{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,6]],"date-time":"2026-05-06T06:29:05Z","timestamp":1778048945240,"version":"3.51.4"},"reference-count":60,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2016,3,1]],"date-time":"2016-03-01T00:00:00Z","timestamp":1456790400000},"content-version":"unspecified","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0"}],"funder":[{"DOI":"10.13039\/501100005725","name":"National Plan for Science, Technology and Innovation","doi-asserted-by":"publisher","award":["10-INF1324-02"],"award-info":[{"award-number":["10-INF1324-02"]}],"id":[{"id":"10.13039\/501100005725","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["J AUDIO SPEECH MUSIC PROC."],"published-print":{"date-parts":[[2016,12]]},"DOI":"10.1186\/s13636-016-0084-y","type":"journal-article","created":{"date-parts":[[2016,3,1]],"date-time":"2016-03-01T00:50:15Z","timestamp":1456793415000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":2,"title":["Developing a unit selection voice given audio without corresponding text"],"prefix":"10.1186","volume":"2016","author":[{"given":"Tejas","family":"Godambe","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Sai Krishna","family":"Rallabandi","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Suryakanth V.","family":"Gangashetty","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ashraf","family":"Alkhairy","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Afshan","family":"Jafri","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2016,3,1]]},"reference":[{"key":"84_CR1","first-page":"18","volume-title":"Joint Meeting of ASA, EAA, and DAGA","author":"M Beutnagel","year":"1999","unstructured":"M Beutnagel, A Conkie, J Schroeter, Y Stylianou, A Syrdal, in Joint Meeting of ASA, EAA, and DAGA. The AT&T next-gen TTS system (Citeseer Berlin, Germany, 1999), pp. 18\u201324."},{"key":"84_CR2","first-page":"373","volume-title":"Proc. of ICASSP","author":"AJ Hunt","year":"1996","unstructured":"AJ Hunt, AW Black, in Proc. of ICASSP, 1. Unit selection in a concatenative speech synthesis system using a large speech database (IEEEAtlanta, Georgia, USA, 1996), pp. 373\u2013376."},{"issue":"1","key":"84_CR3","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1186\/1687-4722-2013-16","volume":"2013","author":"S Ouni","year":"2013","unstructured":"S Ouni, V Colotte, U Musti, A Toutios, B Wrobel-Dautcourt, M-O Berger, C Lavecchia, Acoustic-visual synthesis technique using bimodal unit-selection. EURASIP J. Audio Speech Music Process. 2013(1), 1\u201313 (2013).","journal-title":"EURASIP J. Audio Speech Music Process"},{"key":"84_CR4","volume-title":"Proc. of Fifth ISCA Workshop on Speech Synthesis","author":"J Kominek","year":"2003","unstructured":"J Kominek, AW Black, in Proc. of Fifth ISCA Workshop on Speech Synthesis. The CMU ARCTIC speech databases (ISCAPittsburgh, PA, USA, 2003). http:\/\/festvox.org\/cmuarctic ."},{"key":"84_CR5","unstructured":"H Harrod, How do you teach a computer to speak like Scarlett Johansson? (2014). http:\/\/goo.gl\/xn5gBw. Accessed 15 Feb 2014."},{"key":"84_CR6","first-page":"1","volume-title":"Proc. of ICME","author":"X Anguera","year":"2011","unstructured":"X Anguera, N Perez, A Urruela, N Oliver, in Proc. of ICME. Automatic synchronization of electronic and audio books via TTS alignment and silence filtering (IEEEBarcelona, Spain, 2011), pp. 1\u20136."},{"key":"84_CR7","first-page":"2399","volume-title":"Proc. of ICSLP","author":"N Campbell","year":"1996","unstructured":"N Campbell, in Proc. of ICSLP, 4. Autolabelling Japanese TOBI (IEEEPhiladelphia, USA, 1996), pp. 2399\u20132402."