{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,30]],"date-time":"2026-01-30T04:22:59Z","timestamp":1769746979603,"version":"3.49.0"},"reference-count":74,"publisher":"Springer Science and Business Media LLC","issue":"22","license":[{"start":{"date-parts":[[2022,4,14]],"date-time":"2022-04-14T00:00:00Z","timestamp":1649894400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2022,4,14]],"date-time":"2022-04-14T00:00:00Z","timestamp":1649894400000},"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":["Multimed Tools Appl"],"published-print":{"date-parts":[[2022,9]]},"DOI":"10.1007\/s11042-022-13054-0","type":"journal-article","created":{"date-parts":[[2022,4,14]],"date-time":"2022-04-14T09:03:14Z","timestamp":1649926994000},"page":"32593-32624","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":19,"title":["A review into deep learning techniques for spoken language identification"],"prefix":"10.1007","volume":"81","author":[{"given":"Irshad Ahmad","family":"Thukroo","sequence":"first","affiliation":[]},{"given":"Rumaan","family":"Bashir","sequence":"additional","affiliation":[]},{"given":"Kaiser J.","family":"Giri","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2022,4,14]]},"reference":[{"issue":"5","key":"13054_CR1","doi-asserted-by":"publisher","first-page":"717","DOI":"10.1016\/S0731-7085(99)00272-1","volume":"22","author":"S Agatonovic-Kustrin","year":"2000","unstructured":"Agatonovic-Kustrin S, Beresford R (2000) Basic concepts of artificial neural network (ANN) modeling and its application in pharmaceutical research. J Pharm Biomed Anal 22(5):717\u2013727","journal-title":"J Pharm Biomed Anal"},{"key":"13054_CR2","doi-asserted-by":"crossref","unstructured":"Albadr MAA, Tiun S (2020) Spoken language identification based on particle swarm optimisation\u2013extreme learning machine approach. Circ Syst Signal Process 1\u201327","DOI":"10.1007\/s00034-020-01388-9"},{"issue":"3","key":"13054_CR3","doi-asserted-by":"publisher","first-page":"711","DOI":"10.1007\/s10772-019-09621-w","volume":"22","author":"MAA Albadr","year":"2019","unstructured":"Albadr MAA, Tiun S, Ayob M, AL-Dhief FT (2019) Spoken language identification based on optimised genetic algorithm\u2013extreme learning machine approach. Int J Speech Technol 22(3):711\u2013727","journal-title":"Int J Speech Technol"},{"key":"13054_CR4","doi-asserted-by":"crossref","unstructured":"Albawi S, Mohammed TA, Al-Zawi S (2017) Understanding of a convolutional neural network. In 2017 international conference on engineering and Technology (ICET) (pp 1\u20136). Ieee","DOI":"10.1109\/ICEngTechnol.2017.8308186"},{"issue":"2","key":"13054_CR5","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 Circ Syst Mag 11(2):82\u2013108","journal-title":"IEEE Circ Syst Mag"},{"key":"13054_CR6","doi-asserted-by":"crossref","unstructured":"Bartz C, Herold T, Yang H, Meinel C (2017) Language identification using deep convolutional recurrent neural networks. In international conference on neural information processing (pp 880\u2013889). Springer, Cham","DOI":"10.1007\/978-3-319-70136-3_93"},{"key":"13054_CR7","doi-asserted-by":"crossref","unstructured":"Bastanfard A, Amirkhani D (2020) Detect hidden message in reverse timestamp in Farsi. In 2020 25th international computer conference, computer society of Iran (CSICC) (pp 1\u20138). IEEE","DOI":"10.1109\/CSICC49403.2020.9050082"},{"key":"13054_CR8","doi-asserted-by":"crossref","unstructured":"Bastanfard A, Amirkhani D, Hasani M Increasing the accuracy of automatic speaker age estimation by using multiple UBMs. In 2019 5th conference on knowledge based engineering and innovation (KBEI) (pp 592\u2013598). IEEE","DOI":"10.1109\/KBEI.2019.8735005"},{"key":"13054_CR9","doi-asserted-by":"crossref","unstructured":"Bastanfard A, Amirkhani D, Naderi S (2020) A singing