{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2023,8,11]],"date-time":"2023-08-11T15:40:06Z","timestamp":1691768406063},"reference-count":70,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2015,1,9]],"date-time":"2015-01-09T00:00:00Z","timestamp":1420761600000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["EURASIP J. Adv. Signal Process."],"published-print":{"date-parts":[[2015,12]]},"DOI":"10.1186\/1687-6180-2015-2","type":"journal-article","created":{"date-parts":[[2015,6,18]],"date-time":"2015-06-18T07:30:07Z","timestamp":1434612607000},"update-policy":"http:\/\/dx.doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":4,"title":["Soft context clustering for F0 modeling in HMM-based speech synthesis"],"prefix":"10.1186","volume":"2015","author":[{"given":"Soheil","family":"Khorram","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hossein","family":"Sameti","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Simon","family":"King","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2015,1,9]]},"reference":[{"issue":"5","key":"768_CR1","doi-asserted-by":"publisher","first-page":"837","DOI":"10.1007\/s12046-011-0048-y","volume":"36","author":"S King","year":"2011","unstructured":"King S: An introduction to statistical parametric speech synthesis.Sadhana 2011,36(5):837\u2013852. 10.1007\/s12046-011-0048-y","journal-title":"Sadhana"},{"key":"768_CR2","doi-asserted-by":"publisher","DOI":"10.1007\/978-94-011-5730-8","volume-title":"An Introduction to Text-to-Speech Synthesis, vol. 3","author":"T Dutoi","year":"1997","unstructured":"Dutoi T: An Introduction to Text-to-Speech Synthesis, vol. 3. Springer book (Kluwer Academic Publishers), The Netherlands; 1997."},{"issue":"11","key":"768_CR3","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 AW: Statistical parametric speech synthesis.Speech Comm 2009,51(11):1039\u20131064. 10.1016\/j.specom.2009.04.004","journal-title":"Speech Comm"},{"key":"768_CR4","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2007.367298","volume-title":"Statistical Parametric Speech Synthesis","author":"AW Black","year":"2007","unstructured":"Black AW, Zen H, Tokuda K: Statistical Parametric Speech Synthesis. IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), Honolulu, Hawaii, USA; 2007. vol 4, pp. IV-1229"},{"key":"768_CR5","volume-title":"Mixed Excitation for HMM-Based Speech Synthesis","author":"T Yoshimura","year":"2001","unstructured":"Yoshimura T, Tokuda K, Masuko T, Kobayashi T, Kitamura T: Mixed Excitation for HMM-Based Speech Synthesis. European Conference on Speech Communication and Technology INTERSPEECH, Aalborg, Denmark; 2001. pp. 2263\u20132266"},{"issue":"3","key":"768_CR6","doi-asserted-by":"publisher","first-page":"187","DOI":"10.1016\/S0167-6393(98)00085-5","volume":"27","author":"H Kawahara","year":"1999","unstructured":"Kawahara H, Masuda-Katsuse I, Cheveign\u00e9 A: Restructuring speech representations using a pitch-adaptive time\u2013frequency smoothing and an instantaneous-frequency-based F0 extraction: possible role of a repetitive structure in sounds.Speech Comm 1999,27(3):187\u2013207.","journal-title":"Speech Comm"},{"issue":"3","key":"768_CR7","doi-asserted-by":"publisher","first-page":"968","DOI":"10.1109\/TASL.2011.2169787","volume":"20","author":"T Drugman","year":"2012","unstructured":"Drugman T, Dutoit T: The deterministic plus stochastic model of the residual signal and its applications.IEEE Transactions on Audio, Speech and Language Processing 