{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,25]],"date-time":"2025-03-25T15:58:30Z","timestamp":1742918310748,"version":"3.40.3"},"publisher-location":"Cham","reference-count":23,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783319491684"},{"type":"electronic","value":"9783319491691"}],"license":[{"start":{"date-parts":[[2016,1,1]],"date-time":"2016-01-01T00:00:00Z","timestamp":1451606400000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2016]]},"DOI":"10.1007\/978-3-319-49169-1_6","type":"book-chapter","created":{"date-parts":[[2016,11,3]],"date-time":"2016-11-03T11:31:46Z","timestamp":1478172706000},"page":"54-63","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Language-Independent Acoustic Cloning of HTS Voices: An Objective Evaluation"],"prefix":"10.1007","author":[{"given":"Carmen","family":"Magari\u00f1os","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Daniel","family":"Erro","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Paula","family":"Lopez-Otero","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Eduardo R.","family":"Banga","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2016,11,4]]},"reference":[{"issue":"11","key":"6_CR1","doi-asserted-by":"publisher","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.: Statistical parametric speech synthesis. Speech Commun. 51(11), 1039\u20131064 (2009)","journal-title":"Speech Commun."},{"key":"6_CR2","unstructured":"Yamagishi, J.: Average-voice-based speech synthesis. Ph.d. dissertation, Tokyo Institute of Technology, Yokohama, Japan (2006)"},{"issue":"6","key":"6_CR3","doi-asserted-by":"publisher","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.: Robust speaker-adaptive HMM-based text-to-speech synthesis. IEEE Trans. Audio Speech Lang. Process. 17(6), 1208\u20131230 (2009)","journal-title":"IEEE Trans. Audio Speech Lang. Process."},{"key":"6_CR4","doi-asserted-by":"publisher","first-page":"1227","DOI":"10.1016\/j.specom.2006.05.003","volume":"48","author":"J Latorre","year":"2006","unstructured":"Latorre, J., Iwano, K., Furui, S.: New approach to the polyglot speech generation by means of an HMM-based speaker adaptable synthesizer. Speech Commun. 48, 1227\u20131242 (2006)","journal-title":"Speech Commun."},{"key":"6_CR5","doi-asserted-by":"crossref","unstructured":"Wu, Y.J., Nankaku, Y., Tokuda, K.: State mapping based method for cross-lingual speaker adaptation in HMM-based speech synthesis. In: Proceedings of Interspeech, pp. 528\u2013531 (2009)","DOI":"10.21437\/Interspeech.2009-192"},{"key":"6_CR6","doi-asserted-by":"publisher","first-page":"703","DOI":"10.1016\/j.specom.2011.12.004","volume":"54","author":"K Oura","year":"2012","unstructured":"Oura, K., Yamagishi, J., Wester, M., King, S., Tokuda, K.: Analysis of unsupervised cross-lingual speaker adaptation for HMM-based speech synthesis using KLD-based transform mapping. Speech Commun. 54, 703\u2013714 (2012)","journal-title":"Speech Commun."},{"key":"6_CR7","doi-asserted-by":"publisher","first-page":"420","DOI":"10.1016\/j.csl.2011.08.003","volume":"27","author":"J Dines","year":"2013","unstructured":"Dines, J., Liang, H., Saheer, L., Gibson, M., Byrne, W., Oura, K., Tokuda, K., Yamagishi, J., King, S., Wester, M., Hirsimki, T., Karhila, R., Kurimo, M.: Personalising speech-to-speech translation: unsupervised cross-lingual speaker adaptation for HMM-based speech synthesis. Comput. Speech Lang. 27, 420\u2013437 (2013)","journal-title":"Comput. Speech Lang."