voice separation method from Persian music based on pitch detection methods. In 2020 6th Iranian conference on signal processing and intelligent systems (ICSPIS) (pp 1\u20137). IEEE","DOI":"10.1109\/ICSPIS51611.2020.9349583"},{"key":"13054_CR10","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1017\/S0962492900000015","volume":"9","author":"MD Buhmann","year":"2000","unstructured":"Buhmann MD (2000) Radial basis functions. Acta Numer 9:1\u201338","journal-title":"Acta Numer"},{"issue":"2","key":"13054_CR11","doi-asserted-by":"publisher","first-page":"233","DOI":"10.3109\/10826089809115863","volume":"33","author":"M Buscema","year":"1998","unstructured":"Buscema M (1998) Back propagation neural networks. Subst Use Misuse 33(2):233\u2013270","journal-title":"Subst Use Misuse"},{"key":"13054_CR12","doi-asserted-by":"crossref","unstructured":"Cai W, Cai D, Huang S, Li M (2019) Utterance-level end-to-end language identification using attention-based CNN-BLSTM. In ICASSP 2019-2019 IEEE international conference on acoustics, speech and signal processing (ICASSP) (pp 5991\u20135995). IEEE","DOI":"10.1109\/ICASSP.2019.8682386"},{"issue":"1","key":"13054_CR13","doi-asserted-by":"publisher","first-page":"111","DOI":"10.1080\/0952813X.2019.1631392","volume":"32","author":"AA Chowdhury","year":"2020","unstructured":"Chowdhury AA, Borkar VS, Birajdar GK (2020) Indian language identification using time-frequency image textural descriptors and GWO-based feature selection. J Exp Theor Artif Intell 32(1):111\u2013132","journal-title":"J Exp Theor Artif Intell"},{"key":"13054_CR14","doi-asserted-by":"publisher","first-page":"181432","DOI":"10.1109\/ACCESS.2020.3028241","volume":"8","author":"A Das","year":"2020","unstructured":"Das A, Guha S, Singh PK, Ahmadian A, Senu N, Sarkar R (2020) A hybrid meta-heuristic feature selection method for identification of Indian spoken languages from audio signals. IEEE Access 8:181432\u2013181449","journal-title":"IEEE Access"},{"issue":"1","key":"13054_CR15","doi-asserted-by":"publisher","first-page":"67","DOI":"10.1007\/s10772-018-09582-6","volume":"22","author":"HS Das","year":"2019","unstructured":"Das HS, Roy P (2019) Optimal prosodic feature extraction and classification in parametric excitation source information for Indian language identification using neural network based Q-learning algorithm. Int J Speech Technol 22(1):67\u201377","journal-title":"Int J Speech Technol"},{"key":"13054_CR16","doi-asserted-by":"crossref","unstructured":"Das HS, Roy P (2019) A deep dive into deep learning techniques for solving spoken language identification problems. In intelligent speech signal processing (pp 81\u2013100). Academic Press","DOI":"10.1016\/B978-0-12-818130-0.00005-2"},{"issue":"4","key":"13054_CR17","doi-asserted-by":"publisher","first-page":"788","DOI":"10.1109\/TASL.2010.2064307","volume":"19","author":"N Dehak","year":"2010","unstructured":"Dehak N, Kenny PJ, Dehak R, Dumouchel P, Ouellet P (2010) Front-end factor analysis for speaker verification. IEEE Trans Audio Speech Lang Process 19(4):788\u2013798","journal-title":"IEEE Trans Audio Speech Lang Process"},{"key":"13054_CR18","doi-asserted-by":"publisher","first-page":"107289","DOI":"10.1016\/j.apacoust.2020.107289","volume":"164","author":"D Deshwal","year":"2020","unstructured":"Deshwal D, Sangwan P, Kumar D (2020) A language identification system using hybrid features and back-propagation neural network. Appl Acoust 164:107289","journal-title":"Appl Acoust"},{"issue":"1","key":"13054_CR19","doi-asserted-by":"publisher","first-page":"105","DOI":"10.1109\/TASLP.2015.2496226","volume":"24","author":"L Ferrer","year":"2015","unstructured":"Ferrer L, Lei Y, McLaren M, Scheffer N (2015) Study of senone-based deep neural network approaches for spoken language recognition. IEEE\/ACM