},{"issue":"5","key":"84_CR8","doi-asserted-by":"publisher","first-page":"1444","DOI":"10.1109\/TASL.2010.2081980","volume":"19","author":"K Prahallad","year":"2011","unstructured":"K Prahallad, AW Black, Segmentation of monologues in audio books for building synthetic voices. IEEE Trans. Audio Speech Lang. Process.19(5), 1444\u20131449 (2011).","journal-title":"IEEE Trans. Audio Speech Lang. Process."},{"key":"84_CR9","doi-asserted-by":"crossref","first-page":"1823","DOI":"10.21437\/Interspeech.2009-531","volume-title":"Proc. of Interspeech","author":"C Cerisara","year":"2009","unstructured":"C Cerisara, O Mella, D Fohr, in Proc. of Interspeech. JTrans, an open-source software for semi-automatic text-to-speech alignment (ISCABrighton, UK, 2009), pp. 1823\u20131826."},{"key":"84_CR10","first-page":"2711","volume-title":"Proc. of ICSLP","author":"PJ Moreno","year":"1998","unstructured":"PJ Moreno, CF Joerg, J-M Van Thong, O Glickman, in Proc. of ICSLP, 98. A recursive algorithm for the forced alignment of very long audio segments (ISCASydney, Australia, 1998), pp. 2711\u20132714."},{"key":"84_CR11","first-page":"4869","volume-title":"Proc. of ICASSP","author":"PJ Moreno","year":"2009","unstructured":"PJ Moreno, C Alberti, in Proc. of ICASSP. A factor automaton approach for the forced alignment of long speech recordings (IEEETaipei, Taiwan, 2009), pp. 4869\u20134872."},{"key":"84_CR12","doi-asserted-by":"crossref","first-page":"1840","DOI":"10.21437\/Interspeech.2012-402","volume-title":"Proc. of Interspeech","author":"G Bordel","year":"2012","unstructured":"G Bordel, M Pe\u00f1agarikano, LJ Rodr\u00edguez-Fuentes, A Varona, in Proc. of Interspeech. A simple and efficient method to align very long speech signals to acoustically imperfect transcriptions (ISCAPortland, USA, 2012), pp. 1840\u20131843."},{"key":"84_CR13","doi-asserted-by":"crossref","first-page":"2222","DOI":"10.21437\/Interspeech.2010-611","volume-title":"Proc. of Interspeech","author":"N Braunschweiler","year":"2010","unstructured":"N Braunschweiler, MJ Gales, S Buchholz, in Proc. of Interspeech. Lightly supervised recognition for automatic alignment of large coherent speech recordings (ISCAMakuhari, Chiba, Japan, 2010), pp. 2222\u20132225."},{"issue":"1","key":"84_CR14","doi-asserted-by":"publisher","first-page":"75","DOI":"10.2298\/CSIS1001075T","volume":"7","author":"Y Tao","year":"2010","unstructured":"Y Tao, L Xueqing, W Bian, A dynamic alignment algorithm for imperfect speech and transcript. Comput. Sci. Inf. Syst. 7(1), 75\u201384 (2010).","journal-title":"Comput. Sci. Inf. Syst"},{"key":"84_CR15","first-page":"5206","volume-title":"Proc. of ICASSP","author":"V Panayotov","year":"2015","unstructured":"V Panayotov, G Chen, D Povey, S Khudanpur, in Proc. of ICASSP. LibriSpeech: an ASR corpus based on public domain audio books (IEEEBrisbane, Queensland, Australia, 2015), pp. 5206\u20135210."},{"key":"84_CR16","first-page":"2440","volume-title":"Proceedings of INTERSPEECH","author":"V Peddinti","year":"2015","unstructured":"V Peddinti, D Povey, S Khudanpur, in Proceedings of INTERSPEECH. A time delay neural network architecture for efficient modeling of long temporal contexts (ISCADresden, Germany, 2015), pp. 2440\u20132444."},{"issue":"1","key":"84_CR17","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1186\/s13636-015-0068-3","volume":"2015","author":"L T\u00f3th","year":"2015","unstructured":"L T\u00f3th, Phone recognition with hierarchical convolutional deep maxout networks. EURASIP J. Audio Speech Music Process.2015(1), 1\u201313 (2015).","journal-title":"EURASIP J. Audio Speech Music Process."},{"issue":"1","key":"84_CR18","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1186\/s13636-015-0058-5","volume":"2015","author":"P Motlicek","year":"2015","unstructured":"P Motlicek, D Imseng, B Potard, PN Garner, I Himawan, Exploiting foreign resources for DNN-based ASR. EURASIP J. Audio Speech Music Process.2015(1), 1\u201310 (2015).","journal-title":"EURASIP J. Audio Speech Music Process."