{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2023,6,12]],"date-time":"2023-06-12T20:29:27Z","timestamp":1686601767962},"reference-count":30,"publisher":"Springer Science and Business Media LLC","issue":"2","license":[{"start":{"date-parts":[[2011,10,14]],"date-time":"2011-10-14T00:00:00Z","timestamp":1318550400000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Int J Speech Technol"],"published-print":{"date-parts":[[2012,6]]},"DOI":"10.1007\/s10772-011-9122-4","type":"journal-article","created":{"date-parts":[[2011,10,13]],"date-time":"2011-10-13T18:16:49Z","timestamp":1318529809000},"page":"65-75","source":"Crossref","is-referenced-by-count":8,"title":["Within-word pronunciation variation modeling for Arabic ASRs: a direct data-driven approach"],"prefix":"10.1007","volume":"15","author":[{"given":"Dia","family":"AbuZeina","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Wasfi","family":"Al-Khatib","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Moustafa","family":"Elshafei","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Husni","family":"Al-Muhtaseb","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2011,10,14]]},"reference":[{"key":"9122_CR1","doi-asserted-by":"crossref","unstructured":"AbuZeina, D., Al-Khatib, W., Elshafei, M., & Al-Muhtaseb, H. (2011). Cross-word Arabic pronunciation variation modeling for speech recognition. International Journal of Speech Technology.","DOI":"10.1007\/s10772-011-9098-0"},{"key":"9122_CR2","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1016\/S1319-1578(04)80006-5","volume":"16","author":"M. Alghamdi","year":"2004","unstructured":"Alghamdi, M., Almuhtasib, H., & Elshafei, M. (2004). Arabic phonological rules. Journal of King Saud University: Computer and Information Sciences, 16, 1\u201325.","journal-title":"Journal of King Saud University: Computer and Information Sciences"},{"key":"9122_CR3","doi-asserted-by":"crossref","first-page":"183","DOI":"10.1007\/s10772-009-9026-8","volume":"10","author":"M. Alghamdi","year":"2009","unstructured":"Alghamdi, M., Elshafei, M., & Almuhtasib, H. (2009). Arabic broadcast news transcription system. International Journal of Speech and Technology, 10, 183\u2013195.","journal-title":"International Journal of Speech and Technology"},{"issue":"4","key":"9122_CR4","doi-asserted-by":"crossref","first-page":"67","DOI":"10.4018\/jitr.2009062905","volume":"2","author":"M. Ali","year":"2009","unstructured":"Ali, M., Moustafa, E., Mansour, A., Husni, A., & Atef, A. (2009). Arabic phonetic dictionaries for speech recognition. Journal of Information Technology Research, 2(4), 67\u201380.","journal-title":"Journal of Information Technology Research"},{"key":"9122_CR5","volume-title":"Algorithms: design techniques and analysis","author":"M. H. Alsuwaiyel","year":"2003","unstructured":"Alsuwaiyel, M. H. (2003). Algorithms: design techniques and analysis. Singapore: World Scientific."},{"key":"9122_CR6","unstructured":"Amdal, I., & Fossler-Lussier, E. (2003). Pronunciation variation modeling in automatic speech recognition. Telektronik, 99(2)."},{"key":"9122_CR7","volume-title":"ASRU 2009: IEEE workshop","author":"H. Al-Haj","year":"2009","unstructured":"Al-Haj, H., Hsiao, R., Lane, I. W., Black, A., & Waibel, A. (2009). Pronunciation modeling for dialectal Arabic speech recognition. In ASRU 2009: IEEE workshop, Italy."},{"issue":"10\u201311","key":"9122_CR8","doi-asserted-by":"crossref","first-page":"763","DOI":"10.1016\/j.specom.2007.02.006","volume":"49","author":"M. Benzeghiba","year":"2007","unstructured":"Benzeghiba, M., De Mori, R., Deroo, O., Dupont, S., Erbes, T., Jouvet, D., Fissore, L., Laface, P., Mertins, A., Ris, C., Rose, R., Tyagi, V., & Wellekens, C. (2007). Automatic speech recognition and speech variability: a review. Speech Communication, 49(10\u201311), 763\u2013786.","journal-title":"Speech Communication"},{"key":"9122_CR9","first-page":"397","volume-title":"The 2009 annual conference of the North American chapter of the ACL","author":"F. Biadsy","year":"2009","unstructured":"Biadsy, F., Habash, N., & Hirschberg, J. (2009). Improving the Arabic pronunciation dictionary for phone and word recognition with linguistically-based pronunciation rules. In The 2009 annual conference of the North American chapter of the ACL, Colorado (pp. 397\u2013405)."