{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,2,21]],"date-time":"2025-02-21T03:20:41Z","timestamp":1740108041384,"version":"3.37.3"},"reference-count":42,"publisher":"Springer Science and Business Media LLC","issue":"25","license":[{"start":{"date-parts":[[2021,9,4]],"date-time":"2021-09-04T00:00:00Z","timestamp":1630713600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2021,9,4]],"date-time":"2021-09-04T00:00:00Z","timestamp":1630713600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"funder":[{"name":"CONACYT INAOE Supercomputing Laboratory\u2019s Deep Learning Platform for Language Technologies","award":["PAPTL 01-008"],"award-info":[{"award-number":["PAPTL 01-008"]}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Neural Comput & Applic"],"published-print":{"date-parts":[[2023,9]]},"DOI":"10.1007\/s00521-021-06408-6","type":"journal-article","created":{"date-parts":[[2021,9,4]],"date-time":"2021-09-04T06:05:52Z","timestamp":1630735552000},"page":"18177-18186","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["Triplet loss-based embeddings for forensic speaker identification in Spanish"],"prefix":"10.1007","volume":"35","author":[{"given":"Emmanuel","family":"Maqueda","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Javier","family":"Alvarez-Jimenez","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Carlos","family":"Mena","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7239-1480","authenticated-orcid":false,"given":"Ivan","family":"Meza","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2021,9,4]]},"reference":[{"issue":"1","key":"6408_CR1","first-page":"109","volume":"53","author":"CG Aitken","year":"2004","unstructured":"Aitken CG, Lucy D (2004) Evaluation of trace evidence in the form of multivariate data. J Royal Statistical Soc: Series C (Appl Statistics) 53(1):109\u2013122","journal-title":"J Royal Statistical Soc: Series C (Appl Statistics"},{"doi-asserted-by":"crossref","unstructured":"Azul D (2013) How do voices become gendered? a critical examination of everyday and medical constructions of the relationship between voice, sex, and gender identity. In: Challenging popular myths of sex, gender and biology, pp. 77\u201388. Springer","key":"6408_CR2","DOI":"10.1007\/978-3-319-01979-6_8"},{"doi-asserted-by":"crossref","unstructured":"Bimbot F, Bonastre JF, Fredouille C, Gravier G, Magrin-Chagnolleau I, Meignier S, Merlin T, Ortega-Garc\u00eda J, Petrovska-Delacr\u00e9taz D, Reynolds DA (2004) A tutorial on text-independent speaker verification. EURASIP J Adv Signal Process 2004(4):101962","key":"6408_CR3","DOI":"10.1155\/S1110865704310024"},{"doi-asserted-by":"crossref","unstructured":"Bredin H (2017) Tristounet: triplet loss for speaker turn embedding. In: 2017 IEEE international conference on acoustics, speech and signal processing (ICASSP), pp. 5430\u20135434. IEEE","key":"6408_CR4","DOI":"10.1109\/ICASSP.2017.7953194"},{"doi-asserted-by":"crossref","unstructured":"Champod C, Vuille J (2011) Scientific evidence in europe-admissibility, evaluation and equality of arms. Int Commentary on Evidence 9(1)","key":"6408_CR5","DOI":"10.2202\/1554-4567.1123"},{"doi-asserted-by":"crossref","unstructured":"Cheng D, Gong Y, Zhou S, Wang J, Zheng N (2016) Person re-identification by multi-channel parts-based cnn with improved triplet loss function. In: Proceedings of the iEEE conference on computer vision and pattern recognition, pp. 1335\u20131344 (2016)","key":"6408_CR6","DOI":"10.1109\/CVPR.2016.149"},{"doi-asserted-by":"crossref","unstructured":"Chopra S, Hadsell R, LeCun Y (2005) Learning a similarity metric discriminatively, with application to face verification. In: 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR\u201905), vol.