{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,8,3]],"date-time":"2025-08-03T03:59:51Z","timestamp":1754193591447,"version":"3.37.3"},"reference-count":43,"publisher":"Springer Science and Business Media LLC","issue":"5","license":[{"start":{"date-parts":[[2022,1,16]],"date-time":"2022-01-16T00:00:00Z","timestamp":1642291200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2022,1,16]],"date-time":"2022-01-16T00:00:00Z","timestamp":1642291200000},"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":["Circuits Syst Signal Process"],"published-print":{"date-parts":[[2022,5]]},"DOI":"10.1007\/s00034-021-01915-2","type":"journal-article","created":{"date-parts":[[2022,1,16]],"date-time":"2022-01-16T00:03:06Z","timestamp":1642291386000},"page":"2825-2844","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":6,"title":["Weighted X-Vectors for Robust Text-Independent Speaker Verification with Multiple Enrollment Utterances"],"prefix":"10.1007","volume":"41","author":[{"given":"Mohsen","family":"Mohammadi","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7367-4765","authenticated-orcid":false,"given":"Hamid Reza","family":"Sadegh Mohammadi","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2022,1,16]]},"reference":[{"key":"1915_CR1","doi-asserted-by":"publisher","first-page":"15400","DOI":"10.1109\/ACCESS.2017.2728801","volume":"5","author":"AKH Al-Ali","year":"2017","unstructured":"A.K.H. Al-Ali, D. Dean, B. Senadji, V. Chandran, G.R. Naik, Enhanced forensic speaker verification using a combination of DWT and MFCC feature warping in the presence of noise and reverberation conditions. IEEE Access 5, 15400\u201315413 (2017). https:\/\/doi.org\/10.1109\/ACCESS.2017.2728801","journal-title":"IEEE Access"},{"key":"1915_CR2","doi-asserted-by":"publisher","unstructured":"G. Biagetti, P. Crippa, L. Falaschetti, S. Orcioni, C. Turchetti, Speaker identification in noisy conditions using short sequences of speech frames, in International Conference on Intelligent Decision Technologies (2017), pp. 43\u201352. https:\/\/doi.org\/10.1007\/978-3-319-59424-8_5","DOI":"10.1007\/978-3-319-59424-8_5"},{"key":"1915_CR3","doi-asserted-by":"crossref","unstructured":"P.M. Bousquet, D. Matrouf, J.F. Bonastre, Intersession compensation and scoring methods in the i-vectors space for speaker recognition, in INTERSPEECH (2011), pp. 485\u2013488","DOI":"10.21437\/Interspeech.2011-137"},{"key":"1915_CR4","doi-asserted-by":"publisher","unstructured":"J.S. Chung, A. Nagrani, A. Zisserman, Voxceleb2: Deep speaker recognition, in INTERSPEECH (2018), pp. 1086\u20131090. https:\/\/doi.org\/10.21437\/Interspeech.2018-1929","DOI":"10.21437\/Interspeech.2018-1929"},{"issue":"4","key":"1915_CR5","doi-asserted-by":"publisher","first-page":"778","DOI":"10.1109\/TASL.2010.2064307","volume":"19","author":"N Dehak","year":"2011","unstructured":"N. Dehak, P. Kenny, R. Dehak, P. Dumouchel, P. Ouellet, Front-end factor analysis for speaker verification. IEEE Trans. Audio Speech Language Process 19(4), 778\u2013798 (2011). https:\/\/doi.org\/10.1109\/TASL.2010.2064307","journal-title":"IEEE Trans. Audio Speech Language Process"},{"key":"1915_CR6","unstructured":"\u201cFreesound.org,\u201d http:\/\/freesound.org"},{"key":"1915_CR7","doi-asserted-by":"crossref","unstructured":"D. Garcia-Romero, C.Y. Espy-Wilson, Analysis of i-vector length normalization in speaker recognition systems, in INTERSPEECH (2011), pp. 