{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2023,2,1]],"date-time":"2023-02-01T13:16:07Z","timestamp":1675257367111},"reference-count":50,"publisher":"Elsevier BV","issue":"1-2","license":[{"start":{"date-parts":[[2002,5,1]],"date-time":"2002-05-01T00:00:00Z","timestamp":1020211200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Speech Communication"],"published-print":{"date-parts":[[2002,5]]},"DOI":"10.1016\/s0167-6393(01)00058-9","type":"journal-article","created":{"date-parts":[[2002,10,15]],"date-time":"2002-10-15T01:51:46Z","timestamp":1034646706000},"page":"27-45","source":"Crossref","is-referenced-by-count":21,"title":["Connectionist speech recognition of Broadcast News"],"prefix":"10.1016","volume":"37","author":[{"given":"A.J.","family":"Robinson","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"G.D.","family":"Cook","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"D.P.W.","family":"Ellis","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"E.","family":"Fosler-Lussier","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"S.J.","family":"Renals","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"D.A.G.","family":"Williams","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"78","reference":[{"key":"10.1016\/S0167-6393(01)00058-9_BIB1","series-title":"Proc. Internat. Conf. on Spoken Language Processing","first-page":"2719","article-title":"Acoustic confidence measures for segmenting broadcast news","author":"Barker","year":"1998"},{"key":"10.1016\/S0167-6393(01)00058-9_BIB2","series-title":"Proc. Internat. Conf. on Spoken Language Processing","first-page":"775","article-title":"Improving posterior confidence measures in hybrid HMM\/ANN speech recognition systems","author":"Bernardis","year":"1998"},{"key":"10.1016\/S0167-6393(01)00058-9_BIB3","series-title":"Continuous Speech Recognition: A Hybrid Approach","author":"Bourlard","year":"1994"},{"key":"10.1016\/S0167-6393(01)00058-9_BIB4","doi-asserted-by":"crossref","unstructured":"Bourlard, H., Morgan, N., 1996. Hybrid connectionist models for continuous speech recognition. In: Lee, C.-H., Soong, F.K., Paliwal, K.K. (Eds.)., Automatic Speech and Speaker Recognition: Advanced Topics. Kluwer Academic Publishers, Dordrecht, Chapter 11, pp. 259\u2013283","DOI":"10.1007\/978-1-4613-1367-0_11"},{"key":"10.1016\/S0167-6393(01)00058-9_BIB5","series-title":"Proc. IEEE Internat. Conf. on Acoustics Speech and Signal Processing","first-page":"373","article-title":"Optimizing recognition and rejection performance in wordspotting systems","author":"Bourlard","year":"1994"},{"key":"10.1016\/S0167-6393(01)00058-9_BIB6","series-title":"Eurospeech-97","first-page":"2707","article-title":"Statistical language modeling using the CMU-Cambridge toolkit","author":"Clarkson","year":"1997"},{"key":"10.1016\/S0167-6393(01)00058-9_BIB7","series-title":"Proc. IEEE Internat. Conf. on Acoustics, Speech, and Signal Processing","first-page":"917","article-title":"Transcribing broadcast news with the 1997 ABBOT system","author":"Cook","year":"1998"},{"key":"10.1016\/S0167-6393(01)00058-9_BIB8","series-title":"Proc. DARPA Speech Recognition Workshop","first-page":"79","article-title":"Transcription of broadcast television and radio news: the 1996 Abbot system","author":"Cook","year":"1997"},{"key":"10.1016\/S0167-6393(01)00058-9_BIB9","series-title":"Proc. IEEE Internat. Conf. on Acoustics, Speech, and Signal Processing","first-page":"511","article-title":"Confidence measures for the SwitchBoard database","author":"Cox","year":"1996"},{"key":"10.1016\/S0167-6393(01)00058-9_BIB10","series-title":"Proc. IEEE Internat. Conf. on Acoustics, Speech, and Signal Processing","first-page":"221","article-title":"Understanding and improving speech recognition performance through the use of diagnostic