{ "labelLang" : "hun", "responseDate" : "2024-03-28 11:27", "content" : { "otype" : "JournalArticle", "mtid" : 31992793, "status" : "APPROVED", "published" : true, "unhandledTickets" : 0, "deleted" : false, "lastRefresh" : "2023-11-22T18:47:53.923+0000", "lastModified" : "2023-08-25T22:39:56.929+0000", "created" : "2021-04-29T13:37:23.415+0000", "creator" : { "otype" : "Author", "mtid" : 10042056, "link" : "/api/author/10042056", "label" : "Tarján Balázs (Beszédfelismerés Statisztikai nyelvi modellezés)", "familyName" : "Tarján", "givenName" : "Balázs", "published" : true, "oldId" : 10042056, "snippet" : true }, "lastDuplumOK" : "2021-04-29T13:37:24.823+0000", "lastDuplumSearch" : "2021-04-29T13:37:24.823+0000", "core" : false, "citation" : true, "publicationPending" : false, "type" : { "otype" : "PublicationType", "mtid" : 24, "link" : "/api/publicationtype/24", "label" : "Folyóiratcikk", "code" : 24, "otypeName" : "JournalArticle", "listPosition" : 1, "published" : true, "oldId" : 24, "snippet" : true }, "subType" : { "otype" : "SubType", "mtid" : 10000059, "link" : "/api/subtype/10000059", "label" : "Szakcikk (Folyóiratcikk)", "name" : "Szakcikk", "nameEng" : "Article", "docType" : { "otype" : "PublicationType", "mtid" : 24, "link" : "/api/publicationtype/24", "label" : "Folyóiratcikk", "code" : 24, "otypeName" : "JournalArticle", "listPosition" : 1, "published" : true, "oldId" : 24, "snippet" : true }, "listPosition" : 101, "published" : true, "oldId" : 10000059, "snippet" : true }, "category" : { "otype" : "Category", "mtid" : 1, "link" : "/api/category/1", "label" : "Tudományos", "published" : true, "oldId" : 1, "snippet" : true }, "languages" : [ { "otype" : "Language", "mtid" : 10002, "link" : "/api/language/10002", "label" : "Angol", "name" : "Angol", "nameEng" : "English", "published" : true, "oldId" : 2, "snippet" : true } ], "firstAuthor" : "Smit, Peter", "authorships" : [ { "otype" : "PersonAuthorship", "mtid" : 96144987, "link" : "/api/authorship/96144987", "label" : "Smit, Peter", "listPosition" : 1, "share" : 0.33333334, "first" : true, "last" : false, "corresponding" : false, "familyName" : "Smit", "givenName" : "Peter", "authorTyped" : true, "editorTyped" : false, "otherTyped" : false, "type" : { "otype" : "AuthorshipType", "mtid" : 1, "link" : "/api/authorshiptype/1", "label" : "Szerző", "code" : 0, "published" : true, "oldId" : 0, "snippet" : true }, "published" : false, "snippet" : true }, { "otype" : "PersonAuthorship", "mtid" : 96144988, "link" : "/api/authorship/96144988", "label" : "Virpioja, Sami", "listPosition" : 2, "share" : 0.33333334, "first" : false, "last" : false, "corresponding" : false, "familyName" : "Virpioja", "givenName" : "Sami", "authorTyped" : true, "editorTyped" : false, "otherTyped" : false, "type" : { "otype" : "AuthorshipType", "mtid" : 1, "link" : "/api/authorshiptype/1", "label" : "Szerző", "code" : 0, "published" : true, "oldId" : 0, "snippet" : true }, "published" : false, "snippet" : true }, { "otype" : "PersonAuthorship", "mtid" : 96144989, "link" : "/api/authorship/96144989", "label" : "Kurimo, Mikko", "listPosition" : 3, "share" : 0.33333334, "first" : false, "last" : true, "corresponding" : false, "familyName" : "Kurimo", "givenName" : "Mikko", "authorTyped" : true, "editorTyped" : false, "otherTyped" : false, "type" : { "otype" : "AuthorshipType", "mtid" : 1, "link" : "/api/authorshiptype/1", "label" : "Szerző", "code" : 0, "published" : true, "oldId" : 0, "snippet" : true }, "published" : false, "snippet" : true } ], "title" : "Advances in subword-based HMM-DNN