},{"key":"9122_CR10","volume-title":"Proceedings of HLT","author":"Billa","year":"2002","unstructured":"Billa, et al. (2002). Arabic speech and test in Tides on Tap. In Proceedings of HLT."},{"issue":"4B","key":"9122_CR11","first-page":"565","volume":"16","author":"Ahmed M. Elshafei","year":"1991","unstructured":"Elshafei, Ahmed M. (1991). Toward an Arabic text-to-speech system. The Arabian Journal of Science and Engineering, 16(4B), 565\u2013583.","journal-title":"The Arabian Journal of Science and Engineering"},{"issue":"3\u20134","key":"9122_CR12","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., Almuhtasib, H., & Alghamdi, M. (2002). Techniques for high quality text-to-speech. Information Sciences, 140(3\u20134), 255\u2013267.","journal-title":"Information Sciences"},{"key":"9122_CR13","doi-asserted-by":"crossref","first-page":"2379","DOI":"10.21437\/Eurospeech.1997-625","volume-title":"Proceedings of EuroSpeech-97","author":"M. Finke","year":"1997","unstructured":"Finke, M., & Waibel, A. (1997). Speaking mode dependent pronunciation modeling in large vocabulary conversational speech recognition. In Proceedings of EuroSpeech-97, Rhodes (pp. 2379\u20132382)."},{"key":"9122_CR14","first-page":"611","volume-title":"International Congress of Phonetic Sciences (ICPhS \u201999)","author":"E. Fosler-Lussier","year":"1999","unstructured":"Fosler-Lussier, E., Greenberg, S., & Morgan, N. (1999). Incorporating contextual phonetics into automatic speech recognition. In International Congress of Phonetic Sciences (ICPhS \u201999), San Francisco, California (pp. 611\u2013614)."},{"key":"9122_CR15","unstructured":"IPA for Arabic (2011). http:\/\/en.wikipedia.org\/wiki\/Wikipedia:IPA_for_Arabic ."},{"key":"9122_CR16","volume-title":"Proceedings ISCA ITRW workshop adaptation methods for speech recognition","author":"S. Helmer","year":"2001","unstructured":"Helmer, S. (2001). Pronunciation adaptation at the lexical level. In Proceedings ISCA ITRW workshop adaptation methods for speech recognition, Sophia Antipolis, France."},{"key":"9122_CR17","volume-title":"ICSLP-1998","author":"J. Jeon","year":"1998","unstructured":"Jeon, J., Cha, S., Chung, M., Park, J., & Hwang, K. (1998). Automatic generation of Korean pronunciation variants by multistage applications of phonological rules. In ICSLP-1998 (paper 0675)."},{"key":"9122_CR18","volume-title":"Speech and language processing","author":"D. Jurafsky","year":"2009","unstructured":"Jurafsky, D., & Martin, J. (2009). Speech and language processing (2nd ed.). Upper Saddle River: Pearson.","edition":"2"},{"key":"9122_CR19","volume-title":"ICSLP","author":"J. M. Kessens","year":"2000","unstructured":"Kessens, J. M., Strik, H., & Cucchiarini, C. (2000). A bottom-up method for obtaining information about pronunciation variation. In ICSLP, Beijing, China."},{"issue":"7","key":"9122_CR20","doi-asserted-by":"crossref","first-page":"1063","DOI":"10.1093\/ietisy\/e90-d.7.1063","volume":"E90-D","author":"L. Kyong-Nim","year":"2007","unstructured":"Kyong-Nim, L., & Minhwa, C. (2007). Morpheme-based modeling of pronunciation variation for large vocabulary continuous speech recognition in Korean. IEICE Transactions on Information and Systems, E90-D(7), 1063\u20131072.","journal-title":"IEICE Transactions on Information and Systems"},{"key":"9122_CR21","doi-asserted-by":"crossref","unstructured":"Liu, Y., & Fung, P. (2003, to appear). Modeling partial pronunciation variations for spontaneous Mandarin speech recognition. Computer Speech and Language.","DOI":"10.1016\/S0885-2308(03)00008-1"},{"key":"9122_CR22","first-page":"1847","volume-title":"Proceedings of the ICSLP","author":"D. McAllister","year":"1998","unstructured":"McAllister, D., et al. (1998). Fabricating conversational speech data with acoustic models: a program to examine model-data mismatch. In Proceedings of the ICSLP, Sydney (pp. 1847\u20131850)."