{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,7,27]],"date-time":"2024-07-27T06:34:25Z","timestamp":1722062065998},"reference-count":52,"publisher":"Springer Science and Business Media LLC","issue":"2","license":[{"start":{"date-parts":[[2010,5,20]],"date-time":"2010-05-20T00:00:00Z","timestamp":1274313600000},"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":[[2010,6]]},"DOI":"10.1007\/s10772-010-9071-3","type":"journal-article","created":{"date-parts":[[2010,5,19]],"date-time":"2010-05-19T09:26:59Z","timestamp":1274261219000},"page":"85-99","source":"Crossref","is-referenced-by-count":2,"title":["Polish unit selection speech synthesis with BOSS: extensions and\u00a0speech corpora"],"prefix":"10.1007","volume":"13","author":[{"given":"Gra\u017cyna","family":"Demenko","sequence":"first","affiliation":[]},{"given":"Katarzyna","family":"Klessa","sequence":"additional","affiliation":[]},{"given":"Marcin","family":"Szyma\u0144ski","sequence":"additional","affiliation":[]},{"given":"Stefan","family":"Breuer","sequence":"additional","affiliation":[]},{"given":"Wolfgang","family":"Hess","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2010,5,20]]},"reference":[{"key":"9071_CR1","unstructured":"Baranowska, E., Francuzik, K., Karpi\u0144ski, M., & Kle\u015bta, J. (2003). Identification of nuclear melody. Placement in Polish read texts. In A. Mettouchi & G. Ferre (Eds.), Interfaces prosodiques, Nantes, France."},{"key":"9071_CR2","doi-asserted-by":"crossref","unstructured":"Batusek, R. A. (2002). Duration model for Czech text-to-speech synthesis. In Proc. of speech prosody, Aix-en-Provence, France.","DOI":"10.21437\/SpeechProsody.2002-27"},{"key":"9071_CR3","unstructured":"Bonafonte, A., H\u00f6ge, H., Kiss, I., Moreno, A., Ziegenhain, U., van\u00a0den Heuvel, H., Hain, H.-U., Wang, X. S., & Garcia, M. N. (2006). TC-STAR: Specifications of language resources and evaluation for speech synthesis. In Proceedings of LREC (international conference on language resources and evaluation), Genoa, Italy."},{"key":"9071_CR4","unstructured":"Bonafonte, A., Lourdes, A., Esquerra1, I., Oller, S., & Moreno, A. (2009). Recent work on the FESTCAT database for speech synthesis. In Proceedings of the I Iberian SLTech 2009, Porto Salvo, Portugal."},{"key":"9071_CR5","volume-title":"Classification and regression trees","author":"L. Breiman","year":"1984","unstructured":"Breiman, L., Friedman, J. H., Olshen, R. A., & Stone, C. J. (1984). Classification and regression trees. Monterey: Wadsworth & Brooks\/Cole Advanced Books & Software."},{"key":"9071_CR6","unstructured":"Breuer, S., & Abresch, J. (2003). Unit selection speech synthesis for a directory enquiries service. In Proceedings of the ICPhS, Barcelona, Spain."},{"key":"9071_CR7","unstructured":"Campbell, N. (1992). Multi-level timing in speech University of Sussex. PhD Thesis. (Exp. Psychol): Brighton, UK."},{"key":"9071_CR8","doi-asserted-by":"crossref","unstructured":"Chung, H., & Huckvale, M. A. (2001). Linguistic factors affecting timing in Korean with application to speech synthesis. In Proceedings of Eurospeech, Scandinavia.","DOI":"10.21437\/Eurospeech.2001-252"},{"key":"9071_CR9","volume-title":"Intonation","author":"A. Cruttenden","year":"1994","unstructured":"Cruttenden, A. (1994). Intonation. Cambridge: Cambridge University Press."},{"key":"9071_CR10","volume-title":"Analiza cech suprasegmentalnych j\u0119zyka polskiego na potrzeby syntezy mowy","author":"G. Demenko","year":"1999","unstructured":"Demenko, G. (1999). Analiza cech suprasegmentalnych j\u0119zyka polskiego na potrzeby syntezy mowy. Pozna\u0144: Wydawnictwo Naukowe UAM."},{"key":"9071_CR11","unstructured":"Demenko, G. (2005). Speech synthesis of Polish based on the concatenation phonetic-acoustic segments. In 2nd language & technology conference: Human language technologies as a challenge for computer science and linguistics, April 21\u201323, 2005, Pozna\u0144, Poland."