{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,22]],"date-time":"2025-03-22T08:27:40Z","timestamp":1742632060727,"version":"3.30.1"},"reference-count":41,"publisher":"Elsevier BV","issue":"1-3","license":[{"start":{"date-parts":[[1998,8,1]],"date-time":"1998-08-01T00:00:00Z","timestamp":901929600000},"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":[[1998,8]]},"DOI":"10.1016\/s0167-6393(98)00031-4","type":"journal-article","created":{"date-parts":[[2003,4,5]],"date-time":"2003-04-05T03:57:58Z","timestamp":1049515078000},"page":"97-116","source":"Crossref","is-referenced-by-count":31,"title":["Automatic segmentation of speech recorded in unknown noisy channel characteristics"],"prefix":"10.1016","volume":"25","author":[{"given":"Bryan L.","family":"Pellom","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"John H.L.","family":"Hansen","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"78","reference":[{"key":"10.1016\/S0167-6393(98)00031-4_BIB1","doi-asserted-by":"crossref","first-page":"1304","DOI":"10.1121\/1.1914702","article-title":"Effectiveness of linear prediction characteristics of the speech wave on automatic speaker identification and verification","volume":"55","author":"Atal","year":"1974","journal-title":"J. Acoust. Soc. Amer."},{"key":"10.1016\/S0167-6393(98)00031-4_BIB2","doi-asserted-by":"crossref","unstructured":"Berouti, M., Schwartz, R., Makhoul, J., 1979. Enhancement of speech corrupted by acoustic noise. In: Proceedings of IEEE International Conference on Acoust. Speech Signal Process., pp. 208\u2013211","DOI":"10.1109\/ICASSP.1979.1170788"},{"key":"10.1016\/S0167-6393(98)00031-4_BIB3","doi-asserted-by":"crossref","unstructured":"Bonafonte, A., Nogueiras, A., Rodriguez-Garro, A., 1996. Explicit segmentation of speech using Gaussian models. In: Proc. ICSLP, pp. 1269\u20131272","DOI":"10.1109\/ICSLP.1996.607841"},{"key":"10.1016\/S0167-6393(98)00031-4_BIB4","doi-asserted-by":"crossref","unstructured":"Brown, K., George, E., 1995. CTIMIT: A speech corpus for the cellular environment with applications to automatic speech recognition. In: Proceedings of IEEE International Conference on Acoust. Speech Signal Process., pp. 105\u2013108","DOI":"10.1109\/ICASSP.1995.479284"},{"issue":"4","key":"10.1016\/S0167-6393(98)00031-4_BIB5","doi-asserted-by":"crossref","first-page":"357","DOI":"10.1016\/0167-6393(93)90083-W","article-title":"Automatic segmentation and labeling of speech based on Hidden Markov Models","volume":"12","author":"Brugnara","year":"1993","journal-title":"Speech Communication"},{"issue":"2","key":"10.1016\/S0167-6393(98)00031-4_BIB6","doi-asserted-by":"crossref","first-page":"345","DOI":"10.1109\/89.279283","article-title":"Elimination of the musical noise phenomenon with the Ephraim and Malah noise suppressor","volume":"2","author":"Capp\u00e9","year":"1994","journal-title":"IEEE Trans. Speech Audio Process."},{"issue":"4","key":"10.1016\/S0167-6393(98)00031-4_BIB7","doi-asserted-by":"crossref","first-page":"357","DOI":"10.1109\/TASSP.1980.1163420","article-title":"Comparison of parametric representations for monosyllabic word recognition in continuously spoken sentences","volume":"ASSP-28","author":"Davis","year":"1980","journal-title":"IEEE Trans. Acoust. Speech Signal Process."