},{"key":"9122_CR23","unstructured":"MITCogNet (2010). http:\/\/mitpdev.mit.edu\/library\/erefs\/arbib\/images\/figures\/A248_fig001.gif ."},{"key":"9122_CR24","unstructured":"Pl\u00f6tz, T. (2005). Advanced stochastic protein sequence analysis. PhD Thesis, Bielefeld University."},{"key":"9122_CR25","doi-asserted-by":"crossref","first-page":"137","DOI":"10.1006\/csla.2000.0140","volume":"14","author":"M. Sara\u00e7lar","year":"2000","unstructured":"Sara\u00e7lar, M., Nock, H., & Khudanpur, S. (2000). Pronunciation modeling by sharing Gaussian densities across phonetic models. Computer Speech and Language, 14, 137\u2013160.","journal-title":"Computer Speech and Language"},{"key":"9122_CR26","doi-asserted-by":"crossref","first-page":"59","DOI":"10.1109\/ICACTE.2008.150","volume-title":"International conference on advanced computer theory and engineering","author":"N. Seman","year":"2008","unstructured":"Seman, N., & Jusoff, K. (2008). Automatic segmentation and labeling for spontaneous standard Malay speech recognition. In International conference on advanced computer theory and engineering, Thailand (pp. 59\u201363)."},{"issue":"4","key":"9122_CR27","doi-asserted-by":"crossref","first-page":"327","DOI":"10.1109\/89.917678","volume":"9","author":"G. Saon","year":"2001","unstructured":"Saon, G., & Padmanabhan, M. (2001). Data-driven approach to designing compound words for continuous speech recognition. IEEE Transactions on Speech and Audio Processing, 9(4), 327\u2013332.","journal-title":"IEEE Transactions on Speech and Audio Processing"},{"key":"9122_CR28","first-page":"2328","volume-title":"Proceedings of the ICSLP-96","author":"T. Sloboda","year":"1996","unstructured":"Sloboda, T., & Waibel, A. (1996). Dictionary learning for spontaneous speech recognition. In Proceedings of the ICSLP-96, Philadelphia, PA, USA (pp. 2328\u20132331)."},{"key":"9122_CR29","doi-asserted-by":"crossref","first-page":"2247","DOI":"10.21437\/Eurospeech.1995-350","volume-title":"EUROSPEECH-95","author":"G. Tajchman","year":"1995","unstructured":"Tajchman, G., Fosler, E., & Jurafsky, D. (1995). Building multiple pronunciation models for novel words using exploratory computational phonology. In EUROSPEECH-95, Madrid, Spain (pp. 2247\u20132250)."},{"issue":"1","key":"9122_CR30","doi-asserted-by":"crossref","first-page":"69","DOI":"10.1016\/S0885-2308(02)00030-X","volume":"17","author":"M. Wester","year":"2003","unstructured":"Wester, M. (2003). Pronunciation modeling for ASR, knowledge-based and data-derived methods. Computer Speech & Language, 17(1), 69\u201385.","journal-title":"Computer Speech & Language"}],"container-title":["International Journal of Speech Technology"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s10772-011-9122-4.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/article\/10.1007\/s10772-011-9122-4\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s10772-011-9122-4","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,6,10]],"date-time":"2023-06-10T12:40:16Z","timestamp":1686400816000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/s10772-011-9122-4"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2011,10,14]]},"references-count":30,"journal-issue":{"issue":"2","published-print":{"date-parts":[[2012,6]]}},"alternative-id":["9122"],"URL":"https:\/\/doi.org\/10.1007\/s10772-011-9122-4","relation":{},"ISSN":["1381-2416","1572-8110"],"issn-type":[{"value":"1381-2416","type":"print"},{"value":"1572-8110","type":"electronic"}],"subject":[],"published":{"date-parts":[[2011,10,14]]}}}