},{"key":"9071_CR12","series-title":"Speech and language technology","volume-title":"Implementation of grapheme-to-phoneme rules and extended SAMPA alphabet in Polish text-to-speech synthesis","author":"G. Demenko","year":"2003","unstructured":"Demenko, G., Wypych, M., & Baranowska, E. (2003). Speech and language technology : Vol. 7. Implementation of grapheme-to-phoneme rules and extended SAMPA alphabet in Polish text-to-speech synthesis. Pozna\u0144: Edition PTFON."},{"key":"9071_CR13","doi-asserted-by":"crossref","unstructured":"Demenko, G., Bachan, J., M\u00f6bius, B., Klessa, K., Szyma\u0144ski, M., & Grocholewski, G. (2008). Development and evaluation of Polish speech corpus for unit selection speech synthesis systems. In Proceedings of Interspeech 2008, Brisbane, Australia.","DOI":"10.21437\/Interspeech.2008-458"},{"key":"9071_CR14","unstructured":"F\u00e9k, M., Pesti, P., N\u00e9meth, G., Zaink\u00f3, C., & Olaszy, G. (2006). Corpus-based unit selection TTS for Hungarian. TSD 2006 367-373 (retrieved from http:\/\/speechlab.tmit.bme.hu\/zainko\/ on 1 March 2010)."},{"key":"9071_CR15","unstructured":"Fujisaki, H., Hirose, K., & Takahashi, N. (1990). Manifestation of linguistic and paralinguistic information in the voice fundamental frequency contours of spoken Japanese. In Proceedings of ICSLP, Kobe, Japan."},{"key":"9071_CR16","unstructured":"Gardner-Bonneau, D. (Ed.) (2003). Special Issue on Speech Synthesis. International Journal of Speech Technology. Kluwer Academic Publishers."},{"key":"9071_CR17","volume-title":"Handbook of standards and resources for spoken language systems","author":"D. Gibbon","year":"1997","unstructured":"Gibbon, D., Moore, R., & Winski, R. (1997). Handbook of standards and resources for spoken language systems. Berlin: Mouton de Gruyter."},{"key":"9071_CR18","doi-asserted-by":"crossref","unstructured":"Grocholewski, S. (1997). Corpora\u2014speech database for Polish diphones. In Proceedings of Eurospeech\u201997 (pp.\u00a01735\u20131738).","DOI":"10.21437\/Eurospeech.1997-492"},{"key":"9071_CR19","volume-title":"Intonation systems. A survey of twenty languages","year":"1998","unstructured":"Hirst, D., & Di Cristo, A. (Eds.) (1998). Intonation systems. A survey of twenty languages. Cambridge: Cambridge University Press."},{"key":"9071_CR20","volume-title":"Akcent j\u0119zyka polskiego","author":"W. Jassem","year":"1962","unstructured":"Jassem, W. (1962). Akcent j\u0119zyka polskiego. Wroc\u0142aw: Ossolineum."},{"issue":"1","key":"9071_CR21","doi-asserted-by":"crossref","first-page":"103","DOI":"10.1017\/S0025100303001191","volume":"23","author":"W. Jassem","year":"2003","unstructured":"Jassem, W. (2003). Illustrations of the IPA: Polish. Journal of the Phonetic Association, 23(1), 103\u2013107.","journal-title":"Journal of the Phonetic Association"},{"key":"9071_CR22","first-page":"289","volume-title":"Speech analysis and synthesis 1","author":"W. Jassem","year":"1968","unstructured":"Jassem, W., Morton, J., & Steffen-Bat\u00f3g, M. (1968). The perception of stress in synthetic speech-like stimuli by Polish listeners. In W. Jassem (Ed.), Speech analysis and synthesis 1 (pp. 289\u2013308). Warszawa: Pa\u0144stwowe Wydawnictwo Naukowe."},{"key":"9071_CR23","unstructured":"Jassem, W., Krzy\u015bko, M., & Stolarski, P. (1981). IPPT PAN: Vol. 33. Regresyjny model izochronizmu zestrojowego w sygnale mowy, Warszawa."},{"key":"9071_CR24","unstructured":"Keating, P. (1979). A phonetic study of a voicing contrast in Polish. Unpublished doctoral dissertation, Brown University."},{"key":"9071_CR25","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 K. Lindblom & K. Ohman (Eds.), Frontiers of speech communication research. London: Academic Press."},{"key":"9071_CR26","unstructured":"Klessa, K. (2006). Analiza iloczasu g\u0142oskowego na potrzeby syntezy mowy polskiej. Unpublished doctoral dissertation, Adam Mickiewicz University, Pozna\u0144, Poland."},{"key":"9071_CR27","unstructured":"Klessa, K., Szyma\u0144ski, M., Breuer, S., & Demenko, G. (2007). Optimization of Polish segmental duration prediction with CART. In SSW6, Bonn."