{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2023,6,4]],"date-time":"2023-06-04T03:40:45Z","timestamp":1685850045116},"reference-count":43,"publisher":"Springer Science and Business Media LLC","issue":"4","license":[{"start":{"date-parts":[[2010,11,4]],"date-time":"2010-11-04T00:00:00Z","timestamp":1288828800000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Int J Speech Technol"],"published-print":{"date-parts":[[2010,12]]},"DOI":"10.1007\/s10772-010-9080-2","type":"journal-article","created":{"date-parts":[[2010,11,3]],"date-time":"2010-11-03T09:00:05Z","timestamp":1288774805000},"page":"219-230","source":"Crossref","is-referenced-by-count":6,"title":["Dual stream speech recognition using articulatory syllable models"],"prefix":"10.1007","volume":"13","author":[{"given":"Antti","family":"Puurula","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Dirk","family":"Van Compernolle","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2010,11,4]]},"reference":[{"key":"9080_CR1","first-page":"492","volume-title":"Proceedings of the 8th Australian international conference on speech science and technology (SST-2000)","author":"S. M. Ahadi","year":"2000","unstructured":"Ahadi, S. M. (2000). Reduced context sensitivity in Persian speech recognition via syllable modeling. In Proceedings of the 8th Australian international conference on speech science and technology (SST-2000) (pp. 492\u2013497). Canberra: Australian Speech Science and Technology Association."},{"key":"9080_CR2","doi-asserted-by":"crossref","first-page":"3333","DOI":"10.21437\/Interspeech.2005-856","volume-title":"Proceedings of Interspeech","author":"G. Aradilla","year":"2005","unstructured":"Aradilla, G., Vepa, J., & Bourlard, H. (2005). Improving speech recognition using a data-driven approach. In Proceedings of Interspeech (Vol. 66, pp. 3333\u20133336)."},{"key":"9080_CR3","first-page":"173","volume-title":"Proceedings of ICASSP","author":"S. Axelrod","year":"2004","unstructured":"Axelrod, S., & Maison, B. (2004). Combination of hidden Markov models with dynamic time warping for speech recognition. In Proceedings of ICASSP (Vol. 1, pp. 173\u2013176)."},{"key":"9080_CR4","volume-title":"Dynamic programming","author":"R. Bellman","year":"1957","unstructured":"Bellman, R. (1957). Dynamic programming. Princeton: Princeton University Press."},{"key":"9080_CR5","first-page":"481","volume-title":"Proceedings of ICASSP","author":"P. Beyerlein","year":"1998","unstructured":"Beyerlein, P. (1998). Discriminative model combination. In Proceedings of ICASSP (pp. 481\u2013484)."},{"key":"9080_CR6","volume-title":"Classification and regression trees","author":"L. Breiman","year":"1984","unstructured":"Breiman, L., Friedman, J., Olshen, R., & Stone, C. (1984). Classification and regression trees. Monterey: Wadsworth and Brooks."},{"key":"9080_CR7","first-page":"69","volume-title":"Proceedings of LREC","author":"C. C. David","year":"2004","unstructured":"David, C. C., Miller, D., & Walker, K. (2004). The Fisher corpus: a resource for the next generations of speech-to-text. In Proceedings of LREC (pp. 69\u201371)."},{"key":"9080_CR8","first-page":"I-181-4","volume-title":"Proceedings of ICASSP","author":"M. Wachter De","year":"2004","unstructured":"De Wachter, M., Demuynck, K., Wambacq, P., & Van Compernolle, D. (2004). A locally weighted distance measure for example based speech recognition. In Proceedings of ICASSP (Vol. 1, p. I-181-4)."},{"issue":"4","key":"9080_CR9","doi-asserted-by":"crossref","first-page":"1377","DOI":"10.1109\/TASL.2007.894524","volume":"15","author":"M. Wachter De","year":"2007","unstructured":"De Wachter, M., Matton, M., Demuynck, K., Wambacq, P., Cools, R., & Van Compernolle, D. (2007). Template-based continuous speech recognition. IEEE Transactions on Audio, Speech, and Language Processing, 15(4), 1377\u20131390.","journal-title":"IEEE Transactions on Audio, Speech, and Language Processing"},{"key":"9080_CR10","first-page":"495","volume-title":"Proceedings of Interspeech","author":"K. Demuynck","year":"2008","unstructured":"Demuynck, K., Roelens, J., Van Compernolle, D., & Wambacq, P. (2008). SPRAAK: an open source speech recognition and automatic annotation kit. In Proceedings of Interspeech (p. 495)."