{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,2,24]],"date-time":"2025-02-24T05:20:38Z","timestamp":1740374438275,"version":"3.37.3"},"reference-count":68,"publisher":"Springer Science and Business Media LLC","issue":"3","license":[{"start":{"date-parts":[[2010,7,30]],"date-time":"2010-07-30T00:00:00Z","timestamp":1280448000000},"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":[[2010,9]]},"DOI":"10.1007\/s10772-010-9077-x","type":"journal-article","created":{"date-parts":[[2010,7,29]],"date-time":"2010-07-29T10:55:20Z","timestamp":1280400920000},"page":"175-188","source":"Crossref","is-referenced-by-count":1,"title":["Phone duration modeling: overview of techniques and\u00a0performance optimization via feature selection in the context of\u00a0emotional speech"],"prefix":"10.1007","volume":"13","author":[{"given":"Alexandros","family":"Lazaridis","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Todor","family":"Ganchev","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Theodoros","family":"Kostoulas","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Iosif","family":"Mporas","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Nikos","family":"Fakotakis","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2010,7,30]]},"reference":[{"key":"9077_CR1","first-page":"37","volume":"6","author":"D. Aha","year":"1991","unstructured":"Aha, D., Kibler, D., & Albert, M. (1991). Instance-based learning algorithms. Journal of Machine Learning, 6, 37\u201366.","journal-title":"Journal of Machine Learning"},{"key":"9077_CR2","doi-asserted-by":"crossref","first-page":"716","DOI":"10.1109\/TAC.1974.1100705","volume":"19","author":"H. Akaike","year":"1974","unstructured":"Akaike, H. (1974). A new look at the statistical model identification. IEEE Transactions on Automatic Control, 19, 716\u2013723.","journal-title":"IEEE Transactions on Automatic Control"},{"key":"9077_CR3","volume-title":"From text to speech: the MITalk system","author":"J. Allen","year":"1987","unstructured":"Allen, J., Hunnicutt, S., & Klatt, D. H. (1987). From text to speech: the MITalk system. Cambridge: Cambridge University Press."},{"key":"9077_CR4","unstructured":"Arvaniti, A., & Baltazani, M. (2000). Greek ToBI: a system for the annotation of Greek speech corpora. In Proceedings of the 2nd international conference on language resources and evaluation (pp. 555\u2013562). Athens, Greece."},{"key":"9077_CR5","doi-asserted-by":"crossref","first-page":"11","DOI":"10.1023\/A:1006559212014","volume":"11","author":"C. G. Atkeson","year":"1996","unstructured":"Atkeson, C. G., Moorey, A. W., & Schaal, S. (1996). Locally weighted learning. Artificial Intelligence Review, 11, 11\u201373.","journal-title":"Artificial Intelligence Review"},{"key":"9077_CR6","doi-asserted-by":"crossref","first-page":"127","DOI":"10.1016\/0167-6393(94)90047-7","volume":"15","author":"P. A. Barbosa","year":"1994","unstructured":"Barbosa, P. A., & Bailly, G. (1994). Characterisation of rhythmic patterns for text-to-speech synthesis. Speech Communication, 15, 127\u2013137.","journal-title":"Speech Communication"},{"key":"9077_CR7","doi-asserted-by":"crossref","first-page":"245","DOI":"10.1016\/0167-6393(87)90029-X","volume":"6","author":"K. Bartkova","year":"1987","unstructured":"Bartkova, K., & Sorin, C. (1987). A model of segmental duration for speech synthesis in French. Speech Communication, 6, 245\u2013260.","journal-title":"Speech Communication"},{"issue":"2","key":"9077_CR8","doi-asserted-by":"crossref","first-page":"1001","DOI":"10.1121\/1.1534836","volume":"113","author":"A. Bell","year":"2003","unstructured":"Bell, A., Jurafsky, D., Fosler-Lussier, E., Girand, C., Gregory, M., & Gildea, D. (2003). Effects of disfluencies, predictability, and utterance position on word form variation in English conversation. Journal of the Acoustical Society of America, 113(2), 1001\u20131024.","journal-title":"Journal of the Acoustical Society of America"},{"key":"9077_CR9","doi-asserted-by":"crossref","unstructured":"Black, A. (2003). Unit selection and emotional speech. In Proceedings of EUROSPEECH\u201903 (pp.