{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,9,15]],"date-time":"2024-09-15T17:20:24Z","timestamp":1726420824049},"reference-count":62,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2024,2,1]],"date-time":"2024-02-01T00:00:00Z","timestamp":1706745600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2024,2,1]],"date-time":"2024-02-01T00:00:00Z","timestamp":1706745600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-017"},{"start":{"date-parts":[[2024,2,1]],"date-time":"2024-02-01T00:00:00Z","timestamp":1706745600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"},{"start":{"date-parts":[[2024,2,1]],"date-time":"2024-02-01T00:00:00Z","timestamp":1706745600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-012"},{"start":{"date-parts":[[2024,2,1]],"date-time":"2024-02-01T00:00:00Z","timestamp":1706745600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,2,1]],"date-time":"2024-02-01T00:00:00Z","timestamp":1706745600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-004"}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Journal of Information Security and Applications"],"published-print":{"date-parts":[[2024,2]]},"DOI":"10.1016\/j.jisa.2023.103665","type":"journal-article","created":{"date-parts":[[2023,12,18]],"date-time":"2023-12-18T10:09:22Z","timestamp":1702894162000},"page":"103665","update-policy":"http:\/\/dx.doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":1,"special_numbering":"C","title":["Residual networks for text-independent speaker identification: Unleashing the power of residual learning"],"prefix":"10.1016","volume":"80","author":[{"ORCID":"http:\/\/orcid.org\/0000-0001-9299-1128","authenticated-orcid":false,"given":"Pooja","family":"Gambhir","sequence":"first","affiliation":[]},{"given":"Amita","family":"Dev","sequence":"additional","affiliation":[]},{"given":"Poonam","family":"Bansal","sequence":"additional","affiliation":[]},{"ORCID":"http:\/\/orcid.org\/0000-0001-6117-3464","authenticated-orcid":false,"given":"Deepak Kumar","family":"Sharma","sequence":"additional","affiliation":[]},{"given":"Deepak","family":"Gupta","sequence":"additional","affiliation":[]}],"member":"78","reference":[{"issue":"3","key":"10.1016\/j.jisa.2023.103665_b1","doi-asserted-by":"crossref","first-page":"2830","DOI":"10.1109\/TITS.2021.3119921","article-title":"Speech emotion recognition enhanced traffic efficiency solution for autonomous vehicles in a 5G-enabled space\u2013air\u2013ground integrated intelligent transportation system","volume":"23","author":"Tan","year":"2021","journal-title":"IEEE Trans Intell Transp Syst"},{"year":"2018","series-title":"Feature extraction for temporal signal recognition: An overview","author":"Rida","key":"10.1016\/j.jisa.2023.103665_b2"},{"key":"10.1016\/j.jisa.2023.103665_b3","doi-asserted-by":"crossref","first-page":"4867","DOI":"10.1007\/s11042-018-6808-5","article-title":"A comprehensive overview of feature representation for biometric recognition","volume":"79","author":"Rida","year":"2020","journal-title":"Multimedia Tools Appl"},{"year":"2017","series-title":"Temporal signals classification","author":"Imad","key":"10.1016\/j.jisa.2023.103665_b4"},{"issue":"1","key":"10.1016\/j.jisa.2023.103665_b5","first-page":"1","article-title":"Vector quantization approach for speaker recognition using MFCC and inverted MFCC","volume":"17","author":"Singh","year":"2011","journal-title":"Int J Comput Appl"},{"year":"2015","series-title":"Information theory and statistics: an overview","author":"Commenges","key":"10.1016\/j.jisa.2023.103665_b6"},{"year":"2019","series-title":"Improving noise robustness in speaker identification using a two-stage attention model","author":"Shi","key":"10.1016\/j.jisa.2023.103665_b7"},{"key":"10.1016\/j.jisa.2023.103665_b8","series-title":"AIP conference proceedings, vol. 2222, no. 1","article-title":"PNCC for forensic automatic speaker recognition","author":"Kurian","year":"2020"},{"key":"10.1016\/j.jisa.2023.103665_b9","series-title":"2018 International conference on computing, mathematics and engineering technologies","first-page":"1","article-title":"Analysis of MFCC and BFCC in a speaker identification system","author":"Kumar","year":"2018"},{"key":"10.1016\/j.jisa.2023.103665_b10","series-title":"2012 International conference on computer communication and informatics","first-page":"1","article-title":"A study on feature extraction techniques for text-independent speaker identification","author":"Sumithra","year":"2012"},{"issue":"7","key":"10.1016\/j.jisa.2023.103665_b11","doi-asserted-by":"crossref","first-page":"1315","DOI":"10.1109\/TASLP.2016.2545928","article-title":"Power-normalized cepstral