},{"key":"84_CR19","volume-title":"Proc. of ASRU","author":"D Povey","year":"2011","unstructured":"D Povey, A Ghoshal, G Boulianne, L Burget, O Glembek, N Goel, M Hannemann, P Motl\u00ed\u010dek, Y Qian, P Schwarz, et al, in Proc. of ASRU. The Kaldi speech recognition toolkit (IEEEWaikoloa, HI, USA, 2011). EPFL-CONF 192584."},{"key":"84_CR20","doi-asserted-by":"crossref","first-page":"1618","DOI":"10.21437\/Interspeech.2008-271","volume-title":"Proc. of Interspeech","author":"M Federico","year":"2008","unstructured":"M Federico, N Bertoldi, M Cettolo, in Proc. of Interspeech. Irstlm: an open source toolkit for handling large scale language models (ISCABrisbane, Australia, 2008), pp. 1618\u20131621."},{"key":"84_CR21","doi-asserted-by":"publisher","first-page":"11","DOI":"10.1007\/978-3-540-76336-9_3","volume-title":"Implementation and Application of Automata","author":"C Allauzen","year":"2007","unstructured":"C Allauzen, M Riley, J Schalkwyk, W Skut, M Mohri, in Implementation and Application of Automata. Openfst: a general and efficient weighted finite-state transducer library (SpringerBerlin, Heidelberg, 2007), pp. 11\u201323."},{"issue":"4","key":"84_CR22","doi-asserted-by":"publisher","first-page":"357","DOI":"10.1109\/TASSP.1980.1163420","volume":"28","author":"SB Davis","year":"1980","unstructured":"SB Davis, P Mermelstein, Comparison of parametric representations for monosyllabic word recognition in continuously spoken sentences. IEEE Trans. Acoust. Speech Signal Process. 28(4), 357\u2013366 (1980).","journal-title":"IEEE Trans. Acoust. Speech Signal Process"},{"key":"84_CR23","unstructured":"RO Duda, PE Hart, DG Stork, Pattern classification (Wiley, 2012)."},{"key":"84_CR24","first-page":"661","volume-title":"Proc. of ICASSP","author":"RA Gopinath","year":"1998","unstructured":"RA Gopinath, in Proc. of ICASSP, 2. Maximum likelihood modeling with Gaussian distributions for classification (IEEEWashington, USA, 1998), pp. 661\u2013664."},{"issue":"3","key":"84_CR25","doi-asserted-by":"publisher","first-page":"272","DOI":"10.1109\/89.759034","volume":"7","author":"MJ Gales","year":"1999","unstructured":"MJ Gales, Semi-tied covariance matrices for hidden Markov models. IEEE Trans. Speech Audio Process. 7(3), 272\u2013281 (1999).","journal-title":"IEEE Trans. Speech Audio Process"},{"issue":"2","key":"84_CR26","doi-asserted-by":"publisher","first-page":"75","DOI":"10.1006\/csla.1998.0043","volume":"12","author":"MJ Gales","year":"1998","unstructured":"MJ Gales, Maximum likelihood linear transformations for HMM-based speech recognition. Comput. Speech Lang.12(2), 75\u201398 (1998).","journal-title":"Comput. Speech Lang."},{"key":"84_CR27","first-page":"11","volume-title":"DARPA Speech Recognition Workshop","author":"S Matsoukas","year":"1997","unstructured":"S Matsoukas, R Schwartz, H Jin, L Nguyen, in DARPA Speech Recognition Workshop. Practical implementations of speaker-adaptive training (CiteseerChantilly, VA, 1997), pp. 11\u201314."},{"key":"84_CR28","first-page":"215","volume-title":"Proc. of ICASSP","author":"X Zhang","year":"2014","unstructured":"X Zhang, J Trmal, D Povey, S Khudanpur, in Proc. of ICASSP. Improving deep neural network acoustic models using generalized maxout networks (IEEEFlorence, Italy, 2014), pp. 215\u2013219."},{"issue":"5","key":"84_CR29","doi-asserted-by":"publisher","first-page":"434","DOI":"10.1016\/j.specom.2008.01.002","volume":"50","author":"M Bisani","year":"2008","unstructured":"M Bisani, H Ney, Joint-sequence models for grapheme-to-phoneme conversion. Speech Commun.50(5), 434\u2013451 (2008).","journal-title":"Speech Commun."