{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,7,3]],"date-time":"2025-07-03T07:42:00Z","timestamp":1751528520714},"publisher-location":"Berlin, Heidelberg","reference-count":39,"publisher":"Springer Berlin Heidelberg","isbn-type":[{"type":"print","value":"9783540643418"},{"type":"electronic","value":"9783540697527"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[1998]]},"DOI":"10.1007\/bfb0054006","type":"book-chapter","created":{"date-parts":[[2006,6,7]],"date-time":"2006-06-07T01:55:04Z","timestamp":1149645304000},"page":"389-417","source":"Crossref","is-referenced-by-count":28,"title":["Hybrid HMM\/ANN systems for speech recognition: Overview and new research directions"],"prefix":"10.1007","author":[{"given":"Herv\u00e9","family":"Bourlard","sequence":"first","affiliation":[]},{"given":"Nelson","family":"Morgan","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2006,5,25]]},"reference":[{"issue":"no.4","key":"14_CR1","doi-asserted-by":"publisher","first-page":"567","DOI":"10.1109\/89.326615","volume":"2","author":"J.B. Allen","year":"1994","unstructured":"Allen, J.B., \u201cHow do humans process and recognize speech?,\u201d IEEE Trans. on Speech and Audio Processing, vol. 2, no. 4, pp.567\u2013577, 1994.","journal-title":"IEEE Trans. on Speech and Audio Processing"},{"key":"14_CR2","doi-asserted-by":"crossref","first-page":"180","DOI":"10.21236\/ADA460339","volume-title":"Improving state-of-the-art continuous speech recognition systems using the N-best paradigm with neural networks","author":"S. Austin","year":"1992","unstructured":"Austin, S., Zavaliagkos, G., Makhoul, J., and Schwartz, J., \u201cImproving state-of-the-art continuous speech recognition systems using the N-best paradigm with neural networks,\u201d Proc. DARPA Speech and Natural Language Workshop (Harriman, NY), Morgan Kaufmann, pp. 180\u2013184, Feb. 1992."},{"key":"14_CR3","first-page":"1","volume":"no. 3","author":"L. Baum","year":"1972","unstructured":"Baum, L., \u201cAn inequality and associated maximization techniques in statistical estimation of probabilistic functions of Markov processes,\u201d Inequalities, no. 3, pp. 1\u20138, 1972.","journal-title":"Inequalities"},{"issue":"no.2","key":"14_CR4","doi-asserted-by":"publisher","first-page":"252","DOI":"10.1109\/72.125866","volume":"3","author":"Y. Bengio","year":"1992","unstructured":"Bengio, Y., De Mori, R., Flammia, G. and Kompe, R., \u201cGlobal optimization of a neural network-Hidden Markov Model hybrid,\u201d IEEE Trans. on Neural Networks, vol. 3, no. 2, pp. 252\u2013259, 1992.","journal-title":"IEEE Trans. on Neural Networks"},{"key":"14_CR5","doi-asserted-by":"crossref","unstructured":"Bilmes, J., Morgan, N., Wu, S., and Bourlard, H., \u201cStochastic perceptual speech models with durational dependence,\u201d Intl. Conference on Spoken Language Processing, pp. 1301\u20131304, 1996.","DOI":"10.1109\/ICSLP.1996.607851"},{"key":"14_CR6","doi-asserted-by":"crossref","unstructured":"Bourlard, H. and Morgan, N., Connectionist Speech Recognition \u2014 A Hybrid Approach, Kluwer Academic Publishers, 1994.","DOI":"10.1007\/978-1-4615-3210-1"},{"key":"14_CR7","doi-asserted-by":"crossref","unstructured":"Bourlard, H., Konig, Y. and Morgan, N., \u201cREMAP: Recursive Estimation and Maximization of A Posteriori Probabilities in connectionist speech recognition\u201d, Proc. EUROSPEECH'95 (Madrid, Spain), Sep. 1995.","DOI":"10.21437\/Eurospeech.1995-402"},{"key":"14_CR8","unstructured":"Bourlard, H. and Dupont, S. (1996), \u201cA new ASR approach based on independent processing and recombination of partial frequency bands,\u201d Proc. of Intl. Conf. on Spoken Language Processing (ICSLP) (Philadelphia), pp. 426\u2013429, Oct. 3\u20136, 1996."