\u00a01649\u20131652). Geneva, Switzerland.","DOI":"10.21437\/Eurospeech.2003-473"},{"issue":"2","key":"9077_CR10","first-page":"123","volume":"24","author":"L. Breiman","year":"1996","unstructured":"Breiman, L. (1996). Bagging predictors. Journal of Machine Learning, 24(2), 123\u2013140.","journal-title":"Journal of Machine Learning"},{"key":"9077_CR11","unstructured":"Burkhardt, F., & Sendlmeier, W. F. (2000). Verification of acoustical correlates of emotional speech using formant-synthesis. In Proceedings of the ISCA workshop on speech & emotion (pp. 151\u2013156). Northern Ireland."},{"key":"9077_CR12","first-page":"211","volume-title":"Talking machines: theories, models and designs","author":"W. N. Campbell","year":"1992","unstructured":"Campbell, W. N. (1992). Syllable based segment duration. In G. Bailly, C. Benoit, & T. R. Sawallis (Eds.), Talking machines: theories, models and designs (pp. 211\u2013224). Amsterdam: Elsevier."},{"key":"9077_CR13","doi-asserted-by":"crossref","first-page":"140","DOI":"10.1159\/000261766","volume":"43","author":"R. Carlson","year":"1986","unstructured":"Carlson, R., & Granstrom, B. (1986). A search for durational rules in real speech database. Phonetica, 43, 140\u2013154.","journal-title":"Phonetica"},{"issue":"6","key":"9077_CR14","doi-asserted-by":"crossref","first-page":"558","DOI":"10.1109\/TSA.2003.818114","volume":"11","author":"J. T. Chien","year":"2003","unstructured":"Chien, J. T., & Huang, C. H. (2003). Bayesian learning of speech duration models. IEEE Transactions on Speech and Audio Processing, 11(6), 558\u2013567.","journal-title":"IEEE Transactions on Speech and Audio Processing"},{"key":"9077_CR15","doi-asserted-by":"crossref","unstructured":"Chung, H. (2002). Duration models and the perceptual evaluation of spoken Korean. In Proceedings of speech prosody (pp. 219\u2013222). France.","DOI":"10.21437\/SpeechProsody.2002-40"},{"key":"9077_CR16","doi-asserted-by":"crossref","unstructured":"Cordoba, R., Montero, J. M., Gutierrez-Ariola, J., & Pardo, J. M. (2001). Duration modeling in a restricted-domain female-voice synthesis in Spanish using neural networks. In Proceedings of ICASSP\u201901 (pp.\u00a0793\u2013796). Utah, USA.","DOI":"10.1109\/ICASSP.2001.941034"},{"issue":"4","key":"9077_CR17","doi-asserted-by":"crossref","first-page":"1553","DOI":"10.1121\/1.395911","volume":"83","author":"T. H. Crystal","year":"1988","unstructured":"Crystal, T. H., & House, A. S. (1988). Segmental durations in connected-speech signals: current results. Journal of the Acoustical Society of America, 83(4), 1553\u20131573.","journal-title":"Journal of the Acoustical Society of America"},{"key":"9077_CR18","doi-asserted-by":"crossref","DOI":"10.1007\/978-94-011-5730-8","volume-title":"An introduction to text-to-speech synthesis","author":"T. Dutoit","year":"1997","unstructured":"Dutoit, T. (1997). An introduction to text-to-speech synthesis. Dordrecht: Kluwer Academic."},{"key":"9077_CR19","doi-asserted-by":"crossref","unstructured":"Epitropakis, G., Tambakas, D., Fakotakis, N., & Kokkinakis, G. (1993). Duration modelling for the Greek language. In Proceedings of EUROSPEECH\u201993 (pp.\u00a01995\u20131998). Berlin, Germany.","DOI":"10.21437\/Eurospeech.1993-451"},{"key":"9077_CR20","unstructured":"Febrer, A., Padrell, J., & Bonafonte, A. (1998). Modeling phone duration: application to Catalan TTS. In Workshop of speech synthesis (pp. 43\u201346). Australia."