Trans Audio Speech Lang Process 24(1):105\u2013116","journal-title":"IEEE\/ACM Trans Audio Speech Lang Process"},{"key":"13054_CR20","unstructured":"Fine TL (2006) Feedforward neural network methodology. Springer Science & Business Media"},{"issue":"2","key":"13054_CR21","doi-asserted-by":"publisher","first-page":"303","DOI":"10.1109\/TMM.2010.2098858","volume":"13","author":"Z Fu","year":"2010","unstructured":"Fu Z, Lu G, Ting KM, Zhang D (2010) A survey of audio-based music classification and annotation. IEEE Trans Multimed 13(2):303\u2013319","journal-title":"IEEE Trans Multimed"},{"issue":"2","key":"13054_CR22","doi-asserted-by":"publisher","first-page":"274","DOI":"10.3390\/electronics9020274","volume":"9","author":"TR Gadekallu","year":"2020","unstructured":"Gadekallu TR, Khare N, Bhattacharya S, Singh S, Reddy Maddikunta PK, Ra IH, Alazab M (2020) Early detection of diabetic retinopathy using PCA-firefly based deep learning model. Electronics 9(2):274","journal-title":"Electronics"},{"key":"13054_CR23","doi-asserted-by":"crossref","unstructured":"Ganapathy S, Han K, Thomas S, Omar M, Segbroeck MV, Narayanan SS (2014) Robust language identification using convolutional neural network features. In Fifteenth annual conference of the international speech communication association","DOI":"10.21437\/Interspeech.2014-419"},{"key":"13054_CR24","doi-asserted-by":"publisher","first-page":"114416","DOI":"10.1016\/j.eswa.2020.114416","volume":"168","author":"A Garain","year":"2021","unstructured":"Garain A, Singh PK, Sarkar R (2021) FuzzyGCP: a deep learning architecture for automatic spoken language identification from speech signals. Expert Syst Appl 168:114416","journal-title":"Expert Syst Appl"},{"key":"13054_CR25","doi-asserted-by":"crossref","unstructured":"Gelly G, Gauvain JL, Le VB, Messaoudi A (2016) A divide-and-conquer approach for language identification based on recurrent neural networks. In INTERSPEECH (pp 3231\u20133235)","DOI":"10.21437\/Interspeech.2016-180"},{"key":"13054_CR26","doi-asserted-by":"crossref","unstructured":"Geng W, Wang W, Zhao Y, Cai X, Xu B, Xinyuan C (2016) End-to-end language identification using attention-based recurrent neural networks. In Interspeech (pp 2944\u20132948)","DOI":"10.21437\/Interspeech.2016-686"},{"key":"13054_CR27","doi-asserted-by":"crossref","unstructured":"Gonzalez-Dominguez J, Lopez-Moreno I, Sak H, Gonzalez-Rodriguez J, Moreno PJ (2014) Automatic language identification using long short-term memory recurrent neural networks. In Fifteenth annual conference of the international speech communication association","DOI":"10.21437\/Interspeech.2014-483"},{"key":"13054_CR28","unstructured":"Gordon RG Jr (2005) Ethnologue, languages of the world. http:\/\/www.ethnologue.com\/"},{"key":"13054_CR29","doi-asserted-by":"publisher","first-page":"182868","DOI":"10.1109\/ACCESS.2020.3028121","volume":"8","author":"S Guha","year":"2020","unstructured":"Guha S, Das A, Singh PK, Ahmadian A, Senu N, Sarkar R (2020) Hybrid feature selection method based on harmony search and naked mole-rat algorithms for spoken language identification from audio signals. IEEE Access 8:182868\u2013182887","journal-title":"IEEE Access"},{"key":"13054_CR30","doi-asserted-by":"crossref","unstructured":"Heracleous P, Takai K, Yasuda K, Mohammad Y, Yoneyama A (2018) Comparative study on spoken language identification based on deep learning. In 2018 26th European signal processing conference (EUSIPCO) (pp 2265\u20132269). IEEE","DOI":"10.23919\/EUSIPCO.2018.8553347"},{"issue":"6","key":"13054_CR31","doi-asserted-by":"publisher","first-page":"82","DOI":"10.1109\/MSP.2012.2205597","volume":"29","author":"G Hinton","year":"2012","unstructured":"Hinton G, Deng L, Yu D, Dahl GE, Mohamed AR, Jaitly N, \u2026 Kingsbury B (2012) Deep neural networks for acoustic