{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,5]],"date-time":"2026-02-05T22:32:21Z","timestamp":1770330741575,"version":"3.49.0"},"reference-count":51,"publisher":"Springer Science and Business Media LLC","issue":"4","license":[{"start":{"date-parts":[[2017,7,28]],"date-time":"2017-07-28T00:00:00Z","timestamp":1501200000000},"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":["Artif Intell Rev"],"published-print":{"date-parts":[[2019,4]]},"DOI":"10.1007\/s10462-017-9573-3","type":"journal-article","created":{"date-parts":[[2017,7,28]],"date-time":"2017-07-28T20:56:37Z","timestamp":1501275397000},"page":"647-672","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":7,"title":["Empirical analysis of linguistic and paralinguistic information for automatic dialect classification"],"prefix":"10.1007","volume":"51","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-9195-5077","authenticated-orcid":false,"given":"Shweta","family":"Sinha","sequence":"first","affiliation":[]},{"given":"Aruna","family":"Jain","sequence":"additional","affiliation":[]},{"given":"Shyam S.","family":"Agrawal","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2017,7,28]]},"reference":[{"issue":"2","key":"9573_CR1","doi-asserted-by":"publisher","first-page":"1130","DOI":"10.1121\/1.2409492","volume":"121","author":"P Adank","year":"2007","unstructured":"Adank P, Van Hout R, Van de Velde H (2007) An acoustic description of the vowels of northern and southern standard Dutch II: regional varietiesa. J Acoust Soc Am 121(2):1130\u20131141","journal-title":"J Acoust Soc Am"},{"issue":"2","key":"9573_CR2","doi-asserted-by":"publisher","first-page":"165","DOI":"10.1007\/s10772-012-9131-y","volume":"15","author":"RK Aggarwal","year":"2012","unstructured":"Aggarwal RK, Dave M (2012) Integration of multiple acoustic and language models for improved Hindi speech recognition system. Int J Speech Technol 15(2):165\u2013180","journal-title":"Int J Speech Technol"},{"issue":"3","key":"9573_CR3","doi-asserted-by":"publisher","first-page":"593","DOI":"10.1007\/s10772-016-9351-7","volume":"19","author":"SS Agrawal","year":"2016","unstructured":"Agrawal SS, Jain A, Sinha S (2016) Analysis and modeling of acoustic information for automatic dialect classification. Int J Speech Technol 19(3):593\u2013609","journal-title":"Int J Speech Technol"},{"key":"9573_CR4","doi-asserted-by":"crossref","first-page":"395","DOI":"10.21437\/Eurospeech.1999-102","volume":"99","author":"M Barkat","year":"1999","unstructured":"Barkat M, Ohala J, Pellegrino F (1999) Prosody as a distinctive feature for the discrimination of Arabic dialects. Eurospeech 99:395\u2013398","journal-title":"Eurospeech"},{"key":"9573_CR5","doi-asserted-by":"publisher","first-page":"118","DOI":"10.1016\/j.specom.2014.10.004","volume":"66","author":"H Behravan","year":"2015","unstructured":"Behravan H, Hautam\u00e4ki V, Kinnunen T (2015) Factors affecting i- vector based foreign accent recognition: a case study in spoken Finnish. Speech Commun 66:118\u2013129","journal-title":"Speech Commun"},{"key":"9573_CR6","unstructured":"Biadsy F (2011) Automatic dialect and accent recognition and its application to speech recognition. Ph.D. Thesis, Columbia University"},{"key":"9573_CR7","doi-asserted-by":"crossref","unstructured":"Biadsy F, Hirschberg J, Ellis DPW (2011) Dialect and accent recognition using phonetic-segmentation supervectors. In: INTERSPEECH, pp 