{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,7,6]],"date-time":"2025-07-06T15:40:07Z","timestamp":1751816407381,"version":"3.41.0"},"publisher-location":"Cham","reference-count":40,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783319959955"},{"type":"electronic","value":"9783319959962"}],"license":[{"start":{"date-parts":[[2018,8,26]],"date-time":"2018-08-26T00:00:00Z","timestamp":1535241600000},"content-version":"unspecified","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\/978-3-319-95996-2_8","type":"book-chapter","created":{"date-parts":[[2018,8,25]],"date-time":"2018-08-25T04:14:29Z","timestamp":1535170469000},"page":"153-176","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Modeling of Filled Pauses and Prolongations to Improve Slovak Spontaneous Speech Recognition"],"prefix":"10.1007","author":[{"given":"J\u00e1n","family":"Sta\u0161","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Daniel","family":"Hl\u00e1dek","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jozef","family":"Juh\u00e1r","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2018,8,26]]},"reference":[{"key":"8_CR1","unstructured":"Adell J, Bonafonte A, Escudero D (2010) Modelling filled pauses prosody to synthese disfluent speech. In: Proceedings of speech prosody, Chicago, IL, paper 624"},{"issue":"1","key":"8_CR2","first-page":"67","volume":"9","author":"P Baranyi","year":"2012","unstructured":"Baranyi P, Csap\u00f3 A (2012) Definition and synergies of cognitive infocommunications. Acta Polytech Hung 9(1):67\u201383","journal-title":"Acta Polytech Hung"},{"key":"8_CR3","doi-asserted-by":"crossref","unstructured":"Baranyi P, Csap\u00f3 A, Sallai GY (2015) Cognitive infocommunications. Springer International Publishing Switzerland","DOI":"10.1007\/978-3-319-19608-4"},{"issue":"1\u20132","key":"8_CR4","doi-asserted-by":"publisher","first-page":"5","DOI":"10.1016\/S0167-6393(00)00067-4","volume":"33","author":"C Barras","year":"2001","unstructured":"Barras C, Geoffrois E, Wu Z, Liberman M (2001) Transcriber: development and use of a tool for assisting speech corpora production. Speech Commun 33(1\u20132):5\u201322","journal-title":"Speech Commun"},{"key":"8_CR5","unstructured":"Be\u0148u\u0161 \u0160, Enos F, Hirschberg J, Shriberg E (2006) Pauses in deceptive speech. In Proceedings of speech prosody, Dresden, Germany, paper 212"},{"key":"8_CR6","unstructured":"Deme A, Mark\u00f3 A (2012) Lengthenings and filled pauses in the spontaneous speech of Hungarian adults and children. In Proceedings of workshop of fluent speech: combining cognitive and educational approaches, Ultrecht, Netherlands"},{"key":"8_CR7","unstructured":"Duchatea J, Laureys T, Wambacq P (2004) Adding robustness to language models for spontaneous speech recognition. In Proceedings of COST278 and ISCA tutorial and research workshop on robustness issues in conversational interaction, Norwich, UK, paper 11"},{"key":"8_CR8","doi-asserted-by":"crossref","unstructured":"Gavuvain JL, Adda G, Lamel L, Adda-Decker M (1997) Transcribing broadcast news: the LIMSI Nov96 Hub4 System. In Proceedings of 1997 darpa speech recognition workshop, Chantilly, Virginia","DOI":"10.21437\/Eurospeech.1997-323"},{"key":"8_CR9","doi-asserted-by":"crossref","unstructured":"Hl\u00e1dek, D, Ond\u00e1\u0161, S, Sta\u0161, J (2014) Online