{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,27]],"date-time":"2026-02-27T21:36:20Z","timestamp":1772228180983,"version":"3.50.1"},"reference-count":95,"publisher":"Elsevier BV","issue":"2-4","license":[{"start":{"date-parts":[[1999,11,1]],"date-time":"1999-11-01T00:00:00Z","timestamp":941414400000},"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":[[1999,11]]},"DOI":"10.1016\/s0167-6393(99)00038-2","type":"journal-article","created":{"date-parts":[[2003,4,5]],"date-time":"2003-04-05T03:57:58Z","timestamp":1049515078000},"page":"225-246","source":"Crossref","is-referenced-by-count":113,"title":["Modeling pronunciation variation for ASR: A survey of the literature"],"prefix":"10.1016","volume":"29","author":[{"given":"Helmer","family":"Strik","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Catia","family":"Cucchiarini","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"78","reference":[{"key":"10.1016\/S0167-6393(99)00038-2_BIB1","doi-asserted-by":"crossref","unstructured":"Adda-Decker, M., Lamel, L., 1998. Pronunciation variants across systems, languages and speaking style. In: Strik, H., Kessens, J.M., Wester, M. (Eds.), Proceedings of the ESCA Workshop on Modeling Pronunciation Variation for Automatic Speech Recognition, Rolduc, Kerkrade, 4\u20136 May 1998. A2RT, University of Nijmegen, pp. 1\u20136","DOI":"10.1016\/S0167-6393(99)00032-1"},{"key":"10.1016\/S0167-6393(99)00038-2_BIB2","doi-asserted-by":"crossref","unstructured":"Adda-Decker, M., Lamel, L., 1999. Pronunciation variants across system configuration, language and speaking style. Speech Communication 29 (2\u20134), 83\u201398","DOI":"10.1016\/S0167-6393(99)00032-1"},{"key":"10.1016\/S0167-6393(99)00038-2_BIB3","doi-asserted-by":"crossref","unstructured":"Aubert, X., Dugast, C., 1995. Improved acoustic\u2013phonetic modeling in Philips\u2019 dictation system by handling liaisons and multiple pronunciations. In: Proceedings of Eurospeech-95, Madrid, pp. 767\u2013770","DOI":"10.21437\/Eurospeech.1995-175"},{"key":"10.1016\/S0167-6393(99)00038-2_BIB4","unstructured":"Bacchiani, M., Ostendorf, M., 1998. Joint acoustic unit design and lexicon generation. In: Strik, H., Kessens, J.M., Wester, M. (Eds.), Proceedings of the ESCA Workshop on Modeling Pronunciation Variation for Automatic Speech Recognition, Rolduc, Kerkrade, 4\u20136 May 1998. A2RT, University of Nijmegen, pp. 7\u201312"},{"key":"10.1016\/S0167-6393(99)00038-2_BIB5","doi-asserted-by":"crossref","unstructured":"Bacchiani, M., Ostendorf, M., 1999. Joint lexicon, acoustic unit inventory and model design. Speech Communication 29 (2\u20134), 99\u2013114","DOI":"10.1016\/S0167-6393(99)00033-3"},{"key":"10.1016\/S0167-6393(99)00038-2_BIB6","unstructured":"Barnett, J., 1974. A phonological rule compiler. In: Erman., L. (Ed.), Proceedings of the IEEE Symposium on Speech Recognition, Carnegie-Mellon University (IEEE Catalog No. 74CH0878-9 AE), 15\u201319 April, Pittsburgh, PA, pp. 188\u2013192"},{"issue":"2","key":"10.1016\/S0167-6393(99)00038-2_BIB7","doi-asserted-by":"crossref","first-page":"145","DOI":"10.1017\/S004740450001037X","article-title":"Language style as audience design","volume":"13","author":"Bell","year":"1984","journal-title":"Language in Society"},{"key":"10.1016\/S0167-6393(99)00038-2_BIB8","unstructured":"Beulen, K., Ortmanns, S., Eiden, A., Martin, S., Welling, L., Overmann, J., Ney, H., 1998. Pronunciation modelling in the RWTH large vocabulary speech recognizer. In: Strik, H., Kessens, J.M., Wester, M. (Eds.), Proceedings of the ESCA Workshop on Modeling Pronunciation Variation for Automatic Speech Recognition, Rolduc, Kerkrade, 4\u20136 May 1998. A2RT, University of Nijmegen, pp. 13\u201316"},{"key":"10.1016\/S0167-6393(99)00038-2_BIB9","doi-asserted-by":"crossref","unstructured":"Blackburn, C.S., Young, S.J., 1995. Towards improved speech recognition using a speech production model. In: Proceedings of EuroSpeech-95, Madrid, pp. 1623\u20131626","DOI":"10.21437\/Eurospeech.1995-393"},{"key":"10.1016\/S0167-6393(99)00038-2_BIB10","doi-asserted-by":"crossref","unstructured":"Blackburn, C.S., Young, S.J., 