speech recognition across languages", "identifiers" : [ { "otype" : "PublicationIdentifier", "mtid" : 18728567, "link" : "/api/publicationidentifier/18728567", "label" : "DOI: 10.1016/j.csl.2020.101158", "source" : { "otype" : "PlainSource", "mtid" : 6, "link" : "/api/publicationsource/6", "label" : "DOI", "type" : { "otype" : "PublicationSourceType", "mtid" : 10001, "link" : "/api/publicationsourcetype/10001", "label" : "DOI", "mayHaveOa" : true, "published" : true, "snippet" : true }, "name" : "DOI", "nameEng" : "DOI", "linkPattern" : "https://doi.org/@@@", "publiclyVisible" : true, "published" : true, "oldId" : 6, "snippet" : true }, "idValue" : "10.1016/j.csl.2020.101158", "realUrl" : "https://doi.org/10.1016/j.csl.2020.101158", "published" : false, "snippet" : true }, { "otype" : "PublicationIdentifier", "mtid" : 18728569, "link" : "/api/publicationidentifier/18728569", "label" : "WoS: 000596372000009", "source" : { "otype" : "PlainSource", "mtid" : 1, "link" : "/api/publicationsource/1", "label" : "WoS", "type" : { "otype" : "PublicationSourceType", "mtid" : 10003, "link" : "/api/publicationsourcetype/10003", "label" : "Indexelő adatbázis", "mayHaveOa" : false, "published" : true, "snippet" : true }, "name" : "WoS", "nameEng" : "WoS", "linkPattern" : "https://www.webofscience.com/wos/woscc/full-record/@@@", "publiclyVisible" : true, "published" : true, "oldId" : 1, "snippet" : true }, "idValue" : "000596372000009", "realUrl" : "https://www.webofscience.com/wos/woscc/full-record/000596372000009", "published" : false, "snippet" : true }, { "otype" : "PublicationIdentifier", "mtid" : 18728570, "link" : "/api/publicationidentifier/18728570", "label" : "Scopus: 85092219457", "source" : { "otype" : "PlainSource", "mtid" : 3, "link" : "/api/publicationsource/3", "label" : "Scopus", "type" : { "otype" : "PublicationSourceType", "mtid" : 10003, "link" : "/api/publicationsourcetype/10003", "label" : "Indexelő adatbázis", "mayHaveOa" : false, "published" : true, "snippet" : true }, "name" : "Scopus", "linkPattern" : "http://www.scopus.com/record/display.url?origin=inward&eid=2-s2.0-@@@", "publiclyVisible" : true, "published" : true, "oldId" : 3, "snippet" : true }, "idValue" : "85092219457", "realUrl" : "http://www.scopus.com/record/display.url?origin=inward&eid=2-s2.0-85092219457", "published" : false, "snippet" : true }, { "otype" : "PublicationIdentifier", "mtid" : 18728568, "link" : "/api/publicationidentifier/18728568", "label" : "Egyéb URL: https://linkinghub.elsevier.com/retrieve/pii/S0885230820300917", "source" : { "otype" : "PlainSource", "mtid" : 40, "link" : "/api/publicationsource/40", "label" : "Egyéb URL", "type" : { "otype" : "PublicationSourceType", "mtid" : 10006, "link" : "/api/publicationsourcetype/10006", "label" : "Link", "mayHaveOa" : true, "published" : true, "snippet" : true }, "name" : "Egyéb URL", "nameEng" : "Other URL", "linkPattern" : "@@@", "publiclyVisible" : true, "published" : true, "oldId" : 40, "snippet" : true }, "idValue" : "https://linkinghub.elsevier.com/retrieve/pii/S0885230820300917", "realUrl" : "https://linkinghub.elsevier.com/retrieve/pii/S0885230820300917", "published" : false, "snippet" : true } ], "journal" : { "otype" : "Journal", "mtid" : 16799, "link" : "/api/journal/16799", "label" : "COMPUTER SPEECH AND LANGUAGE 0885-2308 1095-8363", "pIssn" : "0885-2308", "eIssn" : "1095-8363", "reviewType" : "REVIEWED", "noIF" : false, "sciIndexed" : true, "scopusIndexed" : true, "lang" : "FOREIGN", "hungarian" : false, "published" : true, "oldId" : 16799, "snippet" : true }, "volume" : "66", "internalId" : "101158", "firstPageOrInternalIdForSort" : "101158", "publishedYear" : 2021, "digital" : null, "printed" : true, "sourceYear" : 2021, "foreignEdition" : true, "foreignLanguage" : true, "fullPublication" : true, "conferencePublication" : false, "nationalOrigin" : null, "missingAuthor" : false, "oaType" : "NONE", "oaCheckDate" : "2023-11-22", "oaFree" : false, "citationCount" : 0, "citationCountUnpublished" : 0, "citationCountWoOther" : 0, "independentCitCountWoOther" : 0, "doiCitationCount" : 0, "wosCitationCount" : 0, "scopusCitationCount" : 0, "independentCitationCount" : 0, "unhandledCitationCount" : 0, "citingPubCount" : 0, "independentCitingPubCount" : 0, "unhandledCitingPubCount" : 0, "citedPubCount" : 1, "citedCount" : 1, "ratings" : [ { "otype" : "MtaRating", "mtid" : 510904, "link" : "/api/mtarating/510904", "label" : "I. Nyelvtudományi Bizottság:INT2 COMPUTER SPEECH AND LANGUAGE 0885-2308 1095-8363", "ratingType" : { "otype" : "RatingType", "mtid" : 10005, "link" : "/api/ratingtype/10005", "label" : "I. Nyelvtudományi Bizottság", "code" : "Nyelvtud Biz", "institute" : { "otype" : "Institute", "mtid" : 14076, "link" : "/api/institute/14076", "label" : "Nyelvtudományi Bizottság I.NYIO [1900-]", "childrenCount" : 0, "allowInstForum" : false, "allowOnlineRegistration" : true, "name" : "Nyelvtudományi Bizottság", "nameEng" : "Nyelvtudományi Bizottság", "published" : true, "oldId" : 14076, "snippet" : true }, "published" : true, "snippet" : true }, "val" : "INT2", "published" : true, "oldId" : 10904, "snippet" : true }, { "otype" : "SjrRating", "mtid" : 11206211, "link" : "/api/sjrrating/11206211", "label" : "sjr:Q2 (2021) Scopus - Human-Computer Interaction COMPUTER SPEECH AND LANGUAGE 0885-2308 1095-8363", "listPos" : 46, "rankValue" : 0.49, "type" : "journal", "ratingType" : { "otype" : "RatingType", "mtid" : 10002, "link" : "/api/ratingtype/10002", "label" : "sjr", "code" : "sjr", "published" : true, "snippet" : true }, "subject" : { "otype" : "ClassificationExternal", "mtid" : 1709, "link" : "/api/classificationexternal/1709", "label" : "Scopus - Human-Computer Interaction", "published" : true, "oldId" : 1709, "snippet" : true }, "ranking" : "Q2", "calculation" : "DIRECT", "published" : true, "snippet" : true } ], "ratingsForSort" : "Q2", "mtaRatingsForSort" : "INT2", "references" : [ { "otype" : "Reference", "mtid" : 20146640, "link" : "/api/reference/20146640", "label" : "1. Ali 2016: The MGB-2 challenge: Arabic multi-dialect broadcast media recognition, p. 279", "listPosition" : 1, "published" : false, "snippet" : true }, { "otype" : "Reference", "mtid" : 20146641, "link" : "/api/reference/20146641", "label" : "2. Ali 2014: Advances in dialectal Arabic speech recognition: a study using twitter to improve Egyptian ASR", "listPosition" : 2, "published" : false, "snippet" : true }, { "otype" : "Reference", "mtid" : 20146642, "link" : "/api/reference/20146642", "label" : "3. Ali 2017: p. 316", "listPosition" : 3, "published" : false, "snippet" : true }, { "otype" : "Reference", "mtid" : 20146643, "link" : "/api/reference/20146643", "label" : "4. Arisoy 2009: Turkish broadcast news transcription and retrieval, IEEE Trans Audio Speech Lang Process, 17, p. 874, DOI: 10.1109/TASL.2008.2012313", "listPosition" : 4, "doi" : "10.1109/TASL.2008.2012313", "published" : false, "snippet" : true }, { "otype" : "Reference", "mtid" : 20146644, "link" : "/api/reference/20146644", "label" : "5. Bisani 2005: Open vocabulary speech recognition with flat hybrid models, p. 725", "listPosition" : 5, "published" : false, "snippet" : true }, { "otype" : "Reference", "mtid" : 20146645, "link" : "/api/reference/20146645", "label" : "6. Botros 2015: On efficient training of word classes and their application to recurrent neural network language models, p. 1443", "listPosition" : 6, "published" : false, "snippet" : true }, { "otype" : "Reference", "mtid" : 20146646, "link" : "/api/reference/20146646", "label" : "7. Chan 2016: Listen, attend and spell: A neural network for large vocabulary conversational speech recognition, p. 4960", "listPosition" : 7, "published" : false, "snippet" : true }, { "otype" : "Reference", "mtid" : 20146647, "link" : "/api/reference/20146647", "label" : "8. Cheng 2017: p. 1586", "listPosition" : 8, "published" : false, "snippet" : true }, { "otype" : "Reference", "mtid" : 20146648, "link" : "/api/reference/20146648", "label" : "9. Choueiter 2006: Morpheme-based language modeling for Arabic LVCSR, p. 1053", "listPosition" : 9, "published" : false, "snippet" : true }, { "otype" : "Reference", "mtid" : 20146649, "link" : "/api/reference/20146649", "label" : "10. Creutz 2007: Morph-based speech recognition and modeling of out-of-vocabulary words across languages, ACM Trans. Speech Lang. Process., 5, p. 3:1, DOI: 10.1145/1322391.1322394", "listPosition" : 10, "doi" : "10.1145/1322391.1322394", "published" : false, "snippet" : true }, { "otype" : "Reference", "mtid" : 20146650, "link" : "/api/reference/20146650", "label" : "11. Creutz 2002: Unsupervised discovery of morphemes, p. 21", "listPosition" : 11, "published" : false, "snippet" : true }, { "otype" : "Reference", "mtid" : 20146651, "link" : "/api/reference/20146651", "label" : "12. Creutz 2007: Unsupervised models for morpheme segmentation and morphology learning, ACM Trans. Speech Lang. Process., 4, DOI: 10.1145/1187415.1187418", "listPosition" : 12, "doi" : "10.1145/1187415.1187418", "published" : false, "snippet" : true }, { "otype" : "Reference", "mtid" : 20146652, "link" : "/api/reference/20146652", "label" : "13. CSC - IT Center for Science, 1998. The Helsinki Korp Version of the Finnish Text Collection. URL: http://urn.fi/urn:nbn:fi:lb-2016050207", "listPosition" : 13, "published" : false, "snippet" : true }, { "otype" : "Reference", "mtid" : 20146653, "link" : "/api/reference/20146653", "label" : "14. Enarvi 2016: TheanoLM – an extensible toolkit for neural network language modeling, p. 3052, DOI: 10.21437/Interspeech.2016-618", "listPosition" : 14, "doi" : "10.21437/Interspeech.2016-618", "published" : false, "snippet" : true }, { "otype" : "Reference", "mtid" : 20146654, "link" : "/api/reference/20146654", "label" : "15. Enarvi 2017: Automatic speech recognition with very large conversational Finnish and Estonian vocabularies, IEEE/ACM Trans Audio Speech Lang Process, 25, p. 2085, DOI: 10.1109/TASLP.2017.2743344", "listPosition" : 15, "doi" : "10.1109/TASLP.2017.2743344", "published" : false, "snippet" : true }, { "otype" : "Reference", "mtid" : 20146655, "link" : "/api/reference/20146655", "label" : "16. Gage 1994: A new algorithm for data compression, The C Users Journal, 12, p. 23", "listPosition" : 16, "published" : false, "snippet" : true }, { "otype" : "Reference", "mtid" : 20146656, "link" : "/api/reference/20146656", "label" : "17. Goel 2000: Minimum Bayes-risk automatic speech recognition, Computer Speech & Language, 14, p. 115, DOI: 10.1006/csla.2000.0138", "listPosition" : 17, "doi" : "10.1006/csla.2000.0138", "published" : false, "snippet" : true }, { "otype" : "Reference", "mtid" : 20146657, "link" : "/api/reference/20146657", "label" : "18. Graves 