modeling in speech recognition: the shared views of four research groups. IEEE Signal Process Mag 29(6):82\u201397","journal-title":"IEEE Signal Process Mag"},{"key":"13054_CR32","doi-asserted-by":"crossref","unstructured":"Hori C, Hori T, Watanabe S, Hershey JR (2016) Context-sensitive and role-dependent spoken language understanding using bidirectional and attention LSTMs. In Interspeech (pp 3236\u20133240)","DOI":"10.21437\/Interspeech.2016-1171"},{"key":"13054_CR33","unstructured":"Jin M, Song Y, McLoughlin IV (2017) End-to-end dnn-cnn classification for language identification"},{"issue":"3","key":"13054_CR34","doi-asserted-by":"publisher","first-page":"544","DOI":"10.1016\/j.dsp.2011.11.008","volume":"22","author":"S Jothilakshmi","year":"2012","unstructured":"Jothilakshmi S, Ramalingam V, Palanivel S (2012) A hierarchical language identification system for Indian languages. Digit Signal Process 22(3):544\u2013553","journal-title":"Digit Signal Process"},{"issue":"7","key":"13054_CR35","doi-asserted-by":"publisher","first-page":"2225","DOI":"10.3390\/app10072225","volume":"10","author":"H Kim","year":"2020","unstructured":"Kim H, Park JS (2020) Automatic language identification using speech rhythm features for multi-lingual speech recognition. Appl Sci 10(7):2225","journal-title":"Appl Sci"},{"key":"13054_CR36","doi-asserted-by":"crossref","unstructured":"Lee CH (2008) Principles of spoken language recognition. In springer handbook of speech processing (pp 785\u2013796). Springer, Berlin, Heidelberg","DOI":"10.1007\/978-3-540-49127-9_39"},{"key":"13054_CR37","doi-asserted-by":"crossref","unstructured":"Lei Y, Ferrer L, Lawson A, McLaren M, Scheffer N (2014) Application of Convolutional Neural Networks to Language Identification in Noisy Conditions. In Odyssey","DOI":"10.21437\/Odyssey.2014-43"},{"issue":"5","key":"13054_CR38","doi-asserted-by":"publisher","first-page":"1136","DOI":"10.1109\/JPROC.2012.2237151","volume":"101","author":"H Li","year":"2013","unstructured":"Li H, Ma B, Lee KA (2013) Spoken language recognition: from fundamentals to practice. Proc IEEE 101(5):1136\u20131159","journal-title":"Proc IEEE"},{"key":"13054_CR39","doi-asserted-by":"crossref","unstructured":"Liu B, Lane I (2016) Joint online spoken language understanding and language modeling with recurrent neural networks. arXiv preprint arXiv:1609.01462","DOI":"10.18653\/v1\/W16-3603"},{"key":"13054_CR40","doi-asserted-by":"publisher","first-page":"46","DOI":"10.1016\/j.csl.2016.03.001","volume":"40","author":"I Lopez-Moreno","year":"2016","unstructured":"Lopez-Moreno I, Gonzalez-Dominguez J, Martinez D, Plchot O, Gonzalez-Rodriguez J, Moreno PJ (2016) On the use of deep feedforward neural networks for automatic language identification. Comput Speech Lang 40:46\u201359","journal-title":"Comput Speech Lang"},{"key":"13054_CR41","doi-asserted-by":"crossref","unstructured":"Lounnas K, Satori H, Hamidi M, Teffahi H, Abbas M, Lichouri M (2020) CLIASR: a combined automatic speech recognition and language identification system. In 2020 1st international conference on innovative research in applied science, engineering and Technology (IRASET) (pp 1\u20135). IEEE","DOI":"10.1109\/IRASET48871.2020.9092020"},{"key":"13054_CR42","doi-asserted-by":"publisher","first-page":"48","DOI":"10.1016\/j.csl.2017.01.006","volume":"44","author":"X Lu","year":"2017","unstructured":"Lu X, Shen P, Tsao Y, Kawai H (2017) Regularization of neural network model with distance metric learning for i-vector based spoken language identification. Comput Speech Lang 44:48\u201360","journal-title":"Comput Speech Lang"},{"issue":"7","key":"13054_CR43","doi-asserted-by":"publisher","first-page":"2053","DOI":"10.1109\/TASL.2007.902861","volume":"15","author":"B Ma","year":"2007","unstructured":"Ma B, Li H, Tong R (2007) Spoken