{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,30]],"date-time":"2025-10-30T01:59:07Z","timestamp":1761789547275,"version":"3.37.3"},"reference-count":8,"publisher":"Wiley","license":[{"start":{"date-parts":[[2019,3,3]],"date-time":"2019-03-03T00:00:00Z","timestamp":1551571200000},"content-version":"unspecified","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100004564","name":"Ministarstvo Prosvete, Nauke i Tehnolo\u0161kog Razvoja","doi-asserted-by":"publisher","award":["TR32035","114-451-2570\/2016-02"],"award-info":[{"award-number":["TR32035","114-451-2570\/2016-02"]}],"id":[{"id":"10.13039\/501100004564","id-type":"DOI","asserted-by":"publisher"}]},{"name":"EUREKA project DANSPLAT","award":["TR32035","114-451-2570\/2016-02"],"award-info":[{"award-number":["TR32035","114-451-2570\/2016-02"]}]},{"name":"Provincial Secretariat for Higher Education and Scientific Research","award":["TR32035","114-451-2570\/2016-02"],"award-info":[{"award-number":["TR32035","114-451-2570\/2016-02"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Computational Intelligence and Neuroscience"],"published-print":{"date-parts":[[2019,3,3]]},"abstract":"<jats:p>Serbian is in a group of highly inflective and morphologically rich languages that use a lot of different word suffixes to express different grammatical, syntactic, or semantic features. This kind of behaviour usually produces a lot of recognition errors, especially in large vocabulary systems\u2014even when, due to good acoustical matching, the correct lemma is predicted by the automatic speech recognition system, often a wrong word ending occurs, which is nevertheless counted as an error. This effect is larger for contexts not present in the language model training corpus. In this manuscript, an approach which takes into account different morphological categories of words for language modeling is examined, and the benefits in terms of word error rates and perplexities are presented. These categories include word type, word case, grammatical number, and gender, and they were all assigned to words in the system vocabulary, where applicable. These additional word features helped to produce significant improvements in relation to the baseline system, both for n-gram-based and neural network-based language models. The proposed system can help overcome a lot of tedious errors in a large vocabulary system, for example, for dictation, both for Serbian and for other languages with similar characteristics.<\/jats:p>","DOI":"10.1155\/2019\/5072918","type":"journal-article","created":{"date-parts":[[2019,3,3]],"date-time":"2019-03-03T18:34:03Z","timestamp":1551638043000},"page":"1-8","source":"Crossref","is-referenced-by-count":10,"title":["Using Morphological Data in Language Modeling for Serbian Large Vocabulary Speech Recognition"],"prefix":"10.1155","volume":"2019","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-5207-6638","authenticated-orcid":true,"given":"Edvin","family":"Pakoci","sequence":"first","affiliation":[{"name":"Department for Power, Electronic and Telecommunication Engineering, Faculty of Technical Sciences, University of Novi Sad, 21000 Novi Sad, Serbia"},{"name":"AlfaNum Speech Technologies, 21000 Novi Sad, Serbia"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5413-1028","authenticated-orcid":true,"given":"Branislav","family":"Popovi\u0107","sequence":"additional","affiliation":[{"name":"Department for Power, Electronic and Telecommunication Engineering, Faculty of Technical Sciences, University of Novi Sad, 21000 Novi Sad, Serbia"},{"name":"Department for Music Production and Sound Design, Academy of Arts, Alfa BK University, 11000 Belgrade, Serbia"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Darko","family":"Pekar","sequence":"additional","affiliation":[{"name":"Department for Power, Electronic and Telecommunication Engineering, Faculty of Technical Sciences, University of Novi Sad, 21000 Novi Sad, Serbia"},{"name":"AlfaNum Speech Technologies, 21000 Novi Sad, Serbia"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"311","reference":[{"volume-title":"A bit of progress in language modeling: extended version","year":"2001","key":"1"},{"key":"2","doi-asserted-by":"publisher","DOI":"10.1109\/5.880083"},{"key":"8","doi-asserted-by":"publisher","DOI":"10.1109\/tasl.2008.924591"},{"key":"10","doi-asserted-by":"publisher","DOI":"10.1016\/s0167-6393(02)00031-6"},{"key":"14","doi-asserted-by":"publisher","DOI":"10.5937\/telfor1402109s"},{"key":"17","doi-asserted-by":"publisher","DOI":"10.15622\/sp.58.3"},{"journal-title":"Acta Polytechnica Hungarica: Journal of Applied Sciences","year":"2019","key":"27"},{"key":"28","doi-asserted-by":"publisher","DOI":"10.1016\/s0167-6393(01)00041-3"}],"container-title":["Computational Intelligence and Neuroscience"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/downloads.hindawi.com\/journals\/cin\/2019\/5072918.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/downloads.hindawi.com\/journals\/cin\/2019\/5072918.xml","content-type":"application\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/downloads.hindawi.com\/journals\/cin\/2019\/5072918.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2019,3,3]],"date-time":"2019-03-03T18:34:06Z","timestamp":1551638046000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.hindawi.com\/journals\/cin\/2019\/5072918\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019,3,3]]},"references-count":8,"alternative-id":["5072918","5072918"],"URL":"https:\/\/doi.org\/10.1155\/2019\/5072918","relation":{},"ISSN":["1687-5265","1687-5273"],"issn-type":[{"type":"print","value":"1687-5265"},{"type":"electronic","value":"1687-5273"}],"subject":[],"published":{"date-parts":[[2019,3,3]]}}}