{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,4]],"date-time":"2026-03-04T14:46:56Z","timestamp":1772635616989,"version":"3.50.1"},"reference-count":42,"publisher":"Springer Science and Business Media LLC","issue":"3","license":[{"start":{"date-parts":[[2026,3,4]],"date-time":"2026-03-04T00:00:00Z","timestamp":1772582400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2026,3,4]],"date-time":"2026-03-04T00:00:00Z","timestamp":1772582400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"funder":[{"DOI":"10.13039\/501100003032","name":"Association Nationale de la Recherche et de la Technologie","doi-asserted-by":"publisher","award":["CIFRE No. 2022\/0524"],"award-info":[{"award-number":["CIFRE No. 2022\/0524"]}],"id":[{"id":"10.13039\/501100003032","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Multimed Tools Appl"],"DOI":"10.1007\/s11042-026-21453-w","type":"journal-article","created":{"date-parts":[[2026,3,4]],"date-time":"2026-03-04T08:05:34Z","timestamp":1772611534000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Text-independent speaker recognition under emotional variations affecting voice"],"prefix":"10.1007","volume":"85","author":[{"given":"Mohamed Alae-Eddine","family":"Eladlani","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5668-6801","authenticated-orcid":false,"given":"Larbi","family":"Boubchir","sequence":"additional","affiliation":[]},{"given":"Khadidja","family":"Benallou","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2026,3,4]]},"reference":[{"key":"21453_CR1","doi-asserted-by":"crossref","unstructured":"Eladlani MA-E, Kaddour SS, Boubchir L, Daachi B (2022) On the use of convolutional neural networks for palm vein recognition. In: 2022 IEEE International Conference on Big Data (Big Data), pp 3586\u20133592. IEEE","DOI":"10.1109\/BigData55660.2022.10020251"},{"issue":"1","key":"21453_CR2","first-page":"15","volume":"10","author":"IM Alsaadi","year":"2021","unstructured":"Alsaadi IM (2021) Study on most popular behavioral biometrics, advantages, disadvantages and recent applications: A review. Int J Sci Technol Res 10(1):15\u201321","journal-title":"Int J Sci Technol Res"},{"key":"21453_CR3","doi-asserted-by":"crossref","unstructured":"H\u00e9bert M (2008) Text-dependent speaker recognition. Springer handbook of speech processing, pp 743\u2013762","DOI":"10.1007\/978-3-540-49127-9_37"},{"issue":"4","key":"21453_CR4","doi-asserted-by":"publisher","first-page":"18","DOI":"10.1109\/79.317924","volume":"11","author":"H Gish","year":"1994","unstructured":"Gish H, Schmidt M (1994) Text-independent speaker identification. IEEE Signal Process Mag 11(4):18\u201332","journal-title":"IEEE Signal Process Mag"},{"key":"21453_CR5","doi-asserted-by":"publisher","first-page":"79236","DOI":"10.1109\/ACCESS.2021.3084299","volume":"9","author":"MM Kabir","year":"2021","unstructured":"Kabir MM, Mridha MF, Shin J, Jahan I, Ohi AQ (2021) A survey of speaker recognition: Fundamental theories, recognition methods and opportunities. IEEE Access 9:79236\u201379263","journal-title":"IEEE Access"},{"key":"21453_CR6","doi-asserted-by":"crossref","unstructured":"Lerato L, Mashao D (2004) Enhancement of gmm speaker identification performance using complementary feature sets. In: 2004 IEEE Africon. 7th Africon Conference in Africa (IEEE Cat. No. 04CH37590), vol 1, pp 257\u201326. IEEE","DOI":"10.1109\/AFRICON.2004.1406669"},{"key":"21453_CR7","unstructured":"Li M, Lu C, Wang A, Narayanan S (2012) Speaker verification using lasso based sparse total variability supervector with plda modeling. In: Proceedings of The 2012 Asia pacific signal and information processing association annual summit and conference, pp 1\u20134"},{"key":"21453_CR8","doi-asserted-by":"crossref","unstructured":"Lukic Y, Vogt C, D\u00fcrr O, Stadelmann T (2016) Speaker identification and clustering using convolutional neural networks. In: 2016 IEEE 26th International Workshop on Machine Learning