1996. Pseudo-articulatory speech synthesis for recognition using automatic feature extraction from X-ray data. In: Proceedings of ICSLP-96, Philadelphia, pp. 969\u2013972","DOI":"10.1109\/ICSLP.1996.607764"},{"key":"10.1016\/S0167-6393(99)00038-2_BIB11","unstructured":"Bonaventura, P., Gallocchio, F., Mari, J., Micca, G., 1998. Speech recognition methods for non-native pronunciation variations. In: Strik, H., Kessens, J.M., Wester, M. (Eds.), Proceedings of the ESCA Workshop on Modeling Pronunciation Variation for Automatic Speech Recognition, Rolduc, Kerkrade, 4\u20136 May 1998. A2RT, University of Nijmegen, pp. 17\u201322"},{"key":"10.1016\/S0167-6393(99)00038-2_BIB12","unstructured":"Cohen, M., 1989. Phonological structures for speech recognition. Ph.D. Thesis, University of California, Berkeley, USA"},{"key":"10.1016\/S0167-6393(99)00038-2_BIB13","unstructured":"Cohen, P.S., Mercer, R.L., 1974. The phonological component of an automatic speech-recognition system. In: Erman, L. (Ed.), Proceedings of the IEEE Symposium on Speech Recognition, Carnegie-Mellon University (IEEE Catalog No. 74CH0878-9 AE), 15\u201319 April, Pittsburgh, PA, pp. 177\u2013187"},{"key":"10.1016\/S0167-6393(99)00038-2_BIB14","unstructured":"Cohen, P.S., Mercer, R.L., 1975. The phonological component of an automatic speech-recognition system. In: Reddy, D.R. (Ed.), Speech Recognition. Academic Press, New York, 1975, pp. 275\u2013320"},{"key":"10.1016\/S0167-6393(99)00038-2_BIB15","first-page":"49","article-title":"Accommodation at work: Some phonological data and their implications","volume":"46","author":"Coupland","year":"1984","journal-title":"International Journal of the Sociology of Language"},{"key":"10.1016\/S0167-6393(99)00038-2_BIB16","doi-asserted-by":"crossref","unstructured":"Cremelie, N., Martens, J.-P., 1995. On the use of pronunciation rules for improved word recognition. In: Proceedings of Eurospeech-95, Madrid, pp. 1747\u20131750","DOI":"10.21437\/Eurospeech.1995-316"},{"key":"10.1016\/S0167-6393(99)00038-2_BIB17","doi-asserted-by":"crossref","unstructured":"Cremelie, N., Martens, J.-P., 1997. Automatic rule-based generation of word pronunciation networks. In: Proceedings of EuroSpeech-97, Rhodes, pp. 2459\u20132462","DOI":"10.21437\/Eurospeech.1997-639"},{"key":"10.1016\/S0167-6393(99)00038-2_BIB18","unstructured":"Cremelie, N., Martens, J.-P., 1998. In search of pronunciation rules. In: Strik, H., Kessens, J.M., Wester, M. (Eds.), Proceedings of the ESCA Workshop on Modeling Pronunciation Variation for Automatic Speech Recognition, Rolduc, Kerkrade, 4\u20136 May 1998. A2RT, University of Nijmegen, pp. 23\u201328"},{"key":"10.1016\/S0167-6393(99)00038-2_BIB19","doi-asserted-by":"crossref","unstructured":"Cremelie, N., Martens, J.-P., 1999. In search of better pronunciation models for speech recognition. Speech Communication 29 (2\u20134), 115\u2013136","DOI":"10.1016\/S0167-6393(99)00034-5"},{"issue":"5","key":"10.1016\/S0167-6393(99)00038-2_BIB20","doi-asserted-by":"crossref","first-page":"2702","DOI":"10.1121\/1.409839","article-title":"A statistical approach to automatic speech recognition using the atomic speech units constructed from overlapping articulatory features","volume":"95","author":"Deng","year":"1994","journal-title":"Journal of the Acoustical Society of America"},{"key":"10.1016\/S0167-6393(99)00038-2_BIB21","doi-asserted-by":"crossref","unstructured":"Deshmukh, N., Weber, M., Picone, J., 1996. Automated generation of N-best pronunciations of proper nouns. In: Proceedings of ICASSP-96, Atlanta, pp. 283\u2013286","DOI":"10.1109\/ICASSP.1996.540413"},{"key":"10.1016\/S0167-6393(99)00038-2_BIB22","doi-asserted-by":"crossref","unstructured":"Downey, S., Wiseman, R., 1997. Dynamic and static improvements to lexical baseforms. In: Proceedings of Eurospeech-97, Rhodes, pp. 1027\u20131030","DOI":"10.21437\/Eurospeech.1997-359"},{"key":"10.1016\/S0167-6393(99)00038-2_BIB23","unstructured":"Erman, L., 1974. Proceedings of the IEEE Symposium on Speech Recognition, Carnegie-Mellon University, (IEEE Catalog No. 74CH0878-9 AE) 15\u201319 April 1974, Pittsburgh, PA, 295 