},{"issue":"6","key":"6_CR8","doi-asserted-by":"publisher","first-page":"1713","DOI":"10.1109\/TASL.2012.2187195","volume":"20","author":"H Zen","year":"2012","unstructured":"Zen, H., Braunschweiler, N., Buchholz, S., Gales, M., Knill, K., Krstulovic, S., Latorre, J.: Statistical parametric speech synthesis based on speaker and language factorization. IEEE Trans. Audio Speech Lang. Process. 20(6), 1713\u20131724 (2012)","journal-title":"IEEE Trans. Audio Speech Lang. Process."},{"key":"6_CR9","doi-asserted-by":"crossref","unstructured":"Magari\u00f1os, C., Erro, D., Banga, E.R.: Language-independent acoustic cloning of HTS voices: a preliminary study. In: Proceedings of ICASSP, pp. 5615\u20135619 (2016)","DOI":"10.1109\/ICASSP.2016.7472752"},{"key":"6_CR10","unstructured":"Zen, H., Nose, T., Yamagishi, J., Sako, S., Masuko, T., Black, A.W., Tokuda, K.: The HMM-based speech synthesis system (HTS) version 2.0. In: Proceedings of 6th ISCA Speech Synthesis Workshop, pp. 294\u2013299. ISCA (2007)"},{"issue":"5","key":"6_CR11","doi-asserted-by":"publisher","first-page":"944","DOI":"10.1109\/TASL.2009.2038669","volume":"18","author":"D Erro","year":"2010","unstructured":"Erro, D., Moreno, A., Bonafonte, A.: INCA algorithm for training voice conversion systems from nonparallel corpora. IEEE Trans. Audio Speech Lang. Process. 18(5), 944\u2013953 (2010)","journal-title":"IEEE Trans. Audio Speech Lang. Process."},{"key":"6_CR12","doi-asserted-by":"crossref","unstructured":"Agiomyrgiannakis, Y.: The matching-minimization algorithm, the INCA algorithm and a mathematical framework for voice conversion with unaligned corpora. In: Proceedings of ICASSP, Shanghai, pp. 5645\u20135649 (2016)","DOI":"10.1109\/ICASSP.2016.7472758"},{"key":"6_CR13","doi-asserted-by":"publisher","first-page":"74","DOI":"10.1109\/MSP.2015.2462851","volume":"32","author":"J Hansen","year":"2015","unstructured":"Hansen, J., Hasan, T.: Speaker recognition by machines and humans: a tutorial review. IEEE Signal Process. Mag. 32, 74\u201399 (2015)","journal-title":"IEEE Signal Process. Mag."},{"key":"6_CR14","doi-asserted-by":"crossref","unstructured":"Cumani, S., Br\u00fcmmer, N., Burget, L., Laface, P.: Fast discriminative speaker verification in the i-vector space. In: Proceedings of ICASSP, pp. 4852\u20134855 (2011)","DOI":"10.1109\/ICASSP.2011.5947442"},{"key":"6_CR15","doi-asserted-by":"publisher","first-page":"788","DOI":"10.1109\/TASL.2010.2064307","volume":"19","author":"N Dehak","year":"2011","unstructured":"Dehak, N., Kenny, P.J., Dehak, R., Dumouchel, P., Ouellet, P.: Front end factor analysis for speaker verification. IEEE Trans. Audio Speech Lang. Process. 19, 788\u2013798 (2011)","journal-title":"IEEE Trans. Audio Speech Lang. Process."},{"key":"6_CR16","doi-asserted-by":"crossref","unstructured":"Moreno, A., Poch, D., Bonafonte, A., Lleida, E., Llisterri, J., Mari\u00f1o, J.B., Nadeu, C.: Albayzin speech database: design of the phonetic corpus. In: EUROSPEECH (1993)","DOI":"10.21437\/Eurospeech.1993-66"},{"key":"6_CR17","unstructured":"Sainz, I., Erro, D., Navas, E., Hern\u00e1ez, I., S\u00e1nchez, J., Saratxaga, I., Odriozola, I., Luengo, I.: Aholab speech synthesizers for albayzin2010. In: Proceedings of FALA 2010, pp. 343\u2013348 (2010)"},{"key":"6_CR18","unstructured":"Bonafonte, A., Aguilar, L., Esquerra, I., Oller, S., Moreno, A.: Recent work on the FESTCAT database for speech synthesis. In: Proceedings of the I Iberian SLTech, pp. 131\u2013132 (2009)"},{"key":"6_CR19","doi-asserted-by":"crossref","unstructured":"Taylor, P., Black, A.W., Caley, R.: The architecture of the festival speech synthesis system. In: Proceedings of the ESCA Workshop in Speech Synthesis, pp. 141\u2013151 (1998)","DOI":"10.1049\/ic:19980957"},{"key":"6_CR20","unstructured":"Rodr\u00edguez-Banga, E., Garc\u00eda-Mateo, C., M\u00e9ndez-Paz\u00f3, F., Gonz\u00e1lez-Gonz\u00e1lez, M., Magari\u00f1os, C.: Cotov\u00eda: an open source TTS for Galician and Spanish. In: Proceedings of IberSPEECH, pp. 308\u2013315. RTTH and SIG-IL (2012)"},{"issue":"2","key":"6_CR21","doi-asserted-by":"publisher","first-page":"184","DOI":"10.1109\/JSTSP.2013.2283471","volume":"8","author":"D Erro","year":"2014","unstructured":"Erro, D., Sainz, I., Navas, E., Hern\u00e1ez, I.: Harmonics plus noise model based vocoder for statistical parametric speech synthesis. IEEE J. Sel. Top. Signal Process. 8(2), 184\u2013194 (2014)","journal-title":"IEEE J. Sel. Top. Signal Process."},{"issue":"4","key":"6_CR22","first-page":"1097","volume":"32","author":"J Ortega-Garcia","year":"2009","unstructured":"Ortega-Garcia, J., Fierrez, J., Alonso-Fernandez, F., Galbally, J., Freire, M.R., Gonzalez-Rodriguez, J., Garcia-Mateo, C., Alba-Castro, J.L., Gonzalez-Agulla, E., Otero-Muras, E., Garcia-Salicetti, S., Allano, L., Ly-Van, B., Dorizzi, B., Kittler, J., Bourlai, T., Poh, N., Deravi, F., Ng, M.W.R., Fairhurst, M., Hennebert, J., Humm, A., Tistarelli, M., Brodo, L., Richiardi, J., Drygajlo, A., Ganster, H., Sukno, F., Pavani, S.K., Frangi, A., Akarun, L., Savran, A.: The multi-scenario multi-environment BioSecure multimodal database (BMDB). IEEE Trans. Pattern Anal. Mach. Intell. 32(4), 1097\u20131111 (2009)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"6_CR23","unstructured":"Povey, D., Ghoshal, A., Boulianne, G., Burget, L., Glembek, O., Goel, N., Hannemann, M., Motlicek, P., Qian, Y., Schwarz, P., Silovsky, J., Stemmer, G., Vesely, K.: The Kaldi speech recognition toolkit. In: IEEE Workshop on Automatic Speech Recognition and Understanding (2011)"}],"container-title":["Lecture Notes in Computer Science","Advances in Speech and Language Technologies for Iberian Languages"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-319-49169-1_6","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,3,13]],"date-time":"2024-03-13T10:30:00Z","timestamp":1710325800000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-319-49169-1_6"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2016]]},"ISBN":["9783319491684","9783319491691"],"references-count":23,"URL":"https:\/\/doi.org\/10.1007\/978-3-319-49169-1_6","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2016]]},"assertion":[{"value":"4 November 2016","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"IberSPEECH","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Advances in Speech and Language Technologies for Iberian Languages","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Lisbon","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Portugal","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2016","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"23 November 2016","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"25 November 2016","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"3","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"iberspeech2016","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/iberspeech2016.inesc-id.pt\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}