coefficients (PNCC) for robust speech recognition","volume":"24","author":"Kim","year":"2016","journal-title":"IEEE\/ACM Trans Audio Speech Lang Process"},{"key":"10.1016\/j.jisa.2023.103665_b12","doi-asserted-by":"crossref","first-page":"47","DOI":"10.1016\/j.procs.2017.09.075","article-title":"Comparison of text-independent speaker identification systems using GMM and i-vector methods","volume":"115","author":"Nayana","year":"2017","journal-title":"Procedia Comput Sci"},{"key":"10.1016\/j.jisa.2023.103665_b13","doi-asserted-by":"crossref","first-page":"5149","DOI":"10.1007\/s00034-019-01113-1","article-title":"Wavelet-based power normalized spectrum for Hindi phoneme classification","volume":"38","author":"Mishra","year":"2019","journal-title":"Circuits Systems Signal Process"},{"key":"10.1016\/j.jisa.2023.103665_b14","series-title":"2018 Asia-pacific signal and information processing association annual summit and conference","first-page":"1945","article-title":"Novel spectral root cepstral features for replay spoof detection","author":"Tapkir","year":"2018"},{"key":"10.1016\/j.jisa.2023.103665_b15","doi-asserted-by":"crossref","first-page":"880","DOI":"10.1016\/j.procs.2017.12.112","article-title":"Speaker recognition for Hindi speech signal using MFCC-GMM approach","volume":"125","author":"Maurya","year":"2018","journal-title":"Procedia Comput Sci"},{"key":"10.1016\/j.jisa.2023.103665_b16","series-title":"Mobile communication and power engineering: Second international joint conference, AIM\/CCPE 2012, Bangalore, India, April 27\u201328, 2012, Revised selected papers","first-page":"200","article-title":"HMM based enhanced dynamic time warping model for efficient Hindi language speech recognition system","author":"Kumar","year":"2013"},{"key":"10.1016\/j.jisa.2023.103665_b17","unstructured":"Upadhyay S, Sharma SK, Kumar P, Upadhyay A. Performance analysis of Hindi voice for speaker recognition and verification using different feature extraction."},{"key":"10.1016\/j.jisa.2023.103665_b18","series-title":"2013 Annual IEEE India conference","first-page":"1","article-title":"Multilingual speaker recognition on Indian languages","author":"Sarkar","year":"2013"},{"key":"10.1016\/j.jisa.2023.103665_b19","unstructured":"Kumar R, Ranjan R, Singh SK, Kala R, Shukla A, Tiwari R. Multilingual speaker recognition using neural network. In: Proceedings of the frontiers of research on speech and music. 2009, p. 1\u20138."},{"year":"2020","series-title":"Data-driven audio recognition: a supervised dictionary approach","author":"Rida","key":"10.1016\/j.jisa.2023.103665_b20"},{"issue":"1","key":"10.1016\/j.jisa.2023.103665_b21","doi-asserted-by":"crossref","first-page":"72","DOI":"10.1109\/89.365379","article-title":"Robust text-independent speaker identification using Gaussian mixture speaker models","volume":"3","author":"Reynolds","year":"1995","journal-title":"IEEE Trans Speech Audio Process"},{"key":"10.1016\/j.jisa.2023.103665_b22","series-title":"2014 IEEE international conference on acoustics, speech and signal processing","first-page":"1650","article-title":"Large-scale speaker identification","author":"Schmidt","year":"2014"},{"year":"2007","series-title":"HMM speaker identification using linear and non-linear merging techniques","author":"Mahola","key":"10.1016\/j.jisa.2023.103665_b23"},{"key":"10.1016\/j.jisa.2023.103665_b24","series-title":"[Proceedings] ICASSP-92: 1992 IEEE international conference on acoustics, speech, and signal processing, vol. 2","first-page":"161","article-title":"Continuous probabilistic acoustic map for speaker identification","author":"Tseng","year":"1992"},{"year":"2021","series-title":"Voice-based patient registration and information retrieval system","author":"Style","key":"10.1016\/j.jisa.2023.103665_b25"},{"key":"10.1016\/j.jisa.2023.103665_b26","series-title":"2015 International conference on soft computing techniques and implementations","first-page":"41","article-title":"Speaker recognition using MFCC, shifted MFCC with vector quantization and fuzzy","author":"Bansal","year":"2015"},{"issue":"1","key":"10.1016\/j.jisa.2023.103665_b27","doi-asserted-by":"crossref","first-page":"70","DOI":"10.1109\/89.736332","article-title":"Binary quantization of feature vectors for robust text-independent speaker identification","volume":"7","author":"Yuan","year":"1999","journal-title":"IEEE Trans Speech Audio Process"},{"key":"10.1016\/j.jisa.2023.103665_b28","doi-asserted-by":"crossref","unstructured":"Moreno PJ, Ho P. A new SVM approach to speaker identification and verification using probabilistic distance kernels. In: INTERSPEECH. 