pp"},{"key":"10.1016\/S0167-6393(99)00038-2_BIB24","doi-asserted-by":"crossref","unstructured":"Eskenazi, M., 1993. Trends in speaking styles research. In: Proceedings of Eurospeech-93, Berlin, pp. 501\u2013509","DOI":"10.21437\/Eurospeech.1993-8"},{"key":"10.1016\/S0167-6393(99)00038-2_BIB25","unstructured":"Ferreiros, J., Mac\u0131\u0301as-Guarasa, J., Pardo, J.M., Villarrubia, L., 1998. Introducing multiple pronunciations in Spanish speech recognition systems. In: Strik, H., Kessens, J.M., Wester, M. (Eds.), Proceedings of the ESCA Workshop on Modeling Pronunciation Variation for Automatic Speech Recognition, Rolduc, Kerkrade, 4\u20136 May 1998. A2RT, University of Nijmegen, pp. 29\u201334"},{"key":"10.1016\/S0167-6393(99)00038-2_BIB26","doi-asserted-by":"crossref","unstructured":"Finke, M., Waibel, A., 1997. Speaking mode dependent pronunciation modeling in large vocabulary conversational speech recognition. In: Proceedings of EuroSpeech-97, Rhodes, pp. 2379\u20132382","DOI":"10.21437\/Eurospeech.1997-625"},{"key":"10.1016\/S0167-6393(99)00038-2_BIB27","doi-asserted-by":"crossref","unstructured":"Flach, G., 1995. Modelling pronunciation variability for spectral domains. In: Proceedings of Eurospeech-95, Madrid, pp. 1743\u20131746","DOI":"10.21437\/Eurospeech.1995-315"},{"key":"10.1016\/S0167-6393(99)00038-2_BIB28","doi-asserted-by":"crossref","unstructured":"Fosler-Lussier, E., Morgan, N., 1998. Effects of speaking rate and word frequency on conversational pronunciations. In: Strik, H., Kessens, J.M., Wester, M. (Eds.), Proceedings of the ESCA Workshop on Modeling Pronunciation Variation for Automatic Speech Recognition, Rolduc, Kerkrade, 4\u20136 May 1998. A2RT, University of Nijmegen, pp. 35\u201340","DOI":"10.1016\/S0167-6393(99)00035-7"},{"key":"10.1016\/S0167-6393(99)00038-2_BIB29","doi-asserted-by":"crossref","unstructured":"Fosler-Lussier, E., Morgan, N., 1999. Effects of speaking rate and word frequency on pronunciations in conversational speech. Speech Communication 29 (2\u20134) 137\u2013158","DOI":"10.1016\/S0167-6393(99)00035-7"},{"key":"10.1016\/S0167-6393(99)00038-2_BIB30","unstructured":"Friedman, J., 1974. Computer exploration of fast speech rules. In: Erman, L. (Ed.), Proceedings of the IEEE Symposium on Speech Recognition, Carnegie-Mellon University (IEEE Catalog No. 74CH0878-9 AE), 15\u201319 April 1974, Pittsburgh, PA, pp. 197\u2013203"},{"key":"10.1016\/S0167-6393(99)00038-2_BIB31","doi-asserted-by":"crossref","unstructured":"Fukada, T., Sagisaka, Y., 1997. Automatic generation of a pronunciation dictionary based on a pronunciation network. In: Proceedings of EuroSpeech-97, Rhodes, pp. 2471\u20132474","DOI":"10.21437\/Eurospeech.1997-642"},{"key":"10.1016\/S0167-6393(99)00038-2_BIB32","unstructured":"Fukada, T., Yoshimura, T., Sagisaka, Y., 1998. Automatic generation of multiple pronunciations based on neural networks and language statistics. In: Strik, H., Kessens, J.M., Wester, M. (Eds.), Proceedings of the ESCA Workshop on Modeling Pronunciation Variation for Automatic Speech Recognition, Rolduc, Kerkrade, 4\u20136 May 1998. A2RT, University of Nijmegen, pp. 41\u201346"},{"issue":"1","key":"10.1016\/S0167-6393(99)00038-2_BIB33","doi-asserted-by":"crossref","first-page":"63","DOI":"10.1016\/S0167-6393(98)00066-1","article-title":"Automatic generation of multiple pronunciations based on neural networks","volume":"27","author":"Fukada","year":"1999","journal-title":"Speech Communication"},{"key":"10.1016\/S0167-6393(99)00038-2_BIB34","series-title":"Speech Style and Social Evaluation","author":"Giles","year":"1975"},{"key":"10.1016\/S0167-6393(99)00038-2_BIB35","unstructured":"Giles, H., Smith, P., 1979. Accommodation theory: Optimal levels of convergence. In: Giles, H., stClair, R. (Eds.), Language and Social Psychology, Blackwell, Oxford"},{"key":"10.1016\/S0167-6393(99)00038-2_BIB36","doi-asserted-by":"crossref","unstructured":"Godfrey, J.J., Ganapathiraju, A., Ramalingam, C.S., Picone, J., 1997. Microsegment-based connected digit recognition. In: Proceedings of ICASSP-97, Munich, pp. 