{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,16]],"date-time":"2026-03-16T10:05:12Z","timestamp":1773655512805,"version":"3.50.1"},"reference-count":50,"publisher":"Springer Science and Business Media LLC","issue":"2","license":[{"start":{"date-parts":[[2016,4,6]],"date-time":"2016-04-06T00:00:00Z","timestamp":1459900800000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"funder":[{"name":"Jordanian Scientific Research Support Fund","award":["EIT\/1\/05\/2011"],"award-info":[{"award-number":["EIT\/1\/05\/2011"]}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Int J Speech Technol"],"published-print":{"date-parts":[[2016,6]]},"DOI":"10.1007\/s10772-015-9304-6","type":"journal-article","created":{"date-parts":[[2016,4,6]],"date-time":"2016-04-06T08:35:37Z","timestamp":1459931737000},"page":"415-432","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":5,"title":["What we have and what is needed, how to evaluate Arabic Speech Synthesizer?"],"prefix":"10.1007","volume":"19","author":[{"given":"Iyad","family":"Abu Doush","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Faisal","family":"Alkhatib","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Abed Al Raoof","family":"Bsoul","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2016,4,6]]},"reference":[{"key":"9304_CR1","doi-asserted-by":"crossref","unstructured":"Abdel-Hamid, O., Abdou, S.\u00a0M., & Rashwan, M. (2006). Improving arabic hmm based speech synthesis quality. INTERSPEECH.","DOI":"10.21437\/Interspeech.2006-390"},{"key":"9304_CR2","unstructured":"Acapela speech synthesizer. (2014). World Wide Web electronic publication. http:\/\/www.acapela-group.com\/text-to-speech-interactive-demo.html ."},{"key":"9304_CR3","doi-asserted-by":"crossref","first-page":"549","DOI":"10.3844\/jcssp.2007.549.555","volume":"3","author":"J Ahmad","year":"2007","unstructured":"Ahmad, J. (2007). Optical character recognition system for arabic text using cursive multi-directional approach. Journal of Computer Science, 3, 549\u2013555.","journal-title":"Journal of Computer Science"},{"key":"9304_CR4","unstructured":"Ali, M. E. M., Al-Muhtaseb, H., & Al-Ghamdi, M. (2007). Automatic segmentation of arabic speech. In Workshop on information technology and islamic sciences, Imam Mohammad Ben Saud University, Riyadh, March."},{"key":"9304_CR5","unstructured":"AlKhateeb, J., H.\u00a0Ren, J., Ipson, S., & Jiang, J. (2008). knowledge-based baseline detection and optimal thresholding for words segmentation in efficient preprocessing of handwritten arabic text. In Fifth international conference on information technology: New generations (pp. 1158\u20131159)."},{"key":"9304_CR6","doi-asserted-by":"crossref","unstructured":"Al-Saud, N.\u00a0B., & Al-Khalifa, H.\u00a0S. (2012). An initial comparative study of arabic speech synthesis engines in ios and android: Proceedings of the 14th international conference on information integration and web-based applications & services, IIWAS \u201912 (pp. 411\u2013414). New York, NY: ACM.","DOI":"10.1145\/2428736.2428812"},{"key":"9304_CR7","unstructured":"Al-Wabil, A., Al-Khalifa, H., & Al-Saleh, W. (2007). Arabic text-to-speech synthesis: A preliminary evaluation. In C. Montgomerie & J. Seale (Eds.), Proceedings of world conference on educational multimedia, hypermedia and telecommunications 2007 (pp. 4423\u20134430). Vancouver: AACE."},{"key":"9304_CR8","unstructured":"Alyazeed, M.\u00a0A., Al-Ghoneimy, M.\u00a0R., & Mohammad, M. (1989). Comparison of syllable and sub-syllable methods for speech synthesis. In Proceedings of the second conference on arabic computational linguistics, Kuwait."},{"key":"9304_CR9","unstructured":"Arabi, automatic arabic text to speech system. (2014). World Wide Web electronic publication. http:\/\/www.arabinlp.com\/Systems\/Demo_SystemsTTS.php?pageLang=en ."},{"key":"9304_CR10","unstructured":"Assaf, M. (2005). A prototype of an arabic diphone speech synthesizer in festival. Master\u2019s thesis, Uppsala University."