2012,20(3):968\u2013981.","journal-title":"IEEE Transactions on Audio, Speech and Language Processing"},{"key":"768_CR8","volume-title":"A Deterministic Plus Stochastic Model of the Residual Signal for Improved Parametric Speech Synthesis","author":"T Drugman","year":"2009","unstructured":"Drugman T, Wilfart G, Dutoit T: A Deterministic Plus Stochastic Model of the Residual Signal for Improved Parametric Speech Synthesis. INTERSPEECH, Brighton, United Kingdom; 2009. pp. 1779\u20131782"},{"issue":"1","key":"768_CR9","doi-asserted-by":"publisher","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 Transactions on Speech and Audio Processing 2001,9(1):21\u201329. 10.1109\/89.890068","journal-title":"IEEE Transactions on Speech and Audio Processing"},{"key":"768_CR10","first-page":"791","volume-title":"Advances in Speech Signal Processing","author":"MY Liberman","year":"1992","unstructured":"Liberman MY, Church KW: Text analysis and word pronunciation in text-to-speech synthesis.Advances in Speech Signal Processing 1992, 791\u2013831."},{"key":"768_CR11","first-page":"1315","volume-title":"Speech Parameter Generation Algorithms for HMM-Based Speech Synthesis","author":"K Tokuda","year":"2000","unstructured":"Tokuda K, Yoshimura T, Masuko T, Kobayashi T, Kitamura T: Speech Parameter Generation Algorithms for HMM-Based Speech Synthesis. IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), Istanbul; 2000:1315\u20131318."},{"issue":"5","key":"768_CR12","doi-asserted-by":"publisher","first-page":"816","DOI":"10.1093\/ietisy\/e90-d.5.816","volume":"E90-D","author":"T Toda","year":"2007","unstructured":"Toda T, Tokuda K: Speech parameter generation algorithm considering global variance for HMM-based speech synthesis.IEICE - Transactions on Information and Systems 2007,E90-D(5):816\u2013824. 10.1093\/ietisy\/e90-d.5.816","journal-title":"IEICE - Transactions on Information and Systems"},{"key":"768_CR13","volume-title":"Parameter Generation Methods With Rich Context Models for High-Quality and Flexible Text-to-Speech Synthesis","author":"S Takamichi","year":"2013","unstructured":"Takamichi S, Toda T, Shiga Y, Sakti S, Neubig G, Nakamura S: Parameter Generation Methods With Rich Context Models for High-Quality and Flexible Text-to-Speech Synthesis. IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), Vancouver, British Columbia, Canada; 2013."},{"key":"768_CR14","first-page":"7869","volume-title":"Fast, low-Artifact Speech Synthesis Considering Global Variance","author":"M Shannon","year":"2013","unstructured":"Shannon M, Byrne W: Fast, low-Artifact Speech Synthesis Considering Global Variance. IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), Vancouver, British Columbia, Canada; 2013:7869\u20137873."},{"key":"768_CR15","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.1996.541110","volume-title":"Unit Selection in a Concatenative Speech Synthesis System Using a Large Speech Database","author":"AJ Hunt","year":"1996","unstructured":"Hunt AJ, Black AW: Unit Selection in a Concatenative Speech Synthesis System Using a Large Speech Database. IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP)373, Atlanta, Georgia, USA, 376; 1996."