{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,23]],"date-time":"2026-06-23T08:46:26Z","timestamp":1782204386995,"version":"3.54.5"},"reference-count":28,"publisher":"Springer Science and Business Media LLC","issue":"2","license":[{"start":{"date-parts":[[2024,6,1]],"date-time":"2024-06-01T00:00:00Z","timestamp":1717200000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2024,6,2]],"date-time":"2024-06-02T00:00:00Z","timestamp":1717286400000},"content-version":"vor","delay-in-days":1,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"funder":[{"name":"The National Research, Development and Innovation Fund of Hungary","award":["FK128615"],"award-info":[{"award-number":["FK128615"]}]},{"DOI":"10.13039\/100009567","name":"Budapest University of Technology and Economics","doi-asserted-by":"crossref","id":[{"id":"10.13039\/100009567","id-type":"DOI","asserted-by":"crossref"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Int J Speech Technol"],"published-print":{"date-parts":[[2024,6]]},"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:p>Deep learning has gained widespread adoption in forensic voice comparison in recent years. It is mainly used to learn speaker representations, known as embedding features or vectors. In this work, the effect of identical twins on two state-of-the-art deep speaker embedding methods was investigated with special focus on metrics of forensic voice comparison. The speaker verification performance has been assessed using the likelihood-ratio framework by likelihood ratio cost and equal error rate. The AVTD twin speech dataset was applied. The results show a significant reduction in speaker verification performance when twin samples are present. Neither the adaptation of LR score calculation to twin samples, nor fine-tuning the pre-trained speaker embedding models seemed to be able to leverage this limitation. It was found that the recognition of same or different speakers was possible even in the case of identical twins but the performance dropped greatly. The lowest EER of the best performing model was 3.4% in the case of non-twin; at the same time, EER was 25.3% when twins were present. This doesn\u2019t mean that the presented methods are useless in case of identical twins, but it must be taken into consideration that in case of a higher likelihood-ratio score (which indicates same speakers on the tested samples), the possibility of twins must also be considered in a real casework.<\/jats:p>","DOI":"10.1007\/s10772-024-10108-6","type":"journal-article","created":{"date-parts":[[2024,6,2]],"date-time":"2024-06-02T13:01:37Z","timestamp":1717333297000},"page":"341-351","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":8,"title":["Effect of identical twins on deep speaker embeddings based forensic voice comparison"],"prefix":"10.1007","volume":"27","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-4780-4252","authenticated-orcid":false,"given":"Mohammed Hamzah","family":"Alsalihi","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"D\u00e1vid","family":"Sztah\u00f3","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2024,6,2]]},"reference":[{"key":"10108_CR1","unstructured":"Alsalihi, M. H., & Sztah\u00f3, D. (2023). Effects of emotional speech on forensic voice comparison using deep speaker embeddings. In 19th Hungarian computational linguistics conference (pp. 159\u2013170). http:\/\/acta.bibl.u-szeged.hu\/78411"},{"key":"10108_CR2","doi-asserted-by":"publisher","unstructured":"Akin, C., Kacar, U., & Kirci, M. (2018). A multi-biometrics for twins identification based speech and ear. arXiv preprint. arXiv:1801.09056https:\/\/doi.org\/10.48550\/arXiv.1801.09056","DOI":"10.48550\/arXiv.1801.09056"},{"key":"10108_CR3","doi-asserted-by":"publisher","first-page":"1475","DOI":"10.1007\/s12065-020-00406-8","volume":"14","author":"AKH