},{"key":"14_CR9","doi-asserted-by":"crossref","unstructured":"Bridle, J.S., \u201cProbabilistic interpretation of feedforward classification network outputs, with relationships to statistical pattern recognition,\u201d in Neurocomputing: Algorithms, Architectures and Applications, F. Fogelman Souli\u00e9 and J. H\u00e9rault (Eds.), NATO ASI Series, pp. 227\u2013236, 1990.","DOI":"10.1007\/978-3-642-76153-9_28"},{"key":"14_CR10","doi-asserted-by":"crossref","unstructured":"Dupont, S. and Bourlard, H., \u201cUsing multiple time scales in a multi-stream speech recognition system,\u201d to be published in Proc. EUROSPEECH'97 (Rhodes, Greece), Sep. 1997.","DOI":"10.21437\/Eurospeech.1997-7"},{"issue":"no.1","key":"14_CR11","doi-asserted-by":"publisher","first-page":"52","DOI":"10.1109\/TASSP.1986.1164788","volume":"34","author":"S. Furui","year":"1986","unstructured":"Furui, S., \u201cSpeaker independent isolated word recognizer using dynamic features of speech spectrum,\u201d IEEE Trans. on Acoustics, Speech, and Signal Processing, vol. 34, no. 1, pp. 52\u201359, 1986.","journal-title":"IEEE Trans. on Acoustics, Speech, and Signal Processing"},{"key":"14_CR12","doi-asserted-by":"crossref","unstructured":"Gish, H., \u201cA probabilistic approach to the understanding and training of neural network classifiers,\u201d in IEEE Proc. Intl. Conf. on Acoustics, Speech and Signal Processing (Albuquerque, NM), pp. 1361\u20131364, 1990.","DOI":"10.1109\/ICASSP.1990.115636"},{"key":"14_CR13","doi-asserted-by":"crossref","unstructured":"Haeb-Umbach, R., Geller, D., Ney, H., \u201cImprovements in connected digit recognition using linear discriminant analysis and mixture densities,\u201d Proc. IEEE Intl. Conf. on Acoustics, Speech, and Signal Processing (Adelaide, Australia), pp. II-239\u2013242, 1994.","DOI":"10.1109\/ICASSP.1993.319279"},{"key":"14_CR14","doi-asserted-by":"crossref","unstructured":"Hennebert, J., Ris, C., Bourlard, H., and Renals, S., \u201cEstimation of global posteriors and forward-backward training of hybrid HMM\/ANN systems,\u201d to be published in Proc. EUROSPEECH'97 (Rhodes, Greece), Sep. 1997.","DOI":"10.21437\/Eurospeech.1997-518"},{"key":"14_CR15","doi-asserted-by":"crossref","unstructured":"Hermansky, H., \u201cPerceptual Linear Predictive (PLP) analysis of speech,\u201d Journal of the Acoust. Soc. Am., vol. 87, no. 4, 1990.","DOI":"10.1121\/1.399423"},{"key":"14_CR16","doi-asserted-by":"crossref","unstructured":"Hochberg, M.M., Renals, S.J., Robinson, A.J., and G.D. Cook., \u201cRecent improvements to the ABBOT large vocabulary CSR system,\u201d Proc. of IEEE Intl. Conf. on Acoustics, Speech, and Signal Processing (Detroit, MI), pp. 69\u201372, 1995.","DOI":"10.1109\/ICASSP.1995.479275"},{"key":"14_CR17","doi-asserted-by":"crossref","unstructured":"Huang, X.D., Lee, K.F. and Waibel, A., \u201cConnectionist speaker normalization and its application to speech recognition,\u201d Proc. of IEEE Workshop on Neural Networks for Signal Processing, pp. 357\u2013366, IEEE Press, 1991.","DOI":"10.1109\/NNSP.1991.239506"},{"key":"14_CR18","doi-asserted-by":"crossref","unstructured":"Katagiri, S., Lee, C., and Juang, B., \u201cNew Discriminative Training Algorithms Based on the Generalized Probabilistic Descent Method\u201d, Proc. of the 1991 IEEE Workshop on Neural Networks for Signal Processing, ppp. 299\u2013308, 1991.","DOI":"10.1109\/NNSP.1991.239512"},{"key":"14_CR19","doi-asserted-by":"crossref","unstructured":"Kohonen, T., \u201cThe \u2018neural\u2019 phonetic typewriter,\u201d IEEE Computer: 11\u201322, 1988.","DOI":"10.1109\/2.28"},{"key":"14_CR20","doi-asserted-by":"crossref","unstructured":"Levin, E., \u201cSpeech recognition using hidden control neural network architecture,\u201d in Proc. IEEE Intl. Conf. on Acoustics, Speech, and Signal Processing (Albuquerque, NM), pp. 