249\u2013252","DOI":"10.21437\/Interspeech.2011-53"},{"key":"1915_CR8","doi-asserted-by":"publisher","unstructured":"D. Garcia-Romero, X. Zhou, C.Y. Espy-Wilson, Multicondition training of Gaussian PLDA models in i-vector space for noise and reverberation robust speaker recognition, in IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) (2012), pp. 4257\u20134260. https:\/\/doi.org\/10.1109\/ICASSP.2012.6288859","DOI":"10.1109\/ICASSP.2012.6288859"},{"key":"1915_CR9","unstructured":"C.S. Greenberg, D. Bans\u00e9, G.R. Doddington, D. Garcia-Romero, J.J. Godfrey, T. Kinnunen, A.F. Martin, A. McCree, M. Przybocki, D.A. Reynolds, The NIST 2014 speaker recognition i-vector machine learning challenge, in The Speaker and Language Recognition Workshop (Odyssey) (2014), pp. 224\u2013230"},{"key":"1915_CR10","doi-asserted-by":"publisher","DOI":"10.1016\/j.compeleceng.2021.107005","volume":"90","author":"RM Hanifa","year":"2021","unstructured":"R.M. Hanifa, K. Isa, S. Mohamad, A review on speaker recognition: Technology and challenges. Comput. Electr. Eng. 90, 107005 (2021). https:\/\/doi.org\/10.1016\/j.compeleceng.2021.107005","journal-title":"Comput. Electr. Eng."},{"issue":"6","key":"1915_CR11","doi-asserted-by":"publisher","first-page":"74","DOI":"10.1109\/MSP.2015.2462851","volume":"32","author":"JHL Hansen","year":"2015","unstructured":"J.H.L. Hansen, T. Hasan, Speaker recognition by machines and humans: a tutorial review. IEEE Signal Process. Mag. 32(6), 74\u201399 (2015). https:\/\/doi.org\/10.1109\/MSP.2015.2462851","journal-title":"IEEE Signal Process. Mag."},{"key":"1915_CR12","doi-asserted-by":"publisher","first-page":"2067","DOI":"10.1109\/TASL.2010.2041110","volume":"18","author":"G Hu","year":"2010","unstructured":"G. Hu, D. Wang, A tandem algorithm for pitch estimation and voiced speech segregation. IEEE Trans. Audio Speech Lang. Process. 18, 2067\u20132079 (2010). https:\/\/doi.org\/10.1109\/TASL.2010.2041110","journal-title":"IEEE Trans. Audio Speech Lang. Process."},{"key":"1915_CR13","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1186\/s13636-021-00204-9","volume":"2021","author":"Y Ke","year":"2021","unstructured":"Y. Ke, A. Li, C. Zheng, R. Peng, X. Li, Low-complexity artificial noise suppression methods for deep learning-based speech enhancement algorithms. EURASIP J. Audio Speech Music Process. 2021, 1\u201315 (2021). https:\/\/doi.org\/10.1186\/s13636-021-00204-9","journal-title":"EURASIP J. Audio Speech Music Process."},{"key":"1915_CR14","unstructured":"P. Kenny, Bayesian speaker verification with heavy-tailed priors, in The Speaker and Language Recognition Workshop (Odyssey) (2010), pp. 1\u201310"},{"key":"1915_CR15","doi-asserted-by":"publisher","first-page":"1990","DOI":"10.1109\/TASL.2012.2191960","volume":"20","author":"T Kinnunen","year":"2012","unstructured":"T. Kinnunen, R. Saeidi, F. Sedlak, L. Kong Aik, J. Sandberg, M. Hansson-Sandsten, H. Li, Low-variance multitaper MFCC features: A case study in robust speaker verification. IEEE Trans. Audio Speech Language Process. 20, 1990\u20132001 (2012). https:\/\/doi.org\/10.1109\/TASL.2012.2191960","journal-title":"IEEE Trans. Audio Speech Language Process."