},{"issue":"5","key":"9077_CR21","doi-asserted-by":"crossref","first-page":"1189","DOI":"10.1214\/aos\/1013203451","volume":"29","author":"J. H. Friedman","year":"2001","unstructured":"Friedman, J. H. (2001). Greedy function approximation: a gradient boosting machine. Annals of Statistics, 29(5), 1189\u20131232.","journal-title":"Annals of Statistics"},{"issue":"4","key":"9077_CR22","doi-asserted-by":"crossref","first-page":"367","DOI":"10.1016\/S0167-9473(01)00065-2","volume":"38","author":"J. H. Friedman","year":"2002","unstructured":"Friedman, J. H. (2002). Stochastic gradient boosting. Computational Statistics and Data Analysis, 38(4), 367\u2013378.","journal-title":"Computational Statistics and Data Analysis"},{"key":"9077_CR23","first-page":"43","volume-title":"Proceedings of the 21st international conference on machine learning","author":"R. Gilad-Bachrach","year":"2004","unstructured":"Gilad-Bachrach, R., Navot, A., & Tishby, N. (2004). Margin based feature selection\u2014theory and algorithms. In P. Tadepalli, R. Givan, & K. Driessens (Eds.), Proceedings of the 21st international conference on machine learning (pp. 43\u201350). Banff: Morgan Kaufmann."},{"key":"9077_CR24","volume-title":"Genetic algorithms in search, optimization and machine learning","author":"D. E. Goldberg","year":"1989","unstructured":"Goldberg, D. E. (1989). Genetic algorithms in search, optimization and machine learning. Boston: Addison\u2013Wesley\/Longman."},{"key":"9077_CR25","doi-asserted-by":"crossref","first-page":"301","DOI":"10.1016\/j.specom.2007.10.002","volume":"50","author":"O. Goubanova","year":"2008","unstructured":"Goubanova, O., & King, S. (2008). Bayesian network for phone duration prediction. Speech Communication, 50, 301\u2013311.","journal-title":"Speech Communication"},{"key":"9077_CR26","unstructured":"Goubanova, O., & Taylor, P. (2000). Using Bayesian belief networks for modeling duration in text-to-speech systems. In Proceedings of the ICSLP\u201900 (pp.\u00a0427\u2013431). Beijing, China."},{"issue":"5","key":"9077_CR27","first-page":"27","volume":"110","author":"M. Gregory","year":"2001","unstructured":"Gregory, M., Bell, A., Jurafsky, D., & Raymond, W. (2001). Frequency and predictability effects on the duration of content words in conversation. Journal of the Acoustical Society of America, 110(5), 27\u201338.","journal-title":"Journal of the Acoustical Society of America"},{"key":"9077_CR28","unstructured":"Hall, M. A. (1999). Correlation-based feature subset selection for machine learning. PhD thesis, Department of Computer Science, University of Waikato, Waikato, New Zealand."},{"key":"9077_CR29","first-page":"359","volume-title":"Proceedings of the 17th international conference on machine learning","author":"M. A. Hall","year":"2000","unstructured":"Hall, M. A. (2000). Correlation-based feature selection for discrete and numeric class machine learning. In P. Langley (Ed.), Proceedings of the 17th international conference on machine learning (pp. 359\u2013366). San Francisco: Morgan Kaufmann."},{"key":"9077_CR30","doi-asserted-by":"crossref","unstructured":"Heuft, B., Portele, T., & Rauth, M. (1996). Emotions in time domain synthesis. In Proceedings of ICSLP\u201996 (pp.\u00a01974\u20131977). Philadelphia, USA.","DOI":"10.1109\/ICSLP.1996.608023"},{"key":"9077_CR31","doi-asserted-by":"crossref","first-page":"268","DOI":"10.1016\/j.specom.2008.09.006","volume":"51","author":"Z. Inanoglu","year":"2009","unstructured":"Inanoglu, Z., & Young, S. (2009). Data-driven emotion conversion in spoken English. Speech Communication, 51, 268\u2013283.","journal-title":"Speech Communication"},{"key":"9077_CR32","unstructured":"Iida, A., Campbell, N., Iga, S., Higuchi, F., & Yasumura, M. (2000). A speech synthesis system for assisting communication. In Proceedings of the ISCA workshop on speech & emotion (pp. 167\u2013172). Northern Ireland."},{"issue":"7","key":"9077_CR33","first-page":"1550","volume":"E83-D","author":"N. Iwahashi","year":"2000","unstructured":"Iwahashi, N., & Sagisaka, Y. (2000). Statistical modeling of speech segment duration by constrained tree regression. IEICE Transactions on Information and Systems, E83-D(7), 1550\u20131559.","journal-title":"IEICE Transactions on Information and Systems"},{"key":"9077_CR34","unstructured":"Jiang, D. N., Zhang, W., Shen, L., & Cai, L. H. (2005). Prosody analysis and modeling for emotional speech synthesis. In Proceedings of ICASSP\u201905 (pp.