2003.","DOI":"10.21437\/Eurospeech.2003-760"},{"key":"10.1016\/j.jisa.2023.103665_b29","series-title":"International conference on natural language processing and knowledge engineering, 2003. Proceedings. 2003","first-page":"305","article-title":"Text-independent speaker recognition using probabilistic SVM with GMM adjustment","author":"Hou","year":"2003"},{"key":"10.1016\/j.jisa.2023.103665_b30","series-title":"2017 International conference on energy, communication, data analytics and soft computing","first-page":"3045","article-title":"A novel speaker identification system using feed-forward neural networks","author":"Khanum","year":"2017"},{"issue":"8","key":"10.1016\/j.jisa.2023.103665_b31","first-page":"36","article-title":"Feed forward back propagation neural network for speaker independent speech recognition","volume":"2","author":"Ayshwarya","year":"2014","journal-title":"Int J Ind Electron Electr Eng"},{"year":"2015","series-title":"Advances in computing, communications and informatics (ICACCI)","author":"Wozniak","key":"10.1016\/j.jisa.2023.103665_b32"},{"issue":"1\u20133","key":"10.1016\/j.jisa.2023.103665_b33","doi-asserted-by":"crossref","first-page":"19","DOI":"10.1006\/dspr.1999.0361","article-title":"Speaker verification using adapted Gaussian mixture models","volume":"10","author":"Reynolds","year":"2000","journal-title":"Digit Signal Process"},{"key":"10.1016\/j.jisa.2023.103665_b34","series-title":"Interspeech 2013","article-title":"Augmenting short-term cepstral features with long-term discriminative features for speaker verification of telephone data","author":"Do","year":"2013"},{"key":"10.1016\/j.jisa.2023.103665_b35","doi-asserted-by":"crossref","first-page":"65","DOI":"10.1016\/j.neunet.2021.03.004","article-title":"Speaker recognition based on deep learning: An overview","volume":"140","author":"Bai","year":"2021","journal-title":"Neural Netw"},{"year":"2007","series-title":"Computerized adaptive testing using neural networks","author":"Jafri","key":"10.1016\/j.jisa.2023.103665_b36"},{"key":"10.1016\/j.jisa.2023.103665_b37","article-title":"Generative adversarial nets","volume":"27","author":"Goodfellow","year":"2014","journal-title":"Adv Neural Inf. Process. Syst."},{"key":"10.1016\/j.jisa.2023.103665_b38","series-title":"2017 IEEE international conference on image processing","first-page":"2089","article-title":"Face aging with conditional generative adversarial networks","author":"Antipov","year":"2017"},{"key":"10.1016\/j.jisa.2023.103665_b39","doi-asserted-by":"crossref","first-page":"211","DOI":"10.1016\/j.neucom.2020.08.040","article-title":"Speakergan: Speaker identification with conditional generative adversarial network","volume":"418","author":"Chen","year":"2020","journal-title":"Neurocomputing"},{"key":"10.1016\/j.jisa.2023.103665_b40","doi-asserted-by":"crossref","unstructured":"Mao X, Li Q, Xie H, Lau RY, Wang Z, Paul Smolley S. Least squares generative adversarial networks. In: Proceedings of the IEEE international conference on computer vision. 2017, p. 2794\u2013802.","DOI":"10.1109\/ICCV.2017.304"},{"year":"2019","series-title":"Improving noise robustness in speaker identification using a two-stage attention model","author":"Shi","key":"10.1016\/j.jisa.2023.103665_b41"},{"key":"10.1016\/j.jisa.2023.103665_b42","series-title":"2013 IEEE international conference on acoustics, speech and signal processing","first-page":"7204","article-title":"Analyzing noise robustness of MFCC and GFCC features in speaker identification","author":"Zhao","year":"2013"},{"key":"10.1016\/j.jisa.2023.103665_b43","doi-asserted-by":"crossref","unstructured":"He K, Zhang X, Ren S, Sun J. Deep residual learning for image recognition. In: Proceedings of the IEEE conference on computer vision and pattern recognition. 2016, p. 770\u20138.","DOI":"10.1109\/CVPR.2016.90"},{"key":"10.1016\/j.jisa.2023.103665_b44","series-title":"ICASSP 2019-2019 IEEE international conference on acoustics, speech and signal processing","first-page":"5791","article-title":"Utterance-level aggregation for speaker recognition in the wild","author":"Xie","year":"2019"},{"key":"10.1016\/j.jisa.2023.103665_b45","doi-asserted-by":"crossref","unstructured":"MohammadAmini M, Matrouf D, Bonastre J-F, Dowerah S, Serizel R, Jouvet D. Learning noise robust ResNet-based speaker embedding for speaker recognition. In: Odyssey 2022: The speaker and language recognition workshop. 