{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2022,3,29]],"date-time":"2022-03-29T00:25:42Z","timestamp":1648513542844},"reference-count":27,"publisher":"Springer Science and Business Media LLC","issue":"4","license":[{"start":{"date-parts":[[2013,4,25]],"date-time":"2013-04-25T00:00:00Z","timestamp":1366848000000},"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":[[2013,12]]},"DOI":"10.1007\/s10772-013-9196-2","type":"journal-article","created":{"date-parts":[[2013,5,1]],"date-time":"2013-05-01T03:15:07Z","timestamp":1367378107000},"page":"461-469","source":"Crossref","is-referenced-by-count":1,"title":["A voice command system for AUTONOMY using a novel speech alignment algorithm"],"prefix":"10.1007","volume":"16","author":[{"given":"Helmut","family":"Hickersberger","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Wolfgang L.","family":"Zagler","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2013,4,25]]},"reference":[{"key":"9196_CR1","doi-asserted-by":"crossref","first-page":"30","DOI":"10.1109\/TASL.2011.2134090","volume":"20","author":"G. E. Dahl","year":"2012","unstructured":"Dahl, G. E., Yu, D., Deng, L., & Acero, A. (2012). Context-dependent pre-trained deep neural networks for large vocabulary speech recognition. IEEE Transactions on Audio, Speech, and Language Processing, 20, 30\u201342.","journal-title":"IEEE Transactions on Audio, Speech, and Language Processing"},{"key":"9196_CR2","unstructured":"Do, V. H. (2011). Hybrid architectures for speech recognition. PhD Thesis, Nanyang, China: Nanyang Technological University."},{"key":"9196_CR3","volume-title":"Proceedings of the Asia-Pacific signal and information processing association annual summit and conference","author":"V. H. Do","year":"2011","unstructured":"Do, V. H., Xiao, X., & Chng, E. S. (2011). Comparison and combination of multilayer perceptrons and deep belief networks in hybrid automatic speech recognition systems. In Proceedings of the Asia-Pacific signal and information processing association annual summit and conference, APSIPA ASC, October 2011, Xi\u2019an, China."},{"key":"9196_CR4","first-page":"143","volume-title":"Symposium on the application of hidden Markov models to text and speech","author":"J. D. Ferguson","year":"1980","unstructured":"Ferguson, J. D. (1980). Variable duration models for speech. In Symposium on the application of hidden Markov models to text and speech, October 1980 (pp. 143\u2013179). Princeton: Institute for Defense Analyses."},{"key":"9196_CR5","doi-asserted-by":"crossref","first-page":"268","DOI":"10.1109\/PROC.1973.9030","volume":"61","author":"G. D. Forney","year":"1973","unstructured":"Forney, G. D. (1973). The viterbi algorithm. Proceedings of the IEEE, 61, 268\u2013278.","journal-title":"Proceedings of the IEEE"},{"key":"9196_CR6","volume-title":"Introduction to statistical pattern recognition","author":"K. Fukunaga","year":"1990","unstructured":"Fukunaga, K. (1990). Introduction to statistical pattern recognition. Boston: Academic Press."},{"key":"9196_CR7","doi-asserted-by":"crossref","first-page":"1400","DOI":"10.1155\/ASP.2005.1400","volume":"9","author":"L. Gu","year":"2005","unstructured":"Gu, L., Harris, J. G., Shrivastav, R. S., & Sapienza, C. (2005). Disordered speech assessment using automatic methods based on quantitative measures. EURASIP Journal on Applied Signal Processing, 9, 1400\u20131409.","journal-title":"EURASIP Journal on Applied Signal Processing"},{"key":"9196_CR8","doi-asserted-by":"crossref","first-page":"586","DOI":"10.1016\/j.medengphy.2006.06.009","volume":"29","author":"M. S. Hawley","year":"2007","unstructured":"Hawley, M. S., Enderby, P., Green, P., Cunningham, S., Brownsell, S., Carmichael, J., Parker, M., Hatzis, A., O\u2019Neill, P., & Palmer, R. (2007). A speech-controlled environmental control system for people with severe dysarthria. Medical Engineering & Physics, 29, 586\u2013593.","journal-title":"Medical Engineering & Physics"},{"key":"9196_CR9","doi-asserted-by":"crossref","first-page":"245","DOI":"10.1007\/BF03159578","volume":"115","author":"H. Hickersberger","year":"1998","unstructured":"Hickersberger, H. (1998). Spracherkennung mit hidden control neural networks. E&I. Elektrotechnik und Informationstechnik, 115, 