{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,7]],"date-time":"2025-11-07T13:40:46Z","timestamp":1762522846600,"version":"3.37.3"},"reference-count":61,"publisher":"Springer Science and Business Media LLC","issue":"12","license":[{"start":{"date-parts":[[2023,10,9]],"date-time":"2023-10-09T00:00:00Z","timestamp":1696809600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2023,10,9]],"date-time":"2023-10-09T00:00:00Z","timestamp":1696809600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["J Ambient Intell Human Comput"],"published-print":{"date-parts":[[2023,12]]},"DOI":"10.1007\/s12652-023-04706-6","type":"journal-article","created":{"date-parts":[[2023,10,9]],"date-time":"2023-10-09T09:27:24Z","timestamp":1696843644000},"page":"16903-16919","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["Cepstral and acoustic ternary pattern based hybrid feature extraction approach for end-to-end bangla speech recognition"],"prefix":"10.1007","volume":"14","author":[{"given":"Mohit","family":"Dua","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"family":"Akanksha","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3091-8109","authenticated-orcid":false,"given":"Shelza","family":"Dua","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2023,10,9]]},"reference":[{"key":"4706_CR1","doi-asserted-by":"crossref","unstructured":"Adhikary R, Fatema, K, Yousuf MA (2021). A Deep Learning Approach for Bangla Speech to Text Conversion. In\u00a02021 Joint 10th International Conference on Informatics, Electronics & Vision (ICIEV) and 2021 5th International Conference on Imaging, Vision & Pattern Recognition (icIVPR)\u00a0(pp. 1\u20138). IEEE","DOI":"10.1109\/ICIEVicIVPR52578.2021.9564239"},{"key":"4706_CR2","doi-asserted-by":"crossref","unstructured":"Ahmed M, Shill PC, Islam K, Mollah, MAS, Akhand MAH. (2015). Acoustic modeling using deep belief network for Bangla speech recognition.In\u00a02015 18th international conference on computer and information technology (ICCIT)\u00a0(pp. 306\u2013311).IEEE","DOI":"10.1109\/ICCITechn.2015.7488087"},{"key":"4706_CR3","doi-asserted-by":"crossref","unstructured":"Al Amin, MA, Islam MT, Kibria S, Rahman MS. (2019). Continuous bengali speech recognition based on deep neural network. In\u00a02019 international conference on electrical, computer and communication engineering (ECCE)\u00a0(pp. 1\u20136).IEEE","DOI":"10.1109\/ECACE.2019.8679341"},{"issue":"4","key":"4706_CR4","first-page":"31","volume":"10","author":"MN Arafa","year":"2018","unstructured":"Arafa MN, Elbarougy R, Ewees AA, Behery GM (2018) A dataset for speech recognition to support Arabic phoneme pronunciation. Int J Image Gr Signal Process 10(4):31","journal-title":"Int J Image Gr Signal Process"},{"issue":"5","key":"4706_CR5","doi-asserted-by":"publisher","first-page":"483","DOI":"10.3390\/electronics8050483","volume":"8","author":"S Aziz","year":"2019","unstructured":"Aziz S, Awais M, Akram T, Khan U, Alhussein M, Aurangzeb K (2019) Automatic scene recognition through acoustic classification for behavioral robotics. Electronics 8(5):483","journal-title":"Electronics"},{"issue":"4","key":"4706_CR6","doi-asserted-by":"publisher","first-page":"3303","DOI":"10.1007\/s11277-021-08181-0","volume":"118","author":"S Bhatt","year":"2021","unstructured":"Bhatt S, Jain A, Dev A (2021) Feature extraction techniques with analysis of confusing words for speech recognition in the Hindi language. Wireless Pers Commun 118(4):3303\u20133333","journal-title":"Wireless Pers