Al-Ali","year":"2021","unstructured":"Al-Ali, A. K. H., Chandran, V., & Naik, G. R. (2021). Enhanced forensic speaker verification performance using the ICA-EBM algorithm under noisy and reverberant environments. Evolutionary Intelligence, 14, 1475\u20131494. https:\/\/doi.org\/10.1007\/s12065-020-00406-8","journal-title":"Evolutionary Intelligence"},{"key":"10108_CR4","doi-asserted-by":"publisher","first-page":"182","DOI":"10.1016\/j.scijus.2008.02.002","volume":"48","author":"A Ariyaeeinia","year":"2008","unstructured":"Ariyaeeinia, A., Morrison, C., Malegaonkar, A., & Black, S. (2008). A test of the effectiveness of speaker verification for differentiating between identical twins. Science & Justice, 48, 182\u2013186. https:\/\/doi.org\/10.1016\/j.scijus.2008.02.002","journal-title":"Science & Justice"},{"key":"10108_CR5","doi-asserted-by":"publisher","first-page":"230","DOI":"10.1016\/j.csl.2005.08.001","volume":"20","author":"N Br\u00fcmmer","year":"2006","unstructured":"Br\u00fcmmer, N., & Du Preez, J. (2006). Application-independent evaluation of speaker detection. Computer Speech & Language, 20, 230\u2013275. https:\/\/doi.org\/10.1016\/j.csl.2005.08.001","journal-title":"Computer Speech & Language"},{"key":"10108_CR6","doi-asserted-by":"publisher","unstructured":"Cihan, A., Umit, K., & Murvet, K. (2019). Twins recognition using hierarchical score level fusion. arXiv preprint. arXiv:1911.05625https:\/\/doi.org\/10.48550\/arXiv.1911.05625","DOI":"10.48550\/arXiv.1911.05625"},{"key":"10108_CR7","doi-asserted-by":"crossref","unstructured":"Desplanques, B., Thienpondt, J., & Demuynck, K. (2020). ECAPA-TDNN: Emphasized channel attention, propagation and aggregation in TDNN based speaker verification. In Proceedings of Interspeech 2020 (pp. 3830\u20133834).https:\/\/doi.org\/10.21437\/Interspeech.2020-2650","DOI":"10.21437\/Interspeech.2020-2650"},{"key":"10108_CR8","doi-asserted-by":"crossref","unstructured":"Ferragne, E., Guyot Talbot, A., Cecchini, M., Beugnet, M., Delano\u00eb-Brun, E., Georgeton, L., St\u00e9coli, S., Bonastre, J.-F., & Fredouille, C. (2024). Forensic audio and voice analysis: TV series reinforce false popular beliefs. Languages, 9(2), 55.","DOI":"10.3390\/languages9020055"},{"key":"10108_CR9","unstructured":"Frost, D., & Ishihara, S. (2015). Likelihood ratio-based forensic voice comparison on L2 speakers: A case of Hong Kong native male production of English vowels. In Proceedings of Australasian language technology association workshop (pp. 39\u201347). Retrieved from http:\/\/hdl.handle.net\/1885\/104003"},{"key":"10108_CR10","doi-asserted-by":"publisher","first-page":"91","DOI":"10.1016\/j.scijus.2011.03.002","volume":"51","author":"SM Geoffrey","year":"2011","unstructured":"Geoffrey, S. M. (2011). Measuring the validity and reliability of forensic likelihood-ratio systems. Science Justice, 51, 91\u201398. https:\/\/doi.org\/10.1016\/j.scijus.2011.03.002","journal-title":"Science Justice"},{"key":"10108_CR11","doi-asserted-by":"publisher","unstructured":"Geoffrey, S. M., Ewald, E., Ramos, D., Gonz\u00e1lez-Rodr\u00edguez, J., & Lozano-D\u00edez, A. (2020). Statistical models in forensic voice comparison. In Handbook of forensic statistics (p.\u00a047). CRC Press. https:\/\/doi.org\/10.1201\/9780367527709","DOI":"10.1201\/9780367527709"},{"key":"10108_CR12","doi-asserted-by":"publisher","first-page":"307","DOI":"10.1080\/00450618.2016.1259351","volume":"50","author":"S Ishihara","year":"2018","unstructured":"Ishihara, S. (2018). Sensitivity of likelihood-ratio based forensic voice comparison under mismatched conditions of within-speaker sample sizes across databases. Australian Journal of Forensic Sciences, 50, 307\u2013322. https:\/\/doi.org\/10.1080\/00450618.2016.1259351","journal-title":"Australian Journal of Forensic Sciences"},{"key":"10108_CR13","doi-asserted-by":"publisher","unstructured":"van Leeuwen, D. A., & Niko, B. (2007). An