},{"key":"84_CR30","first-page":"181","volume-title":"Proc. of ICASSP","author":"R Kneser","year":"1995","unstructured":"R Kneser, H Ney, in Proc. of ICASSP, 1. Improved backing-off for m-gram language modeling (IEEEDetroit, Michigan, USA, 1995), pp. 181\u2013184."},{"key":"84_CR31","first-page":"310","volume-title":"Proc. of ACL","author":"SF Chen","year":"1996","unstructured":"SF Chen, J Goodman, in Proc. of ACL. An empirical study of smoothing techniques for language modeling (Association for Computational LinguisticsSanta Cruz, California, USA, 1996), pp. 310\u2013318."},{"key":"84_CR32","volume-title":"Proc. of Blizzard Challenge 2015","author":"SK Rallabandi","year":"2015","unstructured":"SK Rallabandi, A Vadapalli, S Achanta, S Gangashetty, in Proc. of Blizzard Challenge 2015. IIIT Hyderabad\u2019s submission to the Blizzard Challenge 2015 (ISCADresden, Germany, 2015)."},{"key":"84_CR33","first-page":"37","volume-title":"Fifth ISCA Workshop on Speech Synthesis","author":"T Hirai","year":"2004","unstructured":"T Hirai, S Tenpaku, in Fifth ISCA Workshop on Speech Synthesis. Using 5 ms segments in concatenative speech synthesis (ISCAPittsburgh, PA, USA, 2004), pp. 37\u201342."},{"key":"84_CR34","volume-title":"Ninth International Conference on Spoken Language Processing","author":"Z-H Ling","year":"2006","unstructured":"Z-H Ling, R-H Wang, in Ninth International Conference on Spoken Language Processing. HMM-based unit selection using frame sized speech segments (ISCAPittsburgh, PA, USA, 2006)."},{"key":"84_CR35","doi-asserted-by":"crossref","first-page":"573","DOI":"10.21437\/Eurospeech.1995-146","volume-title":"Eurospeech Proceedings: 4th European Conference on Speech Communication and Technology","author":"RE Donovan","year":"1995","unstructured":"RE Donovan, PC Woodland, in Eurospeech Proceedings: 4th European Conference on Speech Communication and Technology, 1. Improvements in an HMM-based speech synthesiser (ISCAMadrid, Spain, 1995), pp. 573\u2013576."},{"key":"84_CR36","doi-asserted-by":"publisher","first-page":"2387","DOI":"10.1109\/ICSLP.1996.607289","volume-title":"Spoken Language, 1996. ICSLP 96. Proceedings., Fourth International Conference On","author":"X Huang","year":"1996","unstructured":"X Huang, A Acero, J Adcock, H-W Hon, J Goldsmith, J Liu, M Plumpe, in Spoken Language, 1996. ICSLP 96. Proceedings., Fourth International Conference On, 4. Whistler: a trainable text-to-speech system (IEEEPhiladelphia, PA, USA, 1996), pp. 2387\u20132390."},{"key":"84_CR37","doi-asserted-by":"crossref","first-page":"601","DOI":"10.21437\/Eurospeech.1997-219","volume-title":"Proc. of Eurospeech","author":"AW Black","year":"1997","unstructured":"AW Black, PA Taylor, in Proc. of Eurospeech. Automatically clustering similar units for unit selection in speech synthesis (ISCARhodes, Greece, 1997), pp. 601\u2013604."},{"key":"84_CR38","first-page":"1317","volume-title":"Proc. of Interspeech","author":"SP Kishore","year":"2003","unstructured":"SP Kishore, AW Black, in Proc. of Interspeech. Unit size in unit selection speech synthesis (ISCAGeneva, Switzerland, 2003), pp. 1317\u20131320."},{"key":"84_CR39","first-page":"115","volume-title":"Fifth ISCA Workshop on Speech Synthesis","author":"H Segi","year":"2004","unstructured":"H Segi, T Takagi, T Ito, in Fifth ISCA Workshop on Speech Synthesis. A concatenative speech synthesis method using context dependent phoneme sequences with variable length as search units (ISCAPittsburgh, PA, USA, 2004), pp. 115\u2013120."},{"issue":"3","key":"84_CR40","doi-asserted-by":"publisher","first-page":"187","DOI":"10.1016\/S0167-6393(98)00085-5","volume":"27","author":"H Kawahara","year":"1999","unstructured":"H Kawahara, I Masuda-Katsuse, A De Cheveigne, Restructuring speech representations using a pitch-adaptive time-frequency smoothing and an instantaneous-frequency-based F0 extraction: possible role of a repetitive structure in sounds. Speech Commun.27(3), 187\u2013207 (1999).","journal-title":"Speech Commun."