},{"key":"9071_CR28","unstructured":"Matou\u0161ek, J., Tihelka, D., & Romportl, J. (2008). Building of a speech corpus optimised for unit selection TTS synthesis. In Proceedings of LREC (international conference on language resources and evaluation), Marrakech, Morocco."},{"key":"9071_CR29","unstructured":"Mixdorff, H. (1998). Intonation patterns of German\u2014Model-based quantitative analysis and synthesis of F0-contours. PhD thesis submitted to TU Dresden."},{"key":"9071_CR30","series-title":"Forum Phoneticum","first-page":"79","volume-title":"Speech and signals: Aspects of speech synthesis and automatic speech recognition","author":"B. M\u00f6bius","year":"2000","unstructured":"M\u00f6bius, B. (2000). Corpus-based speech synthesis: Methods and challenges. In W. Sendlmeier (Ed.), Forum Phoneticum : Vol. 69. Speech and signals: Aspects of speech synthesis and automatic speech recognition (pp. 79\u201396). Frankfurt a. M.: Hector."},{"key":"9071_CR31","unstructured":"M\u00f6bius, B. (2001). Rare events and closed domains: Two delicate concepts in speech synthesis. In Fourth ISCA ITRW on speech synthesis, Perthshire, Scotland."},{"key":"9071_CR32","doi-asserted-by":"crossref","unstructured":"M\u00f6bius, B., & van Santen, J. P. H. (1996). Modeling segmental duration in German text-to-speech synthesis. In Proceedings of the international conference on spoken language processing (Vol.\u00a04, pp.\u00a02395\u20132398) Philadelphia, PA.","DOI":"10.1109\/ICSLP.1996.607291"},{"key":"9071_CR33","doi-asserted-by":"crossref","first-page":"150","DOI":"10.1177\/002383096500800303","volume":"8","author":"J. Morton","year":"1965","unstructured":"Morton, J., & Jassem, W. (1965). Acoustic correlates of stress. Language and Speech, 8, 150\u2013181.","journal-title":"Language and Speech"},{"issue":"5","key":"9071_CR34","doi-asserted-by":"crossref","first-page":"360","DOI":"10.1109\/89.536930","volume":"4","author":"M. Ostendorf","year":"1996","unstructured":"Ostendorf, M., Digalakis, Vassilios V., & Kimball, Owen A. (1996). From HMM\u2019s to segment models: A unified view of stochastic modeling for speech recognition. IEEE Transactions on Speech and Audio Processing, 4(5), 360\u2013378.","journal-title":"IEEE Transactions on Speech and Audio Processing"},{"key":"9071_CR35","unstructured":"Richter, L. (1974). Por\u00f3wnanie iloczasu samog\u0142osek polskich wym\u00f3wionych w logatomach oraz w wyrazach. In Biuletyn Polskiego towarzystwa fonetycznego (Vol.\u00a032, pp.\u00a0173\u2013178)."},{"key":"9071_CR36","unstructured":"Richter, L. (1978). Wp\u0142yw pozycji w zestroju akcentowym na czas trwania g\u0142osek. In Lingua Posnaniensia, Vol. 21, Pozna\u0144, Poland."},{"key":"9071_CR37","unstructured":"Riedi, M. P. (1998). Controlling segmental duration in speech synthesis systems. PhD thesis, TIK-Schriftenreihe (26), ETH Z\u00fcrich."},{"key":"9071_CR38","doi-asserted-by":"crossref","DOI":"10.1007\/978-1-4612-2258-3","volume-title":"Computing prosody, computational models for processing spontaneous speech","author":"Y. Sagisaka","year":"1997","unstructured":"Sagisaka, Y., Campbell, N., & Higuchi, N. (1997). Computing prosody, computational models for processing spontaneous speech. New York: Springer."},{"key":"9071_CR39","unstructured":"\u015aledzi\u0144ski, D. (2007). Fonetyczno-akustyczna analiza struktury sylaby w j\u0119zyku polskim na potrzeby technologii mowy. Unpublished PhD Thesis, Adam Mickiewicz University, Pozna\u0144, Poland."},{"key":"9071_CR40","volume-title":"Studia phonetica posnaniensia","author":"M. Steffen-Bat\u00f3g","year":"1993","unstructured":"Steffen-Bat\u00f3g, M., & Nowakowski, P. (1993). An algorithm for phonetic transcription of orthographic texts in Polish. In M. Steffen-Bat\u00f3g & W. Awedyk (Eds.), Studia phonetica posnaniensia, Vol.\u00a03. Pozna\u0144: Wydawnictwo Naukowe UAM."},{"key":"9071_CR41","volume-title":"Automatyzacja transkrypcji fonematycznej tekst\u00f3w polskich","author":"M. Steffen-Batogowa","year":"1975","unstructured":"Steffen-Batogowa, M. (1975). Automatyzacja transkrypcji fonematycznej tekst\u00f3w polskich. Warszawa: PWN."