{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,7,11]],"date-time":"2025-07-11T10:22:01Z","timestamp":1752229321453,"version":"3.37.3"},"reference-count":30,"publisher":"Springer Science and Business Media LLC","issue":"3","license":[{"start":{"date-parts":[[2020,9,1]],"date-time":"2020-09-01T00:00:00Z","timestamp":1598918400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2020,9,1]],"date-time":"2020-09-01T00:00:00Z","timestamp":1598918400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Int J Speech Technol"],"published-print":{"date-parts":[[2020,9]]},"DOI":"10.1007\/s10772-020-09749-0","type":"journal-article","created":{"date-parts":[[2020,9,7]],"date-time":"2020-09-07T02:02:15Z","timestamp":1599444135000},"page":"695-704","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":4,"title":["Unsupervised stemmed text corpus for language modeling and transcription of Telugu broadcast news"],"prefix":"10.1007","volume":"23","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-3524-3534","authenticated-orcid":false,"given":"Mythilisharan","family":"Pala","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Laxminarayana","family":"Parayitam","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Venkataramana","family":"Appala","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2020,9,7]]},"reference":[{"key":"9749_CR1","unstructured":"Anumanchipalli, G., et al. (2005). Development of Indian Language Speech Databases for Large Vocabulary Speech Recognition Systems. In: Proceedings on SPECOM, 2005."},{"key":"9749_CR2","unstructured":"Basha Shaik, M. A., Rybach, D., Hahn, S., Schl\u00fcter, R., & Ney, H. (2012). Hierarchical Hybrid Language models for Open Vocabulary Continuous Speech Recognition using WFST. In: Proceedings of Working Statuary Percept Audit (SAPA \u2013 SCALE) (pp. 46\u201351)."},{"issue":"1","key":"9749_CR3","first-page":"31","volume":"18","author":"PF Brown","year":"1992","unstructured":"Brown, P. F., Della Pietra, V. J., Mercer, R. L., Della Pietra, S. A., & Lai, J. C. (1992). An estimate of an upper bound for the entropy of English. Computational Linguistics, 18(1), 31\u201340.","journal-title":"Computational Linguistics"},{"key":"9749_CR4","unstructured":"Chen, S., Beeferman, D., Rosenfeld, R. (1998). Evaluation metrics for language models. In: Proceedings of DARPA broadcast news transcription and understanding workshop, pp. 275\u2013280."},{"key":"9749_CR5","unstructured":"Chen, S. & Goodman, J. (1998). An empirical study of smoothing techniques for language modeling (Tech. Rep. No. TR-10-98)."},{"issue":"1","key":"9749_CR6","doi-asserted-by":"publisher","first-page":"19","DOI":"10.1016\/0885-2308(91)90016-J","volume":"5","author":"KW Church","year":"1991","unstructured":"Church, K. W., & Gale, W. A. (1991). A comparison of the enhanced Good-Turing and deleted estimation methods for estimating probabilities of English bigrams. Computer Speech & Language, 5(1), 19\u201354.","journal-title":"Computer Speech & Language"},{"issue":"1","key":"9749_CR7","doi-asserted-by":"publisher","first-page":"30","DOI":"10.1109\/TASL.2011.2134090","volume":"20","author":"E Dahl","year":"2012","unstructured":"Dahl, E., Yu, D., Deng, L., & Acero, A. (2012). Context-dependent pre-trained deep neural networks for large-vocabulary speech recognition. IEEE Transactions on Audio, Speech and Language Processing, 20(1), 30\u201342.","journal-title":"IEEE Transactions on Audio, Speech and Language Processing"},{"key":"9749_CR8","unstructured":"Ganapathiraju, M., & Levin, L. (2006). TelMore: Morphological Generator for Telugu Nouns and verbs. In: Proceedings of the second international conference on universal digital library, Alexandria, Egypt, November 17\u201319, 2006, pp. 1\u20137."},{"key":"9749_CR9","unstructured":"Hsu, B.-J. (2007). Generalized linear interpolation of language models. In: 2007 IEEE workshop on automatic speech recognition & understanding (ASRU), 2007, pp. 136\u2013140."