},{"issue":"2","key":"768_CR16","doi-asserted-by":"publisher","first-page":"533","DOI":"10.1093\/ietisy\/e90-d.2.533","volume":"90","author":"J Yamagishi","year":"2007","unstructured":"Yamagishi J, Kobayashi T: Average-voice-based speech synthesis using HSMM-based speaker adaptation and adaptive training.IEICE - Transactions on Information and Systems 2007,90(2):533\u2013543.","journal-title":"IEICE - Transactions on Information and Systems"},{"issue":"6","key":"768_CR17","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 ZH, Toda T, Tokuda K, King S, Renals S: Robust speaker-adaptive HMM-based text-to-speech synthesis.IEEE Transactions on Audio, Speech, and Language Processing 2009,17(6):1208\u20131230.","journal-title":"IEEE Transactions on Audio, Speech, and Language Processing"},{"issue":"1","key":"768_CR18","doi-asserted-by":"publisher","first-page":"66","DOI":"10.1109\/TASL.2008.2006647","volume":"17","author":"J Yamagishi","year":"2009","unstructured":"Yamagishi J, Kobayashi T, Nakano Y, Ogata K, Isogai J: Analysis of speaker adaptation algorithms for HMM-based speech synthesis and a constrained SMAPLR adaptation algorithm.IEEE Transactions on Audio, Speech, and Language Processing 2009,17(1):66\u201383.","journal-title":"IEEE Transactions on Audio, Speech, and Language Processing"},{"issue":"6","key":"768_CR19","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 MJ, Knill K, Krstulovic S, Latorre J: Statistical parametric speech synthesis based on speaker and language factorization.IEEE Transactions on Audio, Speech, and Language Processing 2012,20(6):1713\u20131724.","journal-title":"IEEE Transactions on Audio, Speech, and Language Processing"},{"key":"768_CR20","first-page":"528","volume-title":"State Mapping Based Method for Cross-Lingual Speaker Adaptation in HMM-Based Speech Synthesis","author":"YJ Wu","year":"2009","unstructured":"Wu YJ, Nankaku Y, Tokuda K: State Mapping Based Method for Cross-Lingual Speaker Adaptation in HMM-Based Speech Synthesis. INTERSPEECH, Brighton, United Kingdom; 2009:528\u2013531."},{"key":"768_CR21","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2010.5495559","volume-title":"A Comparison of Supervised and Unsupervised Cross-Lingual Speaker Adaptation Approaches for HMM-Based Speech Synthesis","author":"H Liang","year":"2010","unstructured":"Liang H, Dines J, Saheer L: A Comparison of Supervised and Unsupervised Cross-Lingual Speaker Adaptation Approaches for HMM-Based Speech Synthesis. IEEE International Conference on Acoustics Speech and Signal Processing (ICASSP), Dallas, Texas, USA; 2010. pp. 4598\u20134601"},{"key":"768_CR22","first-page":"4642","volume-title":"Unsupervised Cross-Lingual Speaker Adaptation for HMM-Based Speech Synthesis Using two-Pass Decision Tree Construction","author":"M Gibson","year":"2010","unstructured":"Gibson M, Hirsimaki T, Karhila R, Kurimo M, Byrne W: Unsupervised Cross-Lingual Speaker Adaptation for HMM-Based Speech Synthesis Using two-Pass Decision Tree Construction. IEEE International Conference on Acoustics Speech and Signal Processing (ICASSP), Dallas, Texas, USA; 2010:4642\u20134645."},{"key":"768_CR23","first-page":"581","volume-title":"Robustness of HMM-Based Speech Synthesis","author":"J Yamagishi","year":"2008","unstructured":"Yamagishi J, Ling Z, King S: Robustness of HMM-Based Speech Synthesis. INTERSPEECH, Brisbane, Australia; 2008:581\u2013584."},{"key":"768_CR24","first-page":"6930","volume-title":"HMM-Based Speech Synthesis Adaptation Using Noisy Data: Analysis and Evaluation Methods","author":"R Karhila","year":"2013","unstructured":"Karhila R, Remes U, Kurimo M: HMM-Based Speech Synthesis Adaptation Using Noisy Data: Analysis and Evaluation Methods. IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), Vancouver, British Columbia, Canada; 2013:6930\u20136934."