{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,1]],"date-time":"2025-11-01T04:57:53Z","timestamp":1761973073906,"version":"build-2065373602"},"publisher-location":"Berlin, Heidelberg","reference-count":31,"publisher":"Springer Berlin Heidelberg","isbn-type":[{"type":"print","value":"9783642358272"},{"type":"electronic","value":"9783642358289"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2013]]},"DOI":"10.1007\/978-3-642-35828-9_30","type":"book-chapter","created":{"date-parts":[[2013,1,2]],"date-time":"2013-01-02T06:22:59Z","timestamp":1357107779000},"page":"274-285","source":"Crossref","is-referenced-by-count":2,"title":["Evalita 2011: Automatic Speech Recognition Large Vocabulary Transcription"],"prefix":"10.1007","author":[{"given":"Marco","family":"Matassoni","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Fabio","family":"Brugnara","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Roberto","family":"Gretter","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","reference":[{"issue":"6","key":"30_CR1","doi-asserted-by":"publisher","first-page":"627","DOI":"10.1121\/1.1906946","volume":"24","author":"K.H. Davis","year":"1952","unstructured":"Davis, K.H., Biddulph, R., Balashek, S.: Automatic recognition of spoken digits. J. Acoust. Soc. Amer.\u00a024(6), 627\u2013642 (1952)","journal-title":"J. Acoust. Soc. Amer."},{"issue":"3","key":"30_CR2","doi-asserted-by":"publisher","first-page":"75","DOI":"10.1109\/MSP.2009.932166","volume":"26","author":"J. Baker","year":"2009","unstructured":"Baker, J., Deng, L., Glass, J., Khudanpur, S., Lee, C.-H., Morgan, N., O\u2019Shaughnessy, D.: Developments and directions in speech recognition and understanding, Part 1 [DSP Education]. IEEE Signal Processing Magazine\u00a026(3), 75\u201380 (2009)","journal-title":"IEEE Signal Processing Magazine"},{"key":"30_CR3","unstructured":"Povey, D.: Discriminative training for large vocabulary speech recognition. Ph.D. thesis, Cambridge University, Cambridge (2004)"},{"key":"30_CR4","unstructured":"Sha, F.: Large margin training of acoustic models for speech recognition. Ph.D. thesis, University of Pennsylvania, Philadelphia (2007)"},{"issue":"3","key":"30_CR5","doi-asserted-by":"publisher","first-page":"492","DOI":"10.1016\/j.csl.2006.09.003","volume":"21","author":"H. Schwenk","year":"2007","unstructured":"Schwenk, H.: Continuous space language models. Computer Speech and Language\u00a021(3), 492\u2013518 (2007)","journal-title":"Computer Speech and Language"},{"key":"30_CR6","unstructured":"Mohamed, A.R., Dahl, G.E., Hinton, G.E.: Deep belief networks for phone recognition. In: NIPS 22 Workshop on Deep Learning for Speech Recognition (2009)"},{"issue":"4","key":"30_CR7","doi-asserted-by":"publisher","first-page":"357","DOI":"10.1109\/TASSP.1980.1163420","volume":"28","author":"S.B. Davis","year":"1980","unstructured":"Davis, S.B., Mermelstein, P.: Comparison of parametric representations for monosyllabic word recognition in continuously spoken sentences. IEEE Trans. Acoust., Speech, and Signal Processing\u00a028(4), 357\u2013366 (1980)","journal-title":"IEEE Trans. Acoust., Speech, and Signal Processing"},{"key":"30_CR8","doi-asserted-by":"crossref","unstructured":"Chiu, Y.-H. , Raj, B. , Stern, R.: Learning based auditory encoding for robust speech recognition. In: IEEE International Conference on Acoustics, Speech and Signal Processing, pp. 428\u2013431 (2010)","DOI":"10.1109\/ICASSP.2010.5495666"},{"issue":"5","key":"30_CR9","doi-asserted-by":"publisher","first-page":"3246","DOI":"10.1121\/1.411700","volume":"97","author":"J. Cohen","year":"1995","unstructured":"Cohen, J., Kamm, T., Andreou, A.: Vocal tract normalization in speech recognition: compensation for system systematic speaker variability. J. Acoust. Soc. Amer.