{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2023,9,5]],"date-time":"2023-09-05T06:34:07Z","timestamp":1693895647223},"reference-count":60,"publisher":"Springer Science and Business Media LLC","issue":"8","license":[{"start":{"date-parts":[[2017,12,4]],"date-time":"2017-12-04T00:00:00Z","timestamp":1512345600000},"content-version":"unspecified","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Circuits Syst Signal Process"],"published-print":{"date-parts":[[2018,8]]},"DOI":"10.1007\/s00034-017-0724-1","type":"journal-article","created":{"date-parts":[[2017,12,4]],"date-time":"2017-12-04T11:17:50Z","timestamp":1512386270000},"page":"3589-3604","update-policy":"http:\/\/dx.doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":10,"title":["Acoustic Feature Analysis and Discriminative Modeling for Language Identification of Closely Related South-Asian Languages"],"prefix":"10.1007","volume":"37","author":[{"given":"Farah","family":"Adeeba","sequence":"first","affiliation":[]},{"given":"Sarmad","family":"Hussain","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2017,12,4]]},"reference":[{"key":"724_CR1","unstructured":"(16 Feb 2017). The 2011 NIST Language Recognition Evaluation Results. https:\/\/www.nist.gov\/itl\/iad\/mig\/lre11-results"},{"key":"724_CR2","unstructured":"(2017). Gurumukhi\u2013Shahmukhi Transliteration. http:\/\/g2s.learnpunjabi.org\/default.aspx"},{"key":"724_CR3","unstructured":"(2017). IPA for Punjabi. https:\/\/en.wikipedia.org\/wiki\/Help:IPA_for_Punjabi"},{"key":"724_CR4","unstructured":"1998 Census Report of Pakistan, Islamabad1998"},{"key":"724_CR5","doi-asserted-by":"crossref","unstructured":"F. Adeeba, S. Hussain, T. Habib, E. Ul-Haq, K. S. Shahid, Comparison of Urdu text to speech synthesis using unit selection and HMM based techniques, Presented at the Oriental COCOSDA Bali (Indonesia, 2016)","DOI":"10.1109\/ICSDA.2016.7918988"},{"key":"724_CR6","unstructured":"F. Adeeba, Q.-u.-A. Akram, H. Khalid, S. Hussain, CLE Urdu books N-grams, Presented at the Conference on Language and Technology (Karachi, Pakistan, 2014)"},{"key":"724_CR7","doi-asserted-by":"crossref","unstructured":"A.K.H. Al-Ali, D. Dean, B. Senadji, V. Chandran, G.R. Naik, Enhanced forensic speaker verification using a combination of DWT and MFCC feature warping in the presence of noise and reverberation conditions. (IEEE Access, 2017) pp. 15400\u201315413","DOI":"10.1109\/ACCESS.2017.2728801"},{"key":"724_CR8","doi-asserted-by":"crossref","first-page":"1117","DOI":"10.1109\/TASLP.2014.2319159","volume":"22","author":"MH Bahari","year":"2014","unstructured":"M.H. Bahari, N. Dehak, H.V. Hamme, L. Burget, A.M. Ali, J. Glass, Non-negative factor analysis of gaussian mixture model weight adaptation for language and dialect recognition. IEEE\/ACM Trans. Audio Speech Lang. Process. 22, 1117\u20131129 (2014)","journal-title":"IEEE\/ACM Trans. Audio Speech Lang. Process."},{"key":"724_CR9","doi-asserted-by":"crossref","first-page":"118","DOI":"10.1016\/j.specom.2014.10.004","volume":"66","author":"H Behravan","year":"2015","unstructured":"H. Behravan, V. Hautam\u00e4ki, T. Kinnunen, Factors affecting i-vector based foreign accent recognition: a case study in spoken Finnish. Speech Commun. 66, 118\u2013129 (2015)","journal-title":"Speech Commun."