2014: Towards end-to-end speech recognition with recurrent neural networks, p. 1764", "listPosition" : 18, "published" : false, "snippet" : true }, { "otype" : "Reference", "mtid" : 20146658, "link" : "/api/reference/20146658", "label" : "19. Hirsimäki 2006: Unlimited vocabulary speech recognition with morph language models applied to Finnish, Computer Speech & Language, 20, p. 515, DOI: 10.1016/j.csl.2005.07.002", "listPosition" : 19, "doi" : "10.1016/j.csl.2005.07.002", "published" : false, "snippet" : true }, { "otype" : "Reference", "mtid" : 20146659, "link" : "/api/reference/20146659", "label" : "20. Hirsimäki 2009: Importance of high-order n-gram models in morph-based speech recognition, IEEE Trans Audio Speech Lang Process, 17, p. 724, DOI: 10.1109/TASL.2008.2012323", "listPosition" : 20, "doi" : "10.1109/TASL.2008.2012323", "published" : false, "snippet" : true }, { "otype" : "Reference", "mtid" : 20146660, "link" : "/api/reference/20146660", "label" : "21. Hochreiter 1997: Long short-term memory, Neural Comput, 9, p. 1735, DOI: 10.1162/neco.1997.9.8.1735", "listPosition" : 21, "doi" : "10.1162/neco.1997.9.8.1735", "published" : false, "snippet" : true }, { "otype" : "Reference", "mtid" : 20146661, "link" : "/api/reference/20146661", "label" : "22. Iskra 2002: SPEECON-Speech databases for consumer devices: Database specification and validation", "listPosition" : 22, "published" : false, "snippet" : true }, { "otype" : "Reference", "mtid" : 20146662, "link" : "/api/reference/20146662", "label" : "23. Kirchhoff 2006: Morphology-based language modeling for conversational Arabic speech recognition, Computer Speech & Language, 20, p. 589, DOI: 10.1016/j.csl.2005.10.001", "listPosition" : 23, "doi" : "10.1016/j.csl.2005.10.001", "published" : false, "snippet" : true }, { "otype" : "Reference", "mtid" : 20146663, "link" : "/api/reference/20146663", "label" : "24. Kneser 1993: Forming word classes by statistical clustering for statistical language modelling, p. 221", "listPosition" : 24, "published" : false, "snippet" : true }, { "otype" : "Reference", "mtid" : 20146664, "link" : "/api/reference/20146664", "label" : "25. Kuo 2012: Large scale hierarchical neural network language models, p. 1672", "listPosition" : 25, "published" : false, "snippet" : true }, { "otype" : "Reference", "mtid" : 20146665, "link" : "/api/reference/20146665", "label" : "26. Kurimo 2017: Modeling under-resourced languages for speech recognition, Lang Resour Eval, 51, p. 961, DOI: 10.1007/s10579-016-9336-9", "listPosition" : 26, "doi" : "10.1007/s10579-016-9336-9", "published" : false, "snippet" : true }, { "otype" : "Reference", "mtid" : 20146666, "link" : "/api/reference/20146666", "label" : "27. Manohar 2017: Jhu kaldi system for Arabic mgb-3 asr challenge using diarization, audio-transcript alignment and transfer learning, p. 346", "listPosition" : 27, "published" : false, "snippet" : true }, { "otype" : "Reference", "mtid" : 20146667, "link" : "/api/reference/20146667", "label" : "28. Mansikkaniemi 2017: p. 3762", "listPosition" : 28, "published" : false, "snippet" : true }, { "otype" : "Reference", "mtid" : 20146668, "link" : "/api/reference/20146668", "label" : "29. Mikolov 2010: Recurrent neural network based language model, p. 1045", "listPosition" : 29, "published" : false, "snippet" : true }, { "otype" : "Reference", "mtid" : 20146669, "link" : "/api/reference/20146669", "label" : "30. Mirjam 2003: Grapheme based speech recognition", "listPosition" : 30, "published" : false, "snippet" : true }, { "otype" : "Reference", "mtid" : 