{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,9,24]],"date-time":"2025-09-24T10:32:30Z","timestamp":1758709950679,"version":"3.37.3"},"reference-count":28,"publisher":"Springer Science and Business Media LLC","issue":"3","license":[{"start":{"date-parts":[[2018,6,28]],"date-time":"2018-06-28T00:00:00Z","timestamp":1530144000000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Int J Speech Technol"],"published-print":{"date-parts":[[2018,9]]},"DOI":"10.1007\/s10772-018-9526-5","type":"journal-article","created":{"date-parts":[[2018,6,28]],"date-time":"2018-06-28T06:23:46Z","timestamp":1530167026000},"page":"649-657","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":14,"title":["Spoken language recognition using a new conditional cascade method to combine acoustic and phonetic results"],"prefix":"10.1007","volume":"21","author":[{"given":"Shabnam","family":"Gholamdokht Firooz","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shaghayegh","family":"Reza","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6733-3702","authenticated-orcid":false,"given":"Yasser","family":"Shekofteh","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2018,6,28]]},"reference":[{"issue":"2","key":"9526_CR1","doi-asserted-by":"publisher","first-page":"82","DOI":"10.1109\/MCAS.2011.941081","volume":"11","author":"E Ambikairajah","year":"2011","unstructured":"Ambikairajah, E., Li, H., Wang, L., Yin, B., & Sethu, V. (2011). Language identification: A tutorial. IEEE Circuits and Systems Magazine, 11(2), 82\u2013108.","journal-title":"IEEE Circuits and Systems Magazine"},{"key":"9526_CR2","doi-asserted-by":"publisher","first-page":"303","DOI":"10.21437\/Odyssey.2016-44","volume":"2016","author":"H Behravan","year":"2016","unstructured":"Behravan, H., Kinnunen, T., & Hautam\u00e4ki, V. (2016). Out-of-set i-vector selection for open-set language identification. Odyssey 2016, 303\u2013310.","journal-title":"Odyssey"},{"unstructured":"Bijankhan, M., Sheikhzadegan, J., & Roohani, M. (1994). FARSDAT-The speech database of Farsi spoken language, In Proceedings Australian Conference on Speech Science and Technology.","key":"9526_CR3"},{"doi-asserted-by":"crossref","unstructured":"Campbell, W. M., Richardson, F., & Reynolds, D. A. (2007). Language recognition with word lattices and support vector machines. In IEEE International Conference on Acoustics, Speech and Signal Processing, 2007, ICASSP 2007.","key":"9526_CR4","DOI":"10.1109\/ICASSP.2007.367238"},{"issue":"4","key":"9526_CR5","doi-asserted-by":"publisher","first-page":"788","DOI":"10.1109\/TASL.2010.2064307","volume":"19","author":"N Dehak","year":"2011","unstructured":"Dehak, N., Kenny, P. J., Dehak, R., Dumouchel, P., & Ouellet, P. (2011a). Front-end factor analysis for speaker verification. IEEE Transactions on Audio, Speech, and Language Processing, 19(4), 788\u2013798.","journal-title":"IEEE Transactions on Audio, Speech, and Language Processing"},{"doi-asserted-by":"crossref","unstructured":"Dehak, N., Torres-Carrasquillo, P. A., Reynolds, D., & Dehak, R. (2011b). Language recognition via i-vectors and dimensionality reduction. In Twelfth Annual Conference of the International Speech Communication Association.","key":"9526_CR6","DOI":"10.21437\/Interspeech.2011-328"},{"key":"9526_CR7","doi-asserted-by":"publisher","first-page":"215","DOI":"10.1016\/j.compeleceng.2016.07.006","volume":"58","author":"SG Firooz","year":"2017","unstructured":"Firooz, S. G., Almasganj, F., & Shekofteh, Y. (2017). Improvement of automatic speech recognition systems via nonlinear dynamical features evaluated from the recurrence plot of speech signals. Computers and Electrical Engineering, 58, 215\u2013226.","journal-title":"Computers and Electrical Engineering"},{"doi-asserted-by":"crossref","unstructured":"Glembek, O., Mat\u011bjka, P., Burget, L., & Mikolov, T. (2008). Advances in phonotactic language recognition. In Ninth Annual Conference of the International Speech Communication