},{"key":"724_CR10","doi-asserted-by":"crossref","unstructured":"N. Bertoldi, M. Federico, Cross-Language Spoken Document Retrieval on the TREC SDR Collection, in Advances in Cross-Language Information Retrieval: Third Workshop of the Cross-Language Evaluation Forum, CLEF 2002 Rome, Italy, Sept 19\u201320, 2002 Revised Papers, C. Peters, M. Braschler, J. Gonzalo, M. Kluck, (Eds.), (Springer, Berlin, 2003) pp. 476\u2013481","DOI":"10.1007\/978-3-540-45237-9_41"},{"key":"724_CR11","first-page":"341","volume":"5","author":"P Boersma","year":"2001","unstructured":"P. Boersma, Praat, a system for doing phonetics by computer. Glot Int. 5, 341\u2013345 (2001)","journal-title":"Glot Int."},{"key":"724_CR12","doi-asserted-by":"crossref","unstructured":"J.P.C.W.M. Campbell, D.A. Reynolds, E. Singer, P.A. Torres-Carrasquillo, Support vector machines for speaker and language recognition, Presented at the Odyssey 2004: The speaker and Language Recognition Workshop (2006)","DOI":"10.1016\/j.csl.2005.06.003"},{"key":"724_CR13","unstructured":"L. Chi-Yueh, W. Hsiao-Chuan, Language identification using pitch contour information, in Proceedings of (ICASSP\u201905) IEEE International Conference on Acoustics, Speech, and Signal Processing (2005), pp. 601\u2013604"},{"key":"724_CR14","doi-asserted-by":"crossref","unstructured":"N. Dehak, P.A. Torres-Carrasquillo, D. Reynolds, R. Dehak, Language recognition via ivectors and dimensionality reduction (2011)","DOI":"10.21437\/Interspeech.2011-328"},{"key":"724_CR15","doi-asserted-by":"crossref","first-page":"2095","DOI":"10.1109\/TASL.2007.902758","volume":"15","author":"N Dehak","year":"2007","unstructured":"N. Dehak, P. Dumouchel, P. Kenny, Modeling prosodic features with joint factor analysis for speaker verification. IEEE Trans. Audio Speech Lang. Process. 15, 2095\u20132103 (2007)","journal-title":"IEEE Trans. Audio Speech Lang. Process."},{"key":"724_CR16","unstructured":"K.C. Djamel MOSTEFA, Sylvie BRUNESSAUX, Karim Boudahmane, New language resources for the Pashto language, Presented at the Language Resource and Evaluation (LREC) (Istanbul, Turkey, 2012)"},{"key":"724_CR17","doi-asserted-by":"crossref","first-page":"613","DOI":"10.1007\/s10579-016-9347-6","volume":"51","author":"M Djellab","year":"2017","unstructured":"M. Djellab, A. Amrouche, A. Bouridane, N. Mehallegue, Algerian Modern Colloquial Arabic Speech Corpus (AMCASC): regional accents recognition within complex socio-linguistic environments. Lang. Resour. Eval. 51, 613\u2013641 (2017)","journal-title":"Lang. Resour. Eval."},{"key":"724_CR18","unstructured":"Ethnologue. (2017, 14 Jan 2017). Sindhi. https:\/\/www.ethnologue.com\/language\/snd"},{"key":"724_CR19","unstructured":"M. Farooq, An Acoustic Phonetic Study of Six Accents of Urdu in Pakistan. MS thesis, Department of English Language and Literature, University of Management and Technology (2014)"},{"key":"724_CR20","doi-asserted-by":"crossref","unstructured":"C.Y.E.-W.D. Garcia-Romero, Analysis of i-vector length normalization in speaker recognition systems, Presented at the Interspeech (Florence, 2011)","DOI":"10.21437\/Interspeech.2011-53"},{"key":"724_CR21","volume-title":"Ethnologue: Languages of the World","author":"RG Gordon","year":"2005","unstructured":"R.G. Gordon, Ethnologue: Languages of the World, 15th edn. (SIL International, Dallas, 2005)","edition":"15"},{"key":"724_CR22","unstructured":"G.A. Grierson, Linguistic Survey of India. vol. Volume IX: Indo-Aryan family. Central group, edn (Office of the Superintendent of Government Printing India, Calcutta, 1916), p. 609"},{"key":"724_CR23","unstructured":"W. Habib, R.H. Basit, S. Hussain, F. Adeeba, Design of speech corpus for open domain Urdu text to speech system using greedy algorithm, in