Commun"},{"key":"4706_CR7","first-page":"750","volume-title":"International conference on next generation computing technologies","author":"T Bhowmik","year":"2017","unstructured":"Bhowmik T, Choudhury A, Mandal SKD (2017) Deep neural network based recognition and classification of bengali phonemes: a case study of bengali unconstrained speech. In: Bhattacharyya P, Sastry HG, Marriboyina V, Sharma R (eds) International conference on next generation computing technologies. Springer, Singapore, pp 750\u2013760"},{"key":"4706_CR8","doi-asserted-by":"crossref","unstructured":"Cai W, Cai D, Liu W, Li G, Li M (2017). Countermeasures for automatic speaker verification replay spoofing attack: on data augmentation, feature representation, classification and fusion. In\u00a0Interspeech\u00a0(pp. 17\u201321)","DOI":"10.21437\/Interspeech.2017-906"},{"issue":"2","key":"4706_CR9","doi-asserted-by":"publisher","first-page":"127","DOI":"10.1007\/s42979-022-01557-4","volume":"4","author":"N Chakravarty","year":"2022","unstructured":"Chakravarty N, Dua M (2022) Noise robust ASV spoof detection using integrated features and Time Delay Neural Network. SN Comput Sci 4(2):127","journal-title":"SN Comput Sci"},{"issue":"9","key":"4706_CR10","doi-asserted-by":"publisher","DOI":"10.1088\/1402-4896\/acea05","volume":"98","author":"N Chakravarty","year":"2023","unstructured":"Chakravarty N, Dua M (2023a) Data augmentation and hybrid feature amalgamation to detect audio deep fake attacks. Phys Scr 98(9):096001","journal-title":"Phys Scr"},{"issue":"1","key":"4706_CR11","first-page":"1","volume":"13","author":"N Chakravarty","year":"2023","unstructured":"Chakravarty N, Dua M (2023b) Spoof Detection using Sequentially Integrated Image and Audio Features. Int J Comput Digit Syst 13(1):1\u20131","journal-title":"Int J Comput Digit Syst"},{"key":"4706_CR12","doi-asserted-by":"publisher","first-page":"371","DOI":"10.1007\/978-3-030-82269-9_29","volume-title":"In international conference on applied intelligence and informatics","author":"S Das","year":"2021","unstructured":"Das S, Yasmin M, Arefin M, Taher KA, Uddin MN, Rahman MA (2021) Mixed bangla-english spoken digit classification using convolutional neural network. In: Kaiser S, Kasabov N, Iftekharuddin K, Zhong N (eds) In international conference on applied intelligence and informatics. Springer, Cham, pp 371\u2013383"},{"key":"4706_CR500","doi-asserted-by":"crossref","unstructured":"Dua M, Akanksha (2023) Gujarati language automatic speech recognition using integrated feature extraction and hybrid acoustic model. In: Proceedings of fourth international conference on communication, computing and electronics systems: ICCCES 2022. Springer Nature Singapore, Singapore, pp 45\u201354","DOI":"10.1007\/978-981-19-7753-4_4"},{"key":"4706_CR14","doi-asserted-by":"publisher","DOI":"10.1016\/j.apacoust.2022.108643","volume":"190","author":"M Dua","year":"2022","unstructured":"Dua M, Kadyan V, Banthia N, Bansal A, Agarwal T (2022) Spectral warping and data augmentation for low resource language ASR system under mismatched conditions. Appl Acoust 190:108643","journal-title":"Appl Acoust"},{"issue":"8","key":"4706_CR15","doi-asserted-by":"publisher","first-page":"2348","DOI":"10.1109\/TSP.2004.831018","volume":"52","author":"A Ganapathiraju","year":"2004","unstructured":"Ganapathiraju A, Hamaker JE, Picone J (2004) Applications of support vector machines to speech recognition. IEEE Trans Signal Process 52(8):2348\u20132355","journal-title":"IEEE Trans Signal