\u00a0281\u2013284). Philadelphia, USA."},{"key":"9077_CR35","first-page":"1107","volume":"5","author":"M. K\u00e4\u00e4ri\u00e4inen","year":"2004","unstructured":"K\u00e4\u00e4ri\u00e4inen, M., & Malinen, T. (2004). Selective rademacher penalization and reduced error pruning of decision trees. Journal of Machine Learning Research, 5, 1107\u20131126.","journal-title":"Journal of Machine Learning Research"},{"key":"9077_CR36","first-page":"249","volume-title":"Proceedings of the 9th international conference on machine learning","author":"K. Kira","year":"1992","unstructured":"Kira, K., & Rendell, L. A. (1992). A practical approach to feature selection. In Sleeman, & P. Edwards (Eds.), Proceedings of the 9th international conference on machine learning (pp. 249\u2013256). Aberdeen, Scotland. San Francisco: Morgan Kaufmann."},{"key":"9077_CR37","doi-asserted-by":"crossref","first-page":"1209","DOI":"10.1121\/1.380986","volume":"59","author":"D. H. Klatt","year":"1976","unstructured":"Klatt, D. H. (1976). Linguistic uses of segmental duration in English: Acoustic and perceptual evidence. Journal of the Acoustical Society of America, 59, 1209\u20131221.","journal-title":"Journal of the Acoustical Society of America"},{"key":"9077_CR38","first-page":"287","volume-title":"Frontiers of speech communication research","author":"D. H. Klatt","year":"1979","unstructured":"Klatt, D. H. (1979). Synthesis by rule of segmental durations in English sentences. In B. Lindlom & S. Ohman (Eds.), Frontiers of speech communication research (pp. 287\u2013300). New York: Academic Press."},{"issue":"3","key":"9077_CR39","doi-asserted-by":"crossref","first-page":"737","DOI":"10.1121\/1.395275","volume":"82","author":"D. H. Klatt","year":"1987","unstructured":"Klatt, D. H. (1987). Review of text-to-speech conversion for English. Journal of the Acoustical Society of America, 82(3), 737\u2013793.","journal-title":"Journal of the Acoustical Society of America"},{"key":"9077_CR40","first-page":"165","volume":"6","author":"K. J. Kohler","year":"1988","unstructured":"Kohler, K. J. (1988). Zeistrukturierung in der Sprachsynthese. ITG-Tagung Digitalc Sprachverarbeitung, 6, 165\u2013170.","journal-title":"ITG-Tagung Digitalc Sprachverarbeitung"},{"key":"9077_CR41","unstructured":"Kominek, J., & Black, A. W. (2003). CMU ARCTIC databases for speech synthesis, CMU-LTI-03-177, Language Technologies Institute, School of Computer Science, Carnegie Mellon University."},{"key":"9077_CR42","first-page":"171","volume-title":"Proceedings of the European conference machine learning","author":"I. Kononenko","year":"1994","unstructured":"Kononenko, I. (1994). Estimating attributes: analysis and extensions of relief. In F. Bergadano & L. De Raedt (Eds.), Proceedings of the European conference machine learning (pp. 171\u2013182). New York: Springer."},{"key":"9077_CR43","unstructured":"Krishna, N. S., & Murthy, H. A. (2004). Duration modeling of Indian languages Hindi and Telugu. In Proceedings of the 5th ISCA speech synthesis workshop (pp. 197\u2013202). Pittsburgh, USA."},{"key":"9077_CR44","unstructured":"Krishna, N. S., Talukdar, P. P., Bali, K., & Ramakrishnan, A. G. (2004). Duration modeling for Hindi text-to-speech synthesis system. In Proceedings of ICSLP\u201904 (pp.\u00a0789\u2013792). Jeju Island, Korea."},{"key":"9077_CR45","doi-asserted-by":"crossref","unstructured":"Lazaridis, A., Zervas, P., & Kokkinakis, G. (2007). Segmental duration modeling for Greek speech synthesis. In Proceedings of ICTAI\u201907 (pp.\u00a0518\u2013521). Patras, Greece.","DOI":"10.1109\/ICTAI.2007.33"},{"key":"9077_CR46","doi-asserted-by":"crossref","first-page":"283","DOI":"10.1016\/S0167-6393(99)00014-X","volume":"28","author":"S. Lee","year":"1999","unstructured":"Lee, S., & Oh, Y. H. (1999a). Tree-based modeling of prosodic phrasing and segmental duration for Korean TTS systems. Speech Communication, 28, 283\u2013300.","journal-title":"Speech Communication"},{"key":"9077_CR47","unstructured":"Lee, S., & Oh, Y. H. (1999b). CART-based modelling of Korean segmental duration. In Proceedings of the oriental COCOSDA\u201999 (pp.