},{"key":"9080_CR11","first-page":"339","volume-title":"Proceedings of ASRU","author":"K. Demuynck","year":"2009","unstructured":"Demuynck, K., Puurula, A., Van Compernolle, D., & Wambacq, P. (2009). The ESAT 2008 system for N-Best Dutch speech recognition benchmark. In Proceedings of ASRU (pp. 339\u2013344)."},{"key":"9080_CR12","doi-asserted-by":"crossref","first-page":"3","DOI":"10.21437\/Eurospeech.1997-7","volume-title":"Proceedings of Eurospeech","author":"S. Dupont","year":"1997","unstructured":"Dupont, S., & Bourlard, H. (1997). Using multiple time scales in a multi-stream speech recognition system. In Proceedings of Eurospeech (pp. 3\u20136)."},{"key":"9080_CR13","volume-title":"Proceedings of ICSLP","author":"J. Frankel","year":"2004","unstructured":"Frankel, J., Wester, M., & King, S. (2004). Articulatory feature recognition using dynamic Bayesian networks. In Proceedings of ICSLP."},{"key":"9080_CR14","doi-asserted-by":"crossref","unstructured":"Ganapathiraju, A., Hamaker, J., Ordowski, M., Doddington, G., & Picone, J. (2001). Syllable-based large vocabulary continuous speech recognition. IEEE Transactions on Speech and Audio Processing.","DOI":"10.1109\/89.917681"},{"key":"9080_CR15","first-page":"112","volume-title":"Proceedings of CoNLL","author":"S. Goldwater","year":"2005","unstructured":"Goldwater, S., & Johnson, M. (2005). Representational bias in unsupervised learning of syllable structure. In Proceedings of CoNLL (pp. 112\u2013119)."},{"key":"9080_CR16","first-page":"781","volume-title":"Proceedings of ICASSP","author":"A. H\u00e4m\u00e4l\u00e4inen","year":"2007","unstructured":"H\u00e4m\u00e4l\u00e4inen, A., Bosch, L., & Boves, L. (2007). Modelling pronunciation variation using multi-path HMMs for syllables. In Proceedings of ICASSP (Vol. 4, pp. 781\u2013784)."},{"key":"9080_CR17","first-page":"1169","volume-title":"Proceedings of ICASSP","author":"Y. Han","year":"2006","unstructured":"Han, Y., H\u00e4m\u00e4l\u00e4inen, A., & Boves, L. (2006). Trajectory clustering of syllable-length acoustic models for continous speech recognition. In Proceedings of ICASSP, Toulouse, France (pp. 1169\u20131172)."},{"key":"9080_CR18","first-page":"297","volume-title":"Proceedings of the ICPhS","author":"M. Hasegawa-Johnson","year":"2007","unstructured":"Hasegawa-Johnson, M., Livescu, K., Lal, P., & Saenko, K. (2007). Audiovisual speech recognition with articulator positions as hidden variables. In Proceedings of the ICPhS (pp. 297\u2013302)."},{"key":"9080_CR19","volume-title":"Proceedings of the 9th international PhD workshop on systems and control, young generation viewpoint","author":"J. Hetjm\u00e1nek","year":"2008","unstructured":"Hetjm\u00e1nek, J., & Pavelka, T. (2008). Automatic speech recognition using context-dependent syllables. In Proceedings of the 9th international PhD workshop on systems and control, young generation viewpoint."},{"issue":"1\u20132","key":"9080_CR20","doi-asserted-by":"crossref","first-page":"67","DOI":"10.1016\/j.cognition.2003.10.011","volume":"92","author":"G. Hickok","year":"2004","unstructured":"Hickok, G., & Poeppel, D. (2004). Dorsal and ventral streams: a framework for understanding aspects of the functional anatomy of language. Cognition, 92(1\u20132), 67\u201399.","journal-title":"Cognition"},{"issue":"5","key":"9080_CR21","doi-asserted-by":"crossref","first-page":"393","DOI":"10.1038\/nrn2113","volume":"8","author":"G. Hickok","year":"2007","unstructured":"Hickok, G., & Poeppel, D. (2007). The cortical organization of speech processing. Nature Reviews Neuroscience, 8(5), 393\u2013402.","journal-title":"Nature Reviews Neuroscience"},{"key":"9080_CR22","first-page":"343","volume-title":"Proceedings of ICPR","author":"T. Kawatani","year":"2000","unstructured":"Kawatani, T. (2000). Handwritten kanji recognition with determinant normalized quadratic discriminant function. In Proceedings of ICPR (Vol. 2, pp. 343\u2013346)."