\u00a01, pp. 539\u2013546. IEEE (2005)","key":"6408_CR7","DOI":"10.1109\/CVPR.2005.202"},{"key":"6408_CR8","doi-asserted-by":"publisher","first-page":"351","DOI":"10.1016\/j.apacoust.2019.07.033","volume":"156","author":"F Ertam","year":"2019","unstructured":"Ertam F (2019) An effective gender recognition approach using voice data via deeper lstm networks. Appl Acoustics 156:351\u2013358","journal-title":"Appl Acoustics"},{"unstructured":"Etzioni O (2018) A hippocratic oath for artificial intelligence practitioners. Tech rep https:\/\/techcrunch.com\/2018\/03\/14\/a-hippocratic-oath-for-artificial-intelligence-practitioners. Accessed 01\/21\/2021","key":"6408_CR9"},{"doi-asserted-by":"crossref","unstructured":"Garcia-Romero D, McCree A (2014) Supervised domain adaptation for i-vector based speaker recognition. In: 2014 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 4047\u20134051. IEEE (2014)","key":"6408_CR10","DOI":"10.1109\/ICASSP.2014.6854362"},{"key":"6408_CR11","doi-asserted-by":"publisher","first-page":"1197","DOI":"10.2307\/1122061","volume":"80","author":"PC Giannelli","year":"1980","unstructured":"Giannelli PC (1980) The admissibility of novel scientific evidence: Frye v. united states, a half-century later. Colum. L. Rev. 80:1197","journal-title":"Colum. L. Rev."},{"doi-asserted-by":"publisher","unstructured":"Gonzalez-Rodriguez J, Fierrez-Aguilar J, Ortega-Garcia J (2003) Forensic identification reporting using automatic speaker recognition systems. In: 2003 IEEE International Conference on Acoustics, Speech, and Signal Processing, 2003. Proceedings. (ICASSP \u201903)., vol.\u00a02, pp. II\u201393. https:\/\/doi.org\/10.1109\/ICASSP.2003.1202302","key":"6408_CR12","DOI":"10.1109\/ICASSP.2003.1202302"},{"unstructured":"Good IJ (1991) Weight of evidence and the bayesian likelihood ratio. The use of statistics in forensic science pp. 85\u2013106","key":"6408_CR13"},{"doi-asserted-by":"crossref","unstructured":"Heigold G, Moreno I, Bengio S, Shazeer N (2016) End-to-end text-dependent speaker verification. In: 2016 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 5115\u20135119. IEEE (2016)","key":"6408_CR14","DOI":"10.1109\/ICASSP.2016.7472652"},{"doi-asserted-by":"crossref","unstructured":"Hoffer E, Ailon N (2015) Deep metric learning using triplet network. In: International Workshop on Similarity-Based Pattern Recognition, pp. 84\u201392. Springer","key":"6408_CR15","DOI":"10.1007\/978-3-319-24261-3_7"},{"doi-asserted-by":"crossref","unstructured":"Huang J, Li Y, Tao J, Lian Z et\u00a0al (2018) Speech emotion recognition from variable-length inputs with triplet loss function. In: Interspeech, pp. 3673\u20133677","key":"6408_CR16","DOI":"10.21437\/Interspeech.2018-1432"},{"issue":"3","key":"6408_CR17","doi-asserted-by":"publisher","first-page":"13","DOI":"10.1109\/MIC.2011.25","volume":"15","author":"D Irani","year":"2011","unstructured":"Irani D, Webb S, Li K, Pu C (2011) Modeling unintended personal-information leakage from multiple online social networks. IEEE Internet Comput 15(3):13\u201319","journal-title":"IEEE Internet Comput"},{"doi-asserted-by":"crossref","unstructured":"Khan U, Hernando Peric\u00e1s FJ (2020) Unsupervised training of siamese networks for speaker verification. In: Interspeech 2020: the 20th Annual Conference of the International Speech Communication Association: 25-29 October 2020: Shanghai, China, pp. 3002\u20133006. International Speech Communication Association (ISCA) (2020)","key":"6408_CR18","DOI":"10.21437\/Interspeech.2020-1882"},{"unstructured":"Li C, Ma X, Jiang B, Li X, Zhang X, Liu X, Cao Y, Kannan A, Zhu Z (2017) Deep speaker: an end-to-end neural speaker embedding system. arXiv preprint arXiv:1705.02304","key":"6408_CR19"},{"issue":"1","key":"6408_CR20","doi-asserted-by":"publisher","first-page":"89","DOI":"10.1017\/S1049096510001939","volume":"44","author":"R McDermott","year":"2011","unstructured":"McDermott R, Hatemi PK (2011) Distinguishing sex and gender. PS. Political Sci Politics 44(1):89\u201392","journal-title":"Political Sci