\u00a0109\u2013112). Taipei, Taiwan."},{"key":"9077_CR48","doi-asserted-by":"crossref","unstructured":"M\u00f6bius, B., & Santen, P. H. J. (1996). Modeling segmental duration in German text-to-speech synthesis. In Proceedings of ICSLP\u201996 (pp.\u00a02395\u20132398). Philadelphia, USA.","DOI":"10.1109\/ICSLP.1996.607291"},{"key":"9077_CR49","doi-asserted-by":"crossref","first-page":"369","DOI":"10.1016\/0167-6393(95)00005-9","volume":"16","author":"I. R. Murray","year":"1995","unstructured":"Murray, I. R., & Arnott, J. L. (1995). Implementation and testing of a system for producing emotion-by-rule in synthetic speech. Speech Communication, 16, 369\u2013390.","journal-title":"Speech Communication"},{"key":"9077_CR50","first-page":"84","volume-title":"Human emotions: a reader","author":"K. Oatley","year":"1998","unstructured":"Oatley, K., & Johnson-Laird, P. (1998). The communicative theory of emotions. In J. Jenkins, K. Oatley, & N. Stein (Eds.), Human emotions: a reader (pp. 84\u201387). Oxford: Blackwell."},{"issue":"1","key":"9077_CR51","doi-asserted-by":"crossref","first-page":"S6","DOI":"10.1121\/1.2022951","volume":"78","author":"J. P. Olive","year":"1985","unstructured":"Olive, J. P., & Liberman, M. Y. (1985). Text to speech\u2014an overview. Journal of the Acoustical Society of America, 78(1), S6.","journal-title":"Journal of the Acoustical Society of America"},{"key":"9077_CR52","unstructured":"Quinlan, R. J. (1992). Learning with continuous classes. In Proceedings of the 5th Australian Joint Conference on Artificial Intelligence (pp. 343\u2013348). Hobart, Tasmania."},{"key":"9077_CR53","doi-asserted-by":"crossref","unstructured":"Rank, E., & Pirker, H. (1998). Generating Emotional Speech with a Concatenative Synthesizer. In Proceedings of ICSLP\u201998 (pp.\u00a0671\u2013674). Sydney, Australia.","DOI":"10.21437\/ICSLP.1998-134"},{"issue":"2","key":"9077_CR54","doi-asserted-by":"crossref","first-page":"282","DOI":"10.1016\/j.csl.2006.06.003","volume":"21","author":"K. S. Rao","year":"2007","unstructured":"Rao, K. S., & Yegnanarayana, B. (2007). Modeling durations of syllables using neural networks. Computer Speech & Language, 21(2), 282\u2013295.","journal-title":"Computer Speech & Language"},{"key":"9077_CR55","first-page":"265","volume-title":"Talking machines: theories, models and designs","author":"M. Riley","year":"1992","unstructured":"Riley, M. (1992). Tree-based modelling for speech synthesis. In G. Bailly, C. Benoit, & T. R. Sawallis (Eds.), Talking machines: theories, models and designs (pp. 265\u2013273). Amsterdam: Elsevier."},{"key":"9077_CR56","first-page":"296","volume-title":"Proceedings of the 14th international conference on machine learning","author":"M. Robnik-Sikonja","year":"1997","unstructured":"Robnik-Sikonja, M., & Kononenko, I. (1997). An adaptation of relief for attribute estimation in regression. In D. H. Fisher (Ed.), Proceedings of the 14th international conference on machine learning (pp. 296\u2013304). San Francisco: Morgan Kaufmann."},{"key":"9077_CR57","doi-asserted-by":"crossref","unstructured":"Silverman, K., Beckman, M., Pitrelli, J., Ostendorf, M., Wightman,\u00a0C., Price, P., Pierrehumbert, J., & Hirschberg, J. (1992). ToBI: a standard for labeling English prosody. In Proceedings of ICSLP\u201992 (pp.\u00a0867\u2013870). Banff, Alberta, Canada.","DOI":"10.21437\/ICSLP.1992-260"},{"key":"9077_CR58","unstructured":"Simoes, A. R. M. (1990). Predicting sound segment duration in connected speech: an acoustical study of Brazilian Portuguese. In Proceedings of the workshop on speech synthesis (pp. 173\u2013176). Autrans, France."