245\u2013250.","journal-title":"E&I. Elektrotechnik und Informationstechnik"},{"key":"9196_CR10","doi-asserted-by":"crossref","first-page":"223","DOI":"10.1016\/S0925-2312(01)00706-8","volume":"50","author":"M. H\u00fcsken","year":"2003","unstructured":"H\u00fcsken, M., & Stagge, P. (2003). Recurrent neural networks for time series classification. Neurocomputing, 50, 223\u2013235.","journal-title":"Neurocomputing"},{"key":"9196_CR11","doi-asserted-by":"crossref","first-page":"441","DOI":"10.1109\/ICASSP.1990.115744","volume-title":"Proceedings of the international conference on acoustics, speech, and signal processing","author":"K. Iso","year":"1990","unstructured":"Iso, K., & Watanabe, T. (1990). Speaker-independent word recognition using a neural prediction model. In Proceedings of the international conference on acoustics, speech, and signal processing, ICASSP, April 1990, Albuquerque, New Mexico, USA (pp. 441\u2013444)."},{"key":"9196_CR12","volume-title":"Proceedings of the 13th annual conference of the international speech communication association INTERSPEECH","author":"N. Jaitly","year":"2012","unstructured":"Jaitly, N., Nguyen, P., Senior, A., & Vanhoucke, V. (2012). Application of pretrained deep neural network to large vocabulary conversational speech recognition. In Proceedings of the 13th annual conference of the international speech communication association INTERSPEECH, September 2012. Portland: ISCA."},{"key":"9196_CR13","doi-asserted-by":"crossref","first-page":"109","DOI":"10.1109\/72.182700","volume":"4","author":"E. Levin","year":"1993","unstructured":"Levin, E. (1993). Hidden control neural architecture modeling of nonlinear time varying systems and its applications. IEEE Transactions on Neural Networks, 4, 109\u2013116.","journal-title":"IEEE Transactions on Neural Networks"},{"key":"9196_CR14","first-page":"1241","volume-title":"Proceedings of the international conference on acoustics, speech, and signal processing","author":"S. E. Levinson","year":"1986","unstructured":"Levinson, S. E. (1986). Continuously variable duration hidden Markov models for speech analysis. In Proceedings of the international conference on acoustics, speech, and signal processing, ICASSP, April 1986, Tokyo, Japan (pp. 1241\u20131244)."},{"key":"9196_CR15","unstructured":"Loidolt, G. (1995). AUTONOM III: Spracherkennung. Diploma thesis, Vienna, Austria: Vienna University of Technology."},{"key":"9196_CR16","doi-asserted-by":"crossref","first-page":"360","DOI":"10.1109\/89.536930","volume":"4","author":"M. Ostendorf","year":"1996","unstructured":"Ostendorf, M., Digalakis, V. V., & Kimbal, O. A. (1996). From HMMs to segment models: a unified view of stochastic modeling for speech recognition. IEEE Transactions on Speech and Audio Processing, 4, 360\u2013378.","journal-title":"IEEE Transactions on Speech and Audio Processing"},{"key":"9196_CR17","series-title":"Lecture notes in computer science","doi-asserted-by":"crossref","first-page":"181","DOI":"10.1007\/3-540-45491-8_39","volume-title":"Proceedings of the 8th international conference on computers helping people with special needs","author":"P. Panek","year":"2002","unstructured":"Panek, P., Beck, C., Mina, S., Seisenbacher, G., & Zagler, W. L. (2002). Technical assistance of motor- and multiple disabled children\u2014some long term experiences. In Lecture notes in computer science: Vol.\u00a02398. Proceedings of the 8th international conference on computers helping people with special needs, ICCHP, July 2002, Linz, Austria (pp. 181\u2013188)."},{"key":"9196_CR18","doi-asserted-by":"crossref","first-page":"257","DOI":"10.1109\/5.18626","volume":"77","author":"L. R. Rabiner","year":"1989","unstructured":"Rabiner, L. R. (1989). A tutorial on hidden Markov models and selected applications in speech recognition. Proceedings of the IEEE, 77, 257\u2013286.","journal-title":"Proceedings of the IEEE"},{"key":"9196_CR19","first-page":"381","volume-title":"Proceedings of the international conference on acoustics, speech, and signal processing","author":"P. Ramesh","year":"1992","unstructured":"Ramesh, P., & Wilpon, J. G. (1992). Modeling state durations in hidden Markov models for automatic speech recognition. In Proceedings of the international conference on acoustics, speech, and signal processing, ICASSP, March 1992, San Francisco, California, USA (pp. 381\u2013384)."