{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,15]],"date-time":"2026-05-15T03:37:44Z","timestamp":1778816264953,"version":"3.51.4"},"reference-count":48,"publisher":"Elsevier BV","issue":"3-4","license":[{"start":{"date-parts":[[2002,7,1]],"date-time":"2002-07-01T00:00:00Z","timestamp":1025481600000},"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":[[2002,7]]},"DOI":"10.1016\/s0167-6393(01)00020-6","type":"journal-article","created":{"date-parts":[[2002,10,15]],"date-time":"2002-10-15T01:51:46Z","timestamp":1034646706000},"page":"303-319","source":"Crossref","is-referenced-by-count":103,"title":["Combining acoustic and articulatory feature information for robust speech recognition"],"prefix":"10.1016","volume":"37","author":[{"given":"Katrin","family":"Kirchhoff","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Gernot A","family":"Fink","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Gerhard","family":"Sagerer","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"78","reference":[{"key":"10.1016\/S0167-6393(01)00020-6_BIB1","doi-asserted-by":"crossref","unstructured":"Berouti, M., Schwartz, R., Makhoul, J., 1979. Enhancement of speech corrupted by acoustic noise. In: Proc. Internat. Conf. Acoust. Speech Signal Process., pp. 208\u2013211","DOI":"10.1109\/ICASSP.1979.1170788"},{"key":"10.1016\/S0167-6393(01)00020-6_BIB2","doi-asserted-by":"crossref","unstructured":"Bitar, N.N., Espy-Wilson, C.Y., 1996. Knowledge-based parameters for HMM speech recognition. In: Proc. Internat. Conf. Acoust. Speech Signal Process., pp. 29\u201332","DOI":"10.1109\/ICASSP.1996.540282"},{"key":"10.1016\/S0167-6393(01)00020-6_BIB3","doi-asserted-by":"crossref","unstructured":"Bitar, N.N., Espy-Wilson, C.Y., 1997. The design of acoustic parameters for speaker-independent speech recognition. In: Proc. European Conf. Speech Comm. Technol., pp. 1239\u20131242","DOI":"10.21437\/Eurospeech.1997-33"},{"key":"10.1016\/S0167-6393(01)00020-6_BIB4","doi-asserted-by":"crossref","first-page":"229","DOI":"10.1006\/csla.1993.1012","article-title":"Discriminative feature selection for speech recognition","volume":"7","author":"Bocchieri","year":"1993","journal-title":"Comput. Speech Language"},{"key":"10.1016\/S0167-6393(01)00020-6_BIB5","series-title":"Advances in Speech Signal Processing","first-page":"309","article-title":"Speech enhancement in the 1980s: noise suppression with pattern matching","author":"Boll","year":"1992"},{"key":"10.1016\/S0167-6393(01)00020-6_BIB6","unstructured":"Chase, L.L., 1997. Error-responsive feedback mechanisms for speech recognizers. Ph.D thesis. Carnegie-Mellon University"},{"key":"10.1016\/S0167-6393(01)00020-6_BIB7","doi-asserted-by":"crossref","unstructured":"Cohn, R.P., 1992. Robust voiced\/unvoiced speech classification using a neural net. In: Proc. Internat. Conf. Acoust. Speech Signal Process., pp. 473\u2013476","DOI":"10.1109\/ICASSP.1991.150370"},{"key":"10.1016\/S0167-6393(01)00020-6_BIB8","doi-asserted-by":"crossref","unstructured":"Cole, R.A., Noel, M., Lander, T., Durham, T., 1995. New telephone speech corpora at CLSU. In: Proc. European Conf. Speech Comm. Technol., pp. 821\u2013824","DOI":"10.21437\/Eurospeech.1995-188"},{"key":"10.1016\/S0167-6393(01)00020-6_BIB9","unstructured":"Craven, M.W., 1996. Extracting comprehensible models from trained neural networks. Ph.D thesis. University of Wisconsin-Madison"},{"issue":"6","key":"10.1016\/S0167-6393(01)00020-6_BIB10","doi-asserted-by":"crossref","first-page":"3058","DOI":"10.1121\/1.404202","article-title":"Structural design of hidden Markov model speech recognizer using multivalued phonetic features: comparison with segmental speech units","volume":"92","author":"Deng","year":"1992","journal-title":"J. Acoust. Soc. Amer."