tools","author":"Eide","year":"1995"},{"key":"10.1016\/S0167-6393(01)00058-9_BIB11","series-title":"Eurospeech-97","first-page":"2379","article-title":"Speaking mode dependent pronunciation modeling in large vocabulary conversational speech recognition","author":"Finke","year":"1997"},{"key":"10.1016\/S0167-6393(01)00058-9_BIB12","series-title":"IEEE Workshop on Automatic Speech Recognition and Understanding","article-title":"A post-processing system to yield reduced word error rates: recognizer output voting error reduction (ROVER)","author":"Fiscus","year":"1997"},{"key":"10.1016\/S0167-6393(01)00058-9_BIB13","doi-asserted-by":"crossref","unstructured":"Fosler-Lussier, J.E., 1999. Dynamic pronunciation models for automatic speech recognition. Ph.D. thesis, University of California, Berkeley","DOI":"10.1016\/S0167-6393(99)00035-7"},{"key":"10.1016\/S0167-6393(01)00058-9_BIB14","series-title":"Proc. DARPA Broadcast News Workshop","article-title":"Not just what, but also when: guided automatic pronunciation modeling for broadcast news","author":"Fosler-Lussier","year":"1999"},{"key":"10.1016\/S0167-6393(01)00058-9_BIB15","series-title":"Proc. Internat. Conf. on Spoken Language Processing","article-title":"Effective structural adaptation of LVCSR systems to unseen domains using hierarchical connectionist acoustic models","author":"Fritsch","year":"1998"},{"key":"10.1016\/S0167-6393(01)00058-9_BIB16","series-title":"Proc. IEEE Internat. Conf. on Acoustics, Speech, and Signal Processing","first-page":"572","article-title":"A tree-search strategy for large vocabulary continuous speech recognition","author":"Gopalakrishnan","year":"1995"},{"key":"10.1016\/S0167-6393(01)00058-9_BIB17","series-title":"Proc. Broadcast News Transcription Understanding Workshop","first-page":"133","article-title":"Segment generation and clustering in the HTK broadcast news transcription system","author":"Hain","year":"1998"},{"key":"10.1016\/S0167-6393(01)00058-9_BIB18","doi-asserted-by":"crossref","first-page":"1738","DOI":"10.1121\/1.399423","article-title":"Perceptual linear predictive PLP analysis of speech","volume":"87","author":"Hermansky","year":"1990","journal-title":"J. Acoust. Soc. Am."},{"issue":"4","key":"10.1016\/S0167-6393(01)00058-9_BIB19","doi-asserted-by":"crossref","first-page":"578","DOI":"10.1109\/89.326616","article-title":"RASTA processing of speech","volume":"2","author":"Hermansky","year":"1994","journal-title":"IEEE Trans. Speech Audio Processing"},{"key":"10.1016\/S0167-6393(01)00058-9_BIB20","series-title":"Eurospeech-95","first-page":"1645","article-title":"New words: effect on recognition performance and incorporation issues","author":"Hetherington","year":"1995"},{"key":"10.1016\/S0167-6393(01)00058-9_BIB21","series-title":"Proc. IEEE Internat. Conf. on Acoustics, Speech, and Signal Processing","first-page":"401","article-title":"Recent improvements to the abbot large vocabulary CSR system","author":"Hochberg","year":"1995"},{"key":"10.1016\/S0167-6393(01)00058-9_BIB22","doi-asserted-by":"crossref","first-page":"675","DOI":"10.1147\/rd.136.0675","article-title":"Fast sequential decoding algorithm using a stack","volume":"13","author":"Jelinek","year":"1969","journal-title":"IBM J. Res. Develop."},{"key":"10.1016\/S0167-6393(01)00058-9_BIB23","unstructured":"Kershaw, D., 1996. Phonetic context-dependency in a hybrid ANN\/HMM speech recognition system. Ph.D. thesis, Cambridge University Engineering Department"},{"key":"10.1016\/S0167-6393(01)00058-9_BIB24","unstructured":"Kingsbury, B.E.D., 1998. Perceptually inspired signal processing strategies for robust speech recognition in reverberant environments. Ph.D. thesis, University of California, Berkeley, CA"},{"key":"10.1016\/S0167-6393(01)00058-9_BIB25","doi-asserted-by":"crossref","first-page":"117","DOI":"10.1016\/S0167-6393(98)00032-6","article-title":"Robust