Process"},{"key":"4706_CR16","doi-asserted-by":"publisher","first-page":"153","DOI":"10.1007\/978-981-16-7657-4_14","volume-title":"Proceedings of Second International Conference on Sustainable Expert Systems","author":"S Guchhait","year":"2022","unstructured":"Guchhait S, Hans ASA, Augustine J (2022) Automatic Speech Recognition of Bengali Using Kaldi. In: Shakya S, Ke-Lin D, Haoxiang W (eds) Proceedings of Second International Conference on Sustainable Expert Systems. Springer, Singapore, pp 153\u2013166"},{"key":"4706_CR17","first-page":"507","volume-title":"In First International Conference on sustainable technologies for computational intelligence","author":"MA Haque","year":"2020","unstructured":"Haque MA, Verma A, Alex JSR, Venkatesan N (2020) Experimental evaluation of CNN architecture for speech recognition. In: Gao XZ, Singh D (eds) In First International Conference on sustainable technologies for computational intelligence. Springer, Singapore, pp 507\u2013514"},{"key":"4706_CR18","doi-asserted-by":"crossref","unstructured":"Hasan MM, Islam MA, Kibria S, Rahman MS. (2019). Towards Lexicon-free Bangla Automatic Speech Recognition System. In\u00a02019 International Conference on Bangla Speech and Language Processing (ICBSLP). IEEE. pp. 1\u20136","DOI":"10.1109\/ICBSLP47725.2019.201544"},{"key":"4706_CR19","doi-asserted-by":"crossref","unstructured":"Hirsch HG, Pearce D. (2000). The Aurora experimental framework for the performance evaluation of speech recognition systems under noisy conditions. In ASR2000-Automatic speech recognition: challenges for the new Millenium ISCA tutorial and research workshop (ITRW).","DOI":"10.21437\/ICSLP.2000-743"},{"key":"4706_CR20","doi-asserted-by":"publisher","first-page":"171","DOI":"10.1007\/978-981-33-4367-2_18","volume-title":"Emerging Technologies in Data Mining and Information Security","author":"SM Islam","year":"2021","unstructured":"Islam SM, Abujar S (2021) Semantics exploration for automatic bangla speech recognition. In: Bhattacharyya S, Chakrabati S, Bhattacharya A, Dutta S (eds) Emerging Technologies in Data Mining and Information Security. . Springer, Singapore, pp 171\u2013179"},{"key":"4706_CR21","first-page":"2","volume":"2","author":"R Isotani","year":"1994","unstructured":"Isotani R, Matsunaga S (1994) A stochastic language model for speech recognition integrating local and global constraints. in Proceedings of ICASSP\u201994. IEEE Int Conf Acoust Speech Signal Process 2:2\u20135","journal-title":"IEEE Int Conf Acoust Speech Signal Process"},{"key":"4706_CR22","doi-asserted-by":"publisher","first-page":"69","DOI":"10.1007\/978-3-030-14524-8_5","volume-title":"Classifiers with Memristive Networks","author":"A Izbassarova","year":"2020","unstructured":"Izbassarova A, Duisembay A, James AP (2020) Speech recognition application using deep learning neural network. In: Learning D (ed) Classifiers with Memristive Networks. Springer, Cham, pp 69\u201379"},{"key":"4706_CR23","doi-asserted-by":"crossref","unstructured":"Jain A, Singh VP, Rath SP (2019). A multi-accent acoustic model using mixture of experts for speech recognition. In\u00a0INTERSPEECH, pp. 779\u2013783","DOI":"10.21437\/Interspeech.2019-1667"},{"key":"4706_CR24","doi-asserted-by":"publisher","DOI":"10.1016\/j.apacoust.2021.108283","volume":"183","author":"A Javed","year":"2021","unstructured":"Javed A, Malik KM, Irtaza A, Malik H (2021) Towards protecting cyber-physical and IoT systems from single-and multi-order voice spoofing attacks. Appl Acoust 