},{"key":"10.1016\/S0167-6393(98)00031-4_BIB8","unstructured":"Deller, J., Proakis, J., Hansen, J., 1993. Discrete-Time Processing of Speech Signals. MacMillan Series for Prentice-Hall Publishers, New York"},{"key":"10.1016\/S0167-6393(98)00031-4_BIB9","doi-asserted-by":"crossref","unstructured":"Eisen, B., 1991. Reliability of speech segmentation and labeling at different levels of transcription. In: Proc. Eurospeech, Berlin, pp. 673\u2013676","DOI":"10.21437\/Eurospeech.1993-163"},{"key":"10.1016\/S0167-6393(98)00031-4_BIB10","doi-asserted-by":"crossref","unstructured":"Eisen, B., Tillman, H., Draxler, C., 1992. Consistency of judgements in manual labeling of phonetic segments: The distinction between clear and unclear cases. In: Proc. ICSLP, Banaff, Canada, pp. 871\u2013874","DOI":"10.21437\/ICSLP.1992-261"},{"issue":"10","key":"10.1016\/S0167-6393(98)00031-4_BIB11","doi-asserted-by":"crossref","first-page":"1526","DOI":"10.1109\/5.168664","article-title":"Statistical-model-based speech enhancement systems","volume":"80","author":"Ephraim","year":"1992","journal-title":"Proc. IEEE"},{"issue":"6","key":"10.1016\/S0167-6393(98)00031-4_BIB12","doi-asserted-by":"crossref","first-page":"1109","DOI":"10.1109\/TASSP.1984.1164453","article-title":"Speech enhancement using a minimum mean-square error short-time spectral amplitude estimator","volume":"ASSP-32","author":"Ephraim","year":"1984","journal-title":"IEEE Trans. Acoust. Speech Signal Process."},{"key":"10.1016\/S0167-6393(98)00031-4_BIB13","doi-asserted-by":"crossref","first-page":"231","DOI":"10.1016\/0167-6393(93)90093-Z","article-title":"Cepstral parameter compensation for HMM recognition in noise","volume":"12","author":"Gales","year":"1993","journal-title":"Speech Communication"},{"key":"10.1016\/S0167-6393(98)00031-4_BIB14","doi-asserted-by":"crossref","first-page":"289","DOI":"10.1006\/csla.1995.0014","article-title":"Robust speech recognition in additive and convolutional noise using parallel model combination","volume":"9","author":"Gales","year":"1995","journal-title":"Comput. Speech Language"},{"issue":"5","key":"10.1016\/S0167-6393(98)00031-4_BIB15","doi-asserted-by":"crossref","first-page":"352","DOI":"10.1109\/89.536929","article-title":"Robust continuous speech recognition using parallel model combination","volume":"4","author":"Gales","year":"1996","journal-title":"IEEE Trans. Speech Audio Process."},{"key":"10.1016\/S0167-6393(98)00031-4_BIB16","doi-asserted-by":"crossref","first-page":"155","DOI":"10.1016\/0885-2308(91)90022-I","article-title":"Word juncture modeling using phonological rules for HMM-based continuous speech recognition","volume":"5","author":"Giachin","year":"1991","journal-title":"Comput. Speech Language"},{"issue":"4","key":"10.1016\/S0167-6393(98)00031-4_BIB17","doi-asserted-by":"crossref","first-page":"795","DOI":"10.1109\/78.80901","article-title":"Constrained iterative speech enhancement with application to automatic speech recognition","volume":"39","author":"Hansen","year":"1991","journal-title":"IEEE Trans. Signal Process."},{"issue":"4","key":"10.1016\/S0167-6393(98)00031-4_BIB18","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 Process."},{"key":"10.1016\/S0167-6393(98)00031-4_BIB19","doi-asserted-by":"crossref","unstructured":"Hunt, A., Black, A., 1996. Unit selection in a concatenative speech synthesis system using a large speech database. In: Proceedings of IEEE International Conference on Acoust. Speech Signal Process., Atlanta, pp. 373\u2013376","DOI":"10.1109\/ICASSP.1996.541110"},{"key":"10.1016\/S0167-6393(98)00031-4_BIB20","doi-asserted-by":"crossref","first-page":"535","DOI":"10.1121\/1.1995189","article-title":"Line spectrum representation of linear prediction coefficients of speech signals","volume":"57","author":"Itakura","year":"1975","journal-title":"J. Acoust. Soc. Amer."