\u00a097(5), pt. 2, 3246\u20133247 (1995)","journal-title":"J. Acoust. Soc. Amer."},{"key":"30_CR10","doi-asserted-by":"crossref","unstructured":"Kumar, N., Andreou, A.G.: Heteroscedastic discriminant analysis and reduced rank HMMs for improved speech recognition. In: Speech Communication, pp. 283\u2013297 (1998)","DOI":"10.1016\/S0167-6393(98)00061-2"},{"key":"30_CR11","unstructured":"Bilmes, J.: A Gentle Tutorial of the EM algorithm and its application to Parameter Estimation for Gaussian Mixture and Hidden Markov Models. Technical Report TR-97-021, International Computer Science Institute (1997)"},{"key":"30_CR12","first-page":"429","volume-title":"Proceedings of the International Conference on Semantic Computing","author":"D. Yu","year":"2007","unstructured":"Yu, D., Deng, L.: Large-Margin Discriminative Training of Hidden Markov Models for Speech Recognition. In: Proceedings of the International Conference on Semantic Computing, pp. 429\u2013438. IEEE Computer Society, Washington, DC (2007)"},{"issue":"2","key":"30_CR13","doi-asserted-by":"publisher","first-page":"291","DOI":"10.1109\/89.279278","volume":"2","author":"J.-L. Gauvain","year":"1994","unstructured":"Gauvain, J.-L., Lee, C.-H.: Maximum a posteriori estimation for multivariate Gaussian mixture observations of Markov chains. IEEE Transactions on Speech and Audio Processing\u00a02(2), 291\u2013298 (1994)","journal-title":"IEEE Transactions on Speech and Audio Processing"},{"key":"30_CR14","first-page":"171","volume":"9","author":"C.J. Leggetter","year":"1995","unstructured":"Leggetter, C.J., Woodland, P.C.: Maximum likelihood linear regression for speaker adaptation of continuous density HMMs. Speech Communication\u00a09, 171\u2013186 (1995)","journal-title":"Speech Communication"},{"key":"30_CR15","unstructured":"Fiscus, J.G.: A post-processing system to yield reduced word error rates: Recognizer Output Voting Error Reduction (ROVER). In: 1997 IEEE Workshop on Automatic Speech Recognition and Understanding, pp. 347\u2013354 (1997)"},{"key":"30_CR16","doi-asserted-by":"crossref","unstructured":"Hoffmeister, B., Hillard, D., Hahn, S., Schluter, R., Ostendorf, M., Ney, H.: Cross-Site and Intra-Site ASR System Combination: Comparisons on Lattice and 1-Best Methods.XS. In: IEEE International Conference on Acoustics, Speech and Signal Processing, vol.\u00a04, pp. 1145\u20131148 (2007)","DOI":"10.1109\/ICASSP.2007.367277"},{"key":"30_CR17","doi-asserted-by":"crossref","unstructured":"Hermansky, H., Ellis, D.P.W., Sharma, S.: Tandem connectionist feature extraction for conventional HMM systems. In: IEEE International Conference on Acoustics, Speech, and Signal Processing, vol.\u00a03, pp. 1635\u20131638 (2000)","DOI":"10.1109\/ICASSP.2000.862024"},{"key":"30_CR18","unstructured":"Pinto, J.P.: Multilayer Perceptron Based Hierarchical Acoustic Modeling for Automatic Speech Recognition. PhD thesis, EPFL Switzerland (2010)"},{"key":"30_CR19","doi-asserted-by":"crossref","unstructured":"Schwarz, P., Matejka, P., Cernocky, J.: Hierarchical Structures of Neural Networks for Phoneme Recognition. In: 2006 IEEE International Conference on Acoustics, Speech and Signal Processing, vol.