433\u2013436, 1990.","DOI":"10.1109\/ICASSP.1990.115740"},{"issue":"no.1","key":"14_CR21","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1162\/neco.1989.1.1.1","volume":"1","author":"R.P. Lippmann","year":"1989","unstructured":"Lippmann, R.P., \u201cReview of neural networks for speech recognition,\u201d Neural Computation, vol. 1, no. 1, pp. 1\u201338, 1989.","journal-title":"Neural Computation"},{"key":"14_CR22","doi-asserted-by":"crossref","unstructured":"Lubensky, D.M., Asadi, A.O. and Naik, J.M., \u201cConnected digit recognition using connectionist probability estimators and mixture-gaussian densities,\u201d IEEE Proc. of the Intl. Conf. on Spoken Language Processing, pp.295\u2013298, Yokohama, Japan, 1994.","DOI":"10.21437\/ICSLP.1994-77"},{"key":"14_CR23","first-page":"630","volume-title":"Advances in Neural Information Processing Systems 2","author":"N. Morgan","year":"1990","unstructured":"Morgan, N. and Bourlard, H., \u201cGeneralization and parameter estimation in feed-forward nets: some experiments, \u201c in Advances in Neural Information Processing Systems 2 (D.S. Touretzky, Ed.), San Mateo, CA: Morgan Kaufmann, pp. 630\u2013637, 1990."},{"key":"14_CR24","first-page":"4462","volume":"VII","author":"N. Morgan","year":"1994","unstructured":"Morgan, N., \u201cBig Dumb Deural Nets (BDNN): a working brute force approach to speech recognition\u201d, Proceedings of the ICNN, vol. VII, pp.4462\u20134465, 1994.","journal-title":"Proceedings of the ICNN"},{"issue":"no.5","key":"14_CR25","doi-asserted-by":"publisher","first-page":"741","DOI":"10.1109\/5.381844","volume":"83","author":"N. Morgan","year":"1995","unstructured":"Morgan, N. and Bourlard, H., \u201cNeural networks for statistical recognition of continuous speech,\u201d Proceedings of the IEEE, vol. 83, no. 5, pp. 741\u2013770, 1995.","journal-title":"Proceedings of the IEEE"},{"key":"14_CR26","doi-asserted-by":"publisher","first-page":"263","DOI":"10.1109\/TASSP.1984.1164320","volume":"32","author":"N. Ney","year":"1984","unstructured":"Ney, N., \u201cThe use of a one-stage dynamic programming algorithm for connected word recognition,\u201d IEEE Trans. on Acoustics, Speech, and Signal Processing, 32:263\u2013271, 1984.","journal-title":"IEEE Trans. on Acoustics, Speech, and Signal Processing"},{"key":"14_CR27","doi-asserted-by":"crossref","unstructured":"Poritz, A., \u201cLinear predictive Hidden Markov Models and the speech signal,\u201d Proc. IEEE Intl. Conf. on Acoustic, Speech, and Signal Processing, pp. 1291\u20131294, Paris, 1982.","DOI":"10.1109\/ICASSP.1982.1171633"},{"key":"14_CR28","doi-asserted-by":"crossref","unstructured":"Poritz, A.B. and Richter, A.L., \u201cOn hidden Markov models in isolated word recognition\u201d, IEEE Proc. Intl. Conf. on Acoustics, Speech, and Signal Processing, pp. 14.3.1\u20134, Tokyo, Japan, 1986.","DOI":"10.1109\/ICASSP.1986.1169200"},{"issue":"no.2","key":"14_CR29","doi-asserted-by":"publisher","first-page":"257","DOI":"10.1109\/5.18626","volume":"77","author":"L.R. Rabiner","year":"1989","unstructured":"Rabiner, L.R., \u201cA tutorial on hidden Markov models and selected applications in speech recognition,\u201d Proceedings of the IEEE, vol. 77, no. 2, pp. 257\u2013285, 1989.","journal-title":"Proceedings of the IEEE"},{"issue":"no.1","key":"14_CR30","doi-asserted-by":"publisher","first-page":"161","DOI":"10.1109\/89.260359","volume":"2","author":"S. Renals","year":"1994","unstructured":"Renals, S., Morgan, N., Bourlard, H., Cohen, M. and Franco, F., \u201cConnectionist probability estimators in HMM speech recognition,\u201d IEEE Trans. on Speech and Audio Processing, vol. 2, no. 1, pp. 161\u2013174, 1994.","journal-title":"IEEE Trans. on Speech and Audio Processing"},{"key":"14_CR31","doi-asserted-by":"crossref","unstructured":"Renals, S. and