Politics"},{"key":"6408_CR21","volume-title":"Librivox spanish ldc2020s01","author":"CDH Mena","year":"2020","unstructured":"Mena CDH (2020) Librivox spanish ldc2020s01. Linguistic Data Consortium, Web Download. Philadelphia"},{"doi-asserted-by":"crossref","unstructured":"Mo J, Xu L (2020) Self-attention networks for speaker identification with negative-focused triplet loss. In: J Phys: Conference Series, vol. 1601, p. 052004. IOP Publishing","key":"6408_CR22","DOI":"10.1088\/1742-6596\/1601\/5\/052004"},{"issue":"4","key":"6408_CR23","doi-asserted-by":"publisher","first-page":"298","DOI":"10.1016\/j.scijus.2009.09.002","volume":"49","author":"GS Morrison","year":"2009","unstructured":"Morrison GS (2009) Forensic voice comparison and the paradigm shift. Sci Justice 49(4):298\u2013308","journal-title":"Sci Justice"},{"issue":"2","key":"6408_CR24","doi-asserted-by":"publisher","first-page":"242","DOI":"10.1016\/j.specom.2010.09.005","volume":"53","author":"GS Morrison","year":"2011","unstructured":"Morrison GS (2011) A comparison of procedures for the calculation of forensic likelihood ratios from acoustic-phonetic data: multivariate kernel density (mvkd) versus gaussian mixture model-universal background model (gmm-ubm). Speech Commun 53(2):242\u2013256","journal-title":"Speech Commun"},{"key":"6408_CR25","volume-title":"Statistical models in forensic voice comparison","author":"GS Morrison","year":"2020","unstructured":"Morrison GS, Enzinger E, Ramos D, Gonz\u00e1lez-Rodr\u00edguez J, Lozano-D\u00edez A (2020) Statistical models in forensic voice comparison. CRC Press LLC Boca Raton, Florida"},{"unstructured":"Morrison GS, Zhang C, Enzinger E (2019) Forensic speech science. The Bloomsbury Companion to Phonet pp. 183\u2013197","key":"6408_CR26"},{"doi-asserted-by":"crossref","unstructured":"Ouyang K, Liang Y, Liu Y, Rosenblum DS, Yang W (2020) Unsupervised learning of disentangled location embeddings. In: 2020 International Joint Conference on Neural Networks (IJCNN), pp. 1\u20138. IEEE (2020)","key":"6408_CR27","DOI":"10.1109\/IJCNN48605.2020.9207324"},{"issue":"2","key":"6408_CR28","first-page":"6","volume":"5","author":"P Rose","year":"1997","unstructured":"Rose P (1997) Identifying criminals by their voice-the emerging applied discipline of forensic phonetics. Aus Language Matt 5(2):6\u20137","journal-title":"Aus Language Matt"},{"doi-asserted-by":"crossref","unstructured":"Rose P (1998) A forensic phonetic investigation into non-contemporaneous variation in the f-pattern of similar-sounding speakers. In: Fifth International Conference on Spoken Language Processing (1998)","key":"6408_CR29","DOI":"10.21437\/ICSLP.1998-234"},{"doi-asserted-by":"crossref","unstructured":"Rose P (1999) Long-and short-term within-speaker differences in the formants of australian\u201c hello\u201d. J Int Phonet Assoc pp. 1\u201331","key":"6408_CR30","DOI":"10.1017\/S0025100300006393"},{"key":"6408_CR31","doi-asserted-by":"publisher","DOI":"10.1201\/9780203166369","volume-title":"Forensic speaker identification","author":"P Rose","year":"2002","unstructured":"Rose P (2002) Forensic speaker identification. cRc Press"},{"unstructured":"Rose P, Lucy D, Osanai T et al (2004) Linguistic-acoustic forensic speaker identification with likelihood ratios from a multivariate hierarchical random effects model-a non-idiot\u2019s bayes\u2019 approach. Proceedings of the 10th Australian International Conference on Speech Science and Technology (2004)","key":"6408_CR32"},{"doi-asserted-by":"crossref","unstructured":"Safavi S, Gan H, Mporas I, Sotudeh R (2016). Fraud detection in voice-based identity authentication applications and services. In: 2016 IEEE 16th international conference on data mining workshops (ICDMW), pp. 1074\u20131081. IEEE (2016)","key":"6408_CR33","DOI":"10.1109\/ICDMW.2016.0155"},{"issue":"5736","key":"6408_CR34","doi-asserted-by":"publisher","first-page":"892","DOI":"10.1126\/science.1111565","volume":"309","author":"MJ Saks","year":"2005","unstructured":"Saks MJ, Koehler JJ (2005) The coming paradigm shift in forensic identification science. Science 309(5736):892\u2013895","journal-title":"Science"},{"doi-asserted-by":"crossref","unstructured":"Schroff F, Kalenichenko D, Philbin J (2015) Facenet: A unified embedding for face recognition and clustering. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp. 815\u2013823 (2015)","key":"6408_CR35","DOI":"10.1109\/CVPR.2015.7298682"},{"doi-asserted-by":"crossref","unstructured":"Snyder D, Garcia-Romero D, Sell G, Povey D, Khudanpur S (2018) X-vectors: Robust dnn embeddings for speaker recognition. In: 2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 5329\u20135333. IEEE (2018)","key":"6408_CR36","DOI":"10.1109\/ICASSP.2018.8461375"},{"issue":"4","key":"6408_CR37","doi-asserted-by":"publisher","first-page":"1098","DOI":"10.1109\/TLA.2015.7106363","volume":"13","author":"P Univaso","year":"2015","unstructured":"Univaso P, Ale JM, Gurlekian JA (2015) Data mining applied to forensic speaker identification. IEEE Latin Am Transa 13(4):1098\u20131111","journal-title":"IEEE Latin Am Trans"},{"doi-asserted-by":"crossref","unstructured":"Wang J, Song Y, Leung T, Rosenberg C, Wang J, Philbin J, Chen B, Wu Y (2014) Learning fine-grained image similarity with deep ranking. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 1386\u20131393 (2014)","key":"6408_CR38","DOI":"10.1109\/CVPR.2014.180"},{"unstructured":"Yaman S, Pelecanos J, Sarikaya R (2012) Bottleneck features for speaker recognition. In: Odyssey 2012-The Speaker and Language Recognition Workshop","key":"6408_CR39"},{"doi-asserted-by":"crossref","unstructured":"Zhang C, Koishida K (2017) End-to-end text-independent speaker verification with triplet loss on short utterances. In: Interspeech, pp. 1487\u20131491","key":"6408_CR40","DOI":"10.21437\/Interspeech.2017-1608"},{"issue":"9","key":"6408_CR41","doi-asserted-by":"publisher","first-page":"1633","DOI":"10.1109\/TASLP.2018.2831456","volume":"26","author":"C Zhang","year":"2018","unstructured":"Zhang C, Koishida K, Hansen JH (2018) Text-independent speaker verification based on triplet convolutional neural network embeddings. IEEE\/ACM Trans on Audio, Speech, and Language Process 26(9):1633\u20131644","journal-title":"IEEE\/ACM Trans on Audio, Speech, and Language Process"},{"doi-asserted-by":"crossref","unstructured":"Zimmer M (2010) \u201cbut the data is already public\u201d: on the ethics of research in facebook. Ethics Inform Technol 12(4):313\u2013325","key":"6408_CR42","DOI":"10.1007\/s10676-010-9227-5"}],"container-title":["Neural Computing and Applications"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00521-021-06408-6.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s00521-021-06408-6\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00521-021-06408-6.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,9,7]],"date-time":"2024-09-07T19:46:42Z","timestamp":1725738402000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s00521-021-06408-6"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,9,4]]},"references-count":42,"journal-issue":{"issue":"25","published-print":{"date-parts":[[2023,9]]}},"alternative-id":["6408"],"URL":"https:\/\/doi.org\/10.1007\/s00521-021-06408-6","relation":{},"ISSN":["0941-0643","1433-3058"],"issn-type":[{"type":"print","value":"0941-0643"},{"type":"electronic","value":"1433-3058"}],"subject":[],"published":{"date-parts":[[2021,9,4]]},"assertion":[{"value":"1 February 2021","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"17 August 2021","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"4 September 2021","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"The authors declare that they have no conflict of interest.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}}]}}