},{"issue":"6","key":"9077_CR59","doi-asserted-by":"crossref","first-page":"2081","DOI":"10.1121\/1.398467","volume":"86","author":"K. Takeda","year":"1989","unstructured":"Takeda, K., Sagisaka, Y., & Kuwabara, H. (1989). On sentence-level factors governing segmental duration in Japanese. Journal of Acoustic Society of America, 86(6), 2081\u20132087.","journal-title":"Journal of Acoustic Society of America"},{"key":"9077_CR60","doi-asserted-by":"crossref","unstructured":"Tesser, F., Cosi, P., Drioli, C., & Tisato, G. (2005). Emotional festival-mbrola TTS synthesis. In Proceedings of INTERSPEECH\u201905 (pp.\u00a0505\u2013508). Lisboa, Portugal.","DOI":"10.21437\/Interspeech.2005-327"},{"key":"9077_CR61","doi-asserted-by":"crossref","unstructured":"Teixeira, J. P., & Freitas, D. (2003). Segmental durations predicted with a neural network. In Proceedings of EUROSPEECH\u201903 (pp.\u00a0169\u2013172). Geneva, Switzerland, September.","DOI":"10.21437\/Eurospeech.2003-91"},{"key":"9077_CR62","doi-asserted-by":"crossref","first-page":"513","DOI":"10.1016\/0167-6393(92)90027-5","volume":"11","author":"J. P. H. Santen van","year":"1992","unstructured":"van Santen, J. P. H. (1992). Contextual effects on vowel durations. Speech Communication, 11, 513\u2013546.","journal-title":"Speech Communication"},{"issue":"2","key":"9077_CR63","doi-asserted-by":"crossref","first-page":"95","DOI":"10.1006\/csla.1994.1005","volume":"8","author":"J. P. H. Santen van","year":"1994","unstructured":"van Santen, J. P. H. (1994). Assignment of segmental duration in text-to-speech synthesis. Computer Speech & Language, 8(2), 95\u2013128.","journal-title":"Computer Speech & Language"},{"key":"9077_CR64","unstructured":"Wang, Y., & Witten, I. H. (1997). Induction of model trees for predicting continuous classes. In Proceedings of the 9th European conference on machine learning (pp. 128\u2013137). University of Economics, Faculty of Informatics and Statistics, Prague, Czech."},{"key":"9077_CR65","unstructured":"Wang, L., Zhao, Y., Chu, M., Zhou, J., & Cao, Z. (2004). Refining segmental boundaries for TTS database using fine contextual-dependent boundary models. In Proceedings of ICASSP\u201904 (pp.\u00a0641\u2013644). Montreal, Canada."},{"key":"9077_CR66","volume-title":"Data mining: practical machine learning tools and techniques","author":"H. I. Witten","year":"2005","unstructured":"Witten, H. I., & Frank, E. (2005). Data mining: practical machine learning tools and techniques (2nd ed.) San Francisco: Morgan Kaufmann.","edition":"2"},{"issue":"5","key":"9077_CR67","doi-asserted-by":"crossref","first-page":"405","DOI":"10.1016\/j.specom.2007.12.003","volume":"50","author":"J. Yamagishi","year":"2008","unstructured":"Yamagishi, J., Kawai, H., & Kobayashi, T. (2008). Phone duration modeling using gradient tree boosting. Speech Communication, 50(5), 405\u2013415.","journal-title":"Speech Communication"},{"key":"9077_CR68","volume-title":"Artificial neural networks","author":"B. Yegnanarayana","year":"1999","unstructured":"Yegnanarayana, B. (1999). Artificial neural networks. New Delhi: Prentice Hall."}],"container-title":["International Journal of Speech Technology"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s10772-010-9077-x.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/article\/10.1007\/s10772-010-9077-x\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s10772-010-9077-x","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,2,23]],"date-time":"2025-02-23T15:43:09Z","timestamp":1740325389000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/s10772-010-9077-x"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2010,7,30]]},"references-count":68,"journal-issue":{"issue":"3","published-print":{"date-parts":[[2010,9]]}},"alternative-id":["9077"],"URL":"https:\/\/doi.org\/10.1007\/s10772-010-9077-x","relation":{},"ISSN":["1381-2416","1572-8110"],"issn-type":[{"type":"print","value":"1381-2416"},{"type":"electronic","value":"1572-8110"}],"subject":[],"published":{"date-parts":[[2010,7,30]]}}}