},{"key":"84_CR41","first-page":"1394","volume-title":"Proc. of Interspeech","author":"AW Black","year":"2006","unstructured":"AW Black, in Proc. of Interspeech. Clustergen: a statistical parametric synthesizer using trajectory modeling (ISCAPittsburgh, PA, USA, 2006), pp. 1394\u20131397."},{"key":"84_CR42","unstructured":"A Black, P Taylor, R Caley, R Clark, K Richmond, S King, V Strom, H Zen, The festival speech synthesis system, version 1.4. 2 (2001). Unpublished document available via http:\/\/www.cstr.ed.ac.uk\/projects\/festival.html ."},{"key":"84_CR43","first-page":"147","volume-title":"Proc. of Eurospeech","author":"P Taylor","year":"1998","unstructured":"P Taylor, AW Black, R Caley, in Proc. of Eurospeech. The architecture of the festival speech synthesis system (ISCAJenolan Caves, Australia, 1998), pp. 147\u2013151."},{"key":"84_CR44","unstructured":"L Breiman, J Friedman, CJ Stone, RA Olshen, Classification and regression trees (CRC press, 1984)."},{"key":"84_CR45","volume-title":"Blizzard Challenge 2014","author":"BSR Rajaram","year":"2014","unstructured":"BSR Rajaram, KHR Shiva, R A G, in Blizzard Challenge 2014. MILE TTS for Tamil for Blizzard Challenge 2014 (ISCASingapore, 2014)."},{"key":"84_CR46","first-page":"554","volume-title":"Proc. of ICASSP","author":"W Verhelst","year":"1993","unstructured":"W Verhelst, M Roelands, in Proc. of ICASSP, 2. An overlap-add technique based on waveform similarity (WSOLA) for high quality time-scale modification of speech (IEEEMinneapolis, Minnesota, USA, 1993), pp. 554\u2013557."},{"key":"84_CR47","first-page":"293","volume-title":"Proc. of ICASSP","author":"H Hon","year":"1998","unstructured":"H Hon, A Acero, X Huang, J Liu, M Plumpe, in Proc. of ICASSP, 1. Automatic generation of synthesis units for trainable text-to-speech systems (IEEESeattle, Washington, USA, 1998), pp. 293\u2013296."},{"key":"84_CR48","doi-asserted-by":"crossref","first-page":"162","DOI":"10.21437\/Interspeech.2010-75","volume-title":"Proc. of Interspeech","author":"H Lu","year":"2010","unstructured":"H Lu, Z-H Ling, S Wei, L-R Dai, R-H Wang, in Proc. of Interspeech. Automatic error detection for unit selection speech synthesis using log likelihood ratio based SVM classifier (ISCAMakuhari, Chiba, Japan, 2010), pp. 162\u2013165."},{"key":"84_CR49","first-page":"889","volume-title":"Proc. of ICASSP","author":"J Adell","year":"2006","unstructured":"J Adell, PD Ag\u00fcero, A Bonafonte, in Proc. of ICASSP. Database pruning for unsupervised building of text-to-speech voices (IEEEToulouse, France, 2006), pp. 889\u2013892."},{"key":"84_CR50","doi-asserted-by":"crossref","first-page":"1949","DOI":"10.21437\/Interspeech.2005-609","volume-title":"Proc. of Interspeech","author":"L Wang","year":"2005","unstructured":"L Wang, Y Zhao, M Chu, FK Soong, Z Cao, in Proc. of Interspeech. Phonetic transcription verification with generalized posterior probability (ISCALisbon, Portugal, 2005), pp. 1949\u20131952."},{"key":"84_CR51","first-page":"155","volume-title":"Fifth ISCA Workshop on Speech Synthesis","author":"J Kominek","year":"2004","unstructured":"J Kominek, AW Black, in Fifth ISCA Workshop on Speech Synthesis. Impact of durational outlier removal from unit selection catalogs (ISCAPittsburgh, PA, USA, 2004), pp. 155\u2013160."},{"key":"84_CR52","first-page":"269","volume-title":"Proc. of Interspeech","author":"H Lu","year":"2015","unstructured":"H Lu, W Zhang, X Shao, Q Zhou, W Lei, H Zhou, A Breen, in Proc. of Interspeech. Pruning Redundant synthesis units based on static and delta unit appearance frequency (ISCADresden, Germany, 2015), pp. 269\u2013273."