20146670, "link" : "/api/reference/20146670", "label" : "31. Mohri 2008: Speech recognition with weighted finite-state transducers, p. 559", "listPosition" : 31, "published" : false, "snippet" : true }, { "otype" : "Reference", "mtid" : 20146671, "link" : "/api/reference/20146671", "label" : "32. Morin 2005: Hierarchical probabilistic neural network language model, 5, p. 246", "listPosition" : 32, "published" : false, "snippet" : true }, { "otype" : "Reference", "mtid" : 20146672, "link" : "/api/reference/20146672", "label" : "33. Mousa 2013: Morpheme-based feature-rich language models using deep neural networks for LVCSR of Egyptian Arabic, p. 8435", "listPosition" : 33, "published" : false, "snippet" : true }, { "otype" : "Reference", "mtid" : 20146673, "link" : "/api/reference/20146673", "label" : "34. Peddinti 2015: A time delay neural network architecture for efficient modeling of long temporal contexts, p. 3214", "listPosition" : 34, "published" : false, "snippet" : true }, { "otype" : "Reference", "mtid" : 20146674, "link" : "/api/reference/20146674", "label" : "35. Povey 2011: The Kaldi speech recognition toolkit", "listPosition" : 35, "published" : false, "snippet" : true }, { "otype" : "Reference", "mtid" : 20146675, "link" : "/api/reference/20146675", "label" : "36. Povey 2016: Purely sequence-trained neural networks for ASR based on lattice-free MMI, p. 2751, DOI: 10.21437/Interspeech.2016-595", "listPosition" : 36, "doi" : "10.21437/Interspeech.2016-595", "published" : false, "snippet" : true }, { "otype" : "Reference", "mtid" : 20146676, "link" : "/api/reference/20146676", "label" : "37. Prabhavalkar 2017: A comparison of sequence-to-sequence models for speech recognition, p. 939", "listPosition" : 37, "published" : false, "snippet" : true }, { "otype" : "Reference", "mtid" : 20146677, "link" : "/api/reference/20146677", "label" : "38. Rao 2017: Multi-accent speech recognition with hierarchical grapheme based models, p. 4815", "listPosition" : 38, "published" : false, "snippet" : true }, { "otype" : "Reference", "mtid" : 20146678, "link" : "/api/reference/20146678", "label" : "39. Rissanen 1978: Modeling by shortest data description, Automatica, 14, p. 465, DOI: 10.1016/0005-1098(78)90005-5", "listPosition" : 39, "doi" : "10.1016/0005-1098(78)90005-5", "published" : false, "snippet" : true }, { "otype" : "Reference", "mtid" : 20146679, "link" : "/api/reference/20146679", "label" : "40. Rosti 1998: SpeechDat Finnish Database for the fixed telephone network", "listPosition" : 40, "published" : false, "snippet" : true }, { "otype" : "Reference", "mtid" : 20146680, "link" : "/api/reference/20146680", "label" : "41. Sainath 2018: No need for a lexicon? Evaluating the value of the pronunciation lexica in end-to-end models, p. 5859", "listPosition" : 41, "published" : false, "snippet" : true }, { "otype" : "Reference", "mtid" : 20146681, "link" : "/api/reference/20146681", "label" : "42. Sennrich 2015: Neural machine translation of rare words with subword units", "listPosition" : 42, "published" : false, "snippet" : true }, { "otype" : "Reference", "mtid" : 20146682, "link" : "/api/reference/20146682", "label" : "43. Siivola 2007: On growing and pruning Kneser-Ney smoothed N-gram models, IEEE Transactions on Audio, Speech & Language Processing, 15, p. 1617, DOI: 10.1109/TASL.2007.896666", "listPosition" : 43, "doi" : "10.1109/TASL.2007.896666", "published" : false, "snippet" : true }, { "otype" : "Reference", "mtid" : 20146683, "link" : "/api/reference/20146683", "label" : "44. Smit 2017: Aalto system for the 2017 