{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,5,2]],"date-time":"2025-05-02T09:40:03Z","timestamp":1746178803095,"version":"3.40.4"},"reference-count":54,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2014,4,7]],"date-time":"2014-04-07T00:00:00Z","timestamp":1396828800000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/2.0"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["J AUDIO SPEECH MUSIC PROC."],"published-print":{"date-parts":[[2014,12]]},"DOI":"10.1186\/1687-4722-2014-12","type":"journal-article","created":{"date-parts":[[2014,4,7]],"date-time":"2014-04-07T19:57:20Z","timestamp":1396900640000},"source":"Crossref","is-referenced-by-count":4,"title":["Context-dependent acoustic modeling based on hidden maximum entropy model for statistical parametric speech synthesis"],"prefix":"10.1186","volume":"2014","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":"Fahimeh","family":"Bahmaninezhad","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Simon","family":"King","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Thomas","family":"Drugman","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2014,4,7]]},"reference":[{"issue":"11","key":"109_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 AW: Statistical parametric speech synthesis. Speech Comm. 2009, 51(11):1039-1064. 10.1016\/j.specom.2009.04.004","journal-title":"Speech Comm"},{"key":"109_CR2","first-page":"IV1229","volume-title":"Statistical parametric speech synthesis, in IEEE International Conference on Acoustics, vol. 4","author":"AW Black","year":"2007","unstructured":"Black AW, Zen H, Tokuda K: Statistical parametric speech synthesis, in IEEE International Conference on Acoustics, vol. 4. Speech and Signal Processing (ICASSP), Honolulu, Hawaii, USA; 2007:IV1229-IV1232."},{"issue":"2","key":"109_CR3","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 - Trans. Info. Syst. 2007, 90(2):533-543.","journal-title":"IEICE - Trans. Info. Syst"},{"key":"109_CR4","first-page":"1208","volume-title":"Robust speaker-adaptive HMM-based text-to-speech synthesis, In IEEE Transactions on Audio, Speech, and Language Processing","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, In IEEE Transactions on Audio, Speech, and Language Processing. 2009, 17(6):1208-1230."},{"key":"109_CR5","first-page":"66","volume-title":"Analysis of speaker adaptation algorithms for HMM-based speech synthesis and a constrained SMAPLR adaptation algorithm, IEEE Transactions on Audio, Speech, and Language Processing","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):66-83."},{"key":"109_CR6","first-page":"528","volume-title":"INTERSPEECH","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. In INTERSPEECH. Brighton, UK; 2009:528-531."},{"key":"109_CR7","first-page":"4598","volume-title":"IEEE International Conference on Acoustics Speech and Signal Processing (ICASSP)","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. In IEEE International Conference on Acoustics Speech and Signal Processing (ICASSP). Dallas, Texas, USA; 2010:4598-4601."},{"key":"109_CR8","first-page":"4642","volume-title":"IEEE International Conference on Acoustics Speech and Signal Processing (ICASSP)","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. In IEEE International Conference on Acoustics Speech and Signal Processing (ICASSP). Dallas, Texas, USA; 2010:4642-4645."},{"key":"109_CR9","doi-asserted-by":"crossref","first-page":"581","DOI":"10.21437\/Interspeech.2008-171","volume-title":"INTERSPEECH","author":"J Yamagishi","year":"2008","unstructured":"Yamagishi J, Ling Z, King S: Robustness of HMM-based speech synthesis. In INTERSPEECH. Brisbane, Australia; 2008:581-584."