natural language processing of the Slovak language. In Proceedings of 5$$^{th}$$ IEEE international conference on cognitive InfoCommunications, CogInfoCom 2014, Vietri sul Mare, Italy, pp 315\u2013316","DOI":"10.1109\/CogInfoCom.2014.7020469"},{"issue":"1","key":"8_CR10","first-page":"11","volume":"10","author":"I Kipyatkova","year":"2013","unstructured":"Kipyatkova I, Karpov A, Verkhodanova V, \u017delezm\u00fd M (2013) Modeling of pronunciation, language and nonverbal units at conversational Russian speech recognition. Int J Comput Sci Appl 10(1):11\u201330","journal-title":"Int J Comput Sci Appl"},{"key":"8_CR11","unstructured":"Lee A, Kawahara T (2009) Recent development of open-source speech recognition engine Julius. In: Proceedings of 2009 Asia-Pacific signal and information processing association: annual summit and conference, APSIPA ASC 2009, Sapporo, Japan, pp 131\u2013137"},{"key":"8_CR12","doi-asserted-by":"crossref","unstructured":"Liu Y, Shriberg E, Stolcke A (2003) Automatic disfluency identification in conversational speech using multiple knowledge sources. In: Proceedings of EUROSPEECH, Geneva, Switzerland, pp 957\u2013960","DOI":"10.21437\/Eurospeech.2003-332"},{"key":"8_CR13","doi-asserted-by":"crossref","unstructured":"Moniz H, Mata AI, Viana MC (2007) On filled pauses and prolongations in European Portuguese. In: Proceedings of INTERSPEECH Antwerp, Belgium, pp 2645\u20132648","DOI":"10.21437\/Interspeech.2007-695"},{"key":"8_CR14","doi-asserted-by":"crossref","unstructured":"Moniz H, Trancoso I, Mata AI (2009) Classification of disfluent phenomena as fluent communicative devices in specific prosodic contexts. In: Proceedings of INTERSPEECH Brighton, UK, pp 1719\u20131722","DOI":"10.21437\/Interspeech.2009-518"},{"key":"8_CR15","unstructured":"Nunes R, Neves L (2008) Filled pauses modeling. L$$^2$$F\u2014Spoken language system laboratory, INESC-ID Lisboa, Technical Report, Lisboa, Portugal, p 9"},{"issue":"8","key":"8_CR16","first-page":"136","volume":"1998\u20134308","author":"K Ohta","year":"2014","unstructured":"Ohta K, Kitaoka N, Nakagawa S (2014) Modeling filled pauses and silences for responses of a spoken dialogue system. Int J Comput 1998\u20134308(8):136\u2013143","journal-title":"Int J Comput"},{"key":"8_CR17","doi-asserted-by":"crossref","unstructured":"Ohtsuki K, Furui S, Sakurai N, Iwasaki A, Zhang Z-P (1999) Recent advances in Japanese broadcast news transcription. In: Proceedings of EUROSPEECH, Budapest, Hungary, pp 671\u2013674","DOI":"10.21437\/Eurospeech.1999-172x"},{"issue":"1","key":"8_CR18","doi-asserted-by":"publisher","first-page":"19","DOI":"10.1006\/csla.1995.0002","volume":"9","author":"S Oviatt","year":"1995","unstructured":"Oviatt S (1995) Predicting spoken disfluencies during human-computer interaction. Comput Speech Lang 9(1):19\u201335","journal-title":"Comput Speech Lang"},{"key":"8_CR19","unstructured":"Pakhomov SA, Savova G (2000) Filled pause distribution and modeling in quasi-spontaneous speech. In: Proceedings of the 14$$^{th}$$ international congress of phonetic sciences, ICSP 1999, San Francisco, CA, pp 31\u201334"},{"key":"8_CR20","doi-asserted-by":"crossref","unstructured":"Peters J (2003) LM studies on filled pauses in spontaneous medical dictation. In: Proceedings of HLT-NAACL 2003, Edmonton, Canada, pp 