language recognition using ensemble classifiers. IEEE Trans Audio Speech Lang Process 15(7):2053\u20132062","journal-title":"IEEE Trans Audio Speech Lang Process"},{"key":"13054_CR44","doi-asserted-by":"crossref","unstructured":"Mahdavi R, Bastanfard A, Amirkhani D (2020) Persian accents identification using modeling of speech articulatory features. In 2020 25th international computer conference, Computer Society of Iran (CSICC) (pp 1\u20139). IEEE","DOI":"10.1109\/CSICC49403.2020.9050139"},{"key":"13054_CR45","doi-asserted-by":"crossref","unstructured":"Masumura R, Asami T, Masataki H, Aono Y (2017) Parallel phonetically aware DNNs and LSTM-RNNs for frame-by-frame discriminative modeling of spoken language identification. In 2017 IEEE international conference on acoustics, speech and signal processing (ICASSP) (pp 5260\u20135264). IEEE","DOI":"10.1109\/ICASSP.2017.7953160"},{"key":"13054_CR46","doi-asserted-by":"crossref","unstructured":"Miao X, McLoughlin I, Yan Y (2019) A new time-frequency attention mechanism for TDNN and CNN-LSTM-TDNN, with application to language identification. In Interspeech (pp 4080\u20134084)","DOI":"10.21437\/Interspeech.2019-1256"},{"key":"13054_CR47","doi-asserted-by":"crossref","unstructured":"Mikolov T, Karafi\u00e1t M, Burget L, \u010cernock\u00fd J, Khudanpur S (2010) Recurrent neural network based language model. In Eleventh annual conference of the international speech communication association","DOI":"10.21437\/Interspeech.2010-343"},{"issue":"1","key":"13054_CR48","doi-asserted-by":"publisher","first-page":"14","DOI":"10.1109\/TASL.2011.2109382","volume":"20","author":"AR Mohamed","year":"2011","unstructured":"Mohamed AR, Dahl GE, Hinton G (2011) Acoustic modeling using deep belief networks. IEEE Trans Audio Speech Lang Process 20(1):14\u201322","journal-title":"IEEE Trans Audio Speech Lang Process"},{"key":"13054_CR49","unstructured":"Montavon G (2009) Deep learning for spoken language identification. In NIPS workshop on deep learning for speech recognition and related applications (pp 1\u20134)"},{"key":"13054_CR50","doi-asserted-by":"crossref","unstructured":"Morchid M (2017) Internal memory gate for recurrent neural networks with application to spoken language understanding. In INTERSPEECH (pp 3316\u20133319)","DOI":"10.21437\/Interspeech.2017-357"},{"key":"13054_CR51","unstructured":"Morchid M Bidirectional internal memory gate recurrent neural networks for spoken language understanding. Int J Speech Technol 1\u20139"},{"issue":"1","key":"13054_CR52","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1007\/s13042-019-00928-3","volume":"11","author":"H Mukherjee","year":"2020","unstructured":"Mukherjee H, Obaidullah SM, Santosh KC, Phadikar S, Roy K (2020) A lazy learning-based language identification from speech using MFCC-2 features. Int J Mach Learn Cybern 11(1):1\u201314","journal-title":"Int J Mach Learn Cybern"},{"issue":"4","key":"13054_CR53","doi-asserted-by":"publisher","first-page":"33","DOI":"10.1109\/79.317925","volume":"11","author":"YK Muthusamy","year":"1994","unstructured":"Muthusamy YK, Barnard E, Cole RA (1994) Reviewing automatic language identification. IEEE Signal Process Mag 11(4):33\u201341","journal-title":"IEEE Signal Process Mag"},{"issue":"6","key":"13054_CR54","doi-asserted-by":"publisher","first-page":"678","DOI":"10.1109\/89.943345","volume":"9","author":"J Navratil","year":"2001","unstructured":"Navratil J (2001) Spoken language recognition-a step toward multilinguality in speech processing. IEEE Trans Speech Audio Process 9(6):678\u2013685","journal-title":"IEEE Trans Speech Audio Process"},{"issue":"4","key":"13054_CR55","doi-asserted-by":"publisher","first-page":"97","DOI":"10.23919\/SAIEE.2009.8531857","volume":"100","author":"M Peche","year":"2009","unstructured":"Peche M, Davel MH, Barnard