},{"key":"9080_CR23","first-page":"1354","volume-title":"Proceedings of Interspeech","author":"J. Kessens","year":"2007","unstructured":"Kessens, J., & Leeuwen, D. Av. (2007). N-best: the Northern- and Southern-Dutch benchmark evaluation of speech recognition technology. In Proceedings of Interspeech (pp. 1354\u20131357)."},{"key":"9080_CR24","first-page":"2274","volume-title":"Proceedings of Interspeech","author":"K. Kirchhoff","year":"1996","unstructured":"Kirchhoff, K. (1996). Syllable-level desynchronisation of phonetic features for speech recognition. In Proceedings of Interspeech (pp. 2274\u20132276)."},{"key":"9080_CR25","doi-asserted-by":"crossref","first-page":"2571","DOI":"10.21437\/Interspeech.2009-677","volume-title":"Proceedings of Interspeech","author":"Dv. Leeuwen","year":"2009","unstructured":"Leeuwen, Dv., Kessens, J., Sanders, E., & Heuvel, Hvd. (2009). Results of the N-Best 2008 Dutch speech recognition evaluation. In Proceedings of Interspeech (pp. 2571\u20132574)."},{"issue":"2","key":"9080_CR26","doi-asserted-by":"crossref","first-page":"141","DOI":"10.1016\/j.inffus.2003.10.007","volume":"5","author":"K. Y. Leung","year":"2004","unstructured":"Leung, K. Y., & Siu, M. (2004). Integration of acoustic and articulatory information with application to speech recognition. Information Fusion, 5(2), 141\u2013151.","journal-title":"Information Fusion"},{"key":"9080_CR27","doi-asserted-by":"crossref","first-page":"2529","DOI":"10.21437\/Eurospeech.2003-693","volume-title":"Proceedings of Eurospeech","author":"K. Livescu","year":"2003","unstructured":"Livescu, K., Glass, J., & Bilmes, J. (2003). Hidden feature models for speech recognition using dynamic Bayesian networks. In Proceedings of Eurospeech (pp. 2529\u20132532)."},{"issue":"9","key":"9080_CR28","doi-asserted-by":"crossref","first-page":"759","DOI":"10.1016\/S0167-8655(00)00031-3","volume":"21","author":"A. M. Mart\u00ednez","year":"2000","unstructured":"Mart\u00ednez, A. M., & Virtri\u00e1, J. (2000). Learning mixture models using a genetic version of the EM algorithm. Pattern Recognition Letters, 21(9), 759\u2013769.","journal-title":"Pattern Recognition Letters"},{"key":"9080_CR29","first-page":"47","volume-title":"Proceedings of ASRU","author":"P. Momayyez","year":"2007","unstructured":"Momayyez, P., Waterhouse, J., & Rose, R. (2007). Exploiting complementary aspects of phonological features in automatic speech recognition. In Proceedings of ASRU (pp. 47\u201352)."},{"key":"9080_CR30","doi-asserted-by":"crossref","first-page":"2513","DOI":"10.21437\/Eurospeech.2003-689","volume-title":"Proceedings of Eurospeech","author":"J. Ogata","year":"2003","unstructured":"Ogata, J., & Ariki, Y. (2003). Syllable-based acoustic modeling for Japanese spontaneous speech recognition. In Proceedings of Eurospeech (pp. 2513\u20132516)."},{"issue":"8","key":"9080_CR31","doi-asserted-by":"crossref","first-page":"1344","DOI":"10.1109\/TPAMI.2005.162","volume":"27","author":"F. Pernkopf","year":"2005","unstructured":"Pernkopf, F., & Bouchaffra, D. (2005). Genetic-based EM algorithm for learning Gaussian mixture models. IEEE Transactions on Pattern Analysis and Machine Intelligence, 27(8), 1344\u20131348.","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"key":"9080_CR32","doi-asserted-by":"crossref","first-page":"663","DOI":"10.1121\/1.383693","volume":"66","author":"L. R. Rabiner","year":"1979","unstructured":"Rabiner, L. R., & Wilpon, J. G. (1979). Considerations in applying clustering techniques to speaker-independent word recognition. Journal of the Acoustical Society of America, 66, 663\u2013673.","journal-title":"Journal of the Acoustical Society of America"},{"key":"9080_CR33","volume-title":"Proceedings of EUSIPCO","author":"R. Rasipuram","year":"2008","unstructured":"Rasipuram, R., Hegde, R. M., & Murthy, H. A. (2008). Incorporating acoustic feature diversity into the linguistic search space for syllable based speech recognition. In Proceedings of EUSIPCO."