82\u201384","DOI":"10.3115\/1073483.1073511"},{"key":"8_CR21","unstructured":"Povey D, Ghoshal A, Boulianne G, Burget L, Glembek O, Goel N, Hannemann M, Motlicek P, Qian Y, Schwarz P, Silovsky J, Stemmer G, Vesely K (2011) The Kaldi speech recognition toolkit. In: Proceedings of IEEE 2011 Workshop on Automatic Speech Recognition and Understanding, ASRU 2011, Waikoloa, HI, US, pp 1\u20134"},{"key":"8_CR22","doi-asserted-by":"crossref","unstructured":"Prylipko D, Vasilenko B, Stolcke A, Wendemuth A (2012) Language modeling of nonverbal vocalizations in spontaneous speech. In: Sojka P et al (eds.), Text, Speech and Dialogue, LNAI 7499, Springer International Publishing Switzerland, pp 488\u2013495","DOI":"10.1007\/978-3-642-32790-2_59"},{"key":"8_CR23","unstructured":"Rose RL (2013) Crosslingual corpus of hesitation phenomena: a corpus for investigating forst and second language speech performance. In: Proceedings of Interspeech, Lyon, France, pp 992\u2013996"},{"key":"8_CR24","doi-asserted-by":"crossref","unstructured":"Rusko M, Juh\u00e1r J, Trnka M, Sta\u0161 J, Darjaa S, Hl\u00e1dek D, Sabo R, Pleva M, Ritomsk\u00fd M, Ond\u00e1\u0161 S (2016) Advances in the Slovak judicial domain dictation system. In: Vetulani, Z et al (Eds.), Human Language Technology Challenges for Computer Science and Linguistics, LNAI 9561, Springer International Publishing Switzerland, pp 16\u201327","DOI":"10.1007\/978-3-319-43808-5_5"},{"key":"8_CR25","unstructured":"Siu M-H, Ostendorf M (1996) Modeling disfluencies in conversational speech. In: Proceedings of ICSLP, Philadelphia, PA, pp 386\u2013389"},{"key":"8_CR26","unstructured":"Sabo R (2008) Anotovan\u00e1 re\u010dov\u00e1 datab\u00e1za parlamentn\u00fdch nahr\u00e1vok (Annotated speech database of parliament proceedings. In: Rusko M et al (eds) Akustika a spracovanie re\u010di. Slovakia, Bratislava, pp 131\u2013135 (in Slovak)"},{"key":"8_CR27","unstructured":"Shriberg EE (1994) Preliminaries to a theory of speech disfluencies. Ph.D. thesis, University of California, Berkeley, p 406"},{"key":"8_CR28","unstructured":"Schramm H, Aubert XL, Meyer C, Peters J (2003) Filled-pause modeling for medical transcription. In: Proceedings of IEEE workshop an spontaneous speech processing and recognition, SSPR 2003, Tokyo, Japan, paper TM06"},{"key":"8_CR29","unstructured":"Somiya M, Kobayashi K, Nishiyaki H, Sekiguchi Y (2007) The effect of filled pauses in a lecture speech on impressive evaluation of listeners. In: Proceedings of INTERSPEECH 2007, Antwerp, Belgium, pp 2645\u20132648"},{"issue":"2","key":"8_CR30","first-page":"39","volume":"8","author":"J Sta\u0161","year":"2015","unstructured":"Sta\u0161 J, Juh\u00e1r J (2015) Modeling of Slovak language for broadcast news transcription. J Electric Electron Eng 8(2):39\u201342","journal-title":"J Electric Electron Eng"},{"key":"8_CR31","unstructured":"Sta\u0161 J, Viszlay P, Lojka M, Koct\u00far T, Hl\u00e1dek D, Kiktov\u00e1 E, Pleva M, Juh\u00e1r J (2015) Automatic subtitling system for transcription, archiving and indexing of Slovak audiovisual recordings. In: Proceedings of the 7$$^{th}$$ Language & Technology Conference, LTC 2015, Pozna\u0144, Poland, pp 186\u2013191"},{"key":"8_CR32","doi-asserted-by":"crossref","unstructured":"Sta\u0161 J, Hl\u00e1dek D, Juh\u00e1r J (2016) Adding filled pauses and disfluent events into