{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,1,22]],"date-time":"2025-01-22T05:24:38Z","timestamp":1737523478050,"version":"3.33.0"},"reference-count":37,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2007,10,18]],"date-time":"2007-10-18T00:00:00Z","timestamp":1192665600000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["SIViP"],"published-print":{"date-parts":[[2008,1]]},"DOI":"10.1007\/s11760-007-0038-z","type":"journal-article","created":{"date-parts":[[2007,10,17]],"date-time":"2007-10-17T05:32:47Z","timestamp":1192599167000},"page":"73-87","source":"Crossref","is-referenced-by-count":9,"title":["Towards a high quality Arabic speech synthesis system based on neural networks and residual excited vocal tract model"],"prefix":"10.1007","volume":"2","author":[{"given":"Fatima","family":"Chouireb","sequence":"first","affiliation":[]},{"given":"Mhania","family":"Guerti","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2007,10,18]]},"reference":[{"key":"38_CR1","first-page":"40","volume":"AU-16","author":"N.R. Dixon","year":"1976","unstructured":"Dixon N.R. and Maxey H.D. (1976). Terminal analog synthesis of continuous speech using the diphone method of segment assembly. IEEE Trans. Audio Electroacoust. AU-16: 40\u201350","journal-title":"IEEE Trans. Audio Electroacoust."},{"key":"38_CR2","doi-asserted-by":"crossref","first-page":"127","DOI":"10.1177\/002383096400700301","volume":"7","author":"J.N. Holmes","year":"1964","unstructured":"Holmes J.N. et al. (1964). Speech synthesis by rule. Lang. Speech 7: 127\u2013143","journal-title":"Lang. Speech"},{"key":"38_CR3","unstructured":"Guerti, M.: Contribution \u00e0 la synth\u00e8se de la parole en Arabe Standard. XVI\u00e8mes Journ\u00e9es d\u2019Etudes sur la Parole (JEP), Soci\u00e9t\u00e9 Fran\u00e7aise d\u2019Acoustique, Hammamet, Tunisie, 5\u20139 Octobre 1987, pp. 290\u2013293 (1987)"},{"key":"38_CR4","doi-asserted-by":"crossref","unstructured":"Hunt, A.J., Black, A.W.: Unit selection in a concatenative speech synthesis system using a large speech database. In: Proceedings of ICASSP\u201996, pp. 373\u2013376 (1996)","DOI":"10.1109\/ICASSP.1996.541110"},{"key":"38_CR5","unstructured":"Guerti, M.: Speech synthesis by rule. In: 8th International conference on computer theory and applications ICCTA\u201998, IEEE (Alexandra Chapter), Alexandria-EGYPT, 15\u201317 September 1998, III.12\u2013III.15 (1998)"},{"key":"38_CR6","doi-asserted-by":"crossref","unstructured":"Tuerk, C., Robinson, T.: Speech Synthesis using neural networks trained on cepstral coefficients. In: Proceedings of Eurospeech\u201993, Berlin, pp. 1713\u20131716 (1993)","DOI":"10.21437\/Eurospeech.1993-391"},{"key":"38_CR7","doi-asserted-by":"crossref","unstructured":"Weijters, T., Thole, J.: Speech synthesis with artificial neural networks. In: Proceedings of ICNN\u201993, San Francisco, pp. 1764\u20131769 (1993)","DOI":"10.1109\/ICNN.1993.298824"},{"key":"38_CR8","doi-asserted-by":"crossref","unstructured":"Karaali, O., Corrigan, G., Gerson, I., Massey, N.: Text-to-speech conversion with neural networks: a recurrent TDNN approach. In: Proceedings of Eurospeech\u201997, Rhodes, Greece, pp. 561\u2013564 (1997)","DOI":"10.21437\/Eurospeech.1997-209"},{"key":"38_CR9","doi-asserted-by":"crossref","unstructured":"Xiang, Z., BI, G.: A neural network model for Chinese speech synthesis. In: Proceedings of IEEE International Symposium on Circuits and Systems, vol. 3, pp. 1859\u20131862 (1990)","DOI":"10.1109\/ISCAS.1990.112027"},{"key":"38_CR10","unstructured":"Cawley, G.C.: The application of neural networks to phonetic modelling. PhD thesis, University of Essex (1996)"},{"key":"38_CR11","unstructured":"Tao, J., Cai, L., Tropf, H.: An optimised neural network based prosody model of Chinese speech synthesis system. In: Proceedings of IEEE TENCON\u201902, pp. 477\u2013480 (2002)"},{"key":"38_CR12","doi-asserted-by":"crossref","unstructured":"Farrokhi, A., Ghammaghami, S.: Predication of prosodic data in Persian text-to-speech systems using recurrent neural network. In: Electronics Letters IEE 2003, vol. 39, no. 25 (2003)","DOI":"10.1049\/el:20031151"},{"key":"38_CR13","doi-asserted-by":"crossref","unstructured":"Teixeira, J.P., Freitas, D.: Segmental durations predicted with a neural network. Eurospeech 2003-Geneva, pp. 169\u2013172 (2003)","DOI":"10.21437\/Eurospeech.2003-91"},{"key":"38_CR14","unstructured":"Vainio, M.: Artificial neural network based prosody models for Finnish text-to-speech synthesis. University of Helsinki, Department of Phonetics, Finland (2001)"},{"key":"38_CR15","doi-asserted-by":"crossref","first-page":"226","DOI":"10.1109\/89.668817","volume":"6","author":"S.H. Chen","year":"1998","unstructured":"Chen S.H., Hwang S.H. and Wang Y.R. (1998). An RNN-based prosodic information synthesizer for Chinese text-to-speech. IEEE Trans. Speech Audio Process. 6: 226\u2013239","journal-title":"IEEE Trans. Speech Audio Process."},{"key":"38_CR16","doi-asserted-by":"crossref","unstructured":"Erdem, C., Zimmermman, H.G.: A data-driven method for input feature selection within neural prosody generation. In: Proceedings of ICASSP 2002, vol. 1, pp. 477\u2013480","DOI":"10.1109\/ICASSP.2002.5743758"},{"key":"38_CR17","unstructured":"Baloul, S.: D\u00e9veloppement d\u2019un syst\u00e8me automatique de synth\u00e8se de la parole \u00e0 partir du texte arabe standard voyell\u00e9. Th\u00e8se de doctorat, universit\u00e9 du Maine, Le Mans, France (2003)"},{"key":"38_CR18","unstructured":"Malfr\u00e8re, F., Deroo, O., Dutoit, T.: Phonetic alignment: Speech synthesis based vs. hybrid HMM\/ANN. In: Proceedings of ICSLP 98, Sydney, Australia, pp. 1571\u20131574"},{"key":"38_CR19","doi-asserted-by":"crossref","unstructured":"Malfr\u00e8re, F., Dutoit, T.: Speech synthesis for text-to-speech alignment and prosodic feature extraction. In: Proceedings of ISCAS\u2019 97, Hong-Kong, pp. 2637\u20132640 (1997)","DOI":"10.1109\/ISCAS.1997.612866"},{"key":"38_CR20","first-page":"43","volume-title":"Speech Processing.","author":"J. Nouza","year":"1997","unstructured":"Nouza J. (1997). Spectral variation functions applied to acoustic\u2013phonetic segmentation of speech signal. In: Wodarz, H.-W. (eds) Speech Processing., pp 43\u201358. Forum Phoneticum, 63, Frankfurt amndt Hand"},{"key":"38_CR21","doi-asserted-by":"crossref","DOI":"10.1007\/978-94-011-5730-8","volume-title":"An Introduction to text-to-speech Synthesis","author":"T. Dutoit","year":"1997","unstructured":"Dutoit T. (1997). An Introduction to text-to-speech Synthesis. Kluwer, The Netherlands"},{"key":"38_CR22","doi-asserted-by":"crossref","unstructured":"Chappell, D.T., Hansen, J.H.L.: A comparison of spectral smoothing methods for segment concatenation based speech synthesis. In: Speech Communication, 36. pp. 343\u2013374, Elsevier, Amsterdam (2002)","DOI":"10.1016\/S0167-6393(01)00008-5"},{"key":"38_CR23","doi-asserted-by":"crossref","first-page":"535","DOI":"10.1121\/1.1995189","volume":"57","author":"F. Itakura","year":"1975","unstructured":"Itakura, F. (1975) Line spectrum representation of linear prediction coefficients of speech signals. J. Acoust. Soc. Am. 57: 535 (abstract)","journal-title":"J. Acoust. Soc. Am."},{"volume-title":"Speech Coding and Synthesis","year":"1995","key":"38_CR24","unstructured":"Kleijn W.B., Paliwal K.K. (eds). (1995). Speech Coding and Synthesis. Elsevier, Amsterdam"},{"key":"38_CR25","first-page":"145","volume":"1","author":"T.J. Sejnowski","year":"1987","unstructured":"Sejnowski T.J. and Rosenberg C.R. (1987). Parallel networks that learn to pronounce English text. Complex Syst. 1: 145\u2013168","journal-title":"Complex Syst."},{"issue":"5","key":"38_CR26","doi-asserted-by":"crossref","first-page":"1763","DOI":"10.1109\/TSA.2005.858548","volume":"14","author":"J. Vepa","year":"2006","unstructured":"Vepa J. and King S. (2006). Subjective evaluation of join cost and smoothing methods for unit selection speech synthesis. IEEE Trans. Speech Audio Process. 14(5): 1763\u20131771","journal-title":"IEEE Trans. Speech Audio Process."