Conference on Language and Technology (CLT) (Karachi, 2014)"},{"key":"724_CR24","doi-asserted-by":"crossref","unstructured":"M. India, J.A.R. Fonollosa, J. Hernando, LSTM Neural Network-based speaker segmentationusing acoustic and language modelling, in Interspeech Stockholm (Sweden, 2017), pp. 2834\u20132838","DOI":"10.21437\/Interspeech.2017-407"},{"key":"724_CR25","unstructured":"Indo Times. http:\/\/www.indotimes.com.au\/"},{"key":"724_CR26","unstructured":"P. Kenny, A small footprint i-vector extractor, in ODYSSEY (2012)"},{"key":"724_CR27","unstructured":"M.A. Kohler, M. Kennedy, Language identification using shifted delta cepstra, in The 2002 45th Midwest Symposium on Circuits and Systems, MWSCAS-2002, vol. 3 (2002), pp. III-69-72"},{"key":"724_CR28","doi-asserted-by":"crossref","unstructured":"T. Lander, R.A. Cole, B.T. Oshika, M. Noel, The OGI 22 language telephone speech corpus, in 4th European Conference on Speech Communication and Technology (Madrid, 1995)","DOI":"10.21437\/Eurospeech.1995-187"},{"key":"724_CR29","doi-asserted-by":"crossref","first-page":"1136","DOI":"10.1109\/JPROC.2012.2237151","volume":"101","author":"H Li","year":"2013","unstructured":"H. Li, B. Ma, K.A. Lee, Spoken language recognition: from fundamentals to practice. Proc. IEEE 101, 1136\u20131159 (2013)","journal-title":"Proc. IEEE"},{"key":"724_CR30","unstructured":"S.O.S.G. Liu, T. Hasan, J.W. Suh, C. Zhang, M. Mehrabani, H. Boril, J.H.L. Hansen, UTD-CRSS systems for NIST language recognition evaluation 2011, Presented at the NIST 2011 Language Recognition Evaluation Workshop (2011)"},{"key":"724_CR31","doi-asserted-by":"crossref","unstructured":"Y. Liu, L. He, Y. Tian, Z. Chen, J. Liu, M.T. Johnson, Comparison of multiple features and modeling methods for text-dependent speaker verification. CoRR abs\/1707.04373 (2017)","DOI":"10.1109\/ASRU.2017.8268995"},{"key":"724_CR32","doi-asserted-by":"crossref","unstructured":"B. Ma, C. Guan, H. Li, C.-H. Lee, Multilingual speech recognition with language identification, in INTERSPEECH (2002)","DOI":"10.21437\/ICSLP.2002-178"},{"key":"724_CR33","unstructured":"A. Martin, A. Le, D. Graff, J. v. Santen. (2017). 2007 NIST Language Recognition Evaluation Supplemental Training Set. https:\/\/catalog.ldc.upenn.edu\/LDC2009S05"},{"key":"724_CR34","doi-asserted-by":"crossref","unstructured":"D. Mart\u00ednez, O. Plchot, L. Burget, O. Glembek, P. Matejka, Language recognition in ivectors space, in Proceedings of Interspeech (Firenze, 2011), pp. 861\u2013864","DOI":"10.21437\/Interspeech.2011-329"},{"key":"724_CR35","unstructured":"L. Mary, B. Yegnanarayana, Prosodic features for language identification, in International Conference on Signal Processing, Communications and Networking, 2008. ICSCN\u201908 (2008), pp. 57\u201362"},{"key":"724_CR36","doi-asserted-by":"crossref","unstructured":"P. Matejka, P. Schwarz, J. Cernocky, P. Chytil, Phonotactic language identification using high quality phoneme recognition, in Proceedings og Eurospeech 2005 (2005)","DOI":"10.21437\/Interspeech.2005-708"},{"key":"724_CR37","volume-title":"A Sindhi-English Dictionary","author":"P Mewaram","year":"1910","unstructured":"P. Mewaram, A Sindhi-English Dictionary (The Sind Juvenile Co-operative Society, Hyderabad, 1910)"},{"key":"724_CR38","doi-asserted-by":"crossref","first-page":"581","DOI":"10.15388\/Informatica.2012.376","volume":"23","author":"GR Naik","year":"2012","unstructured":"G.R. Naik, Measure of quality of source separation for sub-and super-Gaussian audio mixtures. Informatica 23, 581\u2013599 (2012)","journal-title":"Informatica"},{"key":"724_CR39","doi-asserted-by":"crossref","first-page":"1333","DOI":"10.1080\/00207217.2011.582450","volume":"99","author":"GR Naik","year":"2012","unstructured":"G.R. Naik, W. Wang, Audio analysis of statistically instantaneous signals with mixed Gaussian probability distributions. Int. J. Electron. 