},{"key":"1915_CR16","doi-asserted-by":"publisher","unstructured":"Z. Lei, Y. Wan, J. Luo, Y. Yang, Mahalanobis metric scoring learned from weighted pairwise constraints in I-vector speaker recognition system, in INTERSPEECH (2016), pp. 1815\u20131819. https:\/\/doi.org\/10.21437\/Interspeech.2016-1071","DOI":"10.21437\/Interspeech.2016-1071"},{"key":"1915_CR17","doi-asserted-by":"publisher","unstructured":"N. Li, M. Mak, SNR-invariant PLDA with multiple speaker subspaces, in IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) (2016), pp. 5565\u20135569. https:\/\/doi.org\/10.1109\/ICASSP.2016.7472742","DOI":"10.1109\/ICASSP.2016.7472742"},{"key":"1915_CR18","doi-asserted-by":"publisher","first-page":"107","DOI":"10.1016\/j.csl.2017.12.001","volume":"49","author":"E Lleida","year":"2018","unstructured":"E. Lleida, L.J. Rodriguez-Fuentes, Speaker and language recognition and characterization: introduction to the CSL special issue. Comput. Speech Lang. 49, 107\u2013120 (2018). https:\/\/doi.org\/10.1016\/j.csl.2017.12.001","journal-title":"Comput. Speech Lang."},{"key":"1915_CR19","doi-asserted-by":"publisher","unstructured":"M. McLaren, Y. Lei, L. Ferrer, Advances in deep neural network approaches to speaker recognition, in IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) (2015), pp. 4814\u20134818. https:\/\/doi.org\/10.1109\/ICASSP.2015.7178885","DOI":"10.1109\/ICASSP.2015.7178885"},{"key":"1915_CR20","doi-asserted-by":"publisher","unstructured":"M. McLaren, D. Van Leeuwen, Source-normalised-and-weighted LDA for robust speaker recognition using i-vectors, in IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) (2011), pp. 5456\u20135459. https:\/\/doi.org\/10.1109\/ICASSP.2011.5947593","DOI":"10.1109\/ICASSP.2011.5947593"},{"key":"1915_CR21","unstructured":"N. McLaughlin, J. Ming, D. Crookes, Speaker recognition in noisy conditions with limited training data, in 19th European Signal Processing Conference (2011), pp. 1294\u20131298."},{"key":"1915_CR22","doi-asserted-by":"publisher","first-page":"1711","DOI":"10.1109\/TASL.2007.899278","volume":"15","author":"J Ming","year":"2007","unstructured":"J. Ming, T.J. Hazen, J.R. Glass, D.A. Reynolds, Robust speaker recognition in noisy conditions. IEEE Trans. Audio Speech Lang. Process. 15, 1711\u20131723 (2007). https:\/\/doi.org\/10.1109\/TASL.2007.899278","journal-title":"IEEE Trans. Audio Speech Lang. Process."},{"key":"1915_CR23","doi-asserted-by":"publisher","unstructured":"M. Mohammadamini, D. Matrouf, P.-G. No\u00e9, Denoising x-vectors for Robust Speaker Recognition, in The Speaker and Language Recognition Workshop (Odyssey) (2020), pp. 75\u201380. https:\/\/doi.org\/10.21437\/odyssey.2020-11","DOI":"10.21437\/odyssey.2020-11"},{"key":"1915_CR24","doi-asserted-by":"publisher","unstructured":"M. Mohammadi, H.R. Sadegh Mohammadi, Weighted I-vector based text-independent speaker verification system, in Iranian Conference on Electrical Engineering (ICEE) (2019), pp. 1647\u20131653. https:\/\/doi.org\/10.1109\/IranianCEE.2019.8786420","DOI":"10.1109\/IranianCEE.2019.8786420"},{"key":"1915_CR25","doi-asserted-by":"publisher","DOI":"10.1016\/j.csl.2019.101027","volume":"60","author":"A Nagrani","year":"2020","unstructured":"A. Nagrani, J.S. Chung, W. Xie, A. Zisserman, Voxceleb: Large-scale speaker verification in the wild. Comput. Speech Lang. 60, 101027 (2020). https:\/\/doi.org\/10.1016\/j.csl.2019.101027","journal-title":"Comput. Speech Lang."},{"key":"1915_CR26","unstructured":"NIST 2016 speaker recognition evaluation plan, https:\/\/www.nist.gov\/itl\/iad\/mig\/speaker-recognition. Accessed 2016"},{"key":"1915_CR27","doi-asserted-by":"publisher","first-page":"403","DOI":"10.1016\/j.csl.2019.06.004","volume":"58","author":"O Novotn\u00fd","year":"2019","unstructured":"O. Novotn\u00fd, O. Plchot, O. Glembek, L. Burget, Analysis of DNN speech signal enhancement for robust speaker recognition. Comput. Speech Lang. 58, 403\u2013421 (2019). https:\/\/doi.org\/10.1016\/j.csl.2019.06.004","journal-title":"Comput. Speech Lang."