},{"key":"38_CR27","first-page":"51","volume-title":"Prosody: Theory and Experiement.","author":"H. Daniel","year":"2000","unstructured":"Daniel H., Di Christo A. and Espesser R. (2000). Levels of representation and levels of analysis for intonation. In: Horne, M. (eds) Prosody: Theory and Experiement., pp 51\u201387. Kluwer, Dordrecht"},{"key":"38_CR28","unstructured":"Fant G., Kruckenberg A.: Intonation analysis and synthesis with reference to Swedish. In: International Somposium on Tonal Aspects of languages: with Emphasis on Tone languages, Beijing, China, 28\u201331 (2004)"},{"key":"38_CR29","doi-asserted-by":"crossref","first-page":"453","DOI":"10.1016\/0167-6393(90)90021-Z","volume":"9","author":"E. Moulines","year":"1990","unstructured":"Moulines E. and Charpentier F. (1990). Pitch-synchronous waveform processing techniques for text-to-speech synthesis using diphones. Speech Commun. 9: 453\u2013467","journal-title":"Speech Commun."},{"key":"38_CR30","unstructured":"Chouireb, F., Guerti, M.: Etude et Application des techniques LPC et TD-PSOLA pour l\u2019analyse\/modification\/synth\u00e8se de la parole. International Conference on Electrical and Electronics Engineering-ICEEE\u20192004, Universit\u00e9 Amar Telidji-Laghouat (Alg\u00e9rie), Special issue IASN 1112\u20134652, 24\u201326 April, pp. 244\u2013250 (2004)"},{"key":"38_CR31","doi-asserted-by":"crossref","unstructured":"Edgington, M., Lowry, A.: Residual-based speech modification algorithm for text-to-speech synthesis. In: ICLSP\u201996, Philadelphia, PA, USA, 3\u20136, October, pp. 1425\u20131428 (1996)","DOI":"10.1109\/ICSLP.1996.607882"},{"key":"38_CR32","doi-asserted-by":"crossref","unstructured":"Gim\u00e9nez de los Galanes, F.M., Savoji, M.H., Pardo, J.M.: New Algorithm for spectral smoothing and envelope modification for LP-PSOLA synthesis. In: Proceedings of ICASSP, vol. 1, pp. 573\u2013576 (1994)","DOI":"10.1109\/ICASSP.1994.389229"},{"key":"38_CR33","doi-asserted-by":"crossref","DOI":"10.1017\/CBO9780511627743","volume-title":"A perceptual study of intonation","author":"J. Hart","year":"1990","unstructured":"Hart J., Collier R. and Cohen A. (1990). A perceptual study of intonation. Cambridge University Press, Cambridge"},{"key":"38_CR34","doi-asserted-by":"crossref","first-page":"293","DOI":"10.1007\/978-1-4612-1894-4_23","volume-title":"Progress in Speech Synthesis.","author":"A. Conkie","year":"1997","unstructured":"Conkie A. and Isard S. (1997). Optimal coupling of diphones. In: Van Santen, J., Sproat, R., Olive, J. and Hirschberg, J. (eds) Progress in Speech Synthesis., pp 293\u2013304. Springer-Verlag, New York"},{"key":"38_CR35","doi-asserted-by":"crossref","unstructured":"Black, A., Campbell, N.: Optimising selection of units from speech databases for concatenative synthesis. In: EUROSPEECH \u201995, Madrid, Spain, pp. 581\u2013584 (1995)","DOI":"10.21437\/Eurospeech.1995-148"},{"issue":"5","key":"38_CR36","doi-asserted-by":"crossref","first-page":"489","DOI":"10.1109\/89.709674","volume":"6","author":"J.H.L. Hansen","year":"1998","unstructured":"Hansen J.H.L. and Chappell D.T. (1998). An auditory-based distortion measure with application to concatenative speech synthesis. IEEE Trans. Speech Audio Process. 6(5): 489\u2013495","journal-title":"IEEE Trans. Speech Audio Process."},{"key":"38_CR37","doi-asserted-by":"crossref","unstructured":"Dutoit, T., Cernak, M.: TTSBOX: A MATLAB toolbox for teaching text-to-speech synthesis. In: ICASSP\u201905, Philadelphia, 18\u201323 March 2005, vol. 5, pp: v\/537\u2013v\/540 (2005)","DOI":"10.1109\/ICASSP.2005.1416359"}],"container-title":["Signal, Image and Video Processing"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s11760-007-0038-z.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/article\/10.1007\/s11760-007-0038-z\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s11760-007-0038-z","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,1,21]],"date-time":"2025-01-21T18:15:17Z","timestamp":1737483317000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/s11760-007-0038-z"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2007,10,18]]},"references-count":37,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2008,1]]}},"alternative-id":["38"],"URL":"https:\/\/doi.org\/10.1007\/s11760-007-0038-z","relation":{},"ISSN":["1863-1703","1863-1711"],"issn-type":[{"type":"print","value":"1863-1703"},{"type":"electronic","value":"1863-1711"}],"subject":[],"published":{"date-parts":[[2007,10,18]]}}}