99, 1333\u20131350 (2012)","journal-title":"Int. J. Electron."},{"key":"724_CR40","doi-asserted-by":"crossref","unstructured":"R.W.M. Ng, T. Lee, C.C. Leung, B. Ma, H. Li, Analysis and selection of prosodic features for language identification, in International Conference Asian Language Processing, IALP\u201909 (2009), pp. 123\u2013128","DOI":"10.1109\/IALP.2009.34"},{"key":"724_CR41","unstructured":"Y. Obuchi, N. Sato, Language identification using phonetic and prosodic HMMs with feature Normalization, in Proceedings of (ICASSP\u201905). IEEE International Conference on Acoustics, Speech, and Signal Processing (2005), pp. 569\u2013572"},{"key":"724_CR42","unstructured":"A. Poddar, M. Sahidullah, G. Saha, Performance comparison of speaker recognition systems in presence of duration variability, in 2015 annual IEEE India conference (INDICON) India (2015), pp. 1\u20136"},{"key":"724_CR43","unstructured":"Punjab Post. http:\/\/punjabpost.ca\/"},{"key":"724_CR44","unstructured":"Punjabi Infoline. http:\/\/www.punjabinfoline.com\/"},{"key":"724_CR45","doi-asserted-by":"crossref","first-page":"19","DOI":"10.1006\/dspr.1999.0361","volume":"10","author":"DA Reynolds","year":"2000","unstructured":"D.A. Reynolds, T.F. Quatieri, R.B. Dunn, Speaker verification using adapted Gaussian mixture models. Digit. Signal Process. 10, 19\u201341 (2000)","journal-title":"Digit. Signal Process."},{"key":"724_CR46","doi-asserted-by":"crossref","unstructured":"M. Scarpiniti, F. Garzia, Security monitoring based on joint automatic speaker recognition and blind source separation, in International Carnahan Conference on Security Technology (ICCST) (Rome, 2014), pp. 1\u20136","DOI":"10.1109\/CCST.2014.6986990"},{"key":"724_CR47","unstructured":"W. Shen, W. Campbell, T. Gleason, D. Reynolds, E. Singer, Experiments with Lattice-based PPRLM language identification, in IEEE Odyssey\u2014The Speaker and Language Recognition Workshop (2006), pp. 1\u20136"},{"key":"724_CR48","doi-asserted-by":"crossref","unstructured":"E. Singer, P.A. Torres-Carrasquillo, D.A. Reynolds, A. McCree, F. Richardson, N. Dehak,et al., The MITLL NIST LRE 2011 language recognition system, in ODYSSEY (2012)","DOI":"10.1109\/ICASSP.2010.5495080"},{"key":"724_CR49","unstructured":"S. Strassel, K. Walker, K. Jones, D. Graff, C. Cieri, New resources for recognition of confusable linguistic varieties: the LRE11 corpus. Presented at the Odyssey 2012: The Speaker and Language Recognition Workshop (Singapore, 2012)"},{"key":"724_CR50","doi-asserted-by":"crossref","first-page":"798","DOI":"10.1109\/JSTSP.2010.2057192","volume":"4","author":"ZH Tan","year":"2010","unstructured":"Z.H. Tan, B. Lindberg, Low-complexity variable frame rate analysis for speech recognition and voice activity detection. IEEE J. Sel. Top. Signal Process. 4, 798\u2013807 (2010)","journal-title":"IEEE J. Sel. Top. Signal Process."