},{"key":"1915_CR28","unstructured":"D. Povey, A. Ghoshal, G. Boulianne, L. Burget, O. Glembek, N. Goel, M. Hannemann, P. Motlicek, Y. Qian, P. Schwarz, J. Silovsky, The Kaldi speech recognition toolkit, in IEEE workshop on automatic speech recognition and understanding (ASRU) (2011)"},{"key":"1915_CR29","doi-asserted-by":"publisher","first-page":"93","DOI":"10.1016\/j.dsp.2014.05.001","volume":"31","author":"P Rajan","year":"2014","unstructured":"P. Rajan, A. Afanasyev, V. Hautam\u00e4ki, T. Kinnunen, From single to multiple enrollment i-vectors: practical PLDA scoring variants for speaker verification. Digital Signal Processing 31, 93\u2013101 (2014). https:\/\/doi.org\/10.1016\/j.dsp.2014.05.001","journal-title":"Digital Signal Processing"},{"key":"1915_CR30","doi-asserted-by":"crossref","unstructured":"P. Rajan, T. Kinnunen, V. Hautam\u00e4ki, Effect of multicondition training on i-vector PLDA configurations for speaker recognition, in INTERSPEECH (2013), pp. 3694\u20133697","DOI":"10.21437\/Interspeech.2013-693"},{"key":"1915_CR31","doi-asserted-by":"publisher","unstructured":"M. Ravanelli, Y. Bengio, Speaker recognition from raw waveform with SincNet, in IEEE Spoken Language Technology Workshop (SLT) (2018), pp. 1021\u20131028. https:\/\/doi.org\/10.1109\/SLT.2018.8639585","DOI":"10.1109\/SLT.2018.8639585"},{"issue":"10","key":"1915_CR32","doi-asserted-by":"publisher","first-page":"1671","DOI":"10.1109\/LSP.2015.2420092","volume":"22","author":"F Richardson","year":"2015","unstructured":"F. Richardson, D. Reynolds, N. Dehak, Deep neural network approaches to speaker and language recognition. IEEE Signal Process. Lett. 22(10), 1671\u20131675 (2015). https:\/\/doi.org\/10.1109\/LSP.2015.2420092","journal-title":"IEEE Signal Process. Lett."},{"key":"1915_CR33","doi-asserted-by":"publisher","unstructured":"M. Rouvier, R. Dufour, P.-M. Bousquet, Review of different robust x-vector extractors for speaker verification, in 28th European Signal Processing Conference (EUSIPCO) (2020), pp. 1\u20135. https:\/\/doi.org\/10.23919\/Eusipco47968.2020.9287426","DOI":"10.23919\/Eusipco47968.2020.9287426"},{"key":"1915_CR34","unstructured":"Y. Shi, Q. Huang, T. Hain, Improving noise robustness in speaker identification using a two-stage attention model. arXiv preprint arXiv:1909.11200v2, (2019)"},{"key":"1915_CR35","doi-asserted-by":"publisher","unstructured":"D. Snyder, D. Garcia-Romero, D. Povey, S. Khudanpur, Deep neural network embeddings for text-independent speaker verification, in INTERSPEECH (2017), pp. 999\u20131003. https:\/\/doi.org\/10.21437\/Interspeech.2017-620","DOI":"10.21437\/Interspeech.2017-620"},{"key":"1915_CR36","doi-asserted-by":"publisher","unstructured":"D. Snyder, D. Garcia-Romero, G. Sell, D. Povey, S. Khudanpur, X-Vectors: Robust DNN embeddings for speaker recognition, in IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) (2018), pp. 5329\u20135333. https:\/\/doi.org\/10.1109\/ICASSP.2018.8461375","DOI":"10.1109\/ICASSP.2018.8461375"},{"issue":"3","key":"1915_CR37","doi-asserted-by":"publisher","first-page":"247","DOI":"10.1016\/0167-6393(93)90095-3","volume":"12","author":"A Varga","year":"1993","unstructured":"A. Varga, H.J. Steeneken, Assessment for automatic speech recognition: II NOISEX-92: a database and an experiment to study the effect of additive noise on speech recognition systems. Speech Commun. 