{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,3,14]],"date-time":"2024-03-14T17:29:42Z","timestamp":1710437382187},"reference-count":26,"publisher":"Springer Science and Business Media LLC","issue":"2","license":[{"start":{"date-parts":[[2013,9,24]],"date-time":"2013-09-24T00:00:00Z","timestamp":1379980800000},"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":[[2014,6]]},"DOI":"10.1007\/s10772-013-9210-8","type":"journal-article","created":{"date-parts":[[2013,9,23]],"date-time":"2013-09-23T11:05:19Z","timestamp":1379934319000},"page":"91-98","source":"Crossref","is-referenced-by-count":3,"title":["Syllable based text to speech synthesis system using auto associative neural network prosody prediction"],"prefix":"10.1007","volume":"17","author":[{"given":"Sudhakar","family":"Sangeetha","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Sekar","family":"Jothilakshmi","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2013,9,24]]},"reference":[{"key":"9210_CR1","doi-asserted-by":"crossref","first-page":"581","DOI":"10.21437\/Eurospeech.1995-148","volume-title":"Proc. EUROSPEECH","author":"A. W. Black","year":"1995","unstructured":"Black, A. W., & Cambpbell, N. (1995). Optimising selection of units from speech database for concatenative synthesis. In Proc. EUROSPEECH (pp. 581\u2013584)."},{"key":"9210_CR2","volume-title":"Proc. ICSLP","author":"A. W. Black","year":"2000","unstructured":"Black, A. W., & Lenzo, K. A. (2000). Limited domain synthesis. In Proc. ICSLP, Beijing, China."},{"issue":"4","key":"9210_CR3","doi-asserted-by":"crossref","first-page":"317","DOI":"10.1016\/j.specom.2007.01.014","volume":"49","author":"R. A. Clark","year":"2007","unstructured":"Clark, R. A., Richmond, K., & King, S. (2007). Multisyn: open-domain unit selection for the festival speech synthesis system. Speech Communication, 49(4), 317\u2013330.","journal-title":"Speech Communication"},{"issue":"3","key":"9210_CR4","doi-asserted-by":"crossref","first-page":"223","DOI":"10.1006\/csla.1999.0123","volume":"13","author":"R. Donovan","year":"1999","unstructured":"Donovan, R., & Woodland, P. (1999). A hidden markov-model-based trainable speech synthesizer. Computer Speech & Language, 13(3), 223\u2013241.","journal-title":"Computer Speech & Language"},{"key":"9210_CR5","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. Norwell: Kluwer Academic."},{"issue":"13","key":"9210_CR6","doi-asserted-by":"crossref","first-page":"305","DOI":"10.1016\/0004-3702(93)90020-C","volume":"63","author":"J. Hirschberg","year":"1993","unstructured":"Hirschberg, J. (1993). Pitch accent in context: predicting intonational prominence from text. Artificial Intelligence, 63(13), 305\u2013340.","journal-title":"Artificial Intelligence"},{"key":"9210_CR7","first-page":"373","volume-title":"Proc. ICASSP","author":"A. Hunt","year":"1996","unstructured":"Hunt, A., & Black, A. W. (1996). Unit selection in a concatenative speech synthesis system using a large speech database. In Proc. ICASSP (pp. 373\u2013376)."},{"key":"9210_CR8","volume-title":"Proc. Blizzard Challenge workshop","author":"V. Karaiskos","year":"2008","unstructured":"Karaiskos, V., King, S., Clark, R. A. J., & Mayo, C. (2008). The Blizzard Challenge 2008. In Proc. Blizzard Challenge workshop, Risbane, Australia."},{"key":"9210_CR9","doi-asserted-by":"crossref","first-page":"1317","DOI":"10.21437\/Eurospeech.2003-133","volume-title":"Proc. of EUROSPEECH","author":"S. P. Kishore","year":"2003","unstructured":"Kishore, S. P., & Black, A. (2003). Unit size in unit selection speech synthesis. In Proc. of EUROSPEECH (pp. 1317\u20131320)."