},{"key":"9304_CR11","first-page":"137","volume":"8","author":"AS Atallah","year":"2008","unstructured":"Atallah, A. S., & Omar, K. (2008). Methods of arabic language baseline detection the state of art. International Journal of Computer Science and Network Security (IJCSNS), 8, 137\u2013143.","journal-title":"International Journal of Computer Science and Network Security (IJCSNS)"},{"key":"9304_CR12","doi-asserted-by":"crossref","unstructured":"Bennett, C.\u00a0L. (2005). Large scale evaluation of corpus-based synthesizers:results and lessons from the blizzard challenge 2005. In Proceedings of interspeech 2005, Lisbon.","DOI":"10.21437\/Interspeech.2005-79"},{"key":"9304_CR13","doi-asserted-by":"crossref","unstructured":"Black, A.\u00a0W., & Tokuda, K. (2005). The blizzard challenge 2005: Evaluating corpus-based speech synthesis on common datasets. In Proceedings of interspeech 2005 (pp. 77\u201380). Lisbon.","DOI":"10.21437\/Interspeech.2005-72"},{"key":"9304_CR14","doi-asserted-by":"crossref","first-page":"55","DOI":"10.1007\/978-1-4471-4072-6_3","volume-title":"Guide to OCR for Arabic scripts","author":"E Borovikov","year":"2012","unstructured":"Borovikov, E., & Zavorin, I. (2012). A multi-stage approach to arabic document analysis. In V. Margner & H. El Abed (Eds.), Guide to OCR for Arabic scripts (pp. 55\u201378). London: Springer."},{"key":"9304_CR15","volume-title":"Evaluation of Text and Speech Systems. From Reading Machines to Talking Machines","author":"N Campbell","year":"2007","unstructured":"Campbell, N. (2007). Evaluation of speech synthesis. In L. Dybkjaer & H. Minker (Eds.), Evaluation of text and speech systems. From reading machines to talking machines. Dordrecht: Springer."},{"key":"9304_CR16","unstructured":"Chabchoub, A., & Cherif, A. (2011). An automatic mbrola tool for high quality arabic speech synthesis. International Journal of Computer Applications, 36(1):1\u20135. Published by Foundation of Computer Science, New York, USA."},{"key":"9304_CR17","unstructured":"Clark, R. A.\u00a0J., Podsiadso, M., Fraser, M., Mayo, C., & King, S. (2007). Statistical analysis of the blizzard challenge 2007 listening test results. In Proceedings of blizzard workshop (in Proc. SSW6), Bonn."},{"issue":"2","key":"9304_CR18","doi-asserted-by":"crossref","first-page":"155","DOI":"10.1006\/csla.1998.0117","volume":"13","author":"R Damper","year":"1999","unstructured":"Damper, R., Marchand, Y., Adamson, M., & Gustafson, K. (1999). Evaluating the pronunciation component of text-to-speech systems for english: A performance comparison of different approaches. Computer Speech and Language, 13(2), 155\u2013176.","journal-title":"Computer Speech and Language"},{"key":"9304_CR19","doi-asserted-by":"crossref","unstructured":"Dutoit, T., Pagel, V., Pierret, N., Bataille, F., & Van der Vrecken, O. (1996). The mbrola project: towards a set of high quality speech synthesizers free of use for non commercial purposes. In Proceedings of fourth international conference on spoken language. ICSLP 96 (vol. 3, pp. 1393\u20131396).","DOI":"10.1109\/ICSLP.1996.607874"},{"issue":"12","key":"9304_CR20","doi-asserted-by":"crossref","first-page":"1829","DOI":"10.1109\/29.45531","volume":"37","author":"Y El-Imam","year":"1989","unstructured":"El-Imam, Y. (1989). An unrestricted vocabulary arabic speech synthesis system. IEEE Transactions on Acoustics, Speech and Signal Processing, 37(12), 1829\u20131845.","journal-title":"IEEE Transactions on Acoustics, Speech and Signal Processing"},{"issue":"4B","key":"9304_CR21","first-page":"565","volume":"16","author":"M Elshafei","year":"1991","unstructured":"Elshafei, M. (1991). Toward an arabic text-to-speech system. Arabian Journal for Science and Engineering, 16(4B), 565\u2013583.","journal-title":"Arabian Journal for Science and Engineering"},{"issue":"34","key":"9304_CR22","doi-asserted-by":"crossref","first-page":"255","DOI":"10.1016\/S0020-0255(01)00175-X","volume":"140","author":"M Elshafei","year":"2002","unstructured":"Elshafei, M., Al-Muhtaseb, H., & Al-Ghamdi, M. (2002). Techniques for high quality arabic speech synthesis. Information Sciences, 140(34), 255\u2013267.","journal-title":"Information Sciences"},{"key":"9304_CR23","unstructured":"Fraser, M., & King, S. (2007). The blizzard challenge 2007. In Proceedings blizzard workshop (in Proc. SSW6), Bonn."},{"key":"9304_CR24","unstructured":"Google translate. (2014). World Wide Web electronic publication. http:\/\/translate.google.com\/ ."