{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,2,21]],"date-time":"2025-02-21T00:48:54Z","timestamp":1740098934572,"version":"3.37.3"},"publisher-location":"Cham","reference-count":19,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783319664286"},{"type":"electronic","value":"9783319664293"}],"license":[{"start":{"date-parts":[[2017,1,1]],"date-time":"2017-01-01T00:00:00Z","timestamp":1483228800000},"content-version":"unspecified","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2017]]},"DOI":"10.1007\/978-3-319-66429-3_79","type":"book-chapter","created":{"date-parts":[[2017,8,12]],"date-time":"2017-08-12T02:02:55Z","timestamp":1502503375000},"page":"788-798","source":"Crossref","is-referenced-by-count":1,"title":["Voice Conversion for TTS Systems with Tuning on the Target Speaker Based on GMM"],"prefix":"10.1007","author":[{"given":"Vadim","family":"Zahariev","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Elias","family":"Azarov","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Alexander","family":"Petrovsky","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2017,8,13]]},"reference":[{"key":"79_CR1","unstructured":"Sebastian, A.: Adobe demos \u201cphotoshop for audio,\u201d lets you edit speech as easily as text. In Ars Technika, electronic resource (2016). https:\/\/goo.gl\/yCkGyp"},{"key":"79_CR2","doi-asserted-by":"crossref","unstructured":"McTear, M., Callejas, Z., Griol, D.: The Conversational Interface: Talking to Smart Devices. Springer, Switzerland (2016)","DOI":"10.1007\/978-3-319-32967-3"},{"key":"79_CR3","doi-asserted-by":"crossref","unstructured":"Dutoit, T.: An Introduction to Text-to-Speech Synthesis. Springer, Netherlands (2013)","DOI":"10.1093\/oxfordhb\/9780199276349.013.0017"},{"key":"79_CR4","doi-asserted-by":"crossref","DOI":"10.1017\/CBO9780511816338","volume-title":"Text-to-Speech Synthesis","author":"P Taylor","year":"2009","unstructured":"Taylor, P.: Text-to-Speech Synthesis. Cambridge University Press, Cambridge (2009)"},{"key":"79_CR5","doi-asserted-by":"crossref","unstructured":"Shikano, K., Lee, K., Reddy, R.: Speaker adaptation through vector quantization. In: ICASSP 1986, Japan, Tokyo, pp. 231\u2013237 (1986)","DOI":"10.1109\/ICASSP.1986.1168676"},{"issue":"1","key":"79_CR6","doi-asserted-by":"crossref","first-page":"39","DOI":"10.1109\/89.890070","volume":"9","author":"E Klabbers","year":"2001","unstructured":"Klabbers, E., Veldhuis, R.: Reducing audible spectral discontinuities. IEEE Trans. Speech Audio Process. 9(1), 39\u201351 (2001)","journal-title":"IEEE Trans. Speech Audio Process."},{"issue":"5","key":"79_CR7","doi-asserted-by":"crossref","first-page":"1763","DOI":"10.1109\/TSA.2005.858548","volume":"14","author":"J Vepa","year":"2006","unstructured":"Vepa, J., King, S.: Subjective evaluation of join cost and smoothing methods for unit selection speech synthesis. IEEE Trans. Audio Speech Lang. Process. 14(5), 1763\u20131771 (2006)","journal-title":"IEEE Trans. Audio Speech Lang. Process."},{"key":"79_CR8","unstructured":"Kirkpatrick, B., O\u2019Brien, D., Scaife, R.: Feature transformation applied to the detection of discontinuities in concatenated speech. In: SSW6-2007, pp. 17\u201321 (2007)"},{"issue":"1","key":"79_CR9","doi-asserted-by":"crossref","first-page":"21","DOI":"10.1109\/89.890068","volume":"9","author":"Y Stylianou","year":"2001","unstructured":"Stylianou, Y.: Applying the harmonic plus noise model in concatenative speech synthesis. IEEE Trans. Speech Audio Process. 