{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,7,3]],"date-time":"2025-07-03T05:24:29Z","timestamp":1751520269939,"version":"3.37.3"},"reference-count":40,"publisher":"Springer Science and Business Media LLC","issue":"3","license":[{"start":{"date-parts":[[2021,4,21]],"date-time":"2021-04-21T00:00:00Z","timestamp":1618963200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2021,4,21]],"date-time":"2021-04-21T00:00:00Z","timestamp":1618963200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Int J Speech Technol"],"published-print":{"date-parts":[[2021,9]]},"DOI":"10.1007\/s10772-021-09846-8","type":"journal-article","created":{"date-parts":[[2021,4,21]],"date-time":"2021-04-21T19:15:50Z","timestamp":1619032550000},"page":"747-759","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":9,"title":["Balanced Arabic corpus design for speech synthesis"],"prefix":"10.1007","volume":"24","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-1489-2076","authenticated-orcid":false,"given":"Aissa","family":"Amrouche","sequence":"first","affiliation":[]},{"given":"Ahc\u00e8ne","family":"Abed","sequence":"additional","affiliation":[]},{"given":"Kamel","family":"Ferrat","sequence":"additional","affiliation":[]},{"given":"Khadidja Nesrine","family":"Boubakeur","sequence":"additional","affiliation":[]},{"given":"Youssouf","family":"Bentrcia","sequence":"additional","affiliation":[]},{"given":"Leila","family":"Falek","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2021,4,21]]},"reference":[{"key":"9846_CR1","doi-asserted-by":"crossref","unstructured":"Abdo, O., Abdou, S., & Fashal, M. (2017). Building audio-visual phonetically annotated Arabic corpus for expressive text to speech. Interspeech 2017, Stockholm.","DOI":"10.21437\/Interspeech.2017-1357"},{"key":"9846_CR2","unstructured":"Abed, A., Amrouche, A., & Boubakeur, K. N. (2017). Investigation of HTK for Arabic phonemes boundary detection. International Conference on Engineering Research and Applications (ICERA-17), pp. 17\u201318"},{"key":"9846_CR3","unstructured":"Abed, A., Amrouche, A., Delmadji, A., & Boubakeur, K. N. (2016) Segmentation Automatique des Signaux Sonores par HMM et RNA pour la langue Arabe. Conf\u00e9rence Internationale en Sciences et Technologies Electriques au Maghreb CISTEM\u201c2016, Marrakech."},{"key":"9846_CR4","unstructured":"Abed, A., & Guerti, M. (2016). HMM\/GMM classification for articulation disorder correction among Algerian children. The International Arab Journal of Information Technology, 13(4)."},{"key":"9846_CR5","unstructured":"Abushariah, M., Ainon, R., Roziati, Z., Elshafei, M., & Khalifa, O. (2012a). Arabic speaker independent continuous automatic speech recognition based on a phonetically rich and balanced speech corpus. The International Arab Journal of Information Technology, 9(1), 84\u201393."},{"key":"9846_CR6","doi-asserted-by":"crossref","unstructured":"Abushariah, M., Ainon, R., Roziati, Z., Elshafei, M., & Khalifa, O. (2012b). Phonetically rich and balanced text and speech corpora for Arabic language, Lang Resources and Evaluation, Springer, pp. 601\u2013634, 46.","DOI":"10.1007\/s10579-011-9166-8"},{"key":"9846_CR7","unstructured":"Alghamdi, M., Alhamid, A. H., & Aldasuqi, M. M. (2003). Database of Arabic sounds: Sentences. Technical Report, Saudi Arabia: King Abdulaziz City of Science and Technology (in Arabic)."},{"key":"9846_CR8","unstructured":"Almosallam, I., Alkhalifa, A., Alghamdi, M., Alkanhal, M., & Alkhairy A. (2013). SASSC: A standard Arabic single speaker corpus. In 8th ISCA Speech Synthesis Workshop."},{"key":"9846_CR9","doi-asserted-by":"crossref","unstructured":"Alsulaiman, M. M., Ghulam, M., Bencherif, M. A, Awais, M., Zulfiqar, A., & Aljabri, M. (2011). Building a rich Arabic speech database. In 5th Asia International Conference on Mathematical Modelling and Computer Simulation.","DOI":"10.1109\/AMS.2011.29"},{"key":"9846_CR10","unstructured":"Amrouche, A., Abed, A., & Boubakeur, K.N. (2017b). New method for stemming of Arabic language text. International Conference on Engineering Research and Applications (ICERA-17), pp. 17\u201318."