},{"key":"768_CR25","first-page":"119","volume-title":"Noise Robustness in HMM-TTS Speaker Adaptation","author":"K Yanagisawa","year":"2013","unstructured":"Yanagisawa K, Latorre J, Wan V, Gales MJ, King S: Noise Robustness in HMM-TTS Speaker Adaptation. 8th ISCA Speech Synthesis Workshop, Barcelona, Spain; 2013:119\u2013124."},{"key":"768_CR26","first-page":"8140","volume-title":"On the (un) Importance of the Contextual Factors in HMM-Based Speech Synthesis and Coding","author":"M Cernak","year":"2013","unstructured":"Cernak M, Motlicek P, Garner PN: On the (un) Importance of the Contextual Factors in HMM-Based Speech Synthesis and Coding. IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), Vancouver, British Columbia, Canada; 2013:8140\u20138143."},{"key":"768_CR27","first-page":"2347","volume-title":"Simultaneous Modeling of Spectrum, Pitch and Duration in HMM-Based Speech Synthesis","author":"T Yoshimura","year":"1999","unstructured":"Yoshimura T, Tokuda K, Masuko T, Kobayashi T, Kitamura T: Simultaneous Modeling of Spectrum, Pitch and Duration in HMM-Based Speech Synthesis. Proceedings of Eurospeech, Budapest, Hungary; 1999:2347\u20132350."},{"key":"768_CR28","first-page":"29","volume-title":"Duration Modeling in HMM-Based Speech Synthesis System","author":"T Yoshimura","year":"1998","unstructured":"Yoshimura T, Tokuda K, Masuko T, Kobayashi T, Kitamura T: Duration Modeling in HMM-Based Speech Synthesis System. Proceedings of ICSLP, Sydney. Australia; 1998:29\u201332."},{"key":"768_CR29","first-page":"294","volume-title":"The HMM-Based Speech Synthesis System (HTS) Version 2.0","author":"H Zen","year":"2007","unstructured":"Zen H, Nose T, Yamagishi J, Sako S, Masuko T, Black A, Keiichi T: The HMM-Based Speech Synthesis System (HTS) Version 2.0. 6th ISCA Workshop on Speech Synthesis (SSW), Bonn, Germany; 2007:294\u2013299."},{"key":"768_CR30","first-page":"227","volume-title":"An HMM-Based Speech Synthesis System Applied to English","author":"K Tokuda","year":"2002","unstructured":"Tokuda K, Zen H, Black AW: An HMM-Based Speech Synthesis System Applied to English. IEEE Workshop on Speech Synthesis, Scotland; 2002:227\u2013230."},{"issue":"1","key":"768_CR31","doi-asserted-by":"publisher","first-page":"325","DOI":"10.1093\/ietisy\/e90-1.1.325","volume":"90","author":"H Zen","year":"2007","unstructured":"Zen H, Toda T, Nakamura M, Tokuda K: Details of the Nitech HMM-based speech synthesis system for the Blizzard Challenge 2005.IEICE Trans Inf Syst 2007,90(1):325\u2013333.","journal-title":"IEICE Trans Inf Syst"},{"issue":"6","key":"768_CR32","doi-asserted-by":"publisher","first-page":"1764","DOI":"10.1093\/ietisy\/e91-d.6.1764","volume":"91","author":"H Zen","year":"2008","unstructured":"Zen H, Toda T, Tokuda K: The Nitech-NAIST HMM-based speech synthesis system for the Blizzard Challenge 2006.IEICE Trans Inf Syst 2008,91(6):1764\u20131773.","journal-title":"IEICE Trans Inf Syst"},{"issue":"5","key":"768_CR33","doi-asserted-by":"publisher","first-page":"1234","DOI":"10.1109\/JPROC.2013.2251852","volume":"101","author":"K Tokuda","year":"2013","unstructured":"Tokuda K, Nankaku Y, Toda T, Zen H, Yamagishi J, Oura K: Speech synthesis based on hidden Markov models.Proc IEEE 2013,101(5):1234\u20131252.","journal-title":"Proc IEEE"},{"key":"768_CR34","volume-title":"The use of Context in Large Vocabulary Speech Recognition","author":"JJ Odell","year":"1995","unstructured":"Odell JJ: The use of Context in Large Vocabulary Speech Recognition. PhD dissertation, Cambridge University; 1995."