},{"key":"9196_CR20","doi-asserted-by":"crossref","first-page":"437","DOI":"10.1109\/ICASSP.1990.115742","volume-title":"Proceedings of the international conference on acoustics, speech, and signal processing","author":"J. Tebelskis","year":"1990","unstructured":"Tebelskis, J., & Waibel, A. (1990). Large vocabulary recognition using linked predictive neural networks. In Proceedings of the international conference on acoustics, speech, and signal processing, ICASSP, April 1990, Albuquerque, New Mexico, USA (pp. 437\u2013440)."},{"key":"9196_CR21","doi-asserted-by":"crossref","first-page":"367","DOI":"10.1007\/BF03157841","volume":"118","author":"W. Tschirk","year":"2001","unstructured":"Tschirk, W. (2001). Neural net speech recognizers\u2014voice remote control devices for disabled people. E&I. Elektrotechnik und Informationstechnik, 118, 367\u2013370.","journal-title":"E&I. Elektrotechnik und Informationstechnik"},{"key":"9196_CR22","doi-asserted-by":"crossref","first-page":"625","DOI":"10.1049\/el:19910392","volume":"27","author":"S. V. Vaseghi","year":"1991","unstructured":"Vaseghi, S. V. (1991). Hidden Markov models with duration-dependent state transition probabilities. Electronics Letters, 27, 625\u2013626.","journal-title":"Electronics Letters"},{"key":"9196_CR23","doi-asserted-by":"crossref","first-page":"328","DOI":"10.1109\/29.21701","volume":"37","author":"A. Waibel","year":"1989","unstructured":"Waibel, A., Hanazawa, T., Hinton, G., Shikano, K., & Lang, K. J. (1989). Phoneme recognition using time-delay neural networks. IEEE Transactions on Acoustics, Speech, and Signal Processing, 37, 328\u2013339.","journal-title":"IEEE Transactions on Acoustics, Speech, and Signal Processing"},{"key":"9196_CR24","doi-asserted-by":"crossref","first-page":"1415","DOI":"10.1109\/5.58323","volume":"78","author":"B. Widrow","year":"1973","unstructured":"Widrow, B., & Lehr, M. (1973). 30 years of adaptive neural networks: perceptron, madaline, and backpropagation. Proceedings of the IEEE, 78, 1415\u20131442.","journal-title":"Proceedings of the IEEE"},{"key":"9196_CR25","doi-asserted-by":"crossref","first-page":"216","DOI":"10.1109\/TSA.2003.811540","volume":"11","author":"R. Yaniv","year":"2003","unstructured":"Yaniv, R., & Burshtein, D. (2003). An enhanced dynamic time warping model for improved estimation of DTW parameters. IEEE Transactions on Speech and Audio Processing, 11, 216\u2013228.","journal-title":"IEEE Transactions on Speech and Audio Processing"},{"key":"9196_CR26","doi-asserted-by":"crossref","first-page":"215","DOI":"10.1016\/j.artint.2009.11.011","volume":"174","author":"S.-Z. Yu","year":"2010","unstructured":"Yu, S.-Z. (2010). Hidden semi-Markov models. Artificial Intelligence, 174, 215\u2013243.","journal-title":"Artificial Intelligence"},{"key":"9196_CR27","first-page":"232","volume-title":"Proceedings of the 10th IEEE symposium on computer-based medical systems","author":"W. L. Zagler","year":"1997","unstructured":"Zagler, W. L., Panek, P., & Flachberger, C. (1997). Technical assistance for severely motor- and multiple impaired children. In Proceedings of the 10th IEEE symposium on computer-based medical systems, June 1997, Maribor, Slovenia (pp. 232\u2013237). Washington: IEEE Computer Society."}],"container-title":["International Journal of Speech Technology"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s10772-013-9196-2.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/article\/10.1007\/s10772-013-9196-2\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s10772-013-9196-2","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2019,5,31]],"date-time":"2019-05-31T00:02:45Z","timestamp":1559260965000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/s10772-013-9196-2"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2013,4,25]]},"references-count":27,"journal-issue":{"issue":"4","published-print":{"date-parts":[[2013,12]]}},"alternative-id":["9196"],"URL":"https:\/\/doi.org\/10.1007\/s10772-013-9196-2","relation":{},"ISSN":["1381-2416","1572-8110"],"issn-type":[{"value":"1381-2416","type":"print"},{"value":"1572-8110","type":"electronic"}],"subject":[],"published":{"date-parts":[[2013,4,25]]}}}