752\u2013756","DOI":"10.21437\/Interspeech.2011-285"},{"issue":"2","key":"9573_CR8","doi-asserted-by":"publisher","first-page":"512","DOI":"10.1109\/72.363492","volume":"6","author":"M Bianchini","year":"1995","unstructured":"Bianchini M, Frasconi P, Gori M (1995) Learning in multilayered networks used as autoassociators. IEEE Trans Neural Netw 6(2):512\u2013515","journal-title":"IEEE Trans Neural Netw"},{"key":"9573_CR9","doi-asserted-by":"crossref","unstructured":"Blackburn CS, Vonwiller J, King RW (1993) Automatic accent classification using artificial neural networks. In: EUROSPEECH, vol 2, pp 1241\u20131244","DOI":"10.21437\/Eurospeech.1993-293"},{"key":"9573_CR10","doi-asserted-by":"publisher","DOI":"10.1017\/CBO9780511805103","volume-title":"Dialectology","author":"JK Chambers","year":"1998","unstructured":"Chambers JK, Trudgill P (1998) Dialectology. Cambridge University Press, Cambridge"},{"key":"9573_CR11","doi-asserted-by":"crossref","unstructured":"Chan MV , Feng X , Heinen JA, Niederjohn RJ (1994) Classification of speech accents with neural networks. In: Neural networks, world congress on computational intelligence, vol 7, pp 4483\u20134486. IEEE","DOI":"10.1109\/ICNN.1994.374994"},{"key":"9573_CR12","unstructured":"Chen T, Huang C, Chang E, Wang J (2001) Automatic accent identification using Gaussian mixture models. In: Workshop on automatic speech recognition and understanding, pp 343\u2013346. IEEE"},{"issue":"2","key":"9573_CR13","doi-asserted-by":"publisher","first-page":"155","DOI":"10.1006\/jpho.2001.0131","volume":"29","author":"T Cho","year":"2001","unstructured":"Cho T, Keating PA (2001) Articulatory and acoustic studies on domain-initial strengthening in Korean. J Phonetics 29(2):155\u2013190","journal-title":"J Phonetics"},{"key":"9573_CR14","first-page":"4","volume":"2","author":"PG Deivapalan","year":"2008","unstructured":"Deivapalan PG, Jha M, Guttikonda R, Murthy HA (2008) DONLabel: an automatic labeling tool for Indian languages. Energy 2:4","journal-title":"Energy"},{"key":"9573_CR15","doi-asserted-by":"crossref","unstructured":"DeMarco A, Cox SJ (2013) Native accent classification via i-vectors and speaker compensation fusion. In :INTERSPEECH, pp 1472\u20131476","DOI":"10.21437\/Interspeech.2013-382"},{"key":"9573_CR16","unstructured":"Dyrud LO (2001) Hindi-Urdu: stress accent or non-stress accent?. Ph.D. Thesis, University of North Dakota"},{"issue":"4","key":"9573_CR17","doi-asserted-by":"publisher","first-page":"358","DOI":"10.1109\/89.917681","volume":"9","author":"A Ganapathiraju","year":"2001","unstructured":"Ganapathiraju A, Hamaker J, Picone J, Ordowski M, Doddington GR (2001) Syllable-based large vocabulary continuous speech recognition. IEEE Trans Speech Audio Process 9(4):358\u2013366","journal-title":"IEEE Trans Speech Audio Process"},{"key":"9573_CR18","unstructured":"Gang L, Lei Y , Hansen JHL (2010) Dialect identification: impact of differences between read versus spontaneous speech. In: Signal processing conference, 2010 18th European, pp 2003\u20132006. IEEE"},{"issue":"1","key":"9573_CR19","doi-asserted-by":"publisher","first-page":"59","DOI":"10.1016\/j.csl.2012.01.003","volume":"27","author":"A Hanani","year":"2013","unstructured":"Hanani A, Russell MJ, Carey MJ (2013) Human and computer recognition of regional accents and ethnic groups from British English speech. Comput Speech Lang 27(1):59\u201374","journal-title":"Comput Speech Lang"},{"key":"9573_CR20","doi-asserted-by":"crossref","unstructured":"Hansen