},{"key":"10.1016\/S0167-6393(01)00020-6_BIB11","doi-asserted-by":"crossref","unstructured":"Deng, L., Sun, D., 1994a. Phonetic classification and recognition using HMM representation of overlapping articulator features for all classes of English sounds. In: Proc. Internat. Conf. Acoust. Speech Signal Process., pp. 45\u201347","DOI":"10.1109\/ICASSP.1994.389359"},{"issue":"5","key":"10.1016\/S0167-6393(01)00020-6_BIB12","doi-asserted-by":"crossref","first-page":"2702","DOI":"10.1121\/1.409839","article-title":"A statistical approach to ASR using atomic units constructed from overlapping articulatory features","volume":"95","author":"Deng","year":"1994","journal-title":"J. Acoust. Soc. Amer."},{"key":"10.1016\/S0167-6393(01)00020-6_BIB13","doi-asserted-by":"crossref","unstructured":"Dupont, S., Luettin, J., 1998. Using the multi-stream approach for continuous audio-visual speech recognition: experiments on the M2VTS database. In: Proc. Internat. Conf. Spoken Language Process., pp. 1283\u20131286","DOI":"10.21437\/ICSLP.1998-276"},{"key":"10.1016\/S0167-6393(01)00020-6_BIB14","doi-asserted-by":"crossref","unstructured":"Eide, E., Rohlicek, J.R., Gish, H., Milter, S., 1993. A linguistic feature representation of the speech waveform. In: Proc. Internat. Conf. Acoust. Speech Signal Process., pp. 483\u2013486","DOI":"10.1109\/ICASSP.1993.319347"},{"key":"10.1016\/S0167-6393(01)00020-6_BIB15","doi-asserted-by":"crossref","unstructured":"Elenius, K., Tacacs, G., 1991. Phoneme recognition with an artificial neural network. In: Proc. European Conf. Speech Comm. Technol., pp. 121\u2013124","DOI":"10.1016\/B978-0-444-89178-5.50148-2"},{"issue":"4","key":"10.1016\/S0167-6393(01)00020-6_BIB16","doi-asserted-by":"crossref","first-page":"2500","DOI":"10.1121\/1.417358","article-title":"An HMM-based speech recognizer using overlapping articulatory features","volume":"100","author":"Erler","year":"1996","journal-title":"J. Acoust. Soc. Amer."},{"key":"10.1016\/S0167-6393(01)00020-6_BIB17","doi-asserted-by":"crossref","unstructured":"Fink, G.A., 1999. Developing HMM-based recognizers with ESMERALDA. In: V\u00e1clav, Petr Sojka (Eds.), Lecture Notes in Artificial Intelligence, Vol. 1692. Springer, Berlin, pp. 229\u2013234","DOI":"10.1007\/3-540-48239-3_42"},{"key":"10.1016\/S0167-6393(01)00020-6_BIB18","doi-asserted-by":"crossref","unstructured":"Fiscus, J.G., 1997. A post-processing system to yield reduced word error rates: Recognizer output voting error reduction (ROVER). In: Proc. IEEE Workshop Automatic Speech Recognition Understanding. Santa Barbara, CA","DOI":"10.1109\/ASRU.1997.659110"},{"key":"10.1016\/S0167-6393(01)00020-6_BIB19","doi-asserted-by":"crossref","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(01)00020-6_BIB20","doi-asserted-by":"crossref","unstructured":"Greenberg, S., Kingsbury, B.E.D., 1997. The modulation spectrogram: in pursuit of an invariant representation of speech. In: Proc. Internat. Conf. Acoust. Speech Signal Process., Vol. 2. pp. 1647\u20131650","DOI":"10.1109\/ICASSP.1997.598826"},{"key":"10.1016\/S0167-6393(01)00020-6_BIB21","doi-asserted-by":"crossref","unstructured":"Halberstadt, A.K., Glass, J.R., 1998. Heterogeneous measurements and multiple classifiers for speech recognition. In: Proc. Internat. Conf. Spoken Language Process., pp. 995\u2013998","DOI":"10.21437\/ICSLP.1998-522"},{"issue":"4","key":"10.1016\/S0167-6393(01)00020-6_BIB22","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(01)00020-6_BIB23","doi-asserted-by":"crossref","unstructured":"Jiang, L., Huang, X., 1999. Unified decoding and feature representation for improved speech recognition. In: Proc. European Conf. Speech Comm. Technol","DOI":"10.21437\/Eurospeech.1999-340x"},{"issue":"12","key":"10.1016\/S0167-6393(01)00020-6_BIB24","doi-asserted-by":"crossref","first-page":"3043","DOI":"10.1109\/78.175747","article-title":"Discriminative learning for minimum error classification","volume":"40","author":"Juang","year":"1992","journal-title":"IEEE Trans. Signal Process."