},{"key":"9749_CR10","unstructured":"Jelinek, R. L. & Mercer, F. (1980). Interpolated estimation of Markov source parameters from sparse data. In: Proceedings of the workshop on pattern recognition in practice, North-Holland, Amsterdam, The Netherlands, 1980, pp. 381\u2013397."},{"key":"9749_CR11","doi-asserted-by":"crossref","unstructured":"Jyothi, P., & Hasegawa-Johnson, M. (2015). Improved Hindi broadcast ASR by adapting the language model and pronunciation model using a priori syntactic and morphophonemic knowledge. In: Proceedings of the annual conference of the International Speech Communication Association, INTERSPEECH, 2015, vol. 2015-January (pp. 3164\u20133168).","DOI":"10.21437\/Interspeech.2015-637"},{"key":"9749_CR12","unstructured":"Kalika Bali, A. R., Talukdar, P. P., & Sridhar Krishna, N. (2004). Tools for the development of a Hindi speech synthesis system. In: 5th ISCA Speech Synthesis Workshop, 2004, pp. 109\u2013114."},{"issue":"3","key":"9749_CR13","doi-asserted-by":"publisher","first-page":"400","DOI":"10.1109\/TASSP.1987.1165125","volume":"35","author":"SM Katz","year":"1987","unstructured":"Katz, S. M. (1987). Estimation of probabilities from sparse data for the language model component of a speech recognizer. IEEE Transaction on Acoustics, 35(3), 400\u2013401.","journal-title":"IEEE Transaction on Acoustics"},{"key":"9749_CR14","unstructured":"Kneser, R. & Ney, H. (2002). Improved backing-off for M-gram language modeling. In: 1995 international conference on acoustics, speech, and signal processing, 2002, vol. 1, pp. 181\u2013184."},{"key":"9749_CR15","volume-title":"Telugu verbal bases","author":"B Krishnamurti","year":"2009","unstructured":"Krishnamurti, B. (2009). Telugu verbal bases. Delhi: Motilal Banarsidass Publishers Pvt. Limited."},{"key":"9749_CR16","volume-title":"A grammar of modern Telugu","author":"B Krishnamurti","year":"1985","unstructured":"Krishnamurti, B., & Gwynn, J. P. L. (1985). A grammar of modern Telugu. Oxford: Oxford University Press."},{"issue":"1","key":"9749_CR17","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1006\/csla.1994.1001","volume":"8","author":"H Ney","year":"1994","unstructured":"Ney, H., Essen, U., & Kneser, R. (1994). On structuring probabilistic dependences in stochastic language modelling. Computer Speech & Language, 8(1), 1\u201338.","journal-title":"Computer Speech & Language"},{"key":"9749_CR18","doi-asserted-by":"publisher","first-page":"174","DOI":"10.1007\/978-94-017-1183-8_6","volume-title":"Corpus-based methods in language and speech processing","author":"H Ney","year":"1997","unstructured":"Ney, H., Martin, S., & Wessel, F. (1997). Statistical language modeling using leaving-one-out. In B. G. Spee & S. Young (Eds.), Corpus-based methods in language and speech processing (pp. 174\u2013207). Berlin: Springer."},{"key":"9749_CR19","doi-asserted-by":"crossref","unstructured":"Pandey, A. K. & Siddiqui, T. J. (2008). An unsupervised Hindi stemmer with heuristic improvements. In: Proceedings of the second workshop on Analytics for noisy unstructured text data - AND\u201908, 2008, pp. 99\u2013105.","DOI":"10.1145\/1390749.1390765"},{"issue":"2","key":"9749_CR20","doi-asserted-by":"publisher","first-page":"404","DOI":"10.1016\/j.csl.2010.06.003","volume":"25","author":"D Povey","year":"2011","unstructured":"Povey, D., et al. (2011a). The subspace Gaussian mixture model: A structured model for speech recognition. Computer Speech & Language, 25(2), 404\u2013439.","journal-title":"Computer Speech & Language"},{"key":"9749_CR21","volume-title":"The Kaldi Speech Recognition Toolkit","author":"D Povey","year":"2011","unstructured":"Povey, D., et al. (2011b). The Kaldi Speech Recognition Toolkit. Okinawa: Proceedings of ASRU."