},{"key":"9071_CR42","unstructured":"Szyma\u0144ski, M., & Grocholewski, S. (2005). Transcription-based automatic segmentation of speech. In Proceedings of 2nd language & technology conference (pp. 11\u201315). Pozna\u0144."},{"key":"9071_CR43","series-title":"LNAI","volume-title":"Proc. 9th international conference on text, speech and dialogue","author":"M. Szyma\u0144ski","year":"2006","unstructured":"Szyma\u0144ski, M., & Grocholewski, S. (2006). Post-processing of automatic segmentation of speech using dynamic programming. In LNAI. Proc. 9th international conference on text, speech and dialogue, Brno. Berlin: Springer."},{"key":"9071_CR44","series-title":"LNAI","volume-title":"Proc. 11th international conference on text, speech and dialog","author":"M. Szyma\u0144ski","year":"2008","unstructured":"Szyma\u0144ski, M., & Grocholewski, S. (2008). Error prediction-based semi-automatic segmentation of speech databases. In LNAI. Proc. 11th international conference on text, speech and dialog, Brno, Czech Republic. Berlin: Springer."},{"key":"9071_CR45","unstructured":"Tokuda, K., & Black, A. (2005). The Blizzard Challenge 2005: Evaluating corpus-based speech synthesis on common datasets. In Proc. Interspeech (Eurospeech) (pp. 77\u201380)."},{"issue":"6","key":"9071_CR46","doi-asserted-by":"crossref","first-page":"617","DOI":"10.1109\/TSA.2003.813579","volume":"11","author":"D. Toledano","year":"2003","unstructured":"Toledano, D., Hern\u00e1ndez G\u00f3mez, L. A., & Villarrubia Grande, L. (2003). Automatic phonetic segmentation. IEEE Transactions on Speech and Audio Processing, 11(6), 617\u2013625.","journal-title":"IEEE Transactions on Speech and Audio Processing"},{"issue":"3","key":"9071_CR47","doi-asserted-by":"crossref","first-page":"327","DOI":"10.1006\/jmps.1993.1022","volume":"37","author":"J. P. H. Santen Van","year":"1993","unstructured":"Van Santen, J. P. H. (1993a). Exploring N-way tables with sums-of-product models. Journal of Mathematical Psychology, 37(3), 327\u2013371.","journal-title":"Journal of Mathematical Psychology"},{"key":"9071_CR48","doi-asserted-by":"crossref","unstructured":"Van Santen, J. P. H. (1993b). Quantitative modeling of segmental duration. In Proceedings of human language technology conference (pp. 323\u2013328), Princeton, New Jersey.","DOI":"10.3115\/1075671.1075747"},{"key":"9071_CR49","doi-asserted-by":"crossref","unstructured":"Van Santen, J., & Buchsbaum, A. L. (1997). Methods for optimal text selection. In Proceedings Eurospeech 1997, Rhodos, Greece.","DOI":"10.21437\/Eurospeech.1997-207"},{"key":"9071_CR50","doi-asserted-by":"crossref","unstructured":"Van Son, R. J. J. H., & Van Santen, J. P. H. (1997). Strong interaction between factors influencing consonant duration. In Proceedings of Eurospeech \u201997, Rhodos.","DOI":"10.21437\/Eurospeech.1997-128"},{"key":"9071_CR51","unstructured":"Wagner, A. (2008). Kompleksowy model intonacji do zastosowania w syntezie mowy. Unpublished doctoral dissertation, Adam Mickiewicz University, Pozna\u0144, Poland."},{"key":"9071_CR52","unstructured":"Wells, J. (1996). The SAMPA homepage. http:\/\/www.phon.ucl.ac.uk\/home\/sampa\/home.htm ."}],"container-title":["International Journal of Speech Technology"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s10772-010-9071-3.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/article\/10.1007\/s10772-010-9071-3\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s10772-010-9071-3","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,3,26]],"date-time":"2024-03-26T21:16:54Z","timestamp":1711487814000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/s10772-010-9071-3"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2010,5,20]]},"references-count":52,"journal-issue":{"issue":"2","published-print":{"date-parts":[[2010,6]]}},"alternative-id":["9071"],"URL":"https:\/\/doi.org\/10.1007\/s10772-010-9071-3","relation":{},"ISSN":["1381-2416","1572-8110"],"issn-type":[{"value":"1381-2416","type":"print"},{"value":"1572-8110","type":"electronic"}],"subject":[],"published":{"date-parts":[[2010,5,20]]}}}