Association.","key":"9526_CR8","DOI":"10.21437\/Interspeech.2008-231"},{"issue":"408","key":"9526_CR9","first-page":"881","volume":"84","author":"KL Lange","year":"1989","unstructured":"Lange, K. L., Little, R. J., & Taylor, J. M. (1989). Robust statistical modeling using the t distribution. Journal of the American Statistical Association, 84(408), 881\u2013896.","journal-title":"Journal of the American Statistical Association"},{"doi-asserted-by":"crossref","unstructured":"Lopez-Moreno, I., Gonzalez-Dominguez, J., Plchot, O., Martinez, D., Gonzalez-Rodriguez, J., & Moreno, P. (2014). Automatic language identification using deep neural networks. In IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 2014, pp.\u00a05337\u20135341.","key":"9526_CR10","DOI":"10.1109\/ICASSP.2014.6854622"},{"doi-asserted-by":"crossref","unstructured":"Ma, J. Z., Zhang, B., Matsoukas, S., Mallidi, S. H. R., Li, F., & Hermansky, H. (2013). Improvements in language identification on the RATS noisy speech corpus. In INTERSPEECH.","key":"9526_CR11","DOI":"10.21437\/Interspeech.2013-40"},{"doi-asserted-by":"crossref","unstructured":"Martinez, D., Plchot, O., Burget, L., Glembek, O., & Mat\u011bjka, P. (2011). Language recognition in ivectors space. In Twelfth Annual Conference of the International Speech Communication Association.","key":"9526_CR12","DOI":"10.21437\/Interspeech.2011-329"},{"unstructured":"Matejka, P. (2009). Phonotactic and acoustic language recognition, PhD thesis.","key":"9526_CR13"},{"doi-asserted-by":"crossref","unstructured":"Matejka, P., Schwarz, P., Cernock\u00fd, J., & Chytil, P. (2005). Phonotactic language identification using high quality phoneme recognition. In Ninth European Conference on Speech Communication and Technology.","key":"9526_CR14","DOI":"10.21437\/Interspeech.2005-708"},{"unstructured":"Mat\u011bjka, P., Sz\u00f6ke, I., Schwarz, P., & \u010cernock\u00fd, J. (2004). Automatic language identification using phoneme and automatically derived unit strings. In International Conference on Text, Speech and Dialogue. New York: Springer.","key":"9526_CR15"},{"doi-asserted-by":"crossref","unstructured":"McCree, A., Sell, G., & Garcia-Romero, D. (2016). Augmented data training of joint acoustic\/phonotactic DNN i-vectors for NIST LRE15. In Proceedings of IEEE Odyssey.","key":"9526_CR16","DOI":"10.21437\/Odyssey.2016-29"},{"doi-asserted-by":"crossref","unstructured":"Ng, R. W., Nicolao, M., Saz, O., Hasan, M., Chettri, B., Doulaty, M., Lee, T., & Hain, T. (2016). The Sheffield language recognition system in NIST LRE 2015. In Proceedings of The Speaker and Language Recognition Workshop Odyssey 2016, ISCA.","key":"9526_CR17","DOI":"10.21437\/Odyssey.2016-26"},{"unstructured":"Niesler, T., & Willett, D. (2006). Language identification and multilingual speech recognition using discriminatively trained acoustic models. In Multilingual Speech and Language Processing.","key":"9526_CR18"},{"unstructured":"Plchot, O., Karafi\u00e1t, M., Br\u00fcmmer, N., Glembek, O., Mat\u011bjka, P., Villiers, E. d., & \u010cernock\u00fd, J. H. (2012). Speaker vectors from subspace gaussian mixture model as complementary features for language identification. Odyssey 2012-The Speaker and Language Recognition Workshop.","key":"9526_CR19"},{"key":"9526_CR20","doi-asserted-by":"publisher","first-page":"74","DOI":"10.21437\/Odyssey.2016-11","volume":"2016","author":"AH Poorjam","year":"2016","unstructured":"Poorjam, A. H., Saeidi, R., Kinnunen, T., & Hautam\u00e4ki, V. (2016). Incorporating uncertainty as a quality measure in i-vector based language recognition. IEEE Odyssey, 2016, 74\u201380.","journal-title":"IEEE Odyssey"},{"key":"9526_CR21","doi-asserted-by":"publisher","first-page":"811","DOI":"10.1007\/978-3-540-49127-9_41","volume-title":"Automatic language recognition via spectral and token based approaches. Springer Handbook of Speech Processing","author":"DA Reynolds","year":"2008","unstructured":"Reynolds, D. A., Campbell, W. M., Shen, W., & Singer, E. (2008). Automatic language recognition via spectral and token based approaches. Springer Handbook of Speech Processing (pp.