},{"issue":"6","key":"9080_CR34","doi-asserted-by":"crossref","first-page":"718","DOI":"10.1038\/nn.2331","volume":"12","author":"J. P. Rauschecker","year":"2009","unstructured":"Rauschecker, J. P., & Scott, S. K. (2009). Maps and streams in the auditory cortex: nonhuman primates illuminate human speech processing. Nature Neuroscience, 12(6), 718\u2013724.","journal-title":"Nature Neuroscience"},{"key":"9080_CR35","doi-asserted-by":"crossref","first-page":"152","DOI":"10.1145\/1027933.1027960","volume-title":"Proceedings of ICMI","author":"K. Saenko","year":"2004","unstructured":"Saenko, K., Darrell, T., & Glass, J. R. (2004). Articulatory features for robust visual speech recognition. In Proceedings of ICMI (pp. 152\u2013158). New York: ACM."},{"key":"9080_CR36","doi-asserted-by":"crossref","first-page":"43","DOI":"10.1109\/TASSP.1978.1163055","volume":"26","author":"H. Sakoe","year":"1978","unstructured":"Sakoe, H. (1978). Dynamic programming algorithm optimization for spoken word recognition. IEEE Transactions on Acoustics, Speech, and Signal Processing, 26, 43\u201349.","journal-title":"IEEE Transactions on Acoustics, Speech, and Signal Processing"},{"issue":"3","key":"9080_CR37","doi-asserted-by":"crossref","first-page":"145","DOI":"10.2307\/2683165","volume":"36","author":"I. G. Sande","year":"1982","unstructured":"Sande, I. G. (1982). Imputation in surveys: coping with reality. The American Statistician, 36(3), 145\u2013152.","journal-title":"The American Statistician"},{"issue":"46","key":"9080_CR38","doi-asserted-by":"crossref","first-page":"18,035","DOI":"10.1073\/pnas.0805234105","volume":"105","author":"D. Saur","year":"2008","unstructured":"Saur, D., Kreher, B. W., Schnell, S., K\u00fcmmerer, D., Kellmeyer, P., Vry, M. S., Umarova, R., Musso, M., Glauche, V., Abel, S., Huber, W., Rijntjes, M., Hennig, J., & Weiller, C. (2008). Ventral and dorsal pathways for language. Proceedings of the National Academy of Sciences, 105(46), 18,035\u201318,040.","journal-title":"Proceedings of the National Academy of Sciences"},{"key":"9080_CR39","first-page":"129","volume-title":"Proceedings of ASRU","author":"A. Sethy","year":"2003","unstructured":"Sethy, A., Ramabhadran, B., & Narayanan, S. (2003). Improvements in English ASR for the MALACH project using syllable-centric models. In Proceedings of ASRU (pp. 129\u2013134)."},{"key":"9080_CR40","volume-title":"Data mining: opportunities and challenges","year":"2003","unstructured":"Wang, J. (Ed.) (2003). Data mining: opportunities and challenges. Hershey: IGI Publishing."},{"key":"9080_CR41","doi-asserted-by":"crossref","unstructured":"White, G. (1976). Speech recognition experiments with linear predication, bandpass filtering. IEEE Transactions on Acoustics, Speech, and Signal Processing, 24(2).","DOI":"10.1109\/TASSP.1976.1162779"},{"key":"9080_CR42","first-page":"854","volume-title":"Proceedings of Interspeech","author":"S. Wu","year":"1998","unstructured":"Wu, S., Kingsbury, B. E. D., Morgan, N., & Greenberg, S. (1998). Performance improvements through combining phone- and syllable-scale information in automatic speech recognition. In Proceedings of Interspeech (pp. 854\u2013857)."},{"key":"9080_CR43","volume-title":"The psycho-biology of language; an introduction to dynamic philology","author":"G. K. Zipf","year":"1935","unstructured":"Zipf, G. K. (1935). The psycho-biology of language; an introduction to dynamic philology. Boston: Houghton Mifflin."}],"container-title":["International Journal of Speech Technology"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s10772-010-9080-2.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/article\/10.1007\/s10772-010-9080-2\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s10772-010-9080-2","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,6,4]],"date-time":"2023-06-04T03:16:11Z","timestamp":1685848571000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/s10772-010-9080-2"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2010,11,4]]},"references-count":43,"journal-issue":{"issue":"4","published-print":{"date-parts":[[2010,12]]}},"alternative-id":["9080"],"URL":"https:\/\/doi.org\/10.1007\/s10772-010-9080-2","relation":{},"ISSN":["1381-2416","1572-8110"],"issn-type":[{"value":"1381-2416","type":"print"},{"value":"1572-8110","type":"electronic"}],"subject":[],"published":{"date-parts":[[2010,11,4]]}}}