language models for speech recognition. In Proc. of the 7th IEEE international conference on cognitive InfoCommunications, CogInfoCom 2016, Wroclaw, Poland, pp 133\u2013137","DOI":"10.1109\/CogInfoCom.2016.7804538"},{"key":"8_CR33","unstructured":"Sta\u0161 J, Koct\u00far T, Viszlay P (2016) Automatick\u00e1 anot\u00e1cia a tvorba re\u010dov\u00e9ho korpusu predn\u00e1\u0161ok TEDxSK a JumpSK (Automatic annotation and building of a speech corpus of TEDxSK and JumpSK talks). In: Proceedings of the 11$$^{th}$$ workshop on intelligent and knowledge oriented technologies and 35th conference on data and knowledge, WIKT & DaZ 2016, Smolenice, Slovakia, pp 127\u2013132 (in Slovak)"},{"key":"8_CR34","doi-asserted-by":"crossref","unstructured":"Stolcke A, Shriberg E (1996) Statistical language modeling for speech disfluencies. In: Proceedings of ICASSP, Atlanta, GA pp 405\u2013408","DOI":"10.1109\/ICASSP.1996.541118"},{"key":"8_CR35","doi-asserted-by":"crossref","unstructured":"Stolcke A, Shriberg E, Hakkani-Tur D, Tur G (1999) Modeling the prosody of hidden events for improved word recognition. In: Proceedings of EUROSPEECH, Budapest, Hungary, pp 311\u2013314","DOI":"10.21437\/Eurospeech.1999-81"},{"key":"8_CR36","doi-asserted-by":"crossref","unstructured":"Stolcke A (2002) SRILM\u2014-An extensible language modeling toolkit. In Proc. of ICSLP, Denver, CO, pp 901\u2013904","DOI":"10.21437\/ICSLP.2002-303"},{"key":"8_CR37","unstructured":"Viszlay P, Sta\u0161 J, Koct\u00far T, Lojka M, Juh\u00e1r J (2016) An extension of the Slovak broadcast news corpus based on semi-automatic annotation. In: Proceedings of LREC, Portoro\u017e, Slovenia, pp 4684\u20134687"},{"key":"8_CR38","unstructured":"Watanabe M (2009) Features and roles of filled pauses in speech communication: a corpus-bases study of spontaneous speech. Hituji Syobo Publishing, p 147"},{"issue":"7","key":"8_CR39","first-page":"388","volume":"4","author":"A \u017dgank","year":"2008","unstructured":"\u017dgank A, Rotovnik T, Mau\u010dec MS (2008) Slovenian spontaneous speech recognition and acoustic modeling of filled pauses and onomatopoeas. WSEAS Trans Signal Process 4(7):388\u2013397","journal-title":"WSEAS Trans Signal Process"},{"key":"8_CR40","first-page":"67","volume-title":"Advances in speech recognition","author":"A \u017dgank","year":"2010","unstructured":"\u017dgank A, Mau\u010dec MS (2010) Modeling of filled pauses and onomatopoeas for spontaneous speech recognition. In: Shabtai NR (ed) Advances in speech recognition. Croatia, Sciyo, pp 67\u201382"}],"container-title":["Topics in Intelligent Engineering and Informatics","Cognitive Infocommunications, Theory and Applications"],"original-title":[],"link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-319-95996-2_8","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,7,6]],"date-time":"2025-07-06T15:13:46Z","timestamp":1751814826000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-319-95996-2_8"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018,8,26]]},"ISBN":["9783319959955","9783319959962"],"references-count":40,"URL":"https:\/\/doi.org\/10.1007\/978-3-319-95996-2_8","relation":{},"ISSN":["2193-9411","2193-942X"],"issn-type":[{"type":"print","value":"2193-9411"},{"type":"electronic","value":"2193-942X"}],"subject":[],"published":{"date-parts":[[2018,8,26]]}}}