{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,5,9]],"date-time":"2024-05-09T05:40:09Z","timestamp":1715233209491},"reference-count":36,"publisher":"Springer Science and Business Media LLC","issue":"2","license":[{"start":{"date-parts":[[2013,4,19]],"date-time":"2013-04-19T00:00:00Z","timestamp":1366329600000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Multimed Tools Appl"],"published-print":{"date-parts":[[2014,9]]},"DOI":"10.1007\/s11042-013-1456-2","type":"journal-article","created":{"date-parts":[[2013,4,18]],"date-time":"2013-04-18T08:58:38Z","timestamp":1366275518000},"page":"1465-1481","source":"Crossref","is-referenced-by-count":1,"title":["Leveraging topical and positional cues for language modeling in speech recognition"],"prefix":"10.1007","volume":"72","author":[{"given":"Hsuan-Sheng","family":"Chiu","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Kuan-Yu","family":"Chen","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Berlin","family":"Chen","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2013,4,19]]},"reference":[{"key":"1456_CR1","doi-asserted-by":"crossref","first-page":"89","DOI":"10.1006\/csla.2001.0185","volume":"16","author":"XL Aubert","year":"2002","unstructured":"Aubert XL (2002) An overview of decoding techniques for large vocabulary continuous speech recognition. Comput Speech Lang 16:89\u2013114","journal-title":"Comput Speech Lang"},{"key":"1456_CR2","first-page":"993","volume":"3","author":"DM Blei","year":"2003","unstructured":"Blei DM, Ng AY, Jordan MI (2003) Latent Dirichlet allocation. J Mach Learn Res 3:993\u20131022","journal-title":"J Mach Learn Res"},{"issue":"5","key":"1456_CR3","doi-asserted-by":"crossref","first-page":"456","DOI":"10.1109\/89.709671","volume":"6","author":"JR Bellegarda","year":"1998","unstructured":"Bellegarda JR (1998) A multi-span language modeling framework for large vocabulary speech recognition. IEEE Trans Speech Audio Process 6(5):456\u2013467","journal-title":"IEEE Trans Speech Audio Process"},{"issue":"11","key":"1456_CR4","doi-asserted-by":"crossref","first-page":"93","DOI":"10.1016\/j.specom.2003.08.002","volume":"42","author":"JR Bellegarda","year":"2004","unstructured":"Bellegarda JR (2004) Statistical language model adaptation: review and perspectives. Speech Comm 42(11):93\u2013108","journal-title":"Speech Comm"},{"issue":"4","key":"1456_CR5","first-page":"467","volume":"18","author":"PF Brown","year":"1992","unstructured":"Brown PF, deSouza P, Mercer RL, Pietra VJD, Lai JC (1992) Class-based n-gram models of natural language. Comput Linguist 18(4):467\u2013479","journal-title":"Comput Linguist"},{"issue":"4","key":"1456_CR6","doi-asserted-by":"crossref","first-page":"283","DOI":"10.1006\/csla.2000.0147","volume":"14","author":"C Chelba","year":"2000","unstructured":"Chelba C, Jelinek F (2000) Structured language modeling. Comput Speech Lang 14(4):283\u2013332","journal-title":"Comput Speech Lang"},{"issue":"1","key":"1456_CR7","first-page":"2:1","volume":"8","author":"B Chen","year":"2009","unstructured":"Chen B (2009) Word topic models for spoken document retrieval and transcription. ACM Trans Asian Lang Inf Process 8(1):2:1\u20132:27","journal-title":"ACM Trans Asian Lang Inf Process"},{"key":"1456_CR8","unstructured":"Chen B, Kuo JW, Tsai WH (2004) Lightly supervised and data-driven approaches to mandarin broadcast news transcription. In: Proc. IEEE International Conference on Acoustics, Speech, Signal Processing (ICASSP 2004), pp 777\u2013780"},{"issue":"1","key":"1456_CR9","first-page":"199","volume":"20","author":"B Chen","year":"2012","unstructured":"Chen B, Lin SH (2012) A risk-aware modeling framework for speech summarization. IEEE Trans Audio Speech Lang Process 20(1):199\u2013210","journal-title":"IEEE Trans Audio Speech Lang Process"},{"key":"1456_CR10","doi-asserted-by":"crossref","unstructured":"Chen B, Liu JW (2011) Discriminative language modeling for speech recognition with relevance information. In: Proc. IEEE International Conference on Multimedia & Expo (ICME 2011), pp 1\u20134","DOI":"10.1109\/ICME.2011.6012004"},{"issue":"13","key":"1456_CR11","doi-asserted-by":"crossref","first-page":"1228","DOI":"10.1016\/j.patrec.2009.05.009","volume":"30","author":"B Chen","year":"2009","unstructured":"Chen B, Liu SH, Chu FH (2009) Training data selection