1755\u20131758","DOI":"10.1109\/ICASSP.1997.598864"},{"key":"10.1016\/S0167-6393(99)00038-2_BIB37","unstructured":"Goldsmith, J., 1976. Autosegmental phonology. Doctoral thesis, Massachussets Institute of Technology, Cambridge. Indiana University Linguistics Club, Bloomington, Indiana; Garland, New York, 1979"},{"key":"10.1016\/S0167-6393(99)00038-2_BIB38","series-title":"Autosegmental and Metrical Phonology","author":"Goldsmith","year":"1990"},{"key":"10.1016\/S0167-6393(99)00038-2_BIB39","doi-asserted-by":"crossref","unstructured":"Greenberg, S., 1998. Speaking in shorthand \u2013 A syllable-centric perspective for understanding pronunciation variation. In: Strik, H., Kessens, J.M., Wester, M. (Eds.), Proceedings of the ESCA Workshop on Modeling Pronunciation Variation for Automatic Speech Recognition, Rolduc, Kerkrade, 4\u20136 May 1998. A2RT, University of Nijmegen, pp. 47\u201356","DOI":"10.1016\/S0167-6393(99)00050-3"},{"key":"10.1016\/S0167-6393(99)00038-2_BIB40","doi-asserted-by":"crossref","unstructured":"Greenberg, S., 1999. Speaking in shorthand \u2013 A syllable-centric perspective for understanding pronunciation variation. Speech Communication 29 (2\u20134) 159\u2013176","DOI":"10.1016\/S0167-6393(99)00050-3"},{"key":"10.1016\/S0167-6393(99)00038-2_BIB41","unstructured":"Heine, H., Evermann, G., Jost, U., 1998. An HMM-based probabilistic lexicon. In: Strik, H., Kessens, J.M., Wester, M. (Eds.), Proceedings of the ESCA Workshop on Modeling Pronunciation Variation for Automatic Speech Recognition, Rolduc, Kerkrade, 4\u20136 May 1998. A2RT, University of Nijmegen, pp. 57\u201362"},{"key":"10.1016\/S0167-6393(99)00038-2_BIB42","doi-asserted-by":"crossref","unstructured":"Holmes, W.J., Russell, M.J., 1996. Modeling speech variability with segmental HMMs. In: Proceedings of ICASSP-96, Atlanta, pp. 447\u2013450","DOI":"10.1109\/ICASSP.1996.541129"},{"key":"10.1016\/S0167-6393(99)00038-2_BIB43","unstructured":"Holter, T., 1997. Maximum likelihood modelling of pronunciation in automatic speech recognition. Ph.D. Thesis, Norwegian University of Science and Technology, December 1997"},{"key":"10.1016\/S0167-6393(99)00038-2_BIB44","doi-asserted-by":"crossref","unstructured":"Holter, T., Svendsen, T., 1998. Maximum likelihood modelling of pronunciation variation. In: Strik, H., Kessens, J.M., Wester, M. (Eds.), Proceedings of the ESCA Workshop on Modeling Pronunciation Variation for Automatic Speech Recognition, Rolduc, Kerkrade, 4\u20136 May 1998. A2RT, University of Nijmegen, pp. 63\u201366","DOI":"10.1016\/S0167-6393(99)00036-9"},{"key":"10.1016\/S0167-6393(99)00038-2_BIB45","doi-asserted-by":"crossref","unstructured":"Holter, T., Svendsen, T., 1999. Maximum likelihood modelling of pronunciation variation. Speech Communication 29 (2\u20134) 177\u2013191","DOI":"10.1016\/S0167-6393(99)00036-9"},{"key":"10.1016\/S0167-6393(99)00038-2_BIB46","doi-asserted-by":"crossref","unstructured":"Imai, T., Ando, A., Miyasaka, E., 1995. A new method for automatic generation of speaker-dependent phonological rules. In: Proceedings of ICASSP-95, Detroit, pp. 864\u2013867","DOI":"10.1109\/ICASSP.1995.479831"},{"key":"10.1016\/S0167-6393(99)00038-2_BIB47","unstructured":"Jelinek, F., Bahl, L.R., Mercer, R.L., 1974. Design of a linguistic statistical decoder for the recognition of continuous speech. In: Erman, L. (Ed.), Proceedings of the IEEE Symposium on Speech Recognition, Carnegie-Mellon University (IEEE Catalog No. 74CH0878-9 AE), 15\u201319 April 1974, Pittsburgh, PA, pp. 255\u2013260"},{"key":"10.1016\/S0167-6393(99)00038-2_BIB48","series-title":"Connected Speech: The Interaction of Syntax and Phonology","author":"Kaisse","year":"1985"},{"key":"10.1016\/S0167-6393(99)00038-2_BIB49","unstructured":"Kessens, J., Wester, M., 1997. Improving recognition performance by modelling pronunciation variation. In: Proceedings of the CLS opening Academic Year \u201897\u2013\u201998, pp. 1\u201320 (http:\/\/lands.let.kun.nl\/literature\/kessens.1997.1.html)"},{"key":"10.1016\/S0167-6393(99)00038-2_BIB50","doi-asserted-by":"crossref","unstructured":"Kessens, J.M., Wester, M., Strik, H., 1999. Improving the performance of a Dutch CSR by modelling within-word and cross-word pronunciation variation. Speech Communication 29 (2\u20134) 193\u2013207","DOI":"10.1016\/S0167-6393(99)00048-5"},{"key":"10.1016\/S0167-6393(99)00038-2_BIB51","doi-asserted-by":"crossref","unstructured":"Kipp, A., Wesenick, M.