},{"key":"9210_CR10","unstructured":"Kominek, J., & Black, A. (2003). CMU ARCTIC databases for speech synthesis. Language Technologies Institute."},{"key":"9210_CR11","volume-title":"National conference on communications (NCC)","author":"E. Raghavendra","year":"2010","unstructured":"Raghavendra, E., & Prahallad, K. (2010). A multilingual screen reader in Indian languages. In National conference on communications (NCC), Chennai, India."},{"key":"9210_CR12","first-page":"389","volume-title":"Proc. IEEE int. conf. multimedia and expo","author":"K. S. Rao","year":"2003","unstructured":"Rao, K. S., & Yegnanarayana, B. (2003). Prosodic manipulation using instants of significant excitation. In Proc. IEEE int. conf. multimedia and expo, Baltimore Maryland, USA (pp. 389\u2013392)."},{"key":"9210_CR13","first-page":"227","volume-title":"Proc. of national conference on communication (NCC)","author":"M. N. Rao","year":"2005","unstructured":"Rao, M. N., Thomas, S., Nagarajan, T., & Murthy, H. A. (2005). Text-to-speech synthesis using syllable like units. In Proc. of national conference on communication (NCC), IIT Kharagpur, India (pp.\u00a0227\u2013280)."},{"key":"9210_CR14","volume-title":"Proc. Eurospeech","author":"R. A. J. Clark","year":"1999","unstructured":"Clark, R. A. J., & Dusterho, K. E. (1999). Objective methods for evaluating synthetic intonation. In Proc. Eurospeech, Budapest, Hungary."},{"issue":"2","key":"9210_CR15","first-page":"202","volume":"73","author":"S. Lokesh","year":"2012","unstructured":"Lokesh, S., & Balakrishnan, G. (2012). Speech enhancement using mel-LPC cepstrum and vector quantization for ASR. European Journal of Scientific Research, 73(2), 202\u2013209.","journal-title":"European Journal of Scientific Research"},{"issue":"5","key":"9210_CR16","doi-asserted-by":"crossref","first-page":"244","DOI":"10.4314\/ijest.v2i5.60157","volume":"2","author":"S. Saraswathi","year":"2010","unstructured":"Saraswathi, S., & Geetha, T. V. (2010). Design of language models at various phases of Tamil speech recognition system. International Journal of Engineering Science and Technology, 2(5), 244\u2013257.","journal-title":"International Journal of Engineering Science and Technology"},{"key":"9210_CR17","first-page":"411","volume-title":"Proc. ICSLP","author":"A. Syrdal","year":"2000","unstructured":"Syrdal, A., Wightman, C., Conkie, A., Stylianou, Y., Beutnagel, M., Schroeter, J., Storm, V., Lee, K., & Makashay, M. (2000). Corpus-based techniques in the at and t nextgen synthesis system. In Proc. ICSLP (pp. 411\u2013416)."},{"key":"9210_CR18","volume-title":"Proc. of 14th European signal processing conference","author":"M. S. Thomas","year":"2006","unstructured":"Thomas, M. S., Rao, N., Murthy, H. A., & Ramalingam, C. S. (2006). Natural sounding tts based on syllable-like units. In Proc. of 14th European signal processing conference, Florence, Italy."},{"key":"9210_CR19","first-page":"13","volume-title":"Proc. of IEEE workshop on applications of signal processing to audio and acoustics","author":"S. Varho","year":"1997","unstructured":"Varho, S., & Alku, P. (1997). Linear predictive method using extrapolated samples for modeling of voiced speech. In Proc. of IEEE workshop on applications of signal processing to audio and acoustics (pp. 13\u201316)."