},{"key":"9846_CR11","unstructured":"Amrouche, A., Falek, L., Teffahi. (2014). Contribution \u00e0 l\u2019am\u00e9lioration du signal de synth\u00e8se dans un syst\u00e8me TTS pour la langue arabe. Fifth International Conference on Arabic Language Processing (CITAL2014), Oujda, Morocco."},{"key":"9846_CR12","unstructured":"Amrouche, A., Falek, L., & Teffahi, H. (2015). Text-to-speech synthesis system for the Arabic language. In International Conference on Automatic control, Telecommunications and Signals (ICATS15)."},{"key":"9846_CR13","unstructured":"Amrouche, A., Falek, L., & Teffahi, H. (2017a). Design and implementation of a diacritic arabic text-to-speech system. The International Arab Journal of Information Technology, 14(4)."},{"key":"9846_CR14","doi-asserted-by":"crossref","unstructured":"Amrouche, A., Falek, L., & Teffahi, H. (2019). Arabic speech synthesis system based on HMM. In Sixth International Conference on Electrical and Electronics Engineering (ICEEE 2019).","DOI":"10.1109\/ICEEE2019.2019.00022"},{"key":"9846_CR15","unstructured":"Attia, M. (2008). Handling Arabic morphological and syntactic ambiguities within the LFG framework with a view to machine translation. PhD Dissertation, University of Manchester."},{"key":"9846_CR16","unstructured":"Barbot, N., Boeffard, O., & Delhay, A. (2012). Comparing performance of different set-covering strategies for linguistic content optimization in speech corpora. International Conference on Language Resources and Evaluation (LREC\u201912)."},{"key":"9846_CR17","unstructured":"Boersma, P., & Weenink, D. (2019). Praat: Doing phonetics by computer [Computer program]. Version 6.0.46, from http:\/\/www.praat.org\/."},{"key":"9846_CR18","unstructured":"Boros, T. et al. (2014). RSS-TOBI: A prosodically enhanced romanian speech corpus. In Proceedings of the International Conference on Language Resources and Evaluation (LREC), pp. 316\u2013320."},{"key":"9846_CR19","unstructured":"Boudraa, M., Boudraa, B., & Guerin, B. (2000). Twenty lists of ten Arabic sentences for assessment. Acta Acustica united with Acustica, pp. 870\u2013882."},{"key":"9846_CR20","volume-title":"A Database of German Emotional Speech","author":"F Burkhardt","year":"2005","unstructured":"Burkhardt, F., Paeschke, A., Rolfes, M., Sendlmeier, W., & Weiss, B. (2005). A database of German emotional speech. Interspeech."},{"key":"9846_CR21","doi-asserted-by":"crossref","unstructured":"Chalamandaris, A., Karabetsos, S., Tsiakoulis, P., & Raptis, S. (2010). A unit selection text-to-speech synthesis system optimized for use with screen readers. EEE Transactions on Consumer Electronics, 56(3).","DOI":"10.1109\/TCE.2010.5606343"},{"key":"9846_CR22","doi-asserted-by":"crossref","unstructured":"Chrobaka, M., Kenyonb, C., & Younga, Y. (2006). The reverse greedy algorithm for the metric K-Median problem. Information Processing Letters, 97(2), 31, 68\u201372.","DOI":"10.1016\/j.ipl.2005.09.009"},{"key":"9846_CR23","unstructured":"Combescure, P. (1981). 20 listes de 10 Phrases Phon\u00e9tiquement Equilibr\u00e9es. Revue d\u2019Acoustique, 14(56), 34\u201338."},{"key":"9846_CR24","doi-asserted-by":"crossref","unstructured":"Farghaly, A., & Shaalan, K. (2009). Arabic natural language processing: Challenges and solutions. ACM Transactions on Asian Language Information Processing, 8(4).","DOI":"10.1145\/1644879.1644881"},{"key":"9846_CR25","doi-asserted-by":"crossref","unstructured":"Ferrat, K., & Guerti, M. (2013). Classification of the Arabic emphatic consonants using time delay neural network. International Journal of Computer Applications, 80(10), 1\u20136.","DOI":"10.5120\/13894-9341"},{"issue":"4","key":"9846_CR26","doi-asserted-by":"publisher","first-page":"571","DOI":"10.1515\/aoa-2017-0061","volume":"42","author":"K Ferrat","year":"2017","unstructured":"Ferrat, K., & Guerti, M. (2017). An experimental study of the gemination in Arabic language. Archives of Acoustics, 42(4), 571\u2013578.","journal-title":"Archives of Acoustics"},{"key":"9846_CR27","unstructured":"Hafte, A., Sebsibe, H. M. (2018). Design of a tigrinya language speech corpus for speech recognition. In Proceedings of the First Workshop on Linguistic Resources for Natural Language Processing, pp. 78\u201382."},{"key":"9846_CR28","unstructured":"Halabi, N. (2016). Modern Standard Arabic Phonetics for Speech Synthesis. Thesis for the degree of Doctor of Philosophy: University of Southampton."