},{"key":"10.1016\/S0167-6393(98)00031-4_BIB21","doi-asserted-by":"crossref","unstructured":"Jankowski, C., Kalyanswamy, A., Basson, S., Spitz, J., 1990. NTIMIT: A phonetically balanced, continuous speech, telephone bandwidth speech database. In: Proceedings of IEEE International Conference on Acoust. Speech Signal Process., pp. 109\u2013112","DOI":"10.1109\/ICASSP.1990.115550"},{"issue":"11","key":"10.1016\/S0167-6393(98)00031-4_BIB22","doi-asserted-by":"crossref","first-page":"1641","DOI":"10.1109\/29.46546","article-title":"Speaker-independent phone recognition using hidden Markov models","volume":"ASSP-37","author":"Lee","year":"1989","journal-title":"IEEE Trans. Acoust. Speech Signal Process."},{"key":"10.1016\/S0167-6393(98)00031-4_BIB23","doi-asserted-by":"crossref","unstructured":"Leung, H., Zue, V., 1984. A procedure for automatic alignment of phonetic transcriptions with continuous speech. In: Proceedings of IEEE International Conference on Acoust. Speech Signal Process., 1984, pp. 2.7.1\u20132.7.4","DOI":"10.1109\/ICASSP.1984.1172426"},{"issue":"3","key":"10.1016\/S0167-6393(98)00031-4_BIB24","doi-asserted-by":"crossref","first-page":"197","DOI":"10.1109\/TASSP.1978.1163086","article-title":"All-pole modeling of degraded speech","volume":"26","author":"Lim","year":"1978","journal-title":"IEEE Trans. Acoust. Speech Signal Process."},{"issue":"2\u20133","key":"10.1016\/S0167-6393(98)00031-4_BIB25","doi-asserted-by":"crossref","first-page":"215","DOI":"10.1016\/0167-6393(92)90016-Z","article-title":"Experiments with a Nonlinear Spectral Subtractor (NSS), Hidden Markov Models and the projection, for robust speech recognition in cars","volume":"11","author":"Lockwood","year":"1992","journal-title":"Speech Communication"},{"key":"10.1016\/S0167-6393(98)00031-4_BIB26","doi-asserted-by":"crossref","unstructured":"Ljolje, A., Riley, M.D., 1991. Automatic segmentation and labeling of speech. In: Proceedings of IEEE International Conference on Acoust. Speech Signal Process., Toronto, pp. 473\u2013476","DOI":"10.1109\/ICASSP.1991.150379"},{"key":"10.1016\/S0167-6393(98)00031-4_BIB27","unstructured":"Marzal, A., Vidal, E., 1990. A review of new approaches for automatic segmentation of speech signals. In: Proc. Eusipco 1990, Barcelona, pp. 43\u201353"},{"issue":"4","key":"10.1016\/S0167-6393(98)00031-4_BIB28","doi-asserted-by":"crossref","first-page":"590","DOI":"10.1109\/89.326617","article-title":"Training issues and channel equalization techniques for the construction of telephone acoustic models using a high-quality speech corpus","volume":"2","author":"Neumeyer","year":"1994","journal-title":"IEEE Trans. Speech Audio Process."},{"key":"10.1016\/S0167-6393(98)00031-4_BIB29","unstructured":"NIST, 1989. National Institute of Standards and Technology (NIST), Getting started with the DARPA TIMIT CD-ROM: An acoustic phonetic continuous speech database, National Institute of Standards and Technology (NIST), Gaithersburg, Maryland"},{"key":"10.1016\/S0167-6393(98)00031-4_BIB30","doi-asserted-by":"crossref","unstructured":"Petek, B., Andersen, O., Dalsgaard, P., 1996. On the robust automatic segmentation of spontaneous speech. In: Proc. ICSLP, pp. 913\u2013916","DOI":"10.1109\/ICSLP.1996.607750"},{"issue":"1","key":"10.1016\/S0167-6393(98)00031-4_BIB31","doi-asserted-by":"crossref","first-page":"19","DOI":"10.1109\/TSA.1996.481449","article-title":"Signal bias removal by maximum likelihood estimation for robust telephone speech recognition","volume":"4","author":"Rahim","year":"1996","journal-title":"IEEE Trans. Speech Audio Process."