183:108283","journal-title":"Appl Acoust"},{"key":"4706_CR25","doi-asserted-by":"publisher","first-page":"739","DOI":"10.1007\/978-981-19-8825-7_63","volume-title":"In Proceedings of International Conference on Recent Trends in Computing","author":"S Joshi","year":"2023","unstructured":"Joshi S, Dua M (2023) Multi-order replay attack detection using enhanced feature extraction and deep learning classification. In: Mahapatra RP (ed) In Proceedings of International Conference on Recent Trends in Computing. Springer Nature Singapore, Cham, pp 739\u2013745"},{"issue":"5","key":"4706_CR26","doi-asserted-by":"publisher","first-page":"673","DOI":"10.1080\/03772063.2017.1369370","volume":"64","author":"V Kadyan","year":"2018","unstructured":"Kadyan V, Mantri A, Aggarwal RK (2018) Refinement of HMM model parameters for Punjabi automatic speech recognition (PASR) system. IETE J Res 64(5):673\u2013688","journal-title":"IETE J Res"},{"key":"4706_CR27","unstructured":"Karim R, Rahman MS, Iqbal MZ. (2002). Recognition of spoken letters in Bangla. In\u00a0Proc. 5th international conference on computer and information technology (ICCIT02)"},{"key":"4706_CR28","doi-asserted-by":"publisher","first-page":"35200","DOI":"10.1109\/ACCESS.2020.2974799","volume":"8","author":"S Kibria","year":"2020","unstructured":"Kibria S, Rahman MS, Selim MR, Iqbal MZ (2020) acoustic analysis of the speakers\u2019 variability for regional accent-affected pronunciation in Bangladeshi Bangla: a study on Sylheti accent. IEEE Access 8:35200\u201335221","journal-title":"IEEE Access"},{"key":"4706_CR29","doi-asserted-by":"publisher","first-page":"84","DOI":"10.1016\/j.specom.2021.12.004","volume":"136","author":"S Kibria","year":"2022","unstructured":"Kibria S, Samin AM, Kobir MH, Rahman MS, Selim MR, Iqbal MZ (2022) Bangladeshi Bangla speech corpus for automatic speech recognition research. Speech Commun 136:84\u201397","journal-title":"Speech Commun"},{"key":"4706_CR30","doi-asserted-by":"crossref","unstructured":"Kim K, Lee K, Gowda D, Park J, Kim S, Jin S, Kim C. (2019). Attention based on-device streaming speech recognition with large speech corpus. In\u00a02019 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU) (pp. 956\u2013963). IEEE","DOI":"10.1109\/ASRU46091.2019.9004027"},{"key":"4706_CR31","first-page":"1","volume":"24","author":"A Kumar","year":"2014","unstructured":"Kumar A, Dua M, Choudhary T (2014) Continuous hindi speech recognition using monophone based acoustic modeling. Int J Comput Appl 24:1\u20135","journal-title":"Int J Comput Appl"},{"issue":"5","key":"4706_CR32","doi-asserted-by":"publisher","first-page":"982","DOI":"10.1109\/JSTSP.2020.2999828","volume":"14","author":"KM Malik","year":"2020","unstructured":"Malik KM, Javed A, Malik H, Irtaza A (2020) A light-weight replay detection framework for voice controlled IoT devices. IEEE J Sel Top Signal Process 14(5):982\u2013996","journal-title":"IEEE J Sel Top Signal Process"},{"key":"4706_CR33","unstructured":"Mandal S, Yadav S, Rai A. (2020). End-to-End Bengali Speech Recognition.\u00a0arXiv preprint arXiv:2009.09615."