for Signal Processing (MLSP), pp 1\u20136. IEEE","DOI":"10.1109\/MLSP.2016.7738816"},{"key":"21453_CR9","unstructured":"M\u00e9ndez A, Rodr\u00edguez JP (2019) Speaker identification with deep neural networks. RIIAA"},{"issue":"2","key":"21453_CR10","first-page":"4085","volume":"75","author":"AA Khan","year":"2023","unstructured":"Khan AA, Jahangir R, Alroobaea R, Alyahyan SY, Almulhi AH, Alsafyani M, Wechtaisong C (2023) An efficient text-independent speaker identification using feature fusion and transformer model. Comput Mater Contin 75(2):4085\u20134100","journal-title":"Comput Mater Contin"},{"issue":"8","key":"21453_CR11","doi-asserted-by":"publisher","first-page":"3603","DOI":"10.3390\/app11083603","volume":"11","author":"F Ye","year":"2021","unstructured":"Ye F, Yang J (2021) A deep neural network model for speaker identification. Appl Sci 11(8):3603","journal-title":"Appl Sci"},{"key":"21453_CR12","doi-asserted-by":"publisher","first-page":"51381","DOI":"10.1109\/ACCESS.2024.3385858","volume":"12","author":"JA Pandian","year":"2024","unstructured":"Pandian JA, Thirunavukarasu R, Kotei E (2024) A novel convolutional neural network model for automatic speaker identification from speech signals. IEEE Access 12:51381\u201351394","journal-title":"IEEE Access"},{"issue":"17","key":"21453_CR13","doi-asserted-by":"publisher","first-page":"14463","DOI":"10.1007\/s00521-022-07261-x","volume":"34","author":"A Garain","year":"2022","unstructured":"Garain A, Ray B, Giampaolo F, Velasquez JD, Singh PK, Sarkar R (2022) Grann: feature selection with golden ratio-aided neural network for emotion, gender and speaker identification from voice signals. Neural Comput Appl 34(17):14463\u201314486","journal-title":"Neural Comput Appl"},{"key":"21453_CR14","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2021.116469","volume":"193","author":"AB Nassif","year":"2022","unstructured":"Nassif AB, Shahin I, Elnagar A, Velayudhan D, Alhudhaif A, Polat K (2022) Emotional speaker identification using a novel capsule nets model. Expert Syst Appl 193:116469","journal-title":"Expert Syst Appl"},{"key":"21453_CR15","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2023.119871","volume":"224","author":"S Hamsa","year":"2023","unstructured":"Hamsa S, Shahin I, Iraqi Y, Damiani E, Nassif AB, Werghi N (2023) Speaker identification from emotional and noisy speech using learned voice segregation and speech vgg. Expert Syst Appl 224:119871","journal-title":"Expert Syst Appl"},{"key":"21453_CR16","doi-asserted-by":"crossref","unstructured":"Sefara TJ, Mokgonyane TB (2020) Emotional speaker recognition based on machine and deep learning. In: 2020 2nd International Multidisciplinary Information Technology and Engineering Conference (IMITEC), pp 1\u20138. IEEE","DOI":"10.1109\/IMITEC50163.2020.9334138"},{"key":"21453_CR17","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2023.122244","volume":"238","author":"D Li","year":"2024","unstructured":"Li D, Yang Z, Liu J, Yang H, Wang Z (2024) Emotion embedding framework with emotional self-attention mechanism for speaker recognition. Expert Syst Appl 238:122244","journal-title":"Expert Syst Appl"},{"key":"21453_CR18","first-page":"3172","volume":"2023","author":"T Lertpetchpun","year":"2023","unstructured":"Lertpetchpun T, Chuangsuwanich E (2023) Instance-based temporal normalization for speaker verification. Proc INTERSPEECH 2023:3172\u20133176","journal-title":"Proc INTERSPEECH"},{"key":"21453_CR19","doi-asserted-by":"crossref","unstructured":"Tomar S, Koolagudi SG (2023) Cnn-mfcc model for speaker recognition using emotive speech. In: 2023 IEEE 8th International Conference for Convergence in Technology (I2CT), pp 1\u20137. IEEE","DOI":"10.1109\/I2CT57861.2023.10126402"},{"key":"21453_CR20","unstructured":"Fayek HM (2016) Speech Processing for Machine Learning: Filter banks, Mel-Frequency Cepstral Coefficients (MFCCs) and What\u2019s