{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,1,13]],"date-time":"2025-01-13T05:40:01Z","timestamp":1736746801083,"version":"3.32.0"},"publisher-location":"Berlin, Heidelberg","reference-count":13,"publisher":"Springer Berlin Heidelberg","isbn-type":[{"type":"print","value":"9783540692676"},{"type":"electronic","value":"9783540692683"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2006]]},"DOI":"10.1007\/11965152_38","type":"book-chapter","created":{"date-parts":[[2007,1,23]],"date-time":"2007-01-23T13:48:58Z","timestamp":1169560138000},"page":"432-443","source":"Crossref","is-referenced-by-count":6,"title":["The IBM Rich Transcription Spring 2006 Speech-to-Text System for Lecture Meetings"],"prefix":"10.1007","author":[{"given":"Jing","family":"Huang","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Martin","family":"Westphal","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Stanley","family":"Chen","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Olivier","family":"Siohan","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Daniel","family":"Povey","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Vit","family":"Libal","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Alvaro","family":"Soneiro","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Henrik","family":"Schulz","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Thomas","family":"Ross","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Gerasimos","family":"Potamianos","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","reference":[{"key":"38_CR1","unstructured":"The LDC Corpus Catalog, Linguistic Data Consortium, University of Pennsylvania. Philadelphia, PA. Available: http:\/\/www.ldc.upenn.edu\/Catalog"},{"key":"38_CR2","unstructured":"Fiscus, J.G.: A post-processing system to yield reduced word error rates: Recognizer output voting error reduction (ROVER). In: Proc. Wksp. on Automatic Speech Recog. and Understanding (ASRU), Santa Barbara, CA, pp. 347\u2013354 (1997)"},{"key":"38_CR3","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"332","DOI":"10.1007\/11677482_29","volume-title":"Machine Learning for Multimodal Interaction","author":"S. Chu","year":"2006","unstructured":"Chu, S., Marcheret, E., Potamianos, G.: Automatic speech recognition and speech activity detection in the CHIL smart room. In: Renals, S., Bengio, S. (eds.) MLMI 2005. LNCS, vol.\u00a03869, pp. 332\u2013343. Springer, Heidelberg (2006)"},{"key":"38_CR4","doi-asserted-by":"crossref","unstructured":"Ajmera, J., Wooters, C.: A robust speaker clustering algorithm. In: Proc. Wksp. on Automatic Speech Recog. and Understanding (ASRU), St. Thomas, US Virgin Islands, pp. 411\u2013416 (2003)","DOI":"10.1109\/ASRU.2003.1318476"},{"key":"38_CR5","doi-asserted-by":"crossref","unstructured":"Stolcke, A., Anguera, X., Boakye, K., Cetin, O., Grezl, F., Janin, A., Mandal, A., Peskin, B., Wooters, C., Zheng, J.: Further progress in meeting recognition: the ICSI-SRI Spring 2005 speech-to-text evaluation system. In: Proc. Rich Transcription 2005 Spring Meeting Recog. Eval., Edinburgh, UK, pp. 39\u201350 (2005)","DOI":"10.1007\/11677482_39"},{"key":"38_CR6","doi-asserted-by":"publisher","first-page":"75","DOI":"10.1006\/csla.1998.0043","volume":"12","author":"M.F.J. Gales","year":"1998","unstructured":"Gales, M.F.J.: Maximum likelihood linear transformations for HMM-based speech recognition. Computer Speech and Language\u00a012, 75\u201398 (1998)","journal-title":"Computer Speech and Language"},{"key":"38_CR7","doi-asserted-by":"crossref","unstructured":"Saon, G., Zweig, G., Padmanabhan, M.: Linear feature space projections for speaker adaptation. In: Proc. IEEE Int. Conf. on Acoustics, Speech and Signal Process (ICASSP), Salt Lake City, UT, pp. 325\u2013328 (2001)","DOI":"10.1109\/ICASSP.2001.940833"},{"key":"38_CR8","doi-asserted-by":"crossref","unstructured":"Wegmann, S., McAllaster, D., Orloff, J., Peskin, B.: Speaker normalization on conversational telephone speech. In: Proc. IEEE Int. Conf. on Acoustics, Speech and Signal Process (ICASSP), Atlanta, GA, pp. 339\u2013341 (1996)","DOI":"10.1109\/ICASSP.1996.541101"},{"key":"38_CR9","doi-asserted-by":"crossref","unstructured":"Saon, G., Padmanabhan, M., Gopinath, R.: Eliminating inter-speaker variability prior to discriminant transforms. In: Proc. Wksp. on Automatic Speech Recog. and Understanding (ASRU), Trento, Italy, pp. 73\u201376 (2001)","DOI":"10.1109\/ASRU.2001.1034592"},{"key":"38_CR10","doi-asserted-by":"crossref","unstructured":"Povey, D., Kingsbury, B., Mangu, L., Saon, G., Soltau, H., Zweig, G.: fMPE: Discriminatively trained features for speech recognition. In: Proc. IEEE Int. Conf. on Acoustics, Speech and Signal Process (ICASSP), Philadelphia, PA, vol.\u00a01, pp. 961\u2013964 (2005)","DOI":"10.1109\/ICASSP.2005.1415275"},{"key":"38_CR11","doi-asserted-by":"crossref","unstructured":"Povey, D., Woodland, P.C.: Minimum phone error and I-smoothing for improved discriminative training. In: Proc. IEEE Int. Conf. on Acoustics, Speech and Signal Process (ICASSP), Orlando, FL, pp. 105\u2013108 (2002)","DOI":"10.1109\/ICASSP.2002.5743665"},{"key":"38_CR12","doi-asserted-by":"publisher","first-page":"359","DOI":"10.1006\/csla.1999.0128","volume":"13","author":"S.F. Chen","year":"1999","unstructured":"Chen, S.F., Goodman, J.: An empirical study of smoothing techniques for language modeling. Computer Speech and Language\u00a013, 359\u2013393 (1999)","journal-title":"Computer Speech and Language"},{"key":"38_CR13","unstructured":"Stolcke, A.: Entropy-based pruning of backoff languge models. In: Proc. DARPA Broadcast News Transcription and Understanding Wksp., Lansdowne, VA, pp. 270\u2013274 (1998)"}],"container-title":["Lecture Notes in Computer Science","Machine Learning for Multimodal Interaction"],"original-title":[],"link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/11965152_38.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,1,13]],"date-time":"2025-01-13T04:28:25Z","timestamp":1736742505000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/11965152_38"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2006]]},"ISBN":["9783540692676","9783540692683"],"references-count":13,"URL":"https:\/\/doi.org\/10.1007\/11965152_38","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2006]]}}}