},{"key":"10.1016\/S0167-6393(01)00020-6_BIB25","doi-asserted-by":"crossref","unstructured":"Kanadera, N., Hermansky, H., Arai, T., 1998. On properties of the modulation spectrum for robust automatic speech recognition. In: Proc. Internat. Conf. Acoust. Speech Signal Process","DOI":"10.1109\/ICASSP.1998.675339"},{"key":"10.1016\/S0167-6393(01)00020-6_BIB26","doi-asserted-by":"crossref","unstructured":"Kingsbury, B.E.D., Morgan, N., 1997. Recognizing reverberant speech with RASTA-PLP. Proc. Internat. Conf. Acoust. Speech Signal Process","DOI":"10.1109\/ICASSP.1997.596174"},{"key":"10.1016\/S0167-6393(01)00020-6_BIB27","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":"2","author":"Kingsbury","year":"1998","journal-title":"Speech Communication"},{"key":"10.1016\/S0167-6393(01)00020-6_BIB28","unstructured":"Kirchhoff, K., 1999. Robust speech recognition using articulatory information. Ph.D thesis. Bielefeld University"},{"key":"10.1016\/S0167-6393(01)00020-6_BIB29","doi-asserted-by":"crossref","unstructured":"Kirchhoff, K., Bilmes, J., 1999. Dynamic classifier combination in hybrid speech recognition systems using utterance-level confidence values. In: Proc. Internat. Conf. Acoust. Speech Signal Process","DOI":"10.1109\/ICASSP.1999.759761"},{"issue":"3","key":"10.1016\/S0167-6393(01)00020-6_BIB30","doi-asserted-by":"crossref","first-page":"226","DOI":"10.1109\/34.667881","article-title":"On combining classifiers","volume":"20","author":"Kittler","year":"1998","journal-title":"IEEE Trans. Pattern Anal. Machine Intell."},{"key":"10.1016\/S0167-6393(01)00020-6_BIB31","unstructured":"Kohler, K., Lex, G., P\u00e4tzold, M., Schefers, M., Simpson, A., Thon, W., 1994. Handbuch zur datenaufnahmen and transliteration in TP14 von VERBMOBIL \u2013 3.0. Verbmobil technical report 11, IPDS Kiel"},{"key":"10.1016\/S0167-6393(01)00020-6_BIB32","series-title":"Machine Learning: Proceedings of the Thirteenth International Conference","first-page":"281","article-title":"Toward optimal feature selection","author":"Koller","year":"1996"},{"key":"10.1016\/S0167-6393(01)00020-6_BIB33","doi-asserted-by":"crossref","unstructured":"Krstulovic, S., 1999. LPC-based inversion of the DRM articulatory model. In: Proc. European Conf. Speech Comm. Technol","DOI":"10.21437\/Eurospeech.1999-35"},{"key":"10.1016\/S0167-6393(01)00020-6_BIB34","series-title":"Automatic Speech Recognition: The Development of the SPHINX System","author":"Lee","year":"1989"},{"key":"10.1016\/S0167-6393(01)00020-6_BIB35","doi-asserted-by":"crossref","first-page":"84","DOI":"10.1109\/TCOM.1980.1094577","article-title":"An algorithm for vector quantizer design","volume":"28","author":"Linde","year":"1980","journal-title":"IEEE Trans. Comm."},{"key":"10.1016\/S0167-6393(01)00020-6_BIB36","doi-asserted-by":"crossref","unstructured":"McMahon, P., Court, P., 1998. Vaseghi, S., Discriminative weighning of multi-resolution subband cepstral features for speech recognition. In: Proc. Internat. Conf. Spoken Language Process., pp. 1055\u20131058","DOI":"10.21437\/ICSLP.1998-537"},{"issue":"3","key":"10.1016\/S0167-6393(01)00020-6_BIB37","doi-asserted-by":"crossref","first-page":"24","DOI":"10.1109\/79.382443","article-title":"Continuous speech recognition","volume":"12","author":"Morgan","year":"1995","journal-title":"IEEE Signal Process. Magaz."},{"issue":"2","key":"10.1016\/S0167-6393(01)00020-6_BIB38","doi-asserted-by":"crossref","first-page":"688","DOI":"10.1121\/1.403994","article-title":"In ferring articulation and recognizing gestures from acoustics with a neural network trained on X-ray microbeam data","volume":"92","author":"Papcun","year":"1992","journal-title":"J. Acoust. Soc. Amer."