12(3), 247\u2013251 (1993). https:\/\/doi.org\/10.1016\/0167-6393(93)90095-3","journal-title":"Speech Commun."},{"key":"1915_CR38","doi-asserted-by":"publisher","unstructured":"E. Variani, X. Lei, E. McDermott, I.L. Moreno, J. Gonzalez-Dominguez, Deep neural networks for small footprint text-dependent speaker verification, in IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) (2014), pp. 4052\u20134056. https:\/\/doi.org\/10.1109\/ICASSP.2014.6854363","DOI":"10.1109\/ICASSP.2014.6854363"},{"key":"1915_CR39","unstructured":"B. Vesnicer, J. Zganec-Gros, S. Dobrisek, V. Struc, Incorporating duration information into i-vector based speaker recognition systems, in The Speaker and Language Recognition Workshop (Odyssey) (2014), pp. 241\u2013248"},{"key":"1915_CR40","doi-asserted-by":"publisher","first-page":"226","DOI":"10.1016\/j.compeleceng.2015.09.003","volume":"48","author":"H Zeinali","year":"2015","unstructured":"H. Zeinali, A. Mirian, H. Sameti, B. BabaAli, Non-speaker information reduction from cosine similarity scoring in i-vector based speaker verification. Comput. Electr. Eng. 48, 226\u2013238 (2015). https:\/\/doi.org\/10.1016\/j.compeleceng.2015.09.003","journal-title":"Comput. Electr. Eng."},{"key":"1915_CR41","unstructured":"H. Zeinali, S. Wang, A. Silnova, P. Mat\u011bjka, O. Plchot, But system description to voxceleb speaker recognition challenge 2019. arXiv preprint arXiv:1910.12592, (2019)"},{"key":"1915_CR42","doi-asserted-by":"crossref","unstructured":"C. Zeng, X. Wang, E. Cooper, J. Yamagishi, Attention back-end for automatic speaker verification with multiple enrollment utterances. arXiv preprint arXiv:2104.01541 (2021)","DOI":"10.1109\/ICASSP43922.2022.9746688"},{"key":"1915_CR43","doi-asserted-by":"publisher","unstructured":"J. Zhou, T. Jiang, Q. Hong, L. Li, Extraction of noise-robust speaker embedding based on generative adversarial networks, in Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC) (2019), pp. 1641\u20131645. https:\/\/doi.org\/10.1109\/APSIPAASC47483.2019.9023295","DOI":"10.1109\/APSIPAASC47483.2019.9023295"}],"container-title":["Circuits, Systems, and Signal Processing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00034-021-01915-2.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s00034-021-01915-2\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00034-021-01915-2.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,1,23]],"date-time":"2023-01-23T03:34:55Z","timestamp":1674444895000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s00034-021-01915-2"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,1,16]]},"references-count":43,"journal-issue":{"issue":"5","published-print":{"date-parts":[[2022,5]]}},"alternative-id":["1915"],"URL":"https:\/\/doi.org\/10.1007\/s00034-021-01915-2","relation":{},"ISSN":["0278-081X","1531-5878"],"issn-type":[{"type":"print","value":"0278-081X"},{"type":"electronic","value":"1531-5878"}],"subject":[],"published":{"date-parts":[[2022,1,16]]},"assertion":[{"value":"17 April 2021","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"16 November 2021","order":2,"name":"revised","label":"Revised","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"18 November 2021","order":3,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"16 January 2022","order":4,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"The authors declare no competing financial interests.","order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Competing interests"}}]}}