},{"key":"4706_CR34","doi-asserted-by":"crossref","unstructured":"Mittal A, Dua M (2021). Static\u2013dynamic features and hybrid deep learning models based spoof detection system for ASV. Complex Intell Syst, 1\u201314.","DOI":"10.1007\/s40747-021-00565-w"},{"key":"4706_CR35","unstructured":"Mohan BJ (2014). Speech recognition using MFCC and DTW.In\u00a02014 international conference on advances in electrical engineering (ICAEE)\u00a0(pp. 1\u20134).IEEE"},{"key":"4706_CR36","unstructured":"Mori D, Ohta K, Nishimura R, Ogawa A, Kitaoka N. (2021). Advanced language model fusion method for encoder-decoder model in Japanese speech recognition. In\u00a02021 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC). IEEE. (pp. 503\u2013510)"},{"key":"4706_CR37","doi-asserted-by":"crossref","unstructured":"Muhammad G, Alotaibi YA, Huda MN. (2009). Automatic speech recognition for Bangla digits.In\u00a02009 12th International Conference on Computers and Information Technology. IEEE. pp. 379\u2013383","DOI":"10.1109\/ICCIT.2009.5407267"},{"key":"4706_CR38","doi-asserted-by":"crossref","unstructured":"Nahid MMH, Islam MA, Islam MS. (2016). A noble approach for recognizing bangla real number automatically using cmu sphinx4. In\u00a02016 5th international conference on informatics, electronics and vision (ICIEV). IEEE. pp. 844\u2013849","DOI":"10.1109\/ICIEV.2016.7760121"},{"key":"4706_CR39","doi-asserted-by":"publisher","first-page":"19143","DOI":"10.1109\/ACCESS.2019.2896880","volume":"7","author":"AB Nassif","year":"2019","unstructured":"Nassif AB, Shahin I, Attili I, Azzeh M, Shaalan K (2019) Speech recognition using deep neural networks: a systematic review. IEEE Access 7:19143\u201319165","journal-title":"IEEE Access"},{"issue":"4","key":"4706_CR40","doi-asserted-by":"publisher","first-page":"2439","DOI":"10.1007\/s11277-014-1752-9","volume":"79","author":"SY Oh","year":"2014","unstructured":"Oh SY, Chung K (2014) Improvement of speech detection using ERB feature extraction. Wireless Pers Commun 79(4):2439\u20132451","journal-title":"Wireless Pers Commun"},{"key":"4706_CR41","doi-asserted-by":"crossref","unstructured":"Paul AK, Das D, Kamal MM (2009). Bangla speech recognition system using LPC and ANN.In\u00a02009 Seventh International Conference on Advances in pattern recognition IEEE pp. 171\u2013174","DOI":"10.1109\/ICAPR.2009.80"},{"key":"4706_CR42","doi-asserted-by":"publisher","first-page":"435","DOI":"10.1007\/978-981-33-6881-1_35","volume-title":"Advances in Speech and Music Technology","author":"R Paul","year":"2021","unstructured":"Paul R, Samudravijaya K (2021) A Continuous Speech Recognition System for Bangla Language. In: Biswas A, Wennekes E, Hong TP, Wieczorkowska A (eds) Advances in Speech and Music Technology. Springer, Singapore, pp 435\u2013447"},{"issue":"1","key":"4706_CR43","doi-asserted-by":"publisher","first-page":"14","DOI":"10.1109\/TSA.2004.834466","volume":"13","author":"P Pujol","year":"2004","unstructured":"Pujol P, Pol S, Nadeu C, Hagen A, Bourlard H (2004) Comparison and combination of features in a hybrid HMM\/MLP and a HMM\/GMM speech recognition system. IEEE Trans Speech Audio Process 13(1):14\u201322","journal-title":"IEEE Trans Speech Audio Process"},{"key":"4706_CR44","doi-asserted-by":"crossref","unstructured":"Rademacher J, Mertins A. (2006). Auditory filterbank based frequency-warping invariant features for automatic speech recognition.\u00a0Proc. ITG-FachtagungSprachkommunikation, Kiel.","DOI":"10.21437\/Interspeech.2006-428"},{"key":"4706_CR45","doi-asserted-by":"publisher","first-page":"272","DOI":"10.5958\/j.0975-8070.1.3.024","volume":"1","author":"M Rahman","year":"2011","unstructured":"Rahman M, Khatun F (2011) Development of isolated speech recognition system for bangla words. Int J Appl Res Info Tech Comp 1:272","journal-title":"Int J Appl Res Info Tech Comp"},{"issue":"1","key":"4706_CR46","doi-asserted-by":"publisher","first-page":"67","DOI":"10.3329\/diujst.v5i1.4384","volume":"5","author":"MM Rahman","year":"2010","unstructured":"Rahman MM, Khan MF, Moni MA (2010) Speech recognition front-end for segmenting and clustering continuous bangla speech. Daffodil Int Univ J Sci Technol 5(1):67\u201372","journal-title":"Daffodil Int Univ J Sci Technol"},{"key":"4706_CR47","doi-asserted-by":"crossref","unstructured":"Rakib M., Hossain M, Mohammed N ,Rahman F (2022). Bangla-Wave: Improving Bangla Automatic Speech Recognition Utilizing N-gram Language Models.