-B., Schiel, F., 1996. Automatic detection and segmentation of pronunciation variants in German speech corpora. In: Proceedings of ICSLP-96, Philadelphia, pp. 106\u2013109","DOI":"10.1109\/ICSLP.1996.607048"},{"key":"10.1016\/S0167-6393(99)00038-2_BIB52","doi-asserted-by":"crossref","unstructured":"Kipp, A., Wesenick, M.-B., Schiel, F., 1997. Pronunciation modeling applied to automatic segmentation of spontaneous speech. In: Proceedings of EuroSpeech-97, Rhodes, pp. 1023\u20131026","DOI":"10.21437\/Eurospeech.1997-358"},{"key":"10.1016\/S0167-6393(99)00038-2_BIB53","series-title":"Sociolinguistic Patterns","author":"Labov","year":"1972"},{"key":"10.1016\/S0167-6393(99)00038-2_BIB54","doi-asserted-by":"crossref","unstructured":"Lamel, L., Adda, G., 1996. On designing pronunciation lexicons for large vocabulary continuous speech recognition. In: Proceedings of ICSLP-96, Philadelphia, pp. 6\u20139","DOI":"10.1109\/ICSLP.1996.606916"},{"key":"10.1016\/S0167-6393(99)00038-2_BIB55","series-title":"Principles of Phonetics","author":"Laver","year":"1994"},{"key":"10.1016\/S0167-6393(99)00038-2_BIB56","unstructured":"Lehtinen, G., Safra, S., 1998. Generation and selection of pronunciation variants for a flexible word recognizer. In: Strik, H., Kessens, J.M., Wester, M. (Eds.), Proceedings of the ESCA Workshop on Modeling Pronunciation Variation for Automatic Speech Recognition, Rolduc, Kerkrade, 4\u20136 May 1998. A2RT, University of Nijmegen, pp. 67\u201372"},{"issue":"1","key":"10.1016\/S0167-6393(99)00038-2_BIB57","doi-asserted-by":"crossref","first-page":"81","DOI":"10.1147\/rd.311.0081","article-title":"A method for efficient storage and rapid application of context-sensitive phonological rules for automatic speech recognition","volume":"31","author":"Mercer","year":"1987","journal-title":"IBM J. Res. Develop."},{"key":"10.1016\/S0167-6393(99)00038-2_BIB58","doi-asserted-by":"crossref","unstructured":"Mirghafori, N., Fosler, E., Morgan, N., 1995. Fast speakers in large vocabulary continuous speech recognition: analysis and antidotes. In: Proceedings of EuroSpeech-95, Madrid, pp. 491\u2013494","DOI":"10.21437\/Eurospeech.1995-131"},{"key":"10.1016\/S0167-6393(99)00038-2_BIB59","unstructured":"Mokbel, H., Jouvet, D., 1998. Derivation of the optimal phonetic transcription set for a word from its acoustic realisations. In: Strik, H., Kessens, J.M., Wester, M. (Eds.), Proceedings of the ESCA Workshop on Modeling Pronunciation Variation for Automatic Speech Recognition, Rolduc, Kerkrade, 4\u20136 May 1998. A2RT, University of Nijmegen, pp. 73\u201378"},{"key":"10.1016\/S0167-6393(99)00038-2_BIB60","unstructured":"Mouria-Beji, F., 1998. Context and speed dependent phonemic models for continuous speech recognition. In: Strik, H., Kessens, J.M., Wester, M. (Eds.), Proceedings of the ESCA Workshop on Modeling Pronunciation Variation for Automatic Speech Recognition, Rolduc, Kerkrade, 4\u20136 May 1998. A2RT, University of Nijmegen, pp. 79\u201384"},{"issue":"2","key":"10.1016\/S0167-6393(99)00038-2_BIB61","doi-asserted-by":"crossref","first-page":"1097","DOI":"10.1121\/1.405558","article-title":"Toward the simulation of emotion in synthetic speech: A review of the literature on human vocal emotion","volume":"93","author":"Murray","year":"1993","journal-title":"Journal of the Acoustical Society of America"},{"key":"10.1016\/S0167-6393(99)00038-2_BIB62","unstructured":"Nock, H.J., Young, S.J., 1998. Detecting and correcting poor pronunciations for multiword units. In: Strik, H., Kessens, J.M., Wester, M. (Eds.), Proceedings of the ESCA Workshop on Modeling Pronunciation Variation for Automatic Speech Recognition, Rolduc, Kerkrade, 4\u20136 May 1998. A2RT, University of Nijmegen, pp. 85\u201390"},{"key":"10.1016\/S0167-6393(99)00038-2_BIB63","unstructured":"O\u2019Malley, M.H., Cole, A., 1974. Testing phonological