},{"key":"109_CR10","first-page":"2263","volume-title":"INTERSPEECH","author":"T Yoshimura","year":"2001","unstructured":"Yoshimura T, Tokuda K, Masuko T, Kobayashi T, Kitamura T: Mixed excitation for HMM-based speech synthesis. In INTERSPEECH. Aalborg, Denmark; 2001:2263-2266."},{"issue":"3","key":"109_CR11","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, de 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):187-207.","journal-title":"Speech Comm"},{"key":"109_CR12","doi-asserted-by":"crossref","first-page":"1779","DOI":"10.21437\/Interspeech.2009-148","volume-title":"INTERSPEECH","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. In INTERSPEECH. Brighton, United Kingdom; 2009:1779-1782."},{"issue":"3","key":"109_CR13","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 Trans. Audio. Speech. Lang. Process 2012, 20(3):968-981.","journal-title":"IEEE Trans. Audio. Speech. Lang. Process"},{"issue":"5","key":"109_CR14","doi-asserted-by":"publisher","first-page":"825","DOI":"10.1093\/ietisy\/e90-d.5.825","volume":"90","author":"H Zen","year":"2007","unstructured":"Zen H, Tokuda K, Masuko T, Kobayasih T, Kitamura T: A hidden semi-Markov model-based speech synthesis system. IEICE - Trans. Info. Syst 2007, 90(5):825.","journal-title":"IEICE - Trans. Info. Syst"},{"key":"109_CR15","first-page":"1751","volume-title":"A Bayesian approach to hidden semi Markov model based speech synthesis, in Proceedings of INTERSPEECH","author":"K Hashimoto","year":"2009","unstructured":"Hashimoto K, Nankaku Y, Tokuda K: A Bayesian approach to hidden semi Markov model based speech synthesis, in Proceedings of INTERSPEECH. Brighton, United Kingdom; 2009:1751-1754."},{"key":"109_CR16","first-page":"4029","volume-title":"A Bayesian approach to HMM-based speech synthesis, in IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","author":"K Hashimoto","year":"2009","unstructured":"Hashimoto K, Zen H, Nankaku Y, Masuko T, Tokuda K: A Bayesian approach to HMM-based speech synthesis, in IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). Taipei, Taiwan; 2009:4029-4032."},{"issue":"3","key":"109_CR17","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. on Info. Syst 2002, 85(3):455-464.","journal-title":"IEICE Trans. on Info. Syst"},{"key":"109_CR18","first-page":"7962","volume-title":"IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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). Vancouver, British Columbia, Canada; 2013:7962-7966."},{"key":"109_CR19","first-page":"100","volume-title":"Proceedings of 7th ISCA Speech Synthesis Workshop","author":"S Takaki","year":"2010","unstructured":"Takaki S, Nankaku Y, Tokuda K: Spectral modeling with contextual additive structure for HMM-based speech synthesis. In Proceedings of 7th ISCA Speech Synthesis Workshop. Kyoto, Japan; 2010:100-105."},{"key":"109_CR20","first-page":"7878","volume-title":"IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","author":"S Takaki","year":"2013","unstructured":"Takaki S, Nankaku Y, Tokuda K: Contextual partial additive structure for HMM-based speech synthesis. In IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). Vancouver, British Columbia, Canada; 2013:7878-7882."},{"issue":"4","key":"109_CR21","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 Trans. Speech. Audio. Process. 2000, 8(4):417-428. 10.1109\/89.848223","journal-title":"IEEE Trans. Speech. Audio. Process"},{"issue":"3","key":"109_CR22","doi-asserted-by":"publisher","first-page":"794","DOI":"10.1109\/TASL.2011.2165280","volume":"20","author":"H Zen","year":"2012","unstructured":"Zen H, Gales MJ, Nankaku Y, Tokuda K: Product of experts for statistical parametric speech synthesis, IEEE Trans. Audio. Speech. Lang. Process. 2012, 20(3):794-805.","journal-title":"Audio. Speech. Lang. Process"},{"issue":"6","key":"109_CR23","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):914-923. 