},{"key":"9749_CR22","doi-asserted-by":"crossref","unstructured":"Powers, D. M. W. (1998). Applications and explanations of Zipf\u2019s law. In: Proceedings of the joint conferences on new methods in language processing and computational natural language learning, 1998 (pp. 151\u2013160).","DOI":"10.3115\/1603899.1603924"},{"key":"9749_CR23","volume-title":"Vyakarana padakosamu Sastra nighantuvu","author":"B Purushottam","year":"1978","unstructured":"Purushottam, B., Srihari Shastri, R., & Venkata Rama, D. (1978). Vyakarana padakosamu Sastra nighantuvu. Hyderabad: Telugu Acadamy."},{"issue":"2","key":"9749_CR24","doi-asserted-by":"publisher","first-page":"257","DOI":"10.1109\/5.18626","volume":"77","author":"LR Rabiner","year":"1989","unstructured":"Rabiner, L. R. (1989). A tutorial on hidden Markov models and selected applications in speech recognition. Proceedings of IEEE, 77(2), 257\u2013286.","journal-title":"Proceedings of IEEE"},{"key":"9749_CR25","unstructured":"Siva Kumar, A. P., Premchand, P., & Govardhan, A. (2011). TelStem: An unsupervised telugu stemmer with heuristic improvements and normalized signatures, 2011."},{"key":"9749_CR26","doi-asserted-by":"crossref","first-page":"901","DOI":"10.21437\/ICSLP.2002-303","volume":"2002","author":"A Stolcke","year":"2002","unstructured":"Stolcke, A. (2002). SRILM an extensible language modeling toolkit. ICSLP, 2002, 901\u2013904.","journal-title":"ICSLP"},{"key":"9749_CR27","volume-title":"Text compression","author":"HW Timothy","year":"1990","unstructured":"Timothy, H. W., Bell, C., & Cleary, J. G. (1990). Text compression. Upper Saddle River, NJ: Prentice-Hall, Inc."},{"key":"9749_CR28","first-page":"189","volume-title":"Mining intelligence and knowledge exploration. MIKE 2017., Lecture No.","author":"VVR Vegesna","year":"2017","unstructured":"Vegesna, V. V. R., Gurugubelli, K., Vydana, H. K., Pulugandla, B., Shrivastava, M., & Vuppala, A. K. (2017). DNN-HMM acoustic modeling for large vocabulary Telugu speech recognition. In P. R. Ghosh & R. Pal (Eds.), Mining intelligence and knowledge exploration. MIKE 2017., Lecture No. (pp. 189\u2013197). Cham: Springer."},{"key":"9749_CR29","volume-title":"Telugu in thirty days","author":"D Venkatawdhani","year":"1976","unstructured":"Venkatawdhani, D. (1976). Telugu in thirty days. Hyderabad: Andhrapradesh Sahitya Acadamy."},{"issue":"4","key":"9749_CR30","doi-asserted-by":"publisher","first-page":"1085","DOI":"10.1109\/18.87000","volume":"37","author":"IH Witten","year":"1991","unstructured":"Witten, I. H., & Bell, T. C. (1991). The zero-frequency problem: estimating the probabilities of novel events in adaptive text compression. IEEE Transactions on Information Theory, 37(4), 1085\u20131094.","journal-title":"IEEE Transactions on Information Theory"}],"container-title":["International Journal of Speech Technology"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10772-020-09749-0.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s10772-020-09749-0\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10772-020-09749-0.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,11,16]],"date-time":"2022-11-16T23:15:10Z","timestamp":1668640510000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s10772-020-09749-0"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,9]]},"references-count":30,"journal-issue":{"issue":"3","published-print":{"date-parts":[[2020,9]]}},"alternative-id":["9749"],"URL":"https:\/\/doi.org\/10.1007\/s10772-020-09749-0","relation":{},"ISSN":["1381-2416","1572-8110"],"issn-type":[{"type":"print","value":"1381-2416"},{"type":"electronic","value":"1572-8110"}],"subject":[],"published":{"date-parts":[[2020,9]]},"assertion":[{"value":"22 November 2019","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"16 August 2020","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"7 September 2020","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}]}}