E (2009) Development of a spoken language identification system for south African languages. SAIEE Africa Res J 100(4):97\u2013103","journal-title":"SAIEE Africa Res J"},{"key":"13054_CR56","doi-asserted-by":"publisher","first-page":"101142","DOI":"10.1016\/j.csl.2020.101142","volume":"66","author":"J Poncelet","year":"2021","unstructured":"Poncelet J, Renkens V (2021) Low resource end-to-end spoken language understanding with capsule networks. Comput Speech Lang 66:101142","journal-title":"Comput Speech Lang"},{"key":"13054_CR57","doi-asserted-by":"crossref","unstructured":"Qian Y, Ubale R, Lange P, Evanini K, Ramanarayanan V, Soong FK (2019) Spoken language understanding of human-machine conversations for language learning applications. J Signal Process Syst 1\u201313","DOI":"10.1007\/s11265-019-01484-3"},{"issue":"10","key":"13054_CR58","doi-asserted-by":"publisher","first-page":"1671","DOI":"10.1109\/LSP.2015.2420092","volume":"22","author":"F Richardson","year":"2015","unstructured":"Richardson F, Reynolds D, Dehak N (2015) Deep neural network approaches to speaker and language recognition. IEEE Signal Process Lett 22(10):1671\u20131675","journal-title":"IEEE Signal Process Lett"},{"key":"13054_CR59","unstructured":"Sharma V, Rai S, Dev A (2012) A comprehensive study of artificial neural networks. Int J Adv Res Comput Sci Softw Eng 2(10)"},{"key":"13054_CR60","doi-asserted-by":"publisher","first-page":"2674","DOI":"10.1109\/TASLP.2020.3023627","volume":"28","author":"P Shen","year":"2020","unstructured":"Shen P, Lu X, Li S, Kawai H (2020) Knowledge distillation-based representation learning for short-utterance spoken language identification. IEEE\/ACM Trans Audio Speech Lang Process 28:2674\u20132683","journal-title":"IEEE\/ACM Trans Audio Speech Lang Process"},{"issue":"5","key":"13054_CR61","doi-asserted-by":"publisher","first-page":"1029","DOI":"10.1109\/TASL.2008.924150","volume":"16","author":"KC Sim","year":"2008","unstructured":"Sim KC, Li H (2008) On acoustic diversification front-end for spoken language identification. IEEE Trans Audio Speech Lang Process 16(5):1029\u20131037","journal-title":"IEEE Trans Audio Speech Lang Process"},{"key":"13054_CR62","doi-asserted-by":"crossref","unstructured":"Song Y, Cui R, Hong X, Mcloughlin I, Shi J, Dai L (2015) Improved language identification using deep bottleneck network. In 2015 IEEE international conference on acoustics, speech and signal processing (ICASSP) (pp 4200\u20134204). IEEE","DOI":"10.1109\/ICASSP.2015.7178762"},{"key":"13054_CR63","doi-asserted-by":"crossref","unstructured":"Torres-Carrasquillo PA, Reynolds DA, Deller JR (2002) Language identification using Gaussian mixture model tokenization. In 2002 IEEE international conference on acoustics, speech, and signal processing (Vol 1, pp I\u2013757). IEEE","DOI":"10.1109\/ICASSP.2002.1005850"},{"issue":"5","key":"13054_CR64","doi-asserted-by":"publisher","first-page":"293","DOI":"10.1109\/TSA.2002.800560","volume":"10","author":"G Tzanetakis","year":"2002","unstructured":"Tzanetakis G, Cook P (2002) Musical genre classification of audio signals. IEEE Trans Speech Audio Process 10(5):293\u2013302","journal-title":"IEEE Trans Speech Audio Process"},{"key":"13054_CR65","doi-asserted-by":"crossref","unstructured":"Ultsch A (1993) Self-organizing neural networks for visualisation and classification. In information and classification (pp 307\u2013313). Springer, Berlin, Heidelberg","DOI":"10.1007\/978-3-642-50974-2_31"},{"key":"13054_CR66","doi-asserted-by":"publisher","first-page":"101748","DOI":"10.1016\/j.cose.2020.101748","volume":"92","author":"D Vasan","year":"2020","unstructured":"Vasan D, Alazab M, Wassan S, Safaei B, Zheng Q (2020) Image-based malware classification using ensemble of CNN architectures (IMCEC). Comput Secur 92:101748","journal-title":"Comput