10.1016\/j.specom.2011.03.003","journal-title":"Speech Comm"},{"key":"109_CR24","first-page":"4025","volume-title":"IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","author":"T Toda","year":"2009","unstructured":"Toda T, Young S: Trajectory training considering global variance for HMM-based speech synthesis. In IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). Taipei, Taiwan; 2009:4025-4028."},{"key":"109_CR25","first-page":"4621","volume-title":"IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","author":"L Qin","year":"2008","unstructured":"Qin L, Wu YJ, Ling ZH, Wang RH, Dai LR: Minimum generation error criterion considering global\/local variance for HMM-based speech synthesis. In IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). Las Vegas, Nevada, USA; 2008:4621-4624."},{"issue":"5","key":"109_CR26","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 - Trans. Info. Syst. Arch 2007, E90-D(5):816-824. 10.1093\/ietisy\/e90-d.5.816","journal-title":"IEICE - Trans. Info. Syst. Arch"},{"key":"109_CR27","first-page":"1315","volume-title":"Speech Parameter Generation Algorithms for HMM-based Speech Synthesis, in ICASSP, vol. 3","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, in ICASSP, vol. 3. Istanbul; 2000:1315-1318."},{"key":"109_CR28","first-page":"660","volume-title":"International Conference on Acoustics, Speech, and Signal Processing (ICASSP), vol. 1","author":"K Tokuda","year":"1995","unstructured":"Tokuda K, Kobayashi T, Imai S: Speech parameter generation from HMM using dynamic features. In International Conference on Acoustics, Speech, and Signal Processing (ICASSP), vol. 1. Detroit, Michigan, USA; 1995:660-663."},{"doi-asserted-by":"crossref","unstructured":"Comparing glottal-flow-excited statistical parametric speech synthesis methods In IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). Vancouver, British Columbia, Canada; 2013:7830-7834.","key":"109_CR29","DOI":"10.1109\/ICASSP.2013.6639188"},{"key":"109_CR30","doi-asserted-by":"crossref","first-page":"2347","DOI":"10.21437\/Eurospeech.1999-513","volume-title":"Proceedings of Eurospeech","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 1999, 2347-2350."},{"key":"109_CR31","first-page":"307","volume-title":"Proceedings of the workshop on Human Language Technology, Association for Computational Linguistics","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 1994, 307-312."},{"key":"109_CR32","volume-title":"Comput. Speech. Lang","author":"CJ Leggetter","year":"1995","unstructured":"Leggetter CJ, Woodland PC: Maximum likelihood linear regression for speaker adaptation of continuous density hidden Markov models. Comput. Speech. Lang. 1995., 9(2):"},{"issue":"4","key":"109_CR33","doi-asserted-by":"publisher","first-page":"294","DOI":"10.1109\/89.506933","volume":"4","author":"VV Digalakis","year":"1996","unstructured":"Digalakis VV, Neumeyer LG: Speaker adaptation using combined transformation and Bayesian methods. IEEE Trans. Speech. Audio. Process. 1996, 4(4):294-300. 10.1109\/89.506933","journal-title":"IEEE Trans. Speech. Audio. Process"},{"issue":"6","key":"109_CR34","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. Audio. Speech. Lang. Process. 2012, 20(6):1713-1724.","journal-title":"IEEE Transactions. Audio. Speech. Lang. Process"},{"key":"109_CR35","first-page":"1","volume-title":"Statistical parametric speech synthesis based on Gaussian process regression, IEEE Journal of Selected Topics in Signal Processing","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, 1-11."