introduction to application-independent evaluation of speaker recognition systems. In Speaker classification I: Fundamentals, features, and methods (pp. 330\u2013353). Springer. https:\/\/doi.org\/10.1007\/978-3-540-74200-519","DOI":"10.1007\/978-3-540-74200-519"},{"key":"10108_CR14","doi-asserted-by":"publisher","unstructured":"Li, J., Zhang, L., Guo, D., Zhuo, S., & Sim, T. (2015). Audio-visual twins database. In 2015 International conference on biometrics (ICB) (pp. 493\u2013500). https:\/\/doi.org\/10.1109\/ICB.2015.7139115","DOI":"10.1109\/ICB.2015.7139115"},{"key":"10108_CR15","doi-asserted-by":"publisher","first-page":"242","DOI":"10.1016\/j.specom.2010.09.005","volume":"53","author":"GS Morrison","year":"2011","unstructured":"Morrison, G. S. (2011). A comparison of procedures for the calculation of forensic likelihood ratios from acoustic\u2013phonetic data: Multivariate kernel density (MVKD) versus gaussian mixture model\u2013universal background model (GMM\u2013UBM). Speech Communication, 53, 242\u2013256. https:\/\/doi.org\/10.1016\/j.specom.2010.09.005","journal-title":"Speech Communication"},{"key":"10108_CR16","doi-asserted-by":"publisher","first-page":"119","DOI":"10.1016\/j.specom.2016.07.006","volume":"85","author":"GS Morrison","year":"2016","unstructured":"Morrison, G. S., & Enzinger, E. (2016). Multi-laboratory evaluation of forensic voice comparison systems under conditions reflecting those of a real forensic case (forensic_eval_01)-introduction. Speech Communication, 85, 119\u2013126. https:\/\/doi.org\/10.1016\/j.specom.2016.07.006","journal-title":"Speech Communication"},{"key":"10108_CR17","doi-asserted-by":"publisher","unstructured":"Morrison, G. S., Weber, P., Enzinger, E., Labrador, B., Lozano-D\u00edez, A., Ramos, D., & Gonz\u00e1lez-Rodr\u00edguez, J. (2022). Forensic voice comparison\u2014human-supervised-automatic approach. In Encyclopedia of forensic sciences (3rd ed., Vol. 2, pp. 720\u2013736). Elsevier. https:\/\/doi.org\/10.1016\/B978-0-12-823677-2.00182-3","DOI":"10.1016\/B978-0-12-823677-2.00182-3"},{"key":"10108_CR18","doi-asserted-by":"publisher","DOI":"10.1016\/j.csl.2019.101027","author":"A Nagrani","year":"2019","unstructured":"Nagrani, A., Chung, J. S., Xie, W., &  Zisserman, A. (2019). Voxceleb: Large-scale speaker verification in the wild. Computer Science and Language. https:\/\/doi.org\/10.1016\/j.csl.2019.101027","journal-title":"Computer Science and Language"},{"key":"10108_CR19","doi-asserted-by":"publisher","unstructured":"Ravanelli, M., Parcollet, T., Plantinga, P., Rouhe, A., Cornell, S., Lugosch, L., Subakan, C., Dawalatabad, N., Heba, A., Zhong, J., Chou, J.-C., Yeh, S.-L., Fu, S.-W., Liao, C.-F., Rastorgueva, E., Grondin, F., Aris, W., Na, H., Gao, Y., \u2026 Bengio, Y. (2021). Speechbrain: A general-purpose speech toolkit. arXiv preprint. arXiv:2106.04624https:\/\/doi.org\/10.48550\/arXiv.2106.04624","DOI":"10.48550\/arXiv.2106.04624"},{"key":"10108_CR20","doi-asserted-by":"publisher","first-page":"385","DOI":"10.1016\/j.measurement.2018.10.057","volume":"134","author":"SB Sabatier","year":"2019","unstructured":"Sabatier, S. B., Trester, M. R., & Dawson, J. M. (2019). Measurement of the impact of identical twin voices on automatic speaker recognition. Measurement, 134, 385\u2013389. https:\/\/doi.org\/10.1016\/j.measurement.2018.10.057","journal-title":"Measurement"},{"key":"10108_CR21","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1016\/j.wocn.2019.04.001","volume":"75","author":"E San Segundo","year":"2019","unstructured":"San Segundo, E., & Yang, J. (2019). Formant dynamics of spanish vocalic sequences in related speakers: A forensic-voice-comparison investigation. Journal of Phonetics, 75, 1\u201326. https:\/\/doi.org\/10.1016\/j.wocn.2019.04.001","journal-title":"Journal of Phonetics"},{"key":"10108_CR22","doi-asserted-by":"crossref","unstructured":"Sigona, F., & Grimaldi, M. (2023). Validation