\u00a01(I), pp. 14\u201319 (2006)","DOI":"10.1109\/ICASSP.2006.1660023"},{"key":"30_CR20","doi-asserted-by":"crossref","unstructured":"Zweig, G., Nguyen, P.: A segmental CRF approach to large vocabulary continuous speech recognition. In: IEEE Workshop on Automatic Speech Recognition and Understanding, pp. 152\u2013157 (2009)","DOI":"10.1109\/ASRU.2009.5372916"},{"issue":"1","key":"30_CR21","doi-asserted-by":"publisher","first-page":"30","DOI":"10.1109\/TASL.2011.2134090","volume":"20","author":"G.E. Dahl","year":"2012","unstructured":"Dahl, G.E., Yu, D., Deng, L., Acero, A.: Context-Dependent Pre-Trained Deep Neural Networks for Large-Vocabulary Speech Recognition. IEEE Transactions on Audio, Speech, and Language Processing\u00a020(1), 30\u201342 (2012)","journal-title":"IEEE Transactions on Audio, Speech, and Language Processing"},{"issue":"3","key":"30_CR22","doi-asserted-by":"publisher","first-page":"400","DOI":"10.1109\/TASSP.1987.1165125","volume":"35","author":"S. Katz","year":"1987","unstructured":"Katz, S.: Estimation of probabilities from sparse data for the language model component of a speech recognizer. IEEE Transactions on Acoustics, Speech and Signal Processing\u00a035(3), 400\u2013401 (1987)","journal-title":"IEEE Transactions on Acoustics, Speech and Signal Processing"},{"issue":"8","key":"30_CR23","doi-asserted-by":"publisher","first-page":"1270","DOI":"10.1109\/5.880083","volume":"88","author":"R. Rosenfeld","year":"2000","unstructured":"Rosenfeld, R.: Two decades of statistical language modeling: where do we go from here? Proceedings of the IEEE\u00a088(8), 1270\u20131278 (2000)","journal-title":"Proceedings of the IEEE"},{"key":"30_CR24","doi-asserted-by":"crossref","unstructured":"Schwenk, H.: Trends and challenges in language modeling for speech recognition and machine translation. In: IEEE Workshop on Automatic Speech Recognition and Understanding, Merano (2009)","DOI":"10.1109\/ASRU.2009.5373531"},{"key":"30_CR25","unstructured":"The History of Automatic Speech Recognition Evaluations at NIST, http:\/\/www.itl.nist.gov\/iad\/mig\/publications\/ASRhistory\/index.html"},{"key":"30_CR26","doi-asserted-by":"crossref","unstructured":"Lamel, L., Gauvain, J.L., Adda, G., Barras, C., Bilinksi, E., Galibert, O., Pujol, A., Schwenk, H., Xuan, Z.: The LIMSI 2006 TC-STAR EPPS Transcription Systems. In: IEEE International Conference on Acoustics, Speech and Signal Processing, vol.\u00a04, pp. 997\u20131000 (2007)","DOI":"10.1109\/ICASSP.2007.367240"},{"key":"30_CR27","unstructured":"SAMPA - computer readable phonetic alphabet, http:\/\/www.phon.ucl.ac.uk\/home\/sampa\/"},{"key":"30_CR28","unstructured":"Gretter, R., Peirone, G.: A Morphological Analyzer for the Italian Language. Istituto per la Ricerca Scientifica e Tecnologica, Tech. Rep. - Ref. No. 9108-01, Italy (December 12, 1991)"},{"key":"30_CR29","unstructured":"NIST: Speech recognition scoring toolkit, http:\/\/www.itl.nist.gov\/iad\/mig\/tools\/"},{"key":"30_CR30","unstructured":"Ronny, R., Shakoor, A., Brugnara, F., Gretter, R.: The FBK ASR system for Evalita 2011. In: Working Notes of EVALITA 2011, Rome, Italy (January 24-25, 2012)"},{"key":"30_CR31","unstructured":"Despres, J., Lamel, L., Gauvain, J.-L., Vieru, B., Woehrling, C., Bac Le, V., Oparin, I.: The Vocapia Research ASR Systems for Evalita 2011. In: Working Notes of EVALITA 2011, Rome, Italy (January 24-25, 2012)"}],"container-title":["Lecture Notes in Computer Science","Evaluation of Natural Language and Speech Tools for Italian"],"original-title":[],"link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-642-35828-9_30.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,4,29]],"date-time":"2025-04-29T15:33:44Z","timestamp":1745940824000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-642-35828-9_30"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2013]]},"ISBN":["9783642358272","9783642358289"],"references-count":31,"URL":"https:\/\/doi.org\/10.1007\/978-3-642-35828-9_30","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2013]]}}}