},{"key":"724_CR51","unstructured":"The Hidden Markov Model Toolkit. http:\/\/htk.eng.cam.ac.uk\/"},{"key":"724_CR52","unstructured":"S. Urooj, S. Hussain, F. Adeeba, F. Jabeen, R. Parveen, CLE Urdu digest corpus, in Conference on Language and Technology(CLT) (Lahore, 2012), pp. 47\u201353"},{"key":"724_CR53","doi-asserted-by":"crossref","first-page":"1297","DOI":"10.1109\/5.880085","volume":"88","author":"A Waibel","year":"2000","unstructured":"A. Waibel, P. Geutner, L.M. Tomokiyo, T. Schultz, M. Woszczyna, Multilinguality in speech and spoken language systems. Proc. IEEE 88, 1297\u20131313 (2000)","journal-title":"Proc. IEEE"},{"key":"724_CR54","unstructured":"J.C. Wells, Computer-coding the IPA: a proposed extension of SAMPA (1999)"},{"key":"724_CR55","doi-asserted-by":"crossref","first-page":"91","DOI":"10.1023\/B:VLSI.0000015089.17975.f4","volume":"36","author":"C-H Wu","year":"2004","unstructured":"C.-H. Wu, G.-L. Yan, Acoustic feature analysis and discriminative modeling of filled pauses for spontaneous speech recognition. J. VLSI Signal Process. Syst. Signal Image Video Technol. 36, 91\u2013104 (2004)","journal-title":"J. VLSI Signal Process. Syst. Signal Image Video Technol."},{"key":"724_CR56","doi-asserted-by":"crossref","first-page":"721","DOI":"10.5057\/jjske.TJSKE-D-16-00075","volume":"15","author":"F Yokomori","year":"2016","unstructured":"F. Yokomori, Y. Ninomiya, M. Morise, A. Tanaka, K. Ozawa, Acoustic feature analysis focusing on gender difference in likability evaluation of female speech. Trans. Jpn. Soc. Kansei Eng. 15, 721\u2013729 (2016)","journal-title":"Trans. Jpn. Soc. Kansei Eng."},{"key":"724_CR57","doi-asserted-by":"crossref","unstructured":"Q. Zhang, H. Bo, x, il, J.H.L. Hansen, Supervector pre-processing for PRSVM-based Chinese and Arabic dialect identification, in 2013 IEEE International Conference on Acoustics, Speech and Signal Processing (2013), pp. 7363\u20137367","DOI":"10.1109\/ICASSP.2013.6639093"},{"key":"724_CR58","unstructured":"Q. Zhang, G. Liu, J.H. Hansen, Robust language recognition based on diverse features, in ODYSSEY: The Speaker and Language and Language Recognition Workshop (2014), pp. 152\u2013157"},{"key":"724_CR59","doi-asserted-by":"crossref","first-page":"1075","DOI":"10.1109\/TASLP.2017.2687104","volume":"25","author":"X Zhang","year":"2017","unstructured":"X. Zhang, D. Wang, Deep learning based binaural speech separation in reverberant environments. IEEE\/ACM Trans. Audio Speech Lang. Process. 25, 1075\u20131084 (2017)","journal-title":"IEEE\/ACM Trans. Audio Speech Lang. Process."},{"key":"724_CR60","doi-asserted-by":"crossref","first-page":"1166","DOI":"10.1109\/5.880078","volume":"88","author":"VW Zue","year":"2000","unstructured":"V.W. Zue, J.R. Glass, Conversational interfaces: advances and challenges. Proc. IEEE 88, 1166\u20131180 (2000)","journal-title":"Proc. IEEE"}],"container-title":["Circuits, Systems, and Signal Processing"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/article\/10.1007\/s00034-017-0724-1\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s00034-017-0724-1.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s00034-017-0724-1.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,8,9]],"date-time":"2022-08-09T21:32:42Z","timestamp":1660080762000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/s00034-017-0724-1"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2017,12,4]]},"references-count":60,"journal-issue":{"issue":"8","published-print":{"date-parts":[[2018,8]]}},"alternative-id":["724"],"URL":"https:\/\/doi.org\/10.1007\/s00034-017-0724-1","relation":{},"ISSN":["0278-081X","1531-5878"],"issn-type":[{"value":"0278-081X","type":"print"},{"value":"1531-5878","type":"electronic"}],"subject":[],"published":{"date-parts":[[2017,12,4]]}}}