JHL, Arslan JHL (1995) Foreign accent classification using source generator based prosodic features. In: Proceeding acoustics, speech, and signal processing, vol 1, pp 836\u2013839. IEEE","DOI":"10.1109\/ICASSP.1995.479824"},{"key":"9573_CR21","doi-asserted-by":"crossref","unstructured":"Hou J, Liu Y, Zheng TF, Olsen J, Tian J (2010) Multi- layered features with SVM for Chinese accent identification. In: Proceeding audio language and image processing (ICALIP), pp 25\u201330. IEEE","DOI":"10.1109\/ICALIP.2010.5685023"},{"issue":"2","key":"9573_CR22","doi-asserted-by":"publisher","first-page":"453","DOI":"10.1109\/TASL.2006.881695","volume":"15","author":"R Huang","year":"2007","unstructured":"Huang R, Hansen JHL, Angkititrakul P (2007) Dialect\/accent classification using unrestricted audio. IEEE Trans Audio Speech Lang Process 15(2):453\u2013464","journal-title":"IEEE Trans Audio Speech Lang Process"},{"key":"9573_CR23","doi-asserted-by":"crossref","unstructured":"Koolagudi SG, Maity S, Vuppala AK, Chakrabarti S, Rao KS (2009) IITKGP-SESC: speech database for emotion analysis. In: Contemporary computing. Springer, Berlin, pp 485\u2013492","DOI":"10.1007\/978-3-642-03547-0_46"},{"key":"9573_CR24","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-4614-1138-3","volume-title":"Dialect accent features for establishing speaker identity: a case study","author":"M Kulshreshtha","year":"2012","unstructured":"Kulshreshtha M, Mathur R (2012) Dialect accent features for establishing speaker identity: a case study. Springer, Berlin"},{"issue":"5.6","key":"9573_CR25","doi-asserted-by":"publisher","first-page":"703","DOI":"10.1147\/rd.485.0703","volume":"48","author":"M Kumar","year":"2004","unstructured":"Kumar M, Rajput N, Verma A (2004) A large-vocabulary continuous speech recognition system for Hindi. IBM J Res Dev 48(5.6):703\u2013715","journal-title":"IBM J Res Dev"},{"key":"9573_CR26","doi-asserted-by":"crossref","unstructured":"Kumpf K, King K (1997) Foreign speaker accent classification using phoneme-dependent accent discrimination models and comparisons with human perception benchmarks. In: EUROSPEECH, pp 2323\u20132326","DOI":"10.21437\/Eurospeech.1997-611"},{"issue":"1","key":"9573_CR27","doi-asserted-by":"publisher","first-page":"98","DOI":"10.1121\/1.1908694","volume":"29","author":"P Ladefoged","year":"1957","unstructured":"Ladefoged P, Broadbent DE (1957) Information conveyed by vowels. J Acoust Soc Am 29(1):98\u2013104","journal-title":"J Acoust Soc Am"},{"key":"9573_CR28","unstructured":"Lazaridis A, Goldman J-P, Avanzi M, Garner PN (2014) Syllable-based regional Swiss French accent identification using prosodic features. In: Nouveaux cahiers de linguistique francaise, number EPFL-CONF-199821"},{"issue":"4","key":"9573_CR29","doi-asserted-by":"publisher","first-page":"353","DOI":"10.1016\/0167-6393(96)00024-6","volume":"18","author":"M Levent","year":"1996","unstructured":"Levent M, Hansen JHL (1996) Language accent classification in American English. Speech Commun 18(4):353\u2013367","journal-title":"Speech Commun"},{"key":"9573_CR30","doi-asserted-by":"crossref","unstructured":"Liu M, Xu B, Hunng T, Deng Y, Li C ( 2000) Mandarin accent adaptation based on context-independent\/context-dependent pronunciation modeling. In: Proceedings acoustics, speech, and signal processing, vol 2, pp II1025\u2013II1028. IEEE","DOI":"10.1109\/ICASSP.2000.859137"},{"issue":"1","key":"9573_CR31","doi-asserted-by":"publisher","first-page":"27","DOI":"10.1016\/0885-2308(87)90025-8","volume":"2","author":"A