9(1), 21\u201329 (2001)","journal-title":"IEEE Trans. Speech Audio Process."},{"issue":"6","key":"79_CR10","doi-asserted-by":"crossref","first-page":"349","DOI":"10.1250\/ast.27.349","volume":"27","author":"H Kawahara","year":"2006","unstructured":"Kawahara, H.: STRAIGHT, exploitation of the other aspect of VOCODER: perceptually isomorphic decomposition of speech sounds. Acoust. Sci. Technol. 27(6), 349\u2013353 (2006)","journal-title":"Acoust. Sci. Technol."},{"key":"79_CR11","doi-asserted-by":"crossref","unstructured":"Agiomyrgiannakis, Y.: Vocaine the vocoder and applications in speech synthesis. In: ICASSP 2015, Brisbane, Australia, pp. 4230\u20134234, April 2015","DOI":"10.1109\/ICASSP.2015.7178768"},{"key":"79_CR12","doi-asserted-by":"crossref","unstructured":"Azarov, E., Vashkevich, M., Petrovsky, A.: Instantaneous harmonic representation of speech using multicomponent sinusoidal excitation. In: INTERSPEECH-2013, Lyon, France, pp. 1697\u20131701 (2013)","DOI":"10.21437\/Interspeech.2013-33"},{"key":"79_CR13","doi-asserted-by":"crossref","unstructured":"Nilsson, M., Resch, B., Kim, M-Y., Kleijn, W.B.: A canonical representation of speech. In: ICASSP-2007, Honolulu, USA, pp. 849\u2013852, April 2007","DOI":"10.1109\/ICASSP.2007.367046"},{"key":"79_CR14","doi-asserted-by":"crossref","unstructured":"Azarov, E., Vashkevich, M., Petrovsky, A.: Guslar: a framework for automated singing voice correction. In: ICASSP-2014, Florence, Italy, pp. 7919\u20137923 (2014)","DOI":"10.1109\/ICASSP.2014.6855142"},{"key":"79_CR15","doi-asserted-by":"crossref","first-page":"65","DOI":"10.1016\/j.specom.2017.01.008","volume":"88","author":"SH Mohammadi","year":"2017","unstructured":"Mohammadi, S.H., Kain, A.: An overview of voice conversion systems. Speech Commun. 88, 65\u201382 (2017)","journal-title":"Speech Commun."},{"key":"79_CR16","doi-asserted-by":"crossref","first-page":"131","DOI":"10.1109\/89.661472","volume":"6","author":"Y Stylinau","year":"1998","unstructured":"Stylinau, Y.: Continuous probabilistic transform for voice conversion. IEEE Trans. Speech Audio Process. 6, 131\u2013142 (1998)","journal-title":"IEEE Trans. Speech Audio Process."},{"key":"79_CR17","first-page":"40","volume":"3","author":"V Zahariev","year":"2014","unstructured":"Zahariev, V., Petrovsky, A.: Voice conversion based on GMM with multifactor regression function and spectral weighting. Speech Technol. 3, 40\u201354 (2014)","journal-title":"Speech Technol."},{"key":"79_CR18","volume-title":"Fundamentals of Speech Recognition","author":"L Rabiner","year":"1993","unstructured":"Rabiner, L.: Fundamentals of Speech Recognition. Printice Hall, United States (1993)"},{"key":"79_CR19","unstructured":"Zahariev, V., Petrovsky, A.: Text-independent learning in the voice conversion system based on hidden Markov models and the grapheme-to-phoneme conversion scheme. In: DSPA-2013, Moscow Russia, pp. 327\u2013332, March 2013"}],"container-title":["Lecture Notes in Computer Science","Speech and Computer"],"original-title":[],"link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-319-66429-3_79","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,8,1]],"date-time":"2022-08-01T03:38:19Z","timestamp":1659325099000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-319-66429-3_79"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2017]]},"ISBN":["9783319664286","9783319664293"],"references-count":19,"URL":"https:\/\/doi.org\/10.1007\/978-3-319-66429-3_79","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2017]]}}}