},{"key":"10.1016\/S0167-6393(01)00020-6_BIB39","doi-asserted-by":"crossref","unstructured":"Potamianos, G., Graf, H.P., 1998. Discriminatie training of HMM stream exponents for speech recognition. In: Proc. Internat. Conf. Acoust. Speech Signal Process., pp. 3733\u20133736","DOI":"10.1109\/ICASSP.1998.679695"},{"key":"10.1016\/S0167-6393(01)00020-6_BIB40","doi-asserted-by":"crossref","unstructured":"Richards, H.B., Mason, J.S., Hunt, M.J., Bridle, J.S., 1996. Deriving articulatory representations of speech with various excitation modes. In: Proc. Internat. Conf. Spoken Language Process","DOI":"10.1109\/ICSLP.1996.607831"},{"key":"10.1016\/S0167-6393(01)00020-6_BIB41","doi-asserted-by":"crossref","unstructured":"Richards, H.B., Mason, J.S., Bridle, J.S., Hunt, M.J., 1997. Vocal tract shape trajectory estimation using MLP analysis-by-synthesis. In: Proc. Internat. Conf. Acoust. Speech Signal Process., pp. 1287\u20131290","DOI":"10.1109\/ICASSP.1997.596181"},{"key":"10.1016\/S0167-6393(01)00020-6_BIB42","doi-asserted-by":"crossref","unstructured":"Saleh, G.M.K., Niranjan, M., 1997. Speech enhancement in a Bayesian framework. In: Proc. Internat. Conf. Acoust. Speech Signal Process., pp. 389\u2013392","DOI":"10.1109\/ICASSP.1998.674449"},{"key":"10.1016\/S0167-6393(01)00020-6_BIB43","doi-asserted-by":"crossref","unstructured":"Schmidtbauer, O., 1989. Robust statistic modelling of systematic variabilities in continuous speech incorporating acoustic-articulatory relations. In: Proc. Internat. Conf. Acoust. Speech Signal Process., pp. 616\u2013619","DOI":"10.1109\/ICASSP.1989.266502"},{"key":"10.1016\/S0167-6393(01)00020-6_BIB44","doi-asserted-by":"crossref","first-page":"133","DOI":"10.1109\/89.260356","article-title":"Techniques for estimating vocal-tract shapes from the speech signal","volume":"2","author":"Schroeter","year":"1994","journal-title":"IEEE Trans. Speech Audio Process."},{"key":"10.1016\/S0167-6393(01)00020-6_BIB45","unstructured":"Steingrimsson, P., Markussen, B., Andersen, O., Dalsgaard, P., Barry, W., 1995. From acoustic signal to phonetic features: a dynamically signal to phonetic features: a dynamically constrained self-organising neural network. In: Proc. Internat. Congress Phonetic Sciences"},{"key":"10.1016\/S0167-6393(01)00020-6_BIB46","doi-asserted-by":"crossref","unstructured":"Strope, B., Alwan, A., 1998. Robust word recognition using threaded spectral peaks. In: Proc. Internat. Conf. Acoust. Speech Signal Process","DOI":"10.1109\/ICASSP.1998.675342"},{"key":"10.1016\/S0167-6393(01)00020-6_BIB47","doi-asserted-by":"crossref","unstructured":"Wesenick, M.B., Kipp, A., 1996. Estimating the quality of phonetic transcriptions and segmentations of speech signals. In: Proc. Internat. Conf. Spoken Language Process., pp. 129\u2013132","DOI":"10.1109\/ICSLP.1996.607054"},{"key":"10.1016\/S0167-6393(01)00020-6_BIB48","unstructured":"Wu, S.-L., Kingsbury, B.E.D., Morgan, N., Greenberg, S., 1998. Incorporating information from syllable-length time scales into automatic speech recognition. In: Proc. Internat. Conf. Acoust. Speech Signal Process., pp. 721\u2013724"}],"container-title":["Speech Communication"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0167639301000206?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0167639301000206?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2024,12,3]],"date-time":"2024-12-03T17:46:47Z","timestamp":1733248007000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S0167639301000206"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2002,7]]},"references-count":48,"journal-issue":{"issue":"3-4","published-print":{"date-parts":[[2002,7]]}},"alternative-id":["S0167639301000206"],"URL":"https:\/\/doi.org\/10.1016\/s0167-6393(01)00020-6","relation":{},"ISSN":["0167-6393"],"issn-type":[{"value":"0167-6393","type":"print"}],"subject":[],"published":{"date-parts":[[2002,7]]}}}