of an ECAPA-TDNN system for forensic automatic speaker recognition under case work conditions. arXiv preprint. http:\/\/arxiv.org\/abs\/2305.10805","DOI":"10.1016\/j.specom.2024.103045"},{"key":"10108_CR23","doi-asserted-by":"publisher","unstructured":"Snyder, D., Garcia-Romero, D., Povey, D., & Khudanpur, S. (2017). Deep neural network embeddings for text-independent speaker verification. In Interspeech (pp. 999\u20131003). https:\/\/doi.org\/10.21437\/Interspeech.2017-620","DOI":"10.21437\/Interspeech.2017-620"},{"key":"10108_CR24","doi-asserted-by":"publisher","unstructured":"Stewart, M. G., & Enzinger, E. (2019). Introduction to forensic voice comparison. In The Routledge handbook of phonetics (pp. 599\u2013634). Routledge. https:\/\/doi.org\/10.4324\/9780429056253-22","DOI":"10.4324\/9780429056253-22"},{"key":"10108_CR25","doi-asserted-by":"publisher","first-page":"871","DOI":"10.1111\/1556-4029.15250","volume":"68","author":"D Sztah\u00f3","year":"2023","unstructured":"Sztah\u00f3, D., & Fejes, A. (2023). Effects of language mismatch in automatic forensic voice comparison using deep learning embeddings. Journal of Forensic Sciences, 68, 871\u2013883. https:\/\/doi.org\/10.1111\/1556-4029.15250","journal-title":"Journal of Forensic Sciences"},{"key":"10108_CR26","doi-asserted-by":"publisher","first-page":"310","DOI":"10.3311\/PPee.17024","volume":"65","author":"D Sztah\u00f3","year":"2021","unstructured":"Sztah\u00f3, D., Szasz\u00e1k, G., & Beke, A. (2021). Deep learning methods in speaker recognition: A review. Periodica Polytechnica Electrical Engineering and Computer Science, 65, 310\u2013328. https:\/\/doi.org\/10.3311\/PPee.17024","journal-title":"Periodica Polytechnica Electrical Engineering and Computer Science"},{"key":"10108_CR27","doi-asserted-by":"publisher","first-page":"38","DOI":"10.1016\/j.specom.2022.01.009","volume":"138","author":"BX Wang","year":"2022","unstructured":"Wang, B. X., Hughes, V., & Foulkes, P. (2022). The effect of sampling variability on systems and individual speakers in likelihood ratio-based forensic voice comparison. Speech Communication, 138, 38\u201349. https:\/\/doi.org\/10.1016\/j.specom.2022.01.009","journal-title":"Speech Communication"},{"key":"10108_CR28","doi-asserted-by":"publisher","first-page":"824","DOI":"10.1109\/TIFS.2020.3023818","volume":"16","author":"L Zheng","year":"2020","unstructured":"Zheng, L., Li, J., Sun, M., Zhang, X., & Zheng, T. F. (2020). When automatic voice disguise meets automatic speaker verification. IEEE Transactions on Information Forensics and Security, 16, 824\u2013837. https:\/\/doi.org\/10.1109\/TIFS.2020.3023818","journal-title":"IEEE Transactions on Information Forensics and Security"}],"container-title":["International Journal of Speech Technology"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10772-024-10108-6.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s10772-024-10108-6","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10772-024-10108-6.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,6,23]],"date-time":"2026-06-23T07:46:42Z","timestamp":1782200802000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s10772-024-10108-6"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,6]]},"references-count":28,"journal-issue":{"issue":"2","published-print":{"date-parts":[[2024,6]]}},"alternative-id":["10108"],"URL":"https:\/\/doi.org\/10.1007\/s10772-024-10108-6","relation":{},"ISSN":["1381-2416","1572-8110"],"issn-type":[{"value":"1381-2416","type":"print"},{"value":"1572-8110","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,6]]},"assertion":[{"value":"6 February 2024","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"9 May 2024","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"2 June 2024","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}]}}