Ljolje","year":"1987","unstructured":"Ljolje A, Fallside F (1987) Recognition of isolated prosodic patterns using Hidden Markov models. Comput Speech Lang 2(1):27\u201334","journal-title":"Comput Speech Lang"},{"key":"9573_CR32","unstructured":"Ma B, Zhu D, Tong R (2006) Chinese dialect identification using tone features based on pitch flux. In :Acoustics, speech and signal processing, vol 1, pp I\u2013I. IEEE"},{"key":"9573_CR33","doi-asserted-by":"crossref","unstructured":"Mehrabani M, Boril H, Hansen JHL (2010) Dialect distance assessment method based on comparison of pitch pattern statistical models. In: Acoustics speech and signal processing (ICASSP), pp 5158\u20135161. IEEE","DOI":"10.1109\/ICASSP.2010.5495019"},{"key":"9573_CR34","unstructured":"Mishra D, Bali K (2011) A comparative phonological study of the dialects of Hindi. In: Proceedings of ICPhS XVII, Hong Kong, pp 17\u201321"},{"key":"9573_CR35","unstructured":"Ohala M (1986) A search for the phonetic correlates of Hindi stress. In: Krishnamurti B, Masica C, Sinha A (eds) South Asian languages: structure, convergence, and diglossia, pp 81\u201392"},{"issue":"10","key":"9573_CR36","doi-asserted-by":"publisher","first-page":"2965","DOI":"10.1016\/j.patcog.2008.05.008","volume":"41","author":"D OShaughnessy","year":"2008","unstructured":"OShaughnessy D (2008) Automatic speech recognition: history, methods and challenges. Pattern Recogn 41(10):2965\u20132979","journal-title":"Pattern Recogn"},{"issue":"2","key":"9573_CR37","doi-asserted-by":"publisher","first-page":"115","DOI":"10.1177\/00238309020450020201","volume":"45","author":"J Peters","year":"2002","unstructured":"Peters J, Gilles P, Auer P, Selting M (2002) Identification of regional varieties by intonational cues: an experimental study on Hamburg and Berlin German. Lang Speech 45(2):115\u2013138","journal-title":"Lang Speech"},{"key":"9573_CR38","volume-title":"Fundamentals of speech recognition","author":"L Rabiner","year":"1993","unstructured":"Rabiner L, Juang B-H (1993) Fundamentals of speech recognition. Prentice Hall, Upper Saddle River"},{"key":"9573_CR39","unstructured":"Raman S (1985) Speech recognition of Hindi stop consonants. Ph.D. Thesis, Indian Institute of Technology, Madras"},{"issue":"1","key":"9573_CR40","doi-asserted-by":"publisher","first-page":"197","DOI":"10.1016\/0167-6393(93)90071-R","volume":"13","author":"PVS Rao","year":"1993","unstructured":"Rao PVS (1993) VOICE: an integrated speech recognition synthesis system for the Hindi language. Speech Commun 13(1):197\u2013205","journal-title":"Speech Commun"},{"key":"9573_CR41","volume-title":"Emotion recognition using speech features","author":"KS Rao","year":"2012","unstructured":"Rao KS, Koolagudi SG (2012) Emotion recognition using speech features. Springer, Berlin"},{"issue":"2","key":"9573_CR42","doi-asserted-by":"publisher","first-page":"240","DOI":"10.1016\/j.csl.2008.06.005","volume":"23","author":"KS Rao","year":"2009","unstructured":"Rao KS, Yegnanarayana B (2009) Intonation modeling for Indian languages. Comput Speech Lang 23(2):240\u2013256","journal-title":"Comput Speech Lang"},{"key":"9573_CR43","unstructured":"Ryan R (2008) Multiclass classification. http:\/\/www.mit.edu\/~9.520\/spring09\/Classes\/ . Accessed 20 Sept 2014"},{"key":"9573_CR44","first-page":"1613","volume":"4","author":"H Rym","year":"2004","unstructured":"Rym