Arabic multi-genre broadcast challenge", "listPosition" : 44, "published" : false, "snippet" : true }, { "otype" : "Reference", "mtid" : 20146684, "link" : "/api/reference/20146684", "label" : "45. Smit 2017: Character-based units for unlimited vocabulary continuous speech recognition", "listPosition" : 45, "published" : false, "snippet" : true }, { "otype" : "Reference", "mtid" : 20146685, "link" : "/api/reference/20146685", "label" : "46. Smit 2016: Automatic speech recognition for northern sámi with comparison to other uralic languages, p. 12", "listPosition" : 46, "published" : false, "snippet" : true }, { "otype" : "Reference", "mtid" : 20146686, "link" : "/api/reference/20146686", "label" : "47. Smit 2017: Improved subword modeling for WFST-based speech recognition", "listPosition" : 47, "published" : false, "snippet" : true }, { "otype" : "Reference", "mtid" : 20146687, "link" : "/api/reference/20146687", "label" : "48. Srivastava 2014: Dropout: a simple way to prevent neural networks from overfitting, The Journal of Machine Learning Research, 15, p. 1929", "listPosition" : 48, "published" : false, "snippet" : true }, { "otype" : "Reference", "mtid" : 20146688, "link" : "/api/reference/20146688", "label" : "49. Srivastava 2015: Training very deep networks, p. 2377", "listPosition" : 49, "published" : false, "snippet" : true }, { "otype" : "Reference", "mtid" : 20146689, "link" : "/api/reference/20146689", "label" : "50. Tarján 2014: A bilingual study on the prediction of morph-based improvement, p. 131", "listPosition" : 50, "published" : false, "snippet" : true }, { "otype" : "Reference", "mtid" : 20146690, "link" : "/api/reference/20146690", "label" : "51. Varjokallio 2013: Learning a Subword Vocabulary Based on Unigram Likelihood, p. 7", "listPosition" : 51, "published" : false, "snippet" : true }, { "otype" : "Reference", "mtid" : 20146691, "link" : "/api/reference/20146691", "label" : "52. Virpioja 2011: Evaluating the Effect of Word Frequencies in a Probabilistic Generative Model of Morphology, 11, p. 230", "listPosition" : 52, "published" : false, "snippet" : true }, { "otype" : "Reference", "mtid" : 20146692, "link" : "/api/reference/20146692", "label" : "53. Virpioja 2013: Morfessor 2.0: Python Implementation and Extensions for Morfessor Baseline", "listPosition" : 53, "published" : false, "snippet" : true }, { "otype" : "Reference", "mtid" : 20146693, "link" : "/api/reference/20146693", "label" : "54. Wang 2018: Phonetic and graphemic systems for multi-genre broadcast transcription", "listPosition" : 54, "published" : false, "snippet" : true }, { "otype" : "Reference", "mtid" : 20146694, "link" : "/api/reference/20146694", "label" : "55. Wong 2017: Multi-task ensembles with teacher-student training, p. 84", "listPosition" : 55, "published" : false, "snippet" : true }, { "otype" : "Reference", "mtid" : 20146695, "link" : "/api/reference/20146695", "label" : "56. Xu 2010: An improved consensus-like method for minimum Bayes risk decoding and lattice combination, p. 4938", "listPosition" : 56, "published" : false, "snippet" : true } ], "hasCitationDuplums" : false, "userChangeableUntil" : "2021-07-28T13:37:24.555+0000", "directInstitutesForSort" : "", "ownerAuthorCount" : 3, "ownerInstituteCount" : 6, "directInstituteCount" : 0, "authorCount" : 3, "contributorCount" : 0, "hasQualityFactor" : true, "link" : "/api/publication/31992793", "label" : "Smit Peter et al. Advances in subword-based HMM-DNN speech recognition across languages. (2021) COMPUTER SPEECH AND LANGUAGE 0885-2308 1095-8363 66", "template" : "