},{"key":"768_CR35","first-page":"307","volume-title":"Tree-Based State Tying for High Accuracy Acoustic Modeling","author":"SJ Young","year":"1994","unstructured":"Young SJ, Odell JJ, Woodland PC: Tree-Based State Tying for High Accuracy Acoustic Modeling. Proceedings of the Workshop on Human Language Technology, Association for Computational Linguistics, Stroudsburg, PA, USA; 1994:307\u2013312."},{"issue":"3","key":"768_CR36","first-page":"455","volume":"85","author":"K Tokuda","year":"2002","unstructured":"Tokuda K, Masuko T, Miyazaki N, Kobayashi T: Multi-space probability distribution HMM.IEICE Trans Inf Syst 2002,85(3):455\u2013464.","journal-title":"IEICE Trans Inf Syst"},{"issue":"5","key":"768_CR37","doi-asserted-by":"publisher","first-page":"825","DOI":"10.1093\/ietisy\/e90-d.5.825","volume":"D-90","author":"H Zen","year":"2007","unstructured":"Zen H, Keiichi T, Masuko T, Kobayashi T, Kitamura T: A hidden semi-Markov model-based speech synthesis system.IEICE Transactions on Information and Systems, E series 2007,D-90(5):825\u2013834.","journal-title":"IEICE Transactions on Information and Systems, E series"},{"key":"768_CR38","doi-asserted-by":"crossref","first-page":"7962","DOI":"10.1109\/ICASSP.2013.6639215","volume-title":"IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP 2013","author":"H Zen","year":"2013","unstructured":"Zen H, Senior A, Schuster M: Statistical Parametric Speech Synthesis Using Deep Neural Networks. In IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP 2013. IEEE; 2013:7962\u20137966."},{"key":"768_CR39","first-page":"261","volume-title":"Combining a Vector Space Representation of Linguistic Context With a Deep Neural Network for Text-to-Speech Synthesis","author":"H Lu","year":"2013","unstructured":"Lu H, King S, Watts O: Combining a Vector Space Representation of Linguistic Context With a Deep Neural Network for Text-to-Speech Synthesis. 8th ISCA Speech Synthesis Workshop, Barcelona, Spain; 2013:261\u2013265."},{"key":"768_CR40","first-page":"7825","volume-title":"Modeling Spectral Envelopes Using Restricted Boltzmann Machines for Statistical Parametric Speech Synthesis","author":"ZH Ling","year":"2013","unstructured":"Ling ZH, Deng L, Yu D: Modeling Spectral Envelopes Using Restricted Boltzmann Machines for Statistical Parametric Speech Synthesis. IEEE Acoustics, Speech and Signal Processing (ICASSP), Vancouver, British Columbia, Canada; 2013:7825\u20137829."},{"key":"768_CR41","first-page":"8012","volume-title":"Multi-Distribution Deep Belief Network for Speech Synthesis","author":"S Kang","year":"2013","unstructured":"Kang S, Qian X, Meng H: Multi-Distribution Deep Belief Network for Speech Synthesis. IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), Vancouver, British Columbia, Canada; 2013:8012\u20138016."},{"key":"768_CR42","first-page":"1","volume":"99","author":"T Koriyama","year":"2013","unstructured":"Koriyama T, Nose T, Kobayashi T: Statistical parametric speech synthesis based on Gaussian process regression.IEEE Journal of Selected Topics in Signal Processing 2013, 99:1\u201311.","journal-title":"IEEE Journal of Selected Topics in Signal Processing"},{"key":"768_CR43","first-page":"1751","volume-title":"A Bayesian Approach to Hidden Semi Markov Model Based Speech Synthesis","author":"K Hashimoto","year":"2009","unstructured":"Hashimoto K, Nankaku Y, Tokuda K: A Bayesian Approach to Hidden Semi Markov Model Based Speech Synthesis. Proceedings of Interspeech, Brighton, United Kingdom; 2009:1751\u20131754."