In-Between. https:\/\/haythamfayek.com\/2016\/04\/21\/speech-processing-for-machine-learning.html"},{"issue":"5","key":"21453_CR21","first-page":"87","volume":"4","author":"OK Hamid","year":"2018","unstructured":"Hamid OK (2018) Frame blocking and windowing speech signal. J Inf Commun Intell Syst (JICIS) 4(5):87\u201394","journal-title":"J Inf Commun Intell Syst (JICIS)"},{"issue":"1995","key":"21453_CR22","first-page":"15","volume":"2","author":"P Heckbert","year":"1995","unstructured":"Heckbert P (1995) Fourier transforms and the fast fourier transform (fft) algorithm. Computer Graphics 2(1995):15\u2013463","journal-title":"Computer Graphics"},{"key":"21453_CR23","doi-asserted-by":"crossref","unstructured":"Kopparapu SK, Laxminarayana M (2010) Choice of mel filter bank in computing mfcc of a resampled speech. In: 10th International Conference on Information Science, Signal Processing and Their Applications (ISSPA 2010), pp 121\u2013124. IEEE","DOI":"10.1109\/ISSPA.2010.5605491"},{"key":"21453_CR24","doi-asserted-by":"crossref","unstructured":"Kopparapu SK, Laxminarayana M (2010) Choice of mel filter bank in computing mfcc of a resampled speech. In: 10th International Conference on Information Science, Signal Processing and Their Applications (ISSPA 2010), pp 121\u2013124. IEEE","DOI":"10.1109\/ISSPA.2010.5605491"},{"issue":"6","key":"21453_CR25","first-page":"74","volume":"15","author":"Y Astuti","year":"2022","unstructured":"Astuti Y, Hidayat R, Bejo A (2022) A mel-weighted spectrogram feature extraction for improved speaker recognition system. Int J Intell Eng Syst 15(6):74\u201382","journal-title":"Int J Intell Eng Syst"},{"issue":"8","key":"21453_CR26","doi-asserted-by":"publisher","first-page":"21","DOI":"10.9790\/3021-04812125","volume":"4","author":"PP Singh","year":"2014","unstructured":"Singh PP, Rani P (2014) An approach to extract feature using mfcc. IOSR J Eng 4(8):21\u201325","journal-title":"IOSR J Eng"},{"key":"21453_CR27","doi-asserted-by":"crossref","unstructured":"Aloysius N, Geetha M (2017) A review on deep convolutional neural networks. In: 2017 International Conference on Communication and Signal Processing (ICCSP), pp 0588\u20130592. IEEE","DOI":"10.1109\/ICCSP.2017.8286426"},{"key":"21453_CR28","doi-asserted-by":"publisher","DOI":"10.1016\/j.dib.2024.110231","volume":"53","author":"KMH Rawf","year":"2024","unstructured":"Rawf KMH, Karim SHT, Abdulrahman AO, Ghafoor KJ (2024) Dataset for the recognition of kurdish sound dialects. Data Brief 53:110231","journal-title":"Data Brief"},{"key":"21453_CR29","doi-asserted-by":"crossref","unstructured":"Rozi A, Wang D, Zhang Z, Zheng TF (2015) An open\/free database and benchmark for uyghur speaker recognition. In: 2015 International Conference Oriental COCOSDA Held Jointly with 2015 Conference on Asian Spoken Language Research and Evaluation (O-COCOSDA\/CASLRE), pp 81\u201385","DOI":"10.1109\/ICSDA.2015.7357869"},{"key":"21453_CR30","doi-asserted-by":"crossref","unstructured":"Bu H, Du J, Na X, Wu B, Zheng H (2017) AISHELL-1: An Open-Source Mandarin Speech Corpus and A Speech Recognition Baseline","DOI":"10.1109\/ICSDA.2017.8384449"},{"key":"21453_CR31","unstructured":"Yamagishi J, Veaux C, MacDonald K et al (2019) Cstr vctk corpus: English multi-speaker corpus for cstr voice cloning toolkit (version 0.92). University of Edinburgh. The Centre for Speech Technology Research (CSTR), pp 271\u2013350"},{"key":"21453_CR32","doi-asserted-by":"crossref","unstructured":"Livingstone SR, Russo FA (2018) The ryerson audio-visual database of emotional speech and song (ravdess): A dynamic, multimodal set of facial and vocal expressions in north american english. PLOS ONE, pp 1\u201335","DOI":"10.1371\/journal.pone.0196391"},{"issue":"4","key":"21453_CR33","doi-asserted-by":"publisher","first-page":"377","DOI":"10.1109\/TAFFC.2014.2336244","volume":"5","author":"H Cao","year":"2014","unstructured":"Cao H, Cooper DG, Keutmann MK, Gur RC, Nenkova A, Verma R (2014) Crema-d: Crowd-sourced emotional multimodal actors dataset. IEEE Trans Affect Comput 5(4):377\u2013390","journal-title":"IEEE Trans Affect Comput"},{"key":"21453_CR34","first-page":"1517","volume":"5","author":"F Burkhardt","year":"2005","unstructured":"Burkhardt F, Paeschke A, Rolfes M, Sendlmeier WF, Weiss B et al (2005) A database of german emotional speech. Interspeech 5:1517\u20131520","journal-title":"Interspeech"},{"issue":"2","key":"21453_CR35","doi-asserted-by":"publisher","first-page":"10","DOI":"10.14500\/aro.10837","volume":"9","author":"KJ Ghafoor","year":"2021","unstructured":"Ghafoor KJ, Rawf KMH, Abdulrahman AO, Taher SH (2021) Kurdish dialect recognition using 1d cnn. ARO-The Scientific Journal of Koya University 9(2):10\u201314","journal-title":"ARO-The Scientific Journal of Koya University"},{"key":"21453_CR36","unstructured":"THUYG-20 database (2026). https:\/\/openslr.org\/22\/ [Accessed: 2025\u201308-08]"},{"key":"21453_CR37","unstructured":"Aishell-1 database (2026). https:\/\/openslr.org\/33\/ [Accessed: 2025\u201308-08]"},{"key":"21453_CR38","unstructured":"VCTK-Corpus database (2026). https:\/\/datashare.ed.ac.uk\/handle\/10283\/3443 [Accessed: 2025\u201308-08]"},{"key":"21453_CR39","doi-asserted-by":"crossref","unstructured":"Ren J, Hu Y, Tai Y-W, Wang C, Xu L, Sun W, Yan Q (2016) Look, listen and learn\u2013a multimodal lstm for speaker identification. In: Proceedings of the AAAI conference on artificial intelligence, vol 30","DOI":"10.1609\/aaai.v30i1.10471"},{"key":"21453_CR40","doi-asserted-by":"crossref","unstructured":"Wang J, Wang K-C, Law MT, Rudzicz F, Brudno M (2019) Centroid-based deep metric learning for speaker recognition. In: ICASSP 2019\u20132019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp 3652\u20133656. IEEE","DOI":"10.1109\/ICASSP.2019.8683393"},{"key":"21453_CR41","doi-asserted-by":"crossref","unstructured":"Eladlani MA-E, Boubchir L, Benallou K (2024) Temporal-spectral analysis for speaker identification and authentication in emotional speech. In: 2024 IEEE\/ACM International Conference on Big Data Computing, Applications and Technologies (BDCAT), pp 354\u2013359. IEEE","DOI":"10.1109\/BDCAT63179.2024.00061"},{"key":"21453_CR42","doi-asserted-by":"crossref","unstructured":"Chicco D (2021) Siamese neural networks: An overview. Artif Neural Netw, pp 73\u201394","DOI":"10.1007\/978-1-0716-0826-5_3"}],"container-title":["Multimedia Tools and Applications"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11042-026-21453-w.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s11042-026-21453-w","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11042-026-21453-w.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,4]],"date-time":"2026-03-04T08:05:50Z","timestamp":1772611550000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s11042-026-21453-w"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,3,4]]},"references-count":42,"journal-issue":{"issue":"3","published-online":{"date-parts":[[2026,3]]}},"alternative-id":["21453"],"URL":"https:\/\/doi.org\/10.1007\/s11042-026-21453-w","relation":{},"ISSN":["1573-7721"],"issn-type":[{"value":"1573-7721","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,3,4]]},"assertion":[{"value":"22 August 2024","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"22 November 2025","order":2,"name":"revised","label":"Revised","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"17 February 2026","order":3,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"4 March 2026","order":4,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"Not applicable","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Competing Interests"}},{"value":"Not applicable","order":3,"name":"Ethics","group":{"name":"EthicsHeading","label":"Ethics Approval and Consent to Participate"}},{"value":"Not applicable","order":4,"name":"Ethics","group":{"name":"EthicsHeading","label":"Consent for Publication"}}],"article-number":"257"}}