},{"key":"9304_CR25","doi-asserted-by":"crossref","unstructured":"Hamad, M., & Hussain, M. (2011). Arabic text-to-speech synthesizer. In The 2011 IEEE student conference on research and development (SCOReD) (pp. 409\u2013414). IEEE.","DOI":"10.1109\/SCOReD.2011.6148774"},{"key":"9304_CR26","doi-asserted-by":"crossref","unstructured":"Hansen, J.\u00a0H., & Pellom, B.\u00a0L. (1998). An effective quality evaluation protocol for speech enhancement algorithms. ICSLP, 7, 2819\u20132822. (Citeseer).","DOI":"10.21437\/ICSLP.1998-350"},{"key":"9304_CR27","volume-title":"Intonation systems: A survey of twenty languages","author":"D Hirst","year":"1998","unstructured":"Hirst, D., & Cristo, A. D. (1998). Intonation systems: A survey of twenty languages (1st ed.). Cambridge: Cambridge University Press.","edition":"1"},{"key":"9304_CR28","doi-asserted-by":"crossref","unstructured":"Hon, H., Acero, A., Huang, X., Liu, J., & Plumpe, M. (1998). Automatic generation of synthesis units for trainable text-to-speech systems. In Proceedings of the 1998 IEEE international conference on acoustics, speech and signal processing, 1998 (vol. 1, pp. 293\u2013296). IEEE.","DOI":"10.1109\/ICASSP.1998.674425"},{"key":"9304_CR29","doi-asserted-by":"crossref","unstructured":"Hunt, A.\u00a0J., & Black, A.\u00a0W. (1996). Unit selection in a concatenative speech synthesis system using a large speech database. In Proceedings of 1996 IEEE international conference on acoustics, speech, and signal processing, 1996. ICASSP-96 (vol. 1, pp. 373\u2013376). IEEE.","DOI":"10.1109\/ICASSP.1996.541110"},{"issue":"5","key":"9304_CR30","first-page":"140","volume":"6","author":"A Indumathi","year":"2012","unstructured":"Indumathi, A., & Chandra, E. (2012). Survey on speech synthesis. Signal Processing: An International Journal (SPIJ), 6(5), 140.","journal-title":"Signal Processing: An International Journal (SPIJ)"},{"key":"9304_CR31","unstructured":"Jayousi, A. Q. M. A. (2007). Arabic text-to-speech synthesizer."},{"issue":"6","key":"9304_CR32","first-page":"342","volume":"5","author":"O Khalifa","year":"2011","unstructured":"Khalifa, O., Obaid, M., Naji, A., & Daoud, J. I. (2011). A rule-based arabic text-to-speech system based on hybrid synthesis technique. Australian Journal of Basic and Applied Sciences, 5(6), 342\u2013354.","journal-title":"Australian Journal of Basic and Applied Sciences"},{"key":"9304_CR33","doi-asserted-by":"crossref","unstructured":"Khalil, K., & Adnan, C. (2013). Arabic hmm-based speech synthesis. In International conference on electrical engineering and software applications (ICEESA), 2013 (pp. 1\u20135).","DOI":"10.1109\/ICEESA.2013.6578437"},{"issue":"3","key":"9304_CR34","doi-asserted-by":"crossref","first-page":"737","DOI":"10.1121\/1.395275","volume":"82","author":"DH Klatt","year":"1987","unstructured":"Klatt, D. H. (1987). Review of text-to-speech conversion for english. Journal of the Acoustical Society of America, 82(3), 737\u2013793.","journal-title":"Journal of the Acoustical Society of America"},{"key":"9304_CR35","doi-asserted-by":"crossref","DOI":"10.1007\/978-3-642-27506-7","volume-title":"Subjective quality measurement of speech","author":"K Kondo","year":"2012","unstructured":"Kondo, K. (2012). Subjective quality measurement of speech. Berlin: Springer."},{"key":"9304_CR36","doi-asserted-by":"crossref","unstructured":"Leila, C., Maamar, K., & Salim, C. (2011). Combining neural networks for arabic handwriting recognition. In 10th international symposium on programming and systems (ISPS), 2011 (pp. 74\u201379).","DOI":"10.1109\/ISPS.2011.5898872"},{"key":"9304_CR37","doi-asserted-by":"crossref","first-page":"712","DOI":"10.1109\/TPAMI.2006.102","volume":"28","author":"M Liana","year":"2006","unstructured":"Liana, M., & Venu, G. (2006). Offline arabic handwriting recognition: A survey. IEEE, Transactions on Pattern Analysis and Machine Intelligence, 28, 712\u2013724.","journal-title":"IEEE, Transactions on Pattern Analysis and Machine Intelligence"},{"key":"9304_CR38","unstructured":"Nuance vocalizer. (2014). World Wide Web electronic publication. http:\/\/enterprisecontent.nuance.com\/vocalizer5-network-demo\/index.html ."