},{"key":"768_CR44","first-page":"1","volume":"12","author":"S Khorram","year":"2014","unstructured":"Khorram S, Sameti H, Bahmaninezhad F, King S, Drugman T: Context-Dependent Acoustic Modeling Based on Hidden Maximum Entropy Model for Statistical Parametric Speech Synthesis.EURASIP Journal on Audio, Speech, and Music Processing 2014, 12:1\u201321.","journal-title":"EURASIP Journal on Audio, Speech, and Music Processing"},{"key":"768_CR45","first-page":"4469","volume-title":"Acoustic Modeling With Contextual Additive Structure for HMM-Based Speech Recognition","author":"Y Nankaku","year":"2008","unstructured":"Nankaku Y, Nakamura K, Zen H, Tokuda K: Acoustic Modeling With Contextual Additive Structure for HMM-Based Speech Recognition. IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), Las Vegas, Nevada, USA; 2008:4469\u20134472."},{"key":"768_CR46","first-page":"100","volume-title":"Spectral Modeling With Contextual Additive Structure for HMM-Based Speech Synthesis","author":"S Takaki","year":"2010","unstructured":"Takaki S, Nankaku Y, Tokuda K: Spectral Modeling With Contextual Additive Structure for HMM-Based Speech Synthesis. Proceedings of 7th ISCA Speech Synthesis Workshop, Kyoto, Japan; 2010:100\u2013105."},{"key":"768_CR47","first-page":"7878","volume-title":"Contextual Partial Additive Structure for HMM-Based Speech Synthesis","author":"S Takaki","year":"2013","unstructured":"Takaki S, Nankaku Y, Tokuda K: Contextual Partial Additive Structure for HMM-Based Speech Synthesis. IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), Vancouver, British Columbia, Canada; 2013:7878\u20137882."},{"issue":"2","key":"768_CR48","doi-asserted-by":"publisher","first-page":"229","DOI":"10.1109\/JSTSP.2014.2305919","volume":"8","author":"S Takaki","year":"2014","unstructured":"Takaki S, Nankaku Y, Tokuda K: Contextual additive structure for HMM-based speech synthesis.IEEE J Selected Topics in Signal Processing 2014,8(2):229\u2013238.","journal-title":"IEEE J Selected Topics in Signal Processing"},{"key":"768_CR49","first-page":"2091","volume-title":"Context-Dependent Additive log F0 Model for HMM-Based Speech Synthesis","author":"H Zen","year":"2009","unstructured":"Zen H, Braunschweiler N: Context-Dependent Additive log F0 Model for HMM-Based Speech Synthesis. INTERSPEECH, Brighton, United Kingdom; 2009:2091\u20132094."},{"key":"768_CR50","first-page":"4017","volume-title":"Modeling pitch trajectory by hierarchical HMM with minimum generation error training","author":"YJ Wu","year":"2012","unstructured":"Wu YJ, Soong F: Modeling pitch trajectory by hierarchical HMM with minimum generation error training. IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), Kyoto, Japan; 2012:4017\u20134020."},{"key":"768_CR51","first-page":"277","volume":"1","author":"S Sakai","year":"2008","unstructured":"Sakai S: Additive modeling of English F0 contour for speech synthesis.Proceedings of ICASSP 2008, 1:277\u2013280.","journal-title":"Proceedings of ICASSP"},{"key":"768_CR52","volume-title":"Generating Natural F0 Trajectory With Additive Trees","author":"Y Qian","year":"2008","unstructured":"Qian Y, Liang H, Soong FK: Generating Natural F0 Trajectory With Additive Trees. INTERSPEECH, Brisbane, Australia; 2008. pp. 2126\u20132129"},{"key":"768_CR53","first-page":"4238","volume-title":"Word-Level Emphasis Modeling in HMM-Based Speech Synthesis","author":"K Yu","year":"2010","unstructured":"Yu K, Mairesse F, Young S: Word-Level Emphasis Modeling in HMM-Based Speech Synthesis. IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), Dallas, Texas, USA; 2010:4238\u20134241."