\u00a0arXiv preprint arXiv:2209.12650.","DOI":"10.1145\/3587828.3587872"},{"issue":"1","key":"4706_CR48","doi-asserted-by":"publisher","first-page":"161","DOI":"10.1109\/89.260359","volume":"2","author":"S Renals","year":"1994","unstructured":"Renals S, Morgan N, Bourlard H, Cohen M, Franco H (1994) Connectionist probability estimators in HMM speech recognition. IEEE Trans Speech Audio Process 2(1):161\u2013174","journal-title":"IEEE Trans Speech Audio Process"},{"issue":"5","key":"4706_CR49","doi-asserted-by":"publisher","first-page":"252","DOI":"10.1250\/ast.42.252","volume":"42","author":"AM Samin","year":"2021","unstructured":"Samin AM, Kobir MH, Kibria S, Rahman MS (2021) Deep learning based large vocabulary continuous speech recognition of an under-resourced language Bangladeshi Bangla. Acoust Sci Technol 42(5):252\u2013260","journal-title":"Acoust Sci Technol"},{"key":"4706_CR50","doi-asserted-by":"crossref","unstructured":"Saranya MS, Padmanabhan R, Murthy HA (2018). Replay attack detection in speaker verification using non-voiced segments and decision level feature switching. In\u00a02018 international conference on signal processing and communications (SPCOM) IEEE. pp. 332\u2013336","DOI":"10.1109\/SPCOM.2018.8724469"},{"key":"4706_CR51","unstructured":"Scharenborg O, Ciannella F, Palaskar S, Black A, Metze F, Ondel L, Hasegawa-Johnson M. (2017). Building an ASR system for a low-research language through the adaptation of a high-resource language ASR system: preliminary results.In\u00a0Proc. Internat.Conference on Natural Language, Signal and Speech Processing (ICNLSSP) (pp. 26\u201330)"},{"key":"4706_CR52","doi-asserted-by":"crossref","unstructured":"Scheidl H, Fiel S, Sablatnig R. (2018). Word beam search: A connectionist temporal classification decoding algorithm. In\u00a02018 16th International Conference on Frontiers in Handwriting Recognition (ICFHR)\u00a0(pp. 253\u2013258).IEEE","DOI":"10.1109\/ICFHR-2018.2018.00052"},{"key":"4706_CR53","doi-asserted-by":"crossref","unstructured":"Sen O, Roy P. (2021). A convolutional neural network based approach to recognize bangla spoken digits from speech signal. In\u00a02021 International Conference on Electronics, Communications and Information Technology (ICECIT)\u00a0(pp. 1\u20134).IEEE","DOI":"10.1109\/ICECIT54077.2021.9641322"},{"key":"4706_CR54","doi-asserted-by":"crossref","unstructured":"Shao Y, Jin Z, Wang D, Srinivasan S (2009). An auditory-based feature for robust speech recognition.In\u00a02009 IEEE International Conference on Acoustics, Speech and Signal Processing\u00a0(pp. 4625\u20134628).IEEE","DOI":"10.1109\/ICASSP.2009.4960661"},{"key":"4706_CR55","unstructured":"Showrav TT. (2022). An Automatic Speech Recognition System for Bengali Language based on Wav2Vec2 and Transfer Learning.