"Uzman, M.: Romanisation in Uzbekistan past and present. J. Roy. Asiatic Soc. 20(1), 49\u201360 (2010)","journal-title":"J. Roy. Asiatic Soc."},{"key":"1_CR53","unstructured":"van Rijnsoever, P.: A multilingual text-to-speech system. In: IPO Annual Progress Report, pp. 34\u201341. Institute for Perception Research, Eindhoven (1988)"},{"key":"1_CR54","unstructured":"Varga, K.: Kaldi ASR: Extending the ASpIRE model (2017). chrisearch.wordpress.com\/2017\/03\/11\/speech-recognition-using-kaldi-extending-and-using-the-aspire-model"},{"key":"1_CR55","unstructured":"Vasu, S.C.: The Asht\u00e1dhy\u00e1y\u00ed of P\u00e1ini. Translated into English, Sindhu Charan Bose (1897"},{"key":"1_CR56","unstructured":"Vaswani, A., et al.: Attention is all you need. In: Guyon, I., Luxburg, U.V., Bengio, S., Wallach, H., Fergus, R., Vishwanathan, S., Garnett, R. (eds.) Advances in Neural Information Processing Systems, vol. 30, pp. 5998\u20136008. Curran Associates, Inc. (2017). http:\/\/papers.nips.cc\/paper\/7181-attention-is-all-you-need.pdf"},{"key":"1_CR57","doi-asserted-by":"publisher","unstructured":"Watanabe, S., et al.: ESPnet: end-to-end speech processing toolkit. In: Proceedings Interspeech, pp. 2207\u20132211 (2018). https:\/\/doi.org\/10.21437\/Interspeech.2018-1456","DOI":"10.21437\/Interspeech.2018-1456"},{"key":"1_CR58","doi-asserted-by":"crossref","unstructured":"\u017belasko, P., Moro-Vel\u00e1zquez, L., Hasegawa-Johnson, M., Scharenborg, O., Dehak, N.: That sounds familiar: an analysis of phonetic representations transfer across languages. In: Proceedings Interspeech (2020)","DOI":"10.21437\/Interspeech.2020-2513"}],"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_1","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,8,14]],"date-time":"2024-08-14T20:53:22Z","timestamp":1723668802000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-030-59430-5_1"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020]]},"ISBN":["9783030594299","9783030594305"],"references-count":58,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-59430-5_1","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)"}}]}}