},{"issue":"4","key":"9304_CR39","doi-asserted-by":"crossref","first-page":"18","DOI":"10.5121\/ijcsit.2010.2402","volume":"2","author":"MZ Rashad","year":"2010","unstructured":"Rashad, M. Z., El-Bakry, H. M., & Isma\u2019il, I. R. (2010). Diphone speech synthesis system for arabic using mary tts. International Journal of Computer Science and Information Technology (IJCSIT), 2(4), 18\u201326.","journal-title":"International Journal of Computer Science and Information Technology (IJCSIT)"},{"issue":"6","key":"9304_CR40","first-page":"653","volume":"54","author":"MA Rashwan","year":"2007","unstructured":"Rashwan, M. A., Fakhr, M. W., Attia, M., & El-Mahallawy, M. S. (2007). Arabic ocr system analogous to hmm-based asr systems implementation and evaluation. Journal of Engineering and Applied Science (JEAS), 54(6), 653.","journal-title":"Journal of Engineering and Applied Science (JEAS)"},{"key":"9304_CR41","unstructured":"Sakhr speech synthesizer. (2014). World Wide Web electronic publication. http:\/\/www.sakhr.com\/tts\/TTS_Demo.aspx ."},{"issue":"4","key":"9304_CR42","doi-asserted-by":"crossref","first-page":"365","DOI":"10.1023\/A:1025708916924","volume":"6","author":"M Schrder","year":"2003","unstructured":"Schrder, M., & Trouvain, J. (2003). The german text-to-speech synthesis system mary: A tool for research, development and teaching. International Journal of Speech Technology, 6(4), 365\u2013377.","journal-title":"International Journal of Speech Technology"},{"key":"9304_CR43","doi-asserted-by":"crossref","unstructured":"Shaker, N., Abou-Zleikha, M., & Al\u00a0Dakkak, O. (2008). Ssml for arabic language. In Text, Speech and Dialogue, pp. 657\u2013664. Springer.","DOI":"10.1007\/978-3-540-87391-4_83"},{"key":"9304_CR44","unstructured":"Sluijter, A., Bosgoed, E., Kerkhoff, J., Meier, E., Rietveld, T., & Swerts, M., et al. (1998). Evaluation of speech synthesis systems for dutch in telecommunication applications. Jenolan Caves: In Proceedings of the Third ESCA\/COCOSDA International Workshop on Speech Synthesis."},{"key":"9304_CR45","unstructured":"Speechworks solution division from ScanSoft, Peabody, MA (2004). White paper\u2014Assessing text-to-speech system quality. Technical report."},{"key":"9304_CR46","unstructured":"Ssml. (2005). Ssml 1.0 say-as attribute values. Working group note 26 may, W3C."},{"key":"9304_CR47","unstructured":"Text to speech by ispeech. (2014). World Wide Web electronic publication. http:\/\/www.ispeech.org\/text.to.speech ."},{"key":"9304_CR48","unstructured":"Tratz, S. C. (2014). Accurate arabic script language\/dialect classification. DTIC Document: Technical report."},{"key":"9304_CR49","unstructured":"Youssef, A., & Emam, O. (2004). An arabic tts system based on the ibm trainable speech synthesizer. JEP-TALN: Le traitement automatique de l\u2019arabe."},{"key":"9304_CR50","unstructured":"Zeki, A. (2005). The segmentation problem on arabic character recognition the state of the art. 1st international conference on information and communication technology (ICICT) (pp. 48\u201357). Pakistan: Karachi."}],"updated-by":[{"DOI":"10.1007\/s10772-016-9350-8","type":"correction","label":"Correction","source":"publisher","updated":{"date-parts":[[2016,6,27]],"date-time":"2016-06-27T00:00:00Z","timestamp":1466985600000}}],"container-title":["International Journal of Speech Technology"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s10772-015-9304-6.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/article\/10.1007\/s10772-015-9304-6\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s10772-015-9304-6","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,8,17]],"date-time":"2023-08-17T14:07:48Z","timestamp":1692281268000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/s10772-015-9304-6"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2016,4,6]]},"references-count":50,"journal-issue":{"issue":"2","published-print":{"date-parts":[[2016,6]]}},"alternative-id":["9304"],"URL":"https:\/\/doi.org\/10.1007\/s10772-015-9304-6","relation":{},"ISSN":["1381-2416","1572-8110"],"issn-type":[{"value":"1381-2416","type":"print"},{"value":"1572-8110","type":"electronic"}],"subject":[],"published":{"date-parts":[[2016,4,6]]}}}