rules. In: Erman, L. (Ed.), Proceedings of the IEEE Symposium on Speech Recognition, Carnegie-Mellon University (IEEE Catalog No. 74CH0878-9 AE), 15\u201319 April 1974, Pittsburgh, PA, pp. 193\u2013196"},{"key":"10.1016\/S0167-6393(99)00038-2_BIB64","unstructured":"Oshika, B.T., Zue, V.W., Weeks, R.V., Neu, H., 1974. The role of phonological rules in speech understanding research. In: Erman, L. (Ed.), Proceedings of the IEEE Symposium on Speech Recognition, Carnegie-Mellon University (IEEE Catalog No. 74CH0878-9 AE), 15\u201319 April 1974, Pittsburgh, PA pp. 204\u2013207"},{"key":"10.1016\/S0167-6393(99)00038-2_BIB65","unstructured":"Perennou, G., Brieussel-Pousse, L., 1998. Phonological component in automatic speech recognition. In: Strik, H., Kessens, J.M., Wester, M. (Eds.), Proceedings of the ESCA Workshop on Modeling Pronunciation Variation for Automatic Speech Recognition, Rolduc, Kerkrade, 4\u20136 May 1998. A2RT, University of Nijmegen, pp. 91\u201396"},{"key":"10.1016\/S0167-6393(99)00038-2_BIB66","unstructured":"Peters, S.D., Stubley, P., 1998. Visualizing speech trajectories. In: Strik, H., Kessens, J.M., Wester, M. (Eds.), Proceedings of the ESCA Workshop on Modeling Pronunciation Variation for Automatic Speech Recognition, Rolduc, Kerkrade, 4\u20136 May 1998. A2RT, University of Nijmegen, pp. 97\u2013102"},{"key":"10.1016\/S0167-6393(99)00038-2_BIB67","unstructured":"Polzin, T.S., Waibel, A.H., 1998. Pronunciation variations in emotional speech. In: Strik, H., Kessens, J.M., Wester, M. (Eds.), Proceedings of the ESCA Workshop on Modeling Pronunciation Variation for Automatic Speech Recognition, Rolduc, Kerkrade, 4\u20136 May 1998. A2RT, University of Nijmegen, pp. 103\u2013108"},{"key":"10.1016\/S0167-6393(99)00038-2_BIB68","doi-asserted-by":"crossref","unstructured":"Pousse, L., Perennou, G., 1997. Dealing with pronunciation variants at the language model level for automatic continuous speech recognition of French. In: Proceedings of Eurospeech-97, Rhodes, pp. 2727\u20132730","DOI":"10.21437\/Eurospeech.1997-688"},{"key":"10.1016\/S0167-6393(99)00038-2_BIB69","unstructured":"Rabinowitz, A.S., 1974. Phonetic to graphemic transformation by use of a stack procedure. In: Erman, L. (Ed.), Proceedings of the IEEE Symposium on Speech Recognition, Carnegie-Mellon University (IEEE Catalog No. 74CH0878-9 AE), 15\u201319 April 1974, Pittsburgh, PA, pp. 212\u2013217"},{"key":"10.1016\/S0167-6393(99)00038-2_BIB70","doi-asserted-by":"crossref","unstructured":"Ravishankar, M., Eskenazi, M., 1997. Automatic generation of context-dependent pronunciations. In: Proceedings of EuroSpeech-97, Rhodes, pp. 2467\u20132470","DOI":"10.21437\/Eurospeech.1997-641"},{"key":"10.1016\/S0167-6393(99)00038-2_BIB71","doi-asserted-by":"crossref","unstructured":"Riley, M., Byrne, W., Finke, M., Khudanpur, S., Ljolje, A., McDonough, J., Nock, H., Saraclar, M., Wooters, C., Zavaliagkos, G., 1998. Stochastic pronunciation modelling from hand-labelled phonetic corpora. In: Strik, H., Kessens, J.M., Wester, M. (Eds.), Proceedings of the ESCA Workshop on Modeling Pronunciation Variation for Automatic Speech Recognition, Rolduc, Kerkrade, 4\u20136 May 1998. A2RT, University of Nijmegen, pp. 109\u2013116","DOI":"10.1016\/S0167-6393(99)00037-0"},{"key":"10.1016\/S0167-6393(99)00038-2_BIB72","doi-asserted-by":"crossref","unstructured":"Riley, M., Byrne, W., Finke, M., Khudanpur, S., Ljolje, A., McDonough, J., Nock, H., Saraclar, M., Wooters, C., Zavaliagkos, G., 1999. Stochastic pronunciation modelling from hand-labelled phonetic corpora. Speech Communication 29 (2\u20134) 209\u2013224","DOI":"10.1016\/S0167-6393(99)00037-0"},{"key":"10.1016\/S0167-6393(99)00038-2_BIB73","unstructured":"Ristad, E.S., Yianilos, P.N., 1998. A surficial pronunciation model. In: Strik, H., Kessens, J.M., Wester, M. (Eds.), Proceedings of the ESCA Workshop on Modeling Pronunciation Variation for Automatic Speech Recognition, Rolduc, Kerkrade, 4\u20136 May 1998. A2RT, University of Nijmegen, pp. 117\u2013120"},{"key":"10.1016\/S0167-6393(99)00038-2_BIB74","unstructured":"Roach, P., Arnfield, S., 1998. Variation information