\u00a0811\u2013824). New York: Springer."},{"unstructured":"Sameti, H., Veisi, H., Bahrani, M., Babaali, B., & Hosseinzadeh, K. (2008). Nevisa, a persian continuous speech recognition system. In Advances in Computer Science and Engineering (pp.\u00a0485\u2013492), New York: Springer.","key":"9526_CR22"},{"issue":"6","key":"9526_CR23","doi-asserted-by":"publisher","first-page":"1923","DOI":"10.1016\/j.dsp.2013.06.011","volume":"23","author":"Y Shekofteh","year":"2013","unstructured":"Shekofteh, Y., & Almasganj, F. (2013). Autoregressive modeling of speech trajectory transformed to the reconstructed phase space for ASR purposes. Digital Signal Processing, 23(6), 1923\u20131932.","journal-title":"Digital Signal Processing"},{"key":"9526_CR24","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1016\/j.engappai.2015.05.001","volume":"44","author":"Y Shekofteh","year":"2015","unstructured":"Shekofteh, Y., Almasganj, F., & Daliri, A. (2015). MLP-based isolated phoneme classification using likelihood features extracted from reconstructed phase space. Engineering Applications of Artificial Intelligence, 44, 1\u20139.","journal-title":"Engineering Applications of Artificial Intelligence"},{"issue":"1","key":"9526_CR25","first-page":"674859","volume":"2008","author":"H Suo","year":"2008","unstructured":"Suo, H., Li, M., Lu, P., & Yan, Y. (2008). Using SVM as back-end classifier for language identification. EURASIP Journal on Audio, Speech, and Music Processing, 2008(1), 674859.","journal-title":"EURASIP Journal on Audio, Speech, and Music Processing"},{"key":"9526_CR26","doi-asserted-by":"publisher","first-page":"50","DOI":"10.1016\/j.specom.2015.10.001","volume":"75","author":"X Wang","year":"2015","unstructured":"Wang, X., Wan, Y., Yang, L., Zhou, R., & Yan, Y. (2015). Phonotactic language recognition using dynamic pronunciation and language branch discriminative information. Speech Communication, 75, 50\u201361.","journal-title":"Speech Communication"},{"issue":"1","key":"9526_CR27","doi-asserted-by":"publisher","first-page":"31","DOI":"10.1109\/TSA.1996.481450","volume":"4","author":"MA Zissman","year":"1996","unstructured":"Zissman, M. A. (1996). Comparison of four approaches to automatic language identification of telephone speech. IEEE Transactions on Speech and Audio Processing, 4(1), 31.","journal-title":"IEEE Transactions on Speech and Audio Processing"},{"doi-asserted-by":"crossref","unstructured":"Zissman, M. A., & Singer, E. (1994). Automatic language identification of telephone speech messages using phoneme recognition and n-gram modeling. In IEEE International Conference on Acoustics, Speech, and Signal Processing, 1994. ICASSP-94.","key":"9526_CR28","DOI":"10.1109\/ICASSP.1994.389377"}],"container-title":["International Journal of Speech Technology"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/article\/10.1007\/s10772-018-9526-5\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s10772-018-9526-5.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s10772-018-9526-5.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,8,26]],"date-time":"2022-08-26T16:20:10Z","timestamp":1661530810000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/s10772-018-9526-5"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018,6,28]]},"references-count":28,"journal-issue":{"issue":"3","published-print":{"date-parts":[[2018,9]]}},"alternative-id":["9526"],"URL":"https:\/\/doi.org\/10.1007\/s10772-018-9526-5","relation":{},"ISSN":["1381-2416","1572-8110"],"issn-type":[{"type":"print","value":"1381-2416"},{"type":"electronic","value":"1572-8110"}],"subject":[],"published":{"date-parts":[[2018,6,28]]},"assertion":[{"value":"15 February 2018","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"23 June 2018","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"28 June 2018","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}]}}