speech recognition using the modulation spectrogram","volume":"25","author":"Kingsbury","year":"1998","journal-title":"Speech Communication"},{"key":"10.1016\/S0167-6393(01)00058-9_BIB26","series-title":"The Auditory Processing of Speech: From Sounds to Words","first-page":"85","article-title":"Temporal resolution and modulation analysis in models of the auditory system","author":"Kohlrausch","year":"1992"},{"key":"10.1016\/S0167-6393(01)00058-9_BIB27","doi-asserted-by":"crossref","first-page":"171","DOI":"10.1006\/csla.1995.0010","article-title":"Maximum likelihood linear regression for speaker adaptation of continuous density hidden Markov models","volume":"9","author":"Leggetter","year":"1995","journal-title":"Computer Speech Language"},{"key":"10.1016\/S0167-6393(01)00058-9_BIB28","series-title":"Trends in Speech Recognition","article-title":"The Harpy speech understanding system","author":"Lowerre","year":"1980"},{"key":"10.1016\/S0167-6393(01)00058-9_BIB29","series-title":"Proc. IEEE Internat. Conf. on Acoustics, Speech, and Signal Processing","first-page":"42.5.1","article-title":"An information theoretic approach to the automatic determination of phonemic baseforms","author":"Lucassen","year":"1984"},{"key":"10.1016\/S0167-6393(01)00058-9_BIB30","doi-asserted-by":"crossref","first-page":"248","DOI":"10.1016\/0743-7315(92)90067-W","article-title":"The ring array processor (RAP): a multiprocessing peripheral for connectionist applications","volume":"14","author":"Morgan","year":"1992","journal-title":"J. Parallel Distributed Comput."},{"key":"10.1016\/S0167-6393(01)00058-9_BIB31","series-title":"Proc. IEEE Internat. Conf. on Acoustics, Speech, and Signal Processing","first-page":"883","article-title":"Word-based confidence measures as a guide for stack search in speech recognition","author":"Neti","year":"1997"},{"key":"10.1016\/S0167-6393(01)00058-9_BIB32","series-title":"Eurospeech-95","first-page":"2171","article-title":"Speaker adaptation for hybrid HMM-ANN continuous speech recognition system","author":"Neto","year":"1995"},{"key":"10.1016\/S0167-6393(01)00058-9_BIB33","series-title":"Problem Solving Methods of Artificial Intelligence","author":"Nilsson","year":"1971"},{"key":"10.1016\/S0167-6393(01)00058-9_BIB34","unstructured":"Odell, J.J., 1995. The use of context in large vocabulary speech recognition. Ph.D. thesis, University of Cambridge"},{"key":"10.1016\/S0167-6393(01)00058-9_BIB35","unstructured":"Pallett, D., 2002. The broadcast news task fix. Speech Communication"},{"key":"10.1016\/S0167-6393(01)00058-9_BIB36","series-title":"Proc. IEEE Internat. Conf. on Acoustics, Speech, and Signal Processing","first-page":"25","article-title":"An efficient A* stack decoder algorithm for continuous speech recognition with a stochastic language model","author":"Paul","year":"1992"},{"key":"10.1016\/S0167-6393(01)00058-9_BIB37","doi-asserted-by":"crossref","first-page":"4","DOI":"10.1109\/97.475820","article-title":"Phone deactivation pruning in large vocabulary continuous speech recognition","volume":"3","author":"Renals","year":"1996","journal-title":"IEEE Signal Processing Lett."},{"key":"10.1016\/S0167-6393(01)00058-9_BIB38","series-title":"Proc. IEEE Internat. Conf. on Acoustics, Speech, and Signal Processing","first-page":"596","article-title":"Efficient search using posterior phone probability estimates","author":"Renals","year":"1995"},{"key":"10.1016\/S0167-6393(01)00058-9_BIB39","doi-asserted-by":"crossref","first-page":"542","DOI":"10.1109\/89.784107","article-title":"Start-synchronous search for large vocabulary continuous speech recognition","volume":"7","author":"Renals","year":"1999","journal-title":"IEEE Trans. Speech Audio Processing"},{"key":"10.1016\/S0167-6393(01)00058-9_BIB40","series-title":"ESCA Tutorial and Research Workshop on Modeling Pronunciation