},{"key":"9210_CR20","first-page":"29","volume-title":"Proc. of spoken language technology (SLT) workshop","author":"Y. R. Venugopalakrishna","year":"2008","unstructured":"Venugopalakrishna, Y. R., Vinodh, M. V., Murthy, H. A., & Ramalingam, C. S. (2008). Methods for improving the quality of syllable based speech synthesis. In Proc. of spoken language technology (SLT) workshop, Goa (pp. 29\u201332)."},{"issue":"6","key":"9210_CR21","doi-asserted-by":"crossref","first-page":"1208","DOI":"10.1109\/TASL.2009.2016394","volume":"17","author":"J. Yamagishi","year":"2009","unstructured":"Yamagishi, J., Nose, T., Zen, H., Ling, Z. H., Toda, T., Tokuda, K., King, S., & Renals, S. (2009). A robust speaker-adaptive HMM-based text-to-speech synthesis. IEEE Transactions on Audio, Speech, and Language Processing, 17(6), 1208\u20131230.","journal-title":"IEEE Transactions on Audio, Speech, and Language Processing"},{"key":"9210_CR22","volume-title":"Artificial neural networks","author":"B. Yegnanarayana","year":"1999","unstructured":"Yegnanarayana, B. (1999). Artificial neural networks. New Delhi: Prentice-Hall."},{"key":"9210_CR23","first-page":"2350","volume-title":"Proc. EUROSPEECH","author":"T. Yoshimura","year":"1999","unstructured":"Yoshimura, T., Tokuda, K., Masuko, T., Kobayashi, T., & Kitamura, T. (1999). Simultaneous modeling of spectrum pitch and duration in hmm-based speech synthesis. In Proc. EUROSPEECH (pp. 2350\u20132374)."},{"issue":"11","key":"9210_CR24","first-page":"2099","volume":"83-D-II","author":"T. Yoshimura","year":"2000","unstructured":"Yoshimura, T., Tokuda, K., Masuko, T., Kobayashi, T., & Kitamura, T. S. (2000). Simultaneous modeling of spectrum pitch and duration in hmm-based speech synthesis. IEICE Transactions, 83-D-II(11), 2099\u20132107.","journal-title":"IEICE Transactions"},{"issue":"1","key":"9210_CR25","doi-asserted-by":"crossref","first-page":"325","DOI":"10.1093\/ietisy\/e90-1.1.325","volume":"90-D","author":"H. Zen","year":"2007","unstructured":"Zen, H., Toda, T., Nakamura, M., & Tokuda, K. (2007). Details of nitech hmm based speech synthesis system for the blizzard challenge 2005. IEICE Transactions on Information and Systems, 90-D(1), 325\u2013333.","journal-title":"IEICE Transactions on Information and Systems"},{"issue":"11","key":"9210_CR26","doi-asserted-by":"crossref","first-page":"1039","DOI":"10.1016\/j.specom.2009.04.004","volume":"51","author":"H. Zen","year":"2009","unstructured":"Zen, H., Tokuda, K., & Black, A. W. (2009). Statistical parametric speech synthesis. Speech Communication, 51(11), 1039\u20131064.","journal-title":"Speech Communication"}],"container-title":["International Journal of Speech Technology"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s10772-013-9210-8.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/article\/10.1007\/s10772-013-9210-8\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s10772-013-9210-8","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,7,4]],"date-time":"2023-07-04T19:20:24Z","timestamp":1688498424000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/s10772-013-9210-8"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2013,9,24]]},"references-count":26,"journal-issue":{"issue":"2","published-print":{"date-parts":[[2014,6]]}},"alternative-id":["9210"],"URL":"https:\/\/doi.org\/10.1007\/s10772-013-9210-8","relation":{},"ISSN":["1381-2416","1572-8110"],"issn-type":[{"value":"1381-2416","type":"print"},{"value":"1572-8110","type":"electronic"}],"subject":[],"published":{"date-parts":[[2013,9,24]]}}}