\u00a0arXiv preprint arXiv:2209.08119"},{"issue":"5","key":"4706_CR56","doi-asserted-by":"publisher","first-page":"525","DOI":"10.1109\/89.784104","volume":"7","author":"R Vergin","year":"1999","unstructured":"Vergin R, O\u2019Shaughnessy D, Farhat A (1999) Generalized mel frequency cepstral coefficients for large-vocabulary speaker-independent continuous-speech recognition. IEEE Trans Speech Audio Process 7(5):525\u2013532","journal-title":"IEEE Trans Speech Audio Process"},{"issue":"8","key":"4706_CR57","doi-asserted-by":"publisher","first-page":"1018","DOI":"10.3390\/sym11081018","volume":"11","author":"D Wang","year":"2019","unstructured":"Wang D, Wang X, Lv S (2019) An overview of end-to-end automatic speech recognition. Symmetry 11(8):1018","journal-title":"Symmetry"},{"key":"4706_CR58","doi-asserted-by":"crossref","unstructured":"Wang X, Xiao Y, Zhu X (2017). Feature Selection Based on CQCCs for Automatic Speaker Verification Spoofing. In\u00a0Interspeech\u00a0(pp. 32\u201336)","DOI":"10.21437\/Interspeech.2017-304"},{"issue":"9","key":"4706_CR59","doi-asserted-by":"publisher","first-page":"2796","DOI":"10.1109\/TCSVT.2018.2869841","volume":"29","author":"B Xiao","year":"2018","unstructured":"Xiao B, Wang K, Bi X, Li W, Han J (2018) 2D-LBP: an enhanced local binary feature for texture image classification. IEEE Trans Circuits Syst Video Technol 29(9):2796\u20132808","journal-title":"IEEE Trans Circuits Syst Video Technol"},{"key":"4706_CR60","unstructured":"Yang Y, Wang P, Wang D (2022). A conformer based acoustic model for robust automatic speech recognition.\u00a0arXiv preprint arXiv:2203.00725."},{"issue":"10","key":"4706_CR61","doi-asserted-by":"publisher","first-page":"4633","DOI":"10.1109\/TNNLS.2017.2771947","volume":"29","author":"H Yu","year":"2017","unstructured":"Yu H, Tan ZH, Ma Z, Martin R, Guo J (2017) Spoofing detection in automatic speaker verification systems using DNN classifiers and dynamic acoustic features. IEEE Trans Neural Netw Learn Syst 29(10):4633\u20134644","journal-title":"IEEE Trans Neural Netw Learn Syst"}],"container-title":["Journal of Ambient Intelligence and Humanized Computing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s12652-023-04706-6.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s12652-023-04706-6\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s12652-023-04706-6.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,12,27]],"date-time":"2023-12-27T11:02:49Z","timestamp":1703674969000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s12652-023-04706-6"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,10,9]]},"references-count":61,"journal-issue":{"issue":"12","published-print":{"date-parts":[[2023,12]]}},"alternative-id":["4706"],"URL":"https:\/\/doi.org\/10.1007\/s12652-023-04706-6","relation":{},"ISSN":["1868-5137","1868-5145"],"issn-type":[{"type":"print","value":"1868-5137"},{"type":"electronic","value":"1868-5145"}],"subject":[],"published":{"date-parts":[[2023,10,9]]},"assertion":[{"value":"28 November 2022","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"19 September 2023","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"9 October 2023","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"I, Ms. Akanksha and Ms. Shelza Dua, on the behalf of all the authors declare that: This study did not receive any finding from any resource. All the authors and the submitted manuscript do not have any conflict of interest.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}},{"value":"This article does not contain any studies with human participants or animal performed by any of the authors.","order":3,"name":"Ethics","group":{"name":"EthicsHeading","label":"Research involving human and animal participants"}}]}}