Hochberg, M., \u201cEfficient search using posterior phone probability estimates,\u201d Proc. of IEEE Intl. Conf. on Acoustics, Speech, and Signal Processing (Detroit, MI), pp. 596\u2013599, 1995.","DOI":"10.1109\/ICASSP.1995.479668"},{"key":"14_CR32","doi-asserted-by":"crossref","first-page":"461","DOI":"10.1162\/neco.1991.3.4.461","volume":"no. 3","author":"M.D. Richard","year":"1991","unstructured":"Richard, M.D. and Lippmann, R.P., \u201cNeural network classifiers estimate Bayesian a posteriori probabilities,\u201d Neural Computation, no. 3, pp. 461\u2013483, 1991.","journal-title":"Neural Computation"},{"key":"14_CR33","unstructured":"Robinson, T., Almeida, L., Boite, J.M., Bourlard, H., Fallside, F., Hochberg, M., Kershaw, D., Kohn, P., Konig, Y., Morgan, N., Neto, J.P., Renals, S., Saerens, M. and Wooters, C., \u201cA neural network based, speaker independent, large vocabulary, continuous speech recognition system: The WERNICKE Project,\u201d Proc. EUROSPEECH'93 (Berlin, Germany), pp. 1941\u20131944, 1993."},{"key":"14_CR34","doi-asserted-by":"crossref","unstructured":"Sorenson, H., \u201cA cepstral noise reduction multi-layer network,\u201d Proc. IEEE Intl. Conf. on Acoustic, Speech, and Signal Processing Toronto, Canada, pp. 933\u2013936, 1991.","DOI":"10.1109\/ICASSP.1991.150493"},{"key":"14_CR35","doi-asserted-by":"crossref","unstructured":"Steeneken, J.M. and Van Leeuwen, D.A., \u201cMulti-lingual assessment of speaker independent large vocabulary speech-recognition systems: the SQALE project (speech recognition quality assessment for language engineering),\u201d Proc. EUROSPEECH'95 (Madrid, Spain), Sep. 1995.","DOI":"10.21437\/Eurospeech.1995-332"},{"key":"14_CR36","doi-asserted-by":"crossref","unstructured":"Tebelskis, J. and Waibel, A., \u201cLarge vocabulary recognition using linked predictive neural networks,\u201d in Proc. IEEE Intl. Conf. on Acoustic, Speech, and Signal Processing (Albuquerque, NM), pp. 437\u2013440, 1990.","DOI":"10.1109\/ICASSP.1990.115742"},{"key":"14_CR37","doi-asserted-by":"crossref","unstructured":"Tomlinson, M.J., Russell, M.J., Moore, R.K., Buckland, A.P., Fawley, M.A., \u201cModelling asynchrony in speech using elementary single-signal decomposition,\u201d Proc. IEEE Intl. Conf. on Acoustics, Speech, and Signal Processing (Munich, Germany), pp. 1247\u20131250, 1997.","DOI":"10.1109\/ICASSP.1997.596171"},{"key":"14_CR38","doi-asserted-by":"crossref","unstructured":"Varga, A. and Moore, R., \u201cHidden Markov model decomposition of speech and noise,\u201d Proc. IEEE Intl. Conf. on Acoustics, Speech, and Signal Processing, pp. 845\u2013848, 1990.","DOI":"10.1109\/ICASSP.1990.115970"},{"issue":"no.1","key":"14_CR39","doi-asserted-by":"publisher","first-page":"151","DOI":"10.1109\/89.260358","volume":"2","author":"G. Zavaliagkos","year":"1994","unstructured":"Zavaliagkos, G., Zhao, Y., Schwartz, R. and Makhoul, J., \u201cA hybrid segmental neural net\/hidden markov model system for continuous speech recognition\u201d IEEE Trans. on Speech and Audio Processing, vol. 2, no. 1, pp. 151\u2013160, 1994.","journal-title":"IEEE Trans. on Speech and Audio Processing"}],"container-title":["Lecture Notes in Computer Science","Adaptive Processing of Sequences and Data Structures"],"original-title":[],"link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/BFb0054006","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,5,7]],"date-time":"2023-05-07T13:05:23Z","timestamp":1683464723000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/BFb0054006"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[1998]]},"ISBN":["9783540643418","9783540697527"],"references-count":39,"URL":"https:\/\/doi.org\/10.1007\/bfb0054006","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[1998]]}}}