Secur"},{"issue":"4","key":"13054_CR67","doi-asserted-by":"publisher","first-page":"67","DOI":"10.29252\/jsdp.17.4.67","volume":"17","author":"H Veisi","year":"2021","unstructured":"Veisi H, Ghoreishi SA, Bastanfard A (2021) Spoken term detection for Persian news of Islamic Republic of Iran broadcasting. Signal Data Process 17(4):67\u201388","journal-title":"Signal Data Process"},{"key":"13054_CR68","doi-asserted-by":"publisher","first-page":"290","DOI":"10.1016\/j.eswa.2018.06.004","volume":"110","author":"RK Vuddagiri","year":"2018","unstructured":"Vuddagiri RK, Vydana HK, Vuppala AK (2018) Curriculum learning based approach for noise robust language identification using DNN with attention. Expert Syst Appl 110:290\u2013297","journal-title":"Expert Syst Appl"},{"key":"13054_CR69","unstructured":"Wikipedia, \u201chttps:\/\/en.wikipedia.org\/wiki\/List_of_animals_by_number_of_neurons\u201d"},{"key":"13054_CR70","unstructured":"Wong KYE (2004) Automatic spoken language identification utilizing acoustic and phonetic speech information (Doctoral dissertation, Queensland University of Technology)"},{"issue":"2","key":"13054_CR71","doi-asserted-by":"publisher","first-page":"358","DOI":"10.1016\/j.csl.2009.05.002","volume":"24","author":"WL Wu","year":"2010","unstructured":"Wu WL, Lu RZ, Duan JY, Liu H, Gao F, Chen YQ (2010) Spoken language understanding using weakly supervised learning. Comput Speech Lang 24(2):358\u2013382","journal-title":"Comput Speech Lang"},{"key":"13054_CR72","doi-asserted-by":"publisher","first-page":"113575","DOI":"10.1016\/j.eswa.2020.113575","volume":"158","author":"G Yasmin","year":"2020","unstructured":"Yasmin G, Das AK, Nayak J, Pelusi D, Ding W (2020) Graph based feature selection investigating boundary region of rough set for language identification. Expert Syst Appl 158:113575","journal-title":"Expert Syst Appl"},{"issue":"1","key":"13054_CR73","doi-asserted-by":"publisher","first-page":"145","DOI":"10.1109\/MSP.2010.939038","volume":"28","author":"D Yu","year":"2010","unstructured":"Yu D, Deng L (2010) Deep learning and its applications to signal and information processing [exploratory dsp]. IEEE Signal Process Mag 28(1):145\u2013154","journal-title":"IEEE Signal Process Mag"},{"issue":"1-2","key":"13054_CR74","doi-asserted-by":"publisher","first-page":"115","DOI":"10.1016\/S0167-6393(00)00099-6","volume":"35","author":"MA Zissman","year":"2001","unstructured":"Zissman MA, Berkling KM (2001) Automatic language identification. Speech Commun 35(1-2):115\u2013124","journal-title":"Speech Commun"}],"container-title":["Multimedia Tools and Applications"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11042-022-13054-0.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s11042-022-13054-0\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11042-022-13054-0.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,8,22]],"date-time":"2022-08-22T05:25:42Z","timestamp":1661145942000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s11042-022-13054-0"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,4,14]]},"references-count":74,"journal-issue":{"issue":"22","published-print":{"date-parts":[[2022,9]]}},"alternative-id":["13054"],"URL":"https:\/\/doi.org\/10.1007\/s11042-022-13054-0","relation":{},"ISSN":["1380-7501","1573-7721"],"issn-type":[{"value":"1380-7501","type":"print"},{"value":"1573-7721","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022,4,14]]},"assertion":[{"value":"20 March 2021","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"1 June 2021","order":2,"name":"revised","label":"Revised","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"4 April 2022","order":3,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"14 April 2022","order":4,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}]}}