for improving discriminative training of acoustic models. Pattern Recognit Lett 30(13):1228\u20131235","journal-title":"Pattern Recognit Lett"},{"issue":"5","key":"1456_CR12","doi-asserted-by":"crossref","first-page":"303","DOI":"10.1109\/TSA.2002.802541","volume":"10","author":"B Chen","year":"2002","unstructured":"Chen B, Wang HM, Lee LS (2002) Discriminating capabilities of syllable-based features and approaches of utilizing them for voice retrieval of speech information in Mandarin Chinese. IEEE Trans Speech Audio Process 10(5):303\u2013314","journal-title":"IEEE Trans Speech Audio Process"},{"key":"1456_CR13","doi-asserted-by":"crossref","unstructured":"Chen KY, Chen B (2011) Relevance language modeling for speech recognition. In: Proc. IEEE International Conference on Acoustics, Speech, Signal Processing (ICASSP 2011), pp 5568\u20135571","DOI":"10.1109\/ICASSP.2011.5947621"},{"key":"1456_CR14","doi-asserted-by":"crossref","unstructured":"Chen KY, Chiu HS, Chen B (2010) Latent topic modeling of word vicinity information for speech recognition. In: Proc. IEEE International Conference on Acoustics, Speech, Signal Processing (ICASSP 2010), pp 5394\u20135397","DOI":"10.1109\/ICASSP.2010.5494942"},{"issue":"1","key":"1456_CR15","doi-asserted-by":"crossref","first-page":"95","DOI":"10.1109\/TASL.2008.2005031","volume":"17","author":"YT Chen","year":"2009","unstructured":"Chen YT, Chen B, Wang HM (2009) A probabilistic generative framework for extractive broadcast news speech summarization. IEEE Trans Audio Speech Lang Process 17(1):95\u2013106","journal-title":"IEEE Trans Audio Speech Lang Process"},{"key":"1456_CR16","doi-asserted-by":"crossref","unstructured":"Chiu HS, Chen GY, Lee CJ, Chen B (2008) Position information for language modeling in speech recognition, In: Proc. 6th International Symposium on Chinese Spoken Language Processing (ISCSLP 2008), pp 101\u2013104","DOI":"10.1109\/CHINSL.2008.ECP.37"},{"key":"1456_CR17","doi-asserted-by":"crossref","unstructured":"Clarkson PR, Robinson AJ (1997) Language model adaptation using mixtures and an exponentially decaying cache. In: Proc. IEEE International Conference on Acoustics, Speech, Signal Processing (ICASSP 1997), pp 799\u2013802","DOI":"10.1109\/ICASSP.1997.596049"},{"issue":"1","key":"1456_CR18","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1111\/j.2517-6161.1977.tb01600.x","volume":"39","author":"AP Dempster","year":"1977","unstructured":"Dempster AP, Laird NM, Rubin DB (1977) Maximum likelihood from incomplete data via the EM algorithm. J R Stat Soc Ser B 39(1):1\u201338","journal-title":"J R Stat Soc Ser B"},{"key":"1456_CR19","doi-asserted-by":"crossref","unstructured":"Gildea D, Hofmann T (1999) Topic-based language models using EM. In: Proc. European Conference on Speech Communication and Technology (Eurospeech 1999), pp 2167\u20132170","DOI":"10.21437\/Eurospeech.1999-479"},{"issue":"3\u20134","key":"1456_CR20","doi-asserted-by":"crossref","first-page":"237","DOI":"10.1093\/biomet\/40.3-4.237","volume":"40","author":"IJ Good","year":"1953","unstructured":"Good IJ (1953) The population frequencies of species and estimation of population parameters. Biometrika 40(3\u20134):237\u2013264","journal-title":"Biometrika"},{"key":"1456_CR21","doi-asserted-by":"crossref","first-page":"177","DOI":"10.1023\/A:1007617005950","volume":"42","author":"T Hofmann","year":"2001","unstructured":"Hofmann T (2001) Unsupervised learning by probabilistic latent semantic analysis. Mach Learn 42:177\u2013196","journal-title":"Mach Learn"},{"key":"1456_CR22","doi-asserted-by":"crossref","unstructured":"Kneser R, Ney H (1995) Improved backing-off for m-gram language modeling. In: Proc. IEEE International Conference on Acoustics, Speech, Signal Processing (ICASSP 1995), vol. I, pp 181\u2013184","DOI":"10.1109\/ICASSP.1995.479394"},{"key":"1456_CR23","doi-asserted-by":"crossref","unstructured":"Koshinaka T, Iso K, Okumura A (2005) An HMM-based text segmentation method using variational Bayes approach and its application to LVCSR for broadcast news. In: Proc. IEEE International Conference on Acoustics, Speech, Signal Processing (ICASSP 2005), pp 485\u2013488","DOI":"10.1109\/ICASSP.2005.1415156"},{"key":"1456_CR24","doi-asserted-by":"crossref","first-page":"45","DOI":"10.1109\/ICASSP.1993.319225","volume":"2","author":"R