2022.","DOI":"10.21437\/Odyssey.2022-6"},{"key":"10.1016\/j.jisa.2023.103665_b46","series-title":"2017 25th European signal processing conference","first-page":"543","article-title":"Residual neural networks for speech recognition","author":"Vydana","year":"2017"},{"key":"10.1016\/j.jisa.2023.103665_b47","series-title":"2018 IEEE international conference on acoustics, speech and signal processing","first-page":"4894","article-title":"A corrective learning approach for text-independent speaker verification","author":"Wen","year":"2018"},{"year":"2019","series-title":"Deep learning methods in speaker recognition: a review","author":"Sztah\u00f3","key":"10.1016\/j.jisa.2023.103665_b48"},{"key":"10.1016\/j.jisa.2023.103665_b49","series-title":"2018 IEEE spoken language technology workshop","first-page":"1021","article-title":"Speaker recognition from raw waveform with sincnet","author":"Ravanelli","year":"2018"},{"year":"2019","series-title":"A deep neural network for short-segment speaker recognition","author":"Hajavi","key":"10.1016\/j.jisa.2023.103665_b50"},{"key":"10.1016\/j.jisa.2023.103665_b51","series-title":"ICASSP 2020-2020 IEEE international conference on acoustics, speech and signal processing","first-page":"7579","article-title":"H-vectors: Utterance-level speaker embedding using a hierarchical attention model","author":"Shi","year":"2020"},{"year":"2014","series-title":"Empirical evaluation of gated recurrent neural networks on sequence modeling","author":"Chung","key":"10.1016\/j.jisa.2023.103665_b52"},{"year":"2020","series-title":"Weakly supervised training of hierarchical attention networks for speaker identification","author":"Shi","key":"10.1016\/j.jisa.2023.103665_b53"},{"year":"2020","series-title":"T-vectors: Weakly supervised speaker identification using hierarchical transformer model","author":"Shi","key":"10.1016\/j.jisa.2023.103665_b54"},{"year":"2019","series-title":"Transformer-xl: Attentive language models beyond a fixed-length context","author":"Dai","key":"10.1016\/j.jisa.2023.103665_b55"},{"key":"10.1016\/j.jisa.2023.103665_b56","series-title":"Advances in neural information processing systems, vol. 30","first-page":"6000","article-title":"Attention is all you need","author":"Shazeer","year":"2017"},{"key":"10.1016\/j.jisa.2023.103665_b57","series-title":"2018 IEEE international conference on acoustics, speech and signal processing","first-page":"5359","article-title":"Attention-based models for text-dependent speaker verification","author":"rahman Chowdhury","year":"2018"},{"key":"10.1016\/j.jisa.2023.103665_b58","series-title":"2015 23rd European signal processing conference","first-page":"270","article-title":"A PEM-based frequency-domain Kalman filter for adaptive feedback cancellation","author":"Bernardi","year":"2015"},{"year":"2015","series-title":"Listen, attend and spell","author":"Chan","key":"10.1016\/j.jisa.2023.103665_b59"},{"year":"2017","series-title":"Investigation of using VAE for i-vector speaker verification","author":"Pekhovsky","key":"10.1016\/j.jisa.2023.103665_b60"},{"issue":"21","key":"10.1016\/j.jisa.2023.103665_b61","doi-asserted-by":"crossref","first-page":"11855","DOI":"10.3390\/su132111855","article-title":"A review on indoor environment quality of Indian school classrooms","volume":"13","author":"Kapoor","year":"2021","journal-title":"Sustainability"},{"issue":"2","key":"10.1016\/j.jisa.2023.103665_b62","doi-asserted-by":"crossref","first-page":"169","DOI":"10.1163\/156853806777239922","article-title":"Improving data analysis in herpetology: using Akaike\u2019s Information Criterion (AIC) to assess the strength of biological hypotheses","volume":"27","author":"Mazerolle","year":"2006","journal-title":"Amphibia-Reptilia"}],"container-title":["Journal of Information Security and Applications"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S2214212623002491?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S2214212623002491?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2024,2,29]],"date-time":"2024-02-29T17:51:34Z","timestamp":1709229094000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S2214212623002491"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,2]]},"references-count":62,"alternative-id":["S2214212623002491"],"URL":"https:\/\/doi.org\/10.1016\/j.jisa.2023.103665","relation":{},"ISSN":["2214-2126"],"issn-type":[{"type":"print","value":"2214-2126"}],"subject":[],"published":{"date-parts":[[2024,2]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"Residual networks for text-independent speaker identification: Unleashing the power of residual learning","name":"articletitle","label":"Article Title"},{"value":"Journal of Information Security and Applications","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.jisa.2023.103665","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2023 Elsevier Ltd. All rights reserved.","name":"copyright","label":"Copyright"}],"article-number":"103665"}}