Variation for Automatic Speech Recognition","first-page":"109","article-title":"Stochastic pronunciation modelling from hand-labelled phonetic corpora","author":"Riley","year":"1998"},{"key":"10.1016\/S0167-6393(01)00058-9_BIB41","doi-asserted-by":"crossref","first-page":"298","DOI":"10.1109\/72.279192","article-title":"The application of recurrent nets to phone probability estimation","volume":"5","author":"Robinson","year":"1994","journal-title":"IEEE Trans. Neural Networks"},{"key":"10.1016\/S0167-6393(01)00058-9_BIB42","series-title":"Proc. IEEE Internat. Conf. on Acoustics, Speech, and Signal Processing","first-page":"829","article-title":"Time-first search for large vocabulary speech recognition","author":"Robinson","year":"1998"},{"key":"10.1016\/S0167-6393(01)00058-9_BIB43","doi-asserted-by":"crossref","unstructured":"Robinson, T., Hochberg, M., Renals, R., 1996. The use of recurrent networks in continuous speech recognition. In: Lee, C.-H., Soong, F.K., Paliwal, K.K. (Eds.) Automatic Speech and Speaker Recognition: Advanced Topics. Kluwer Academic Publishers, Dordrecht, Chapter 10, pp. 233\u2013258","DOI":"10.1007\/978-1-4613-1367-0_10"},{"key":"10.1016\/S0167-6393(01)00058-9_BIB44","doi-asserted-by":"crossref","unstructured":"Schwartz, R., Nguyen, L., Makhoul, J., 1996. Multiple-pass search strategies. In: Lee, C.-H., Soong, F.K., Paliwal, K.K. (Eds.) Automatic Speech and Speaker Recognition: Advanced Topics. Kluwer Academic Publishers, Dordrecht, Chapter 18, pp. 429\u2013456","DOI":"10.1007\/978-1-4613-1367-0_18"},{"key":"10.1016\/S0167-6393(01)00058-9_BIB45","series-title":"Proc. Speech Recognition Workshop","first-page":"97","article-title":"Automatic segmentation, classification and clustering of broadcast news audio","author":"Siegler","year":"1997"},{"issue":"3","key":"10.1016\/S0167-6393(01)00058-9_BIB46","doi-asserted-by":"crossref","first-page":"79","DOI":"10.1109\/2.485896","article-title":"SPERT-II: a vector microprocessor system","volume":"29","author":"Wawrzynek","year":"1996","journal-title":"IEEE Computer"},{"key":"10.1016\/S0167-6393(01)00058-9_BIB47","first-page":"687","article-title":"Speech\/music discrimination based on posterior probability features","volume":"Vol. II","author":"Williams","year":"1999"},{"key":"10.1016\/S0167-6393(01)00058-9_BIB48","series-title":"ESCA Workshop on Modeling Pronunciation Variation for Automatic Speech Recognition","first-page":"151","article-title":"Confidence measures for evaluating pronunciation models","author":"Williams","year":"1998"},{"key":"10.1016\/S0167-6393(01)00058-9_BIB49","doi-asserted-by":"crossref","first-page":"395","DOI":"10.1006\/csla.1999.0129","article-title":"Confidence measures from local posterior probability estimates","volume":"13","author":"Williams","year":"1999","journal-title":"Computer Speech Language"},{"key":"10.1016\/S0167-6393(01)00058-9_BIB50","unstructured":"Wu, S.-L., 1998. Incorporating information from syllable-length time scales into automatic speech recognition. Ph.D. thesis, University of California, Berkeley"}],"container-title":["Speech Communication"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0167639301000589?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0167639301000589?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2019,5,2]],"date-time":"2019-05-02T05:29:36Z","timestamp":1556774976000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S0167639301000589"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2002,5]]},"references-count":50,"journal-issue":{"issue":"1-2","published-print":{"date-parts":[[2002,5]]}},"alternative-id":["S0167639301000589"],"URL":"https:\/\/doi.org\/10.1016\/s0167-6393(01)00058-9","relation":{},"ISSN":["0167-6393"],"issn-type":[{"value":"0167-6393","type":"print"}],"subject":[],"published":{"date-parts":[[2002,5]]}}}