in pronunciation dictionaries. In: Strik, H., Kessens, J.M., Wester, M. (Eds.), Proceedings of the ESCA Workshop on Modeling Pronunciation Variation for Automatic Speech Recognition, Rolduc, Kerkrade, 4\u20136 May 1998. A2RT, University of Nijmegen, pp. 121\u2013124"},{"key":"10.1016\/S0167-6393(99)00038-2_BIB75","doi-asserted-by":"crossref","unstructured":"Roe, D.B., Riley, M.D., 1994. Prediction of word confusabilities for speech recognition. In: Proceedings of ICSLP-94, Yokohama, pp. 227\u2013230","DOI":"10.21437\/ICSLP.1994-60"},{"key":"10.1016\/S0167-6393(99)00038-2_BIB76","doi-asserted-by":"crossref","first-page":"213","DOI":"10.1177\/002383098002300301","article-title":"Stylistic variation and evaluative reactions to speech","volume":"23","author":"Romaine","year":"1980","journal-title":"Language and Speech"},{"key":"10.1016\/S0167-6393(99)00038-2_BIB77","unstructured":"Rovner, P., Makhoul, J., Wolf, J., Colarusso, J., 1974. Where the words are: lexical retrieval in a speech understanding system. In: Erman, L. (Ed.), Proceedings of the IEEE Symposium on Speech Recognition, Carnegie-Mellon University (IEEE Catalog No. 74CH0878-9 AE), 15\u201319 April 1974, Pittsburgh, PA, pp. 160\u2013164"},{"key":"10.1016\/S0167-6393(99)00038-2_BIB78","unstructured":"Safra, S., Lehtinen, G., Huber, K., 1998. Modeling pronunciation variations and coarticulation with finite-state transducers in CSR. In: Strik, H., Kessens, J.M., Wester, M. (Eds.), Proceedings of the ESCA Workshop on Modeling Pronunciation Variation for Automatic Speech Recognition, Rolduc, Kerkrade, 4\u20136 May 1998. A2RT, University of Nijmegen, pp. 125\u2013130"},{"key":"10.1016\/S0167-6393(99)00038-2_BIB79","unstructured":"Scherer, K.R., Giles, H., 1979. Social Markers in Speech. Cambridge University Press, Cambridge"},{"key":"10.1016\/S0167-6393(99)00038-2_BIB80","unstructured":"Schiel, F., Kipp, A., Tillmann, H.G., 1998. Statistical modelling of pronunciation: It\u2019s not the model, it\u2019s the data. In: Strik, H., Kessens, J.M., Wester, M. (Eds.), Proceedings of the ESCA Workshop on Modeling Pronunciation Variation for Automatic Speech Recognition, Rolduc, Kerkrade, 4\u20136 May 1998. A2RT, University of Nijmegen, pp. 131\u2013136"},{"key":"10.1016\/S0167-6393(99)00038-2_BIB81","unstructured":"Shockey, L., Erman, L.D., 1974. Sub-lexical levels in the HEARSAY II speech understanding system. In: Erman, L. (Ed.), Proceedings of the IEEE Symposium on Speech Recognition, Carnegie-Mellon University (IEEE Catalog No. 74CH0878-9 AE), 15\u201319 April 1974, Pittsburgh, PA, pp. 208\u2013210"},{"key":"10.1016\/S0167-6393(99)00038-2_BIB82","doi-asserted-by":"crossref","unstructured":"Sloboda, T., Waibel, A., 1996. Dictionary learning for spontaneous speech recognition. In: Proceedings of ICSLP-96, Philadelphia, pp. 2328\u20132331","DOI":"10.1109\/ICSLP.1996.607274"},{"key":"10.1016\/S0167-6393(99)00038-2_BIB83","unstructured":"Strik, H., 1998. Publications on pronunciation variation and ASR. http:\/\/lands.let.kun.nl\/TSpublic\/strik\/pron-var\/references.html"},{"key":"10.1016\/S0167-6393(99)00038-2_BIB84","unstructured":"Strik, H., Cucchiarini, C., 1998. Modeling pronunciation variation for ASR: overview and comparison of methods. In: Strik, H., Kessens, J.M., Wester, M. (Eds.), Proceedings of the ESCA Workshop on Modeling Pronunciation Variation for Automatic Speech Recognition, Rolduc, Kerkrade, 4\u20136 May 1998. A2RT, University of Nijmegen, pp. 137\u2013144"},{"key":"10.1016\/S0167-6393(99)00038-2_BIB85","unstructured":"Strik, H., Kessens, J.M., Wester, M., 1998. Proceedings of the ESCA Workshop on Modeling Pronunciation Variation for Automatic Speech Recognition, Rolduc, Kerkrade, 4\u20136 May 1998. A2RT, University of Nijmegen, 168 pp"},{"key":"10.1016\/S0167-6393(99)00038-2_BIB86","doi-asserted-by":"crossref","unstructured":"Svendsen, T., Soong, F., Purnhagen, H., 1995. Optimizing acoustic baseforms for HMM-based speech recognition. In: Proceedings of EuroSpeech-95, Madrid, pp. 783\u2013786","DOI":"10.21437\/Eurospeech.1995-179"},{"key":"10.1016\/S0167-6393(99)00038-2_BIB87","unstructured":"Tappert, C.C., 