H, Melissa B-D, Emmanuel F, Fran\u00e7ois P (2004) Speech timing and rhythmic structure in Arabic dialects: a comparison of two approaches. Interspeech 4:1613\u20131616","journal-title":"Interspeech"},{"issue":"7","key":"9573_CR45","doi-asserted-by":"publisher","first-page":"472","DOI":"10.1109\/TSA.2002.804298","volume":"10","author":"CC Sekhar","year":"2002","unstructured":"Sekhar CC, Yegnanarayana B (2002) A constraint satisfaction model for recognition of stop consonant-vowel (SCV) utterances. IEEE Trans Speech Audio Process 10(7):472\u2013480","journal-title":"IEEE Trans Speech Audio Process"},{"key":"9573_CR46","doi-asserted-by":"crossref","unstructured":"Sinha S, Agrawal SS, Jain A (2013) Dialectal influences on acoustic duration of Hindi phonemes. In: Conference on Asian spoken language research and evaluation (O- COCOSDA\/CASLRE), pp 1\u20135. IEEE","DOI":"10.1109\/ICSDA.2013.6709866"},{"issue":"4","key":"9573_CR47","doi-asserted-by":"publisher","first-page":"243","DOI":"10.1007\/s40012-015-0063-y","volume":"2","author":"S Sinha","year":"2015","unstructured":"Sinha S, Jain A, Agrawal SS (2015) Fusion of multi-stream speech features for dialect classification. CSI Trans ICT 2(4):243\u2013252","journal-title":"CSI Trans ICT"},{"key":"9573_CR48","doi-asserted-by":"crossref","unstructured":"Tang H, Ghorbani AA (2003) Accent classification using support vector machine and hidden Markov model. In: Advances in artificial intelligence. Springer, Berlin, pp 629\u2013631","DOI":"10.1007\/3-540-44886-1_65"},{"key":"9573_CR49","unstructured":"Torres-Carrasquillo PA , Gleason TP , Reynolds DA (2004) Dialect identification using Gaussian mixture models. In: ODYSSEY 04-The speaker and language recognition workshop, pp 297\u2013300"},{"key":"9573_CR50","doi-asserted-by":"crossref","unstructured":"Yan Q, Vaseghi S (2003) Analysis, modelling and synthesis of formants of British, American and Australian accents. In: Proceeding acoustics, speech, and signal processing, vol 1, pp I\u2013712. IEEE","DOI":"10.1109\/ICASSP.2003.1198880"},{"issue":"2","key":"9573_CR51","doi-asserted-by":"publisher","first-page":"77","DOI":"10.1007\/s10772-011-9123-3","volume":"15","author":"DC Zheng","year":"2012","unstructured":"Zheng DC, Dyke D, Berryman F, Morgan C (2012) A new approach to acoustic analysis of two British regional accents: Birmingham and Liverpool accents. Int J Speech Technol 15(2):77\u201385","journal-title":"Int J Speech Technol"}],"container-title":["Artificial Intelligence Review"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s10462-017-9573-3.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/article\/10.1007\/s10462-017-9573-3\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s10462-017-9573-3.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,24]],"date-time":"2025-06-24T18:42:28Z","timestamp":1750790548000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/s10462-017-9573-3"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2017,7,28]]},"references-count":51,"journal-issue":{"issue":"4","published-print":{"date-parts":[[2019,4]]}},"alternative-id":["9573"],"URL":"https:\/\/doi.org\/10.1007\/s10462-017-9573-3","relation":{},"ISSN":["0269-2821","1573-7462"],"issn-type":[{"value":"0269-2821","type":"print"},{"value":"1573-7462","type":"electronic"}],"subject":[],"published":{"date-parts":[[2017,7,28]]},"assertion":[{"value":"28 July 2017","order":1,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}]}}