Lau","year":"1993","unstructured":"Lau R, Rosenfeld R, Roukos S (1993) Trigger-based language models: a maximum entropy approach. Proc IEEE Int Conf Acoust Speech Signal Process 2:45\u201348","journal-title":"Proc IEEE Int Conf Acoust Speech Signal Process"},{"key":"1456_CR25","unstructured":"Lee HS, Chen B (2009) Generalized likelihood ratio discriminant analysis. In: Proc. IEEE workshop on Automatic Speech Recognition and Understanding (ASRU 2009), pp 158\u2013163"},{"key":"1456_CR26","doi-asserted-by":"crossref","first-page":"373","DOI":"10.1016\/j.csl.2006.06.006","volume":"21","author":"B Roark","year":"2007","unstructured":"Roark B, Saraclar M, Collins M (2007) Discriminative n-gram language modeling. Comput Speech Lang 21:373\u2013392","journal-title":"Comput Speech Lang"},{"issue":"8","key":"1456_CR27","doi-asserted-by":"crossref","first-page":"1270","DOI":"10.1109\/5.880083","volume":"88","author":"R Rosenfeld","year":"2000","unstructured":"Rosenfeld R (2000) Two decades of statistical language modeling: where do we go from here. Proc IEEE 88(8):1270\u20131278","journal-title":"Proc IEEE"},{"key":"1456_CR28","doi-asserted-by":"crossref","first-page":"43","DOI":"10.1006\/csla.1996.0022","volume":"11","author":"S Ortmanns","year":"1997","unstructured":"Ortmanns S, Ney H, Aubert X (1997) A word graph algorithm for large vocabulary continuous speech recognition. Comput Speech Lang 11:43\u201372","journal-title":"Comput Speech Lang"},{"issue":"3","key":"1456_CR29","first-page":"150","volume":"25","author":"M Ostendorf","year":"2008","unstructured":"Ostendorf M (2008) Speech technology and information access. IEEE Signal Process Mag 25(3):150\u2013152","journal-title":"IEEE Signal Process Mag"},{"key":"1456_CR30","doi-asserted-by":"crossref","unstructured":"Pallett D, Fisher W, Fiscus J (1990) Tools for the analysis of benchmark speech recognition tests. In: Proc. IEEE International Conference on Acoustics, Speech, Signal Processing, pp 97\u2013100","DOI":"10.1109\/ICASSP.1990.115546"},{"key":"1456_CR31","unstructured":"Ponte JM, Croft WB (1998) A language modeling approach to information retrieval. In: Proc. the ACM International Conference on Research and Development in Information Retrieval (SIGIR 1998), pp 275\u2013281"},{"key":"1456_CR32","unstructured":"Saul L, Pereira F, (1997) Aggregate and mixed-order Markov models for statistical language processing In: Proc. Empirical Methods on Natural Language Processing (EMNLP 1997), pp 81\u201389"},{"key":"1456_CR33","unstructured":"Stolcke A (2000) SRI language modeling toolkit. Version 1.3.3. http:\/\/www.speech.sri.com\/projects\/srilm\/"},{"key":"1456_CR34","doi-asserted-by":"crossref","unstructured":"Tur G, Mori RD (eds) (2011) Spoken language understanding\u2014systems for extracting semantic information from speech. John Wiley and Sons, New York, NY","DOI":"10.1002\/9781119992691"},{"issue":"1","key":"1456_CR35","first-page":"219","volume":"10","author":"HM Wang","year":"2005","unstructured":"Wang HM, Chen B, Kuo JW, Cheng SS (2005) MATBN: a Mandarin Chinese broadcast news corpus. Int J Comput Linguist Chin Lang Process 10(1):219\u2013235","journal-title":"Int J Comput Linguist Chin Lang Process"},{"key":"1456_CR36","doi-asserted-by":"crossref","unstructured":"Zhai CX (2008) Statistical language models for information retrieval. Morgan & Claypool Publishers, United States","DOI":"10.2200\/S00158ED1V01Y200811HLT001"}],"container-title":["Multimedia Tools and Applications"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s11042-013-1456-2.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/article\/10.1007\/s11042-013-1456-2\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s11042-013-1456-2","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,5,9]],"date-time":"2024-05-09T05:21:02Z","timestamp":1715232062000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/s11042-013-1456-2"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2013,4,19]]},"references-count":36,"journal-issue":{"issue":"2","published-print":{"date-parts":[[2014,9]]}},"alternative-id":["1456"],"URL":"https:\/\/doi.org\/10.1007\/s11042-013-1456-2","relation":{},"ISSN":["1380-7501","1573-7721"],"issn-type":[{"value":"1380-7501","type":"print"},{"value":"1573-7721","type":"electronic"}],"subject":[],"published":{"date-parts":[[2013,4,19]]}}}