},{"key":"84_CR53","doi-asserted-by":"crossref","first-page":"1377","DOI":"10.21437\/Interspeech.2004-456","volume-title":"Proc. of Interspeech","author":"R Kumar","year":"2004","unstructured":"R Kumar, SP Kishore, in Proc. of Interspeech. Automatic pruning of unit selection speech databases for synthesis without loss of naturalness (ISCAJeju island, Korea, 2004), pp. 1377\u20131380."},{"key":"84_CR54","first-page":"67","volume-title":"Proc. of ICON","author":"V Raghavendra","year":"2009","unstructured":"V Raghavendra, K Prahallad, in Proc. of ICON. Database pruning for Indian language unit selection synthesizers (ACLHyderabad, India, 2009), pp. 67\u201374."},{"key":"84_CR55","unstructured":"D Schwarz, G Beller, B Verbrugghe, S Britton, et al, in Proceedings of the COST-G6 Conference on Digital Audio Effects (DAFx), Montreal, Canada. Real-time corpus-based concatenative synthesis with catart (Citeseer, 2006), pp. 279\u2013282."},{"key":"84_CR56","first-page":"11937","volume-title":"Proc. of ICASSP","author":"RE Donovan","year":"2000","unstructured":"RE Donovan, in Proc. of ICASSP, 2. Segment pre-selection in decision-tree based speech synthesis systems (IEEEIstanbul, Turkey, 2000), pp. 11937\u201311940."},{"issue":"3","key":"84_CR57","doi-asserted-by":"publisher","first-page":"288","DOI":"10.1109\/89.906002","volume":"9","author":"F Wessel","year":"2001","unstructured":"F Wessel, R Schl\u00fcter, K Macherey, H Ney, Confidence measures for large vocabulary continuous speech recognition. IEEE Trans. Speech Audio Process. 9(3), 288\u2013298 (2001).","journal-title":"IEEE Trans. Speech Audio Process"},{"issue":"4","key":"84_CR58","doi-asserted-by":"publisher","first-page":"455","DOI":"10.1016\/j.specom.2004.12.004","volume":"45","author":"H Jiang","year":"2005","unstructured":"H Jiang, Confidence measures for speech recognition: a survey. Speech Commun. 45(4), 455\u2013470 (2005).","journal-title":"Speech Commun"},{"key":"84_CR59","first-page":"183","volume-title":"Proc. of Spoken Language Technology Workshop","author":"NT Vu","year":"2010","unstructured":"NT Vu, F Kraus, T Schultz, in Proc. of Spoken Language Technology Workshop. Multilingual A-stabil: a new confidence score for multilingual unsupervised training (ISCABerkley, CA, USA, 2010), pp. 183\u2013188."},{"issue":"4","key":"84_CR60","doi-asserted-by":"publisher","first-page":"381","DOI":"10.1016\/0167-6393(96)00026-X","volume":"18","author":"C Beno\u00eet","year":"1996","unstructured":"C Beno\u00eet, M Grice, V Hazan, The sus test: a method for the assessment of text-to-speech synthesis intelligibility using semantically unpredictable sentences. Speech Commun. 18(4), 381\u2013392 (1996).","journal-title":"Speech Commun"}],"container-title":["EURASIP Journal on Audio, Speech, and Music Processing"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1186\/s13636-016-0084-y.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/article\/10.1186\/s13636-016-0084-y\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1186\/s13636-016-0084-y","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1186\/s13636-016-0084-y.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,8,17]],"date-time":"2023-08-17T02:25:52Z","timestamp":1692239152000},"score":1,"resource":{"primary":{"URL":"https:\/\/asmp-eurasipjournals.springeropen.com\/articles\/10.1186\/s13636-016-0084-y"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2016,3,1]]},"references-count":60,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2016,12]]}},"alternative-id":["84"],"URL":"https:\/\/doi.org\/10.1186\/s13636-016-0084-y","relation":{},"ISSN":["1687-4722"],"issn-type":[{"value":"1687-4722","type":"electronic"}],"subject":[],"published":{"date-parts":[[2016,3,1]]},"article-number":"6"}}