1974. Experiments with a tree search method for converting noisy phonetic representation into standard orthography. In: Erman, L. (Ed.), Proceedings of the IEEE Symposium on Speech Recognition, Carnegie-Mellon University (IEEE Catalog No. 74CH0878-9 AE), 15\u201319 April 1974, Pittsburgh, PA, pp. 261\u2013266"},{"key":"10.1016\/S0167-6393(99)00038-2_BIB88","doi-asserted-by":"crossref","unstructured":"Torre, D., Villarrubia, L., Hern\u00e1ndez, L., Elvira, J.M., 1997. Automatic alternative transcription generation and vocabulary selection for flexible word recognizers. In: Proceedings of ICASSP-97, Munich, pp. 1463\u20131466","DOI":"10.1109\/ICASSP.1997.596225"},{"key":"10.1016\/S0167-6393(99)00038-2_BIB89","doi-asserted-by":"crossref","unstructured":"Wesenick, M.-B., 1996. Automatic generation of German pronunciation variants. In: Proceedings of ICSLP-96, Philadelphia, pp. 125\u2013128","DOI":"10.1109\/ICSLP.1996.607053"},{"key":"10.1016\/S0167-6393(99)00038-2_BIB90","doi-asserted-by":"crossref","unstructured":"Wester, M., Kessens, J.M., Strik, H., 1998a. Improving the performance of a Dutch CSR by modelling pronunciation variation. In: Strik, H., Kessens, J.M., Wester, M. (Eds.), Proceedings of the ESCA Workshop on Modeling Pronunciation Variation for Automatic Speech Recognition, Rolduc, Kerkrade, 4\u20136 May 1998. A2RT, University of Nijmegen, pp. 145\u2013150","DOI":"10.1016\/S0167-6393(99)00048-5"},{"key":"10.1016\/S0167-6393(99)00038-2_BIB91","doi-asserted-by":"crossref","unstructured":"Wester, M., Kessens, J.M., Cucchiarini, C., Strik, H., 1998b. Selection of pronunciation variants in spontaneous speech: Comparing the performance of man and machine. In: Proceedings of the ESCA workshop, SPoSS 98 \u2013 Sound Patterns of Spontaneous Speech: Production and Perception: Aix-en-Provence, France, 24\u201326 September 1998, pp. 157\u2013160","DOI":"10.21437\/ICSLP.1998-604"},{"key":"10.1016\/S0167-6393(99)00038-2_BIB92","unstructured":"Wester, M., Kessens, J.M., Cucchiarini, C., Strik, H., 1999. Comparison between expert listeners and continuous speech recognizers in selecting pronunciation variants. In: Proceedings of the 14th International Congress of Phonetic Sciences (ICPhS-99), San Fransico, USA, 1999"},{"key":"10.1016\/S0167-6393(99)00038-2_BIB93","unstructured":"Williams, G., Renals, S., 1998. Confidence measures for evaluating pronunciation models. In: Strik, H., Kessens, J.M., Wester, M. (Eds.), Proceedings of the ESCA Workshop on Modeling Pronunciation Variation for Automatic Speech Recognition, Rolduc, Kerkrade, 4\u20136 May 1998. A2RT, University of Nijmegen, pp. 151\u2013156"},{"key":"10.1016\/S0167-6393(99)00038-2_BIB94","unstructured":"Wiseman, R., Downey, S., 1998. Dynamic and static improvements to lexical baseforms. In: Strik, H., Kessens, J.M., Wester, M. (Eds.), Proceedings of the ESCA Workshop on Modeling Pronunciation Variation for Automatic Speech Recognition, Rolduc, Kerkrade, 4\u20136 May 1998. A2RT, University of Nijmegen, pp. 157\u2013162"},{"key":"10.1016\/S0167-6393(99)00038-2_BIB95","doi-asserted-by":"crossref","unstructured":"Zeppenfeld, T., Finke, M., Ries, K., Westphal, M., Waibel, A., 1997. Recognition of conversational speech using the JANUS speech engine. In: Proceedings of ICASSP-97, Munich, pp. 1815\u20131818","DOI":"10.1109\/ICASSP.1997.598889"}],"container-title":["Speech Communication"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0167639399000382?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0167639399000382?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2023,4,15]],"date-time":"2023-04-15T22:03:57Z","timestamp":1681596237000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S0167639399000382"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[1999,11]]},"references-count":95,"journal-issue":{"issue":"2-4","published-print":{"date-parts":[[1999,11]]}},"alternative-id":["S0167639399000382"],"URL":"https:\/\/doi.org\/10.1016\/s0167-6393(99)00038-2","relation":{},"ISSN":["0167-6393"],"issn-type":[{"value":"0167-6393","type":"print"}],"subject":[],"published":{"date-parts":[[1999,11]]}}}