},{"key":"9846_CR29","unstructured":"Itunuoluwa, I., Jelili, O., & Olufunke O. (2014). Design and implementation of text to speech conversion for visually impaired people. International Journal of Applied Information Systems (IJAIS) Foundation of Computer Science FCS."},{"key":"9846_CR30","doi-asserted-by":"crossref","unstructured":"Janyoi, P., & Seresangtakul, P. (2020). F0 modeling for isarn speech synthesis using deep neural networks and syllable-level feature representation. The International Arab Journal of Information Technology, 17(6).","DOI":"10.34028\/iajit\/17\/6\/9"},{"key":"9846_CR31","unstructured":"Jawaid, B., Kamran, A., & Bojar O. (2014). A tagged corpus and a tagger for Urdu. In Proceedings of the 9th International Conference on Language Resources and Evaluation (LREC 2014)."},{"key":"9846_CR32","doi-asserted-by":"crossref","unstructured":"Muljono, H. A., Winarsih, N. A. S., & Supriyanto, C. (2019). An evaluation of sentence selection methods on the different phone-sized units for constructing Indonesian speech corpus. International Journal of Speech Technology, 23(1), 141\u2013147.","DOI":"10.1007\/s10772-019-09662-1"},{"key":"9846_CR33","unstructured":"Niladri, S. D., & Ramamoorthy, L. (2019). Utility and application of language corpora. Springer pp. 1\u201316."},{"key":"9846_CR34","unstructured":"Novitasari, S., Tjandra, A., Sakti S., & Nakamura, S. (2020). Cross-lingual machine speech chain for javanese, sundanese, balinese, and bataks speech recognition and synthesis. In Language Resources and Evaluation Conference (LREC 2020)."},{"key":"9846_CR35","unstructured":"Qiong, H., Yannis, S., Ranniery, M., Korin, R., Junichi, Y., & Javier, L. (2014). An investigation of the application of dynamic sinusoidal models to statistical parametric speech synthesis. In Interspeech 2014. pp. 780\u2013784."},{"key":"9846_CR36","unstructured":"Satori, H., Hiyassat, H., Harti, M., & Chenfour N, (2009). Investigation arabic speech recognition using CMU sphinx system. The International Arab Journal of Information Technology,\u00a06(2), 186\u2013190."},{"key":"9846_CR37","unstructured":"Tadashi, I., Sunao, H., Masanobu, A., Yusuke, I., Noboru, M., & Hideyuki, M. (2015). Sub-band text-to-speech combining sample-based spectrum with statistically generated spectrum. In 16th Annual Conference of the International Speech Communication Association."},{"key":"9846_CR38","unstructured":"Tengku, M. T. S., & AbuAta, B. (2013). Arabic word stemming algorithms and retrieval effectiveness. In Proceedings of the World Congress on Engineering WCE 2013,."},{"key":"9846_CR39","unstructured":"Thao, V. D., Do-Dat, T., & Thu-Trang, T. N. (2011). Non-uniform unit selection in Vietnamese Speech Synthesis. In Proceedings of the 2011 Symposium on Information and Communication Technology, SoICT 2011."},{"key":"9846_CR40","unstructured":"Tian, J., Jani, N., & Imre, K. (2005). Optimal subset selection from text databases. In Proceedings of the IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP), pp 305\u2013308."}],"container-title":["International Journal of Speech Technology"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10772-021-09846-8.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s10772-021-09846-8\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10772-021-09846-8.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2021,8,17]],"date-time":"2021-08-17T11:34:18Z","timestamp":1629200058000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s10772-021-09846-8"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,4,21]]},"references-count":40,"journal-issue":{"issue":"3","published-print":{"date-parts":[[2021,9]]}},"alternative-id":["9846"],"URL":"https:\/\/doi.org\/10.1007\/s10772-021-09846-8","relation":{},"ISSN":["1381-2416","1572-8110"],"issn-type":[{"type":"print","value":"1381-2416"},{"type":"electronic","value":"1572-8110"}],"subject":[],"published":{"date-parts":[[2021,4,21]]},"assertion":[{"value":"2 January 2021","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"5 April 2021","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"21 April 2021","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}]}}