},{"key":"10.1016\/S0167-6393(98)00031-4_BIB32","doi-asserted-by":"crossref","unstructured":"Reynolds, D., 1997. HTIMIT and LLHDB: Speech corpora for the study of handset transducer effects. IEEE International Conference on Acoust. Speech Signal Process., pp. 1535\u20131538","DOI":"10.1109\/ICASSP.1997.596243"},{"key":"10.1016\/S0167-6393(98)00031-4_BIB33","doi-asserted-by":"crossref","unstructured":"Svendson, T., Soong, F.K., 1987. On the automatic segmentation of speech signals. In: Proceedings of IEEE International Conference on Acoust. Speech Signal Process., pp. 77\u201380","DOI":"10.1109\/ICASSP.1987.1169628"},{"key":"10.1016\/S0167-6393(98)00031-4_BIB34","doi-asserted-by":"crossref","unstructured":"Torkkola, K., 1988. Automatic alignment of speech with phonetic transcriptions in real time. In: Proceedings of IEEE International Conference on Acoust. Speech Signal Process., pp. 611\u2013614","DOI":"10.1109\/ICASSP.1988.196659"},{"issue":"4","key":"10.1016\/S0167-6393(98)00031-4_BIB35","doi-asserted-by":"crossref","first-page":"1008","DOI":"10.1109\/78.80941","article-title":"Automatic segmentation of speech","volume":"39","author":"van Hemert","year":"1991","journal-title":"IEEE Trans. Signal Process."},{"key":"10.1016\/S0167-6393(98)00031-4_BIB36","doi-asserted-by":"crossref","unstructured":"Varga, A.P., Moore, R.K., 1990. Hidden Markov model decomposition of speech and noise. In: IEEE International Conference on Acoust. Speech Signal Process., pp. 845\u2013848","DOI":"10.1109\/ICASSP.1990.115970"},{"key":"10.1016\/S0167-6393(98)00031-4_BIB37","doi-asserted-by":"crossref","unstructured":"Vorstermans, A., Martens, J.P., Van Coile, B., 1995. Fast automatic segmentation and labeling: Results on TIMIT and EUROM0. In: Proc. Eurospeech, pp. 1397\u20131400","DOI":"10.21437\/Eurospeech.1995-224"},{"issue":"4","key":"10.1016\/S0167-6393(98)00031-4_BIB38","doi-asserted-by":"crossref","first-page":"271","DOI":"10.1016\/S0167-6393(96)00037-4","article-title":"Automatic segmentation and labeling of multi-lingual speech data","volume":"19","author":"Vorstermans","year":"1996","journal-title":"Speech Communication"},{"key":"10.1016\/S0167-6393(98)00031-4_BIB39","doi-asserted-by":"crossref","unstructured":"Wesenick, M., Kipp, A., 1996. Estimating the quality of phonetic transcriptions and segmentations of speech signals. In: Proc. ICSLP, pp. 129\u2013132","DOI":"10.1109\/ICSLP.1996.607054"},{"key":"10.1016\/S0167-6393(98)00031-4_BIB40","unstructured":"Wightman, C., Talkin, D., 1994. The aligner: A system for automatic alignment of English text and speech. Software Documentation, Entropic Research Laboratory, Washington DC, USA"},{"key":"10.1016\/S0167-6393(98)00031-4_BIB41","doi-asserted-by":"crossref","unstructured":"Wightman, C., Talkin, D., 1997. The aligner: Text-to-speech alignment using Markov models. In: Van Santen, Sproat, Olive, Hirschberg (Eds.), Progress in Speech Synthesis. Springer, New York, pp. 313\u2013323","DOI":"10.1007\/978-1-4612-1894-4_25"}],"container-title":["Speech Communication"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0167639398000314?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0167639398000314?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2024,12,4]],"date-time":"2024-12-04T08:56:27Z","timestamp":1733302587000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S0167639398000314"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[1998,8]]},"references-count":41,"journal-issue":{"issue":"1-3","published-print":{"date-parts":[[1998,8]]}},"alternative-id":["S0167639398000314"],"URL":"https:\/\/doi.org\/10.1016\/s0167-6393(98)00031-4","relation":{},"ISSN":["0167-6393"],"issn-type":[{"type":"print","value":"0167-6393"}],"subject":[],"published":{"date-parts":[[1998,8]]}}}