},{"issue":"6","key":"768_CR54","doi-asserted-by":"publisher","first-page":"914","DOI":"10.1016\/j.specom.2011.03.003","volume":"53","author":"K Yu","year":"2011","unstructured":"Yu K, Zen H, Mairesse F, Young S: Context adaptive training with factorized decision trees for HMM-based statistical parametric speech synthesis.Speech Comm 2011,53(6):914\u2013923. 10.1016\/j.specom.2011.03.003","journal-title":"Speech Comm"},{"issue":"4","key":"768_CR55","doi-asserted-by":"publisher","first-page":"417","DOI":"10.1109\/89.848223","volume":"8","author":"MJ Gales","year":"2000","unstructured":"Gales MJ: Cluster adaptive training of hidden Markov models.IEEE Transactions on Speech and Audio Processing 2000,8(4):417\u2013428. 10.1109\/89.848223","journal-title":"IEEE Transactions on Speech and Audio Processing"},{"issue":"2","key":"768_CR56","doi-asserted-by":"publisher","first-page":"221","DOI":"10.1016\/S0165-0114(03)00089-7","volume":"138","author":"C Olaru","year":"2003","unstructured":"Olaru C, Wehenkel L: A complete fuzzy decision tree technique.Fuzzy Set Syst 2003,138(2):221\u2013254. 10.1016\/S0165-0114(03)00089-7","journal-title":"Fuzzy Set Syst"},{"issue":"2","key":"768_CR57","doi-asserted-by":"publisher","first-page":"125","DOI":"10.1016\/0165-0114(94)00229-Z","volume":"69","author":"Y Yuan","year":"1995","unstructured":"Yuan Y, Shaw MJ: Induction of fuzzy decision trees.Fuzzy Set Syst 1995,69(2):125\u2013139. 10.1016\/0165-0114(94)00229-Z","journal-title":"Fuzzy Set Syst"},{"issue":"1","key":"768_CR58","doi-asserted-by":"publisher","first-page":"4","DOI":"10.1109\/MASSP.1986.1165342","volume":"3","author":"L Rabiner","year":"1986","unstructured":"Rabiner L, Juang BH: An introduction to hidden Markov models.IEEE ASSP Mag 1986,3(1):4\u201316.","journal-title":"IEEE ASSP Mag"},{"issue":"5","key":"768_CR59","doi-asserted-by":"publisher","first-page":"1071","DOI":"10.1109\/TASL.2010.2076805","volume":"19","author":"K Yu","year":"2011","unstructured":"Yu K, Young S: Continuous F0 modeling for HMM based statistical parametric speech synthesis.IEEE Transactions on Audio, Speech, and Language Processing 2011,19(5):1071\u20131079.","journal-title":"IEEE Transactions on Audio, Speech, and Language Processing"},{"issue":"6","key":"768_CR60","doi-asserted-by":"publisher","first-page":"47","DOI":"10.1109\/79.543975","volume":"13","author":"TK Moon","year":"1996","unstructured":"Moon TK: The expectation-maximization algorithm.IEEE Signal Process Mag 1996,13(6):47\u201360. 10.1109\/79.543975","journal-title":"IEEE Signal Process Mag"},{"key":"768_CR61","unstructured":"HMM-based speech synthesis system (HTS). http:\/\/hts.sp.nitech.ac.jp\/"},{"key":"768_CR62","volume-title":"Implementing an HSMM-Based Speech Synthesis System Using an Efficient Forward-Backward Algorithm, Nagoya Institute of Technology, Technical Report TR-SP-0001","author":"H Zen","year":"2007","unstructured":"Zen H: Implementing an HSMM-Based Speech Synthesis System Using an Efficient Forward-Backward Algorithm, Nagoya Institute of Technology, Technical Report TR-SP-0001. 2007."},{"key":"768_CR63","first-page":"143","volume-title":"Variable Duration Models for Speech","author":"JD Ferguson","year":"1980","unstructured":"Ferguson JD: Variable Duration Models for Speech. Proceedings of the Symposium on the Application Hidden Markov Models to Text and Speech, USA; 1980:143\u2013179."