},{"key":"109_CR36","first-page":"4238","volume-title":"IEEE International Conference on Acoustics Speech and Signal Processing (ICASSP)","author":"K Yu","year":"2010","unstructured":"Yu K, Mairesse F, Young S: Word-level emphasis modeling in HMM-based speech synthesis. In IEEE International Conference on Acoustics Speech and Signal Processing (ICASSP). Dallas, Texas, USA; 2010:4238-4241."},{"key":"109_CR37","doi-asserted-by":"crossref","first-page":"2091","DOI":"10.21437\/Interspeech.2009-599","volume-title":"INTERSPEECH","author":"H Zen","year":"2009","unstructured":"Zen H, Braunschweiler N: Context-dependent additive log f_0 model for HMM-based speech synthesis. In INTERSPEECH. Brighton, United Kingdom; 2009:2091-2094."},{"key":"109_CR38","first-page":"277","volume-title":"Additive modeling of English f0 contour for speech synthesis, in Proceedings of ICASSP","author":"S Sakai","year":"2008","unstructured":"Sakai S: Additive modeling of English f0 contour for speech synthesis, in Proceedings of ICASSP. Las Vegas, Nevada, USA; 2008:277-280."},{"key":"109_CR39","doi-asserted-by":"crossref","first-page":"2126","DOI":"10.21437\/Interspeech.2008-551","volume-title":"INTERSPEECH","author":"Y Qian","year":"2008","unstructured":"Qian Y, Liang H, Soong FK: Generating natural F0 trajectory with additive trees. In INTERSPEECH. Brisbane, Australia; 2008:2126-2129."},{"key":"109_CR40","first-page":"4017","volume-title":"IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","author":"YJ Wu","year":"2012","unstructured":"Wu YJ, Soong F: Modeling pitch trajectory by hierarchical HMM with minimum generation error training. In IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). Kyoto, Japan; 2012:4017-4020."},{"key":"109_CR41","doi-asserted-by":"publisher","first-page":"39","DOI":"10.1016\/0096-0551(96)00005-7","volume":"22","author":"AL Berger","year":"1996","unstructured":"Berger AL, Pietra VJD, Pietra SAD: A maximum entropy approach to natural language processing. Computer Ling 1996, 22: 39-71. 10.1016\/0096-0551(96)00005-7","journal-title":"Computer Ling"},{"key":"109_CR42","volume-title":"A maximum entropy approach to named entity recognition, PhD dissertation (New York University)","author":"A Borthwick","year":"1999","unstructured":"Borthwick A: A maximum entropy approach to named entity recognition, PhD dissertation (New York University). 1999."},{"key":"109_CR43","first-page":"1","volume-title":"Exploiting acoustic and syntactic features for prosody labeling in a maximum entropy framework, in Proceedings of NAACL HLT","author":"V Rangarajan","year":"2007","unstructured":"Rangarajan V, Narayanan S, Bangalore S: Exploiting acoustic and syntactic features for prosody labeling in a maximum entropy framework, in Proceedings of NAACL HLT. 2007, 1-8."},{"key":"109_CR44","first-page":"133","volume-title":"A maximum entropy model for part-of-speech tagging, in Proceedings of the conference on empirical methods in natural language processing","author":"A Ratnaparkhi","year":"1996","unstructured":"Ratnaparkhi A: A maximum entropy model for part-of-speech tagging, in Proceedings of the conference on empirical methods in natural language processing. 1996, 1: 133-142."},{"key":"109_CR45","volume-title":"The use of context in large vocabulary speech recognition, PhD dissertation (Cambridge University)","author":"JJ Odell","year":"1995","unstructured":"Odell JJ: The use of context in large vocabulary speech recognition, PhD dissertation (Cambridge University). 1995."},{"issue":"2","key":"109_CR46","doi-asserted-by":"publisher","first-page":"79","DOI":"10.1250\/ast.21.79","volume":"21","author":"K Shinoda","year":"2000","unstructured":"Shinoda K, Takao W: MDL-based context-dependent subword modeling for speech recognition. J. Acoust. Soc. Jpn 2000, 21(2):79-86. 