},{"issue":"1","key":"768_CR64","doi-asserted-by":"publisher","first-page":"29","DOI":"10.1016\/S0885-2308(86)80009-2","volume":"1","author":"SE Levinson","year":"1986","unstructured":"Levinson SE: Continuously variable duration hidden Markov models for automatic speech recognition.Computer Speech and Language 1986,1(1):29\u201345. 10.1016\/S0885-2308(86)80009-2","journal-title":"Computer Speech and Language"},{"issue":"1","key":"768_CR65","doi-asserted-by":"publisher","first-page":"11","DOI":"10.1109\/LSP.2002.806705","volume":"10","author":"SZ Yu","year":"2003","unstructured":"Yu SZ, Kobayashi H: An efficient forward-backward algorithm for an explicit-duration hidden Markov model.IEEE Signal Processing Letters 2003,10(1):11\u201314.","journal-title":"IEEE Signal Processing Letters"},{"key":"768_CR66","first-page":"717","volume-title":"Speaker Adaptation With Autonomous Model Complexity Control by MDL Principle","author":"K Shinoda","year":"1996","unstructured":"Shinoda K, Watanabe T: Speaker Adaptation With Autonomous Model Complexity Control by MDL Principle. Proceedings of ICASSP, Atlanta, Georgia, USA; 1996:717\u2013720."},{"issue":"1","key":"768_CR67","first-page":"39","volume":"22","author":"AL Berger","year":"1996","unstructured":"Berger AL, Pietra VJD, Pietra SAD: A maximum entropy approach to natural language processing.Computational Linguistics 1996,22(1):39\u201371.","journal-title":"Computational Linguistics"},{"key":"768_CR68","first-page":"133","volume-title":"A Maximum Entropy Model for Part-of-Speech Tagging","author":"A Ratnaparkhi","year":"1996","unstructured":"Ratnaparkhi A: A Maximum Entropy Model for Part-of-Speech Tagging. Proceedings of the Conference on Empirical Methods in Natural Language Processin, PA, USA; 1996:133\u2013142."},{"key":"768_CR69","first-page":"1","volume-title":"The CSTR\/EMIME HTS System for Blizzard Challenge","author":"J Yamagishi","year":"2010","unstructured":"Yamagishi J, Watts O: The CSTR\/EMIME HTS System for Blizzard Challenge. Proceedings of Blizzard Challenge 2010, Japan; 2010:1\u20136."},{"key":"768_CR70","volume-title":"Average-Voice-Based Speech Synthesis","author":"J Yamagishi","year":"2006","unstructured":"Yamagishi J: Average-Voice-Based Speech Synthesis. PhD thesis, Tokyo Institute of Technology; 2006."}],"container-title":["EURASIP Journal on Advances in Signal Processing"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/article\/10.1186\/1687-6180-2015-2\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1186\/1687-6180-2015-2.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1186\/1687-6180-2015-2.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,8,11]],"date-time":"2023-08-11T15:19:19Z","timestamp":1691767159000},"score":1,"resource":{"primary":{"URL":"https:\/\/asp-eurasipjournals.springeropen.com\/articles\/10.1186\/1687-6180-2015-2"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2015,1,9]]},"references-count":70,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2015,12]]}},"alternative-id":["768"],"URL":"https:\/\/doi.org\/10.1186\/1687-6180-2015-2","relation":{},"ISSN":["1687-6180"],"issn-type":[{"value":"1687-6180","type":"electronic"}],"subject":[],"published":{"date-parts":[[2015,1,9]]},"assertion":[{"value":"29 August 2014","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"5 December 2014","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"9 January 2015","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}],"article-number":"2"}}