10.1250\/ast.21.79","journal-title":"J. Acoust. Soc. Jpn"},{"issue":"3","key":"109_CR47","first-page":"595","volume":"E93-D","author":"K Oura","year":"2010","unstructured":"Oura K, Zen H, Nankaku Y, Lee A, Tokuda K: A covariance-tying technique for HMM-based speech synthesis. J. IEICE 2010, E93-D(3):595-601.","journal-title":"J. IEICE"},{"key":"109_CR48","doi-asserted-by":"publisher","DOI":"10.1007\/b98874","volume-title":"Numerical Optimization","author":"J Nocedal","year":"1999","unstructured":"Nocedal J, Stephen JW: Numerical Optimization. Book of Springer, USA; 1999."},{"key":"109_CR49","first-page":"826","volume-title":"Proceedings of 5th Australian International Conference on Speech Science and Technology (SST)","author":"M Bijankhan","year":"1994","unstructured":"Bijankhan M, Sheikhzadegan J, Roohani MR, Samareh Y, Lucas C, Tebiani M: The speech database of Farsi spoken language. Proceedings of 5th Australian International Conference on Speech Science and Technology (SST) 1994, 826-831."},{"issue":"4","key":"109_CR50","doi-asserted-by":"publisher","first-page":"729","DOI":"10.1023\/A:1005886709040","volume":"15","author":"J Ghomeshi","year":"1997","unstructured":"Ghomeshi J: Non-projecting nouns and the ezafe: construction in Persian. Nat. Lang. Ling. Theor. 1997, 15(4):729-788. 10.1023\/A:1005886709040","journal-title":"Nat. Lang. Ling. Theor"},{"key":"109_CR51","doi-asserted-by":"publisher","first-page":"125","DOI":"10.1109\/PACRIM.1993.407206","volume-title":"IEEE Pacific Rim Conference on Communications, Computers and Signal Processing, vol. 1","author":"R Kubichek","year":"1993","unstructured":"Kubichek R: Mel-cepstral distance measure for objective speech quality assessment. IEEE Pacific Rim Conference on Communications, Computers and Signal Processing, vol. 1 1993, 125-128."},{"key":"109_CR52","first-page":"1797","volume-title":"Continuous control of the degree of articulation in HMM-based speech synthesis, 12th Annual Conference of the International Speech Communication Association (ISCA)","author":"B Picart","year":"2011","unstructured":"Picart B, Drugman T, Dutoit T: Continuous control of the degree of articulation in HMM-based speech synthesis, 12th Annual Conference of the International Speech Communication Association (ISCA). INTERSPEECH, Florence, Italy; 2011:1797-1800."},{"key":"109_CR53","volume-title":"Average-Voice-Based Speech Synthesis, PhD dissertation","author":"J Yamagishi","year":"2006","unstructured":"Yamagishi J: Average-Voice-Based Speech Synthesis, PhD dissertation. Tokyo Institute of 1362 Technology, Yokohama; 2006."},{"key":"109_CR54","first-page":"1","volume-title":"The CSTR\/EMIME HTS system for Blizzard challenge, in Proceedings of Blizzard Challenge 2010","author":"J Yamagishi","year":"2010","unstructured":"Yamagishi J, Watts O: The CSTR\/EMIME HTS system for Blizzard challenge, in Proceedings of Blizzard Challenge 2010. Kyoto, Japan; 2010:1-6."}],"container-title":["EURASIP Journal on Audio, Speech, and Music Processing"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/article\/10.1186\/1687-4722-2014-12\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1186\/1687-4722-2014-12.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1186\/1687-4722-2014-12.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,5,2]],"date-time":"2025-05-02T09:01:22Z","timestamp":1746176482000},"score":1,"resource":{"primary":{"URL":"https:\/\/asmp-eurasipjournals.springeropen.com\/articles\/10.1186\/1687-4722-2014-12"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2014,4,7]]},"references-count":54,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2014,12]]}},"alternative-id":["109"],"URL":"https:\/\/doi.org\/10.1186\/1687-4722-2014-12","relation":{},"ISSN":["1687-4722"],"issn-type":[{"type":"electronic","value":"1687-4722"}],"subject":[],"published":{"date-parts":[[2014,4,7]]},"article-number":"12"}}