{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,5,3]],"date-time":"2025-05-03T13:43:40Z","timestamp":1746279820498,"version":"3.40.3"},"publisher-location":"Cham","reference-count":37,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783030916985"},{"type":"electronic","value":"9783030916992"}],"license":[{"start":{"date-parts":[[2021,1,1]],"date-time":"2021-01-01T00:00:00Z","timestamp":1609459200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2021,1,1]],"date-time":"2021-01-01T00:00:00Z","timestamp":1609459200000},"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":[],"published-print":{"date-parts":[[2021]]},"DOI":"10.1007\/978-3-030-91699-2_39","type":"book-chapter","created":{"date-parts":[[2021,11,27]],"date-time":"2021-11-27T05:03:29Z","timestamp":1637989409000},"page":"572-585","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["Speech2Phone: A Novel and Efficient Method for Training Speaker Recognition Models"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-0160-7173","authenticated-orcid":false,"given":"Edresson","family":"Casanova","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5647-0891","authenticated-orcid":false,"given":"Arnaldo","family":"Candido Junior","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9637-9657","authenticated-orcid":false,"given":"Christopher","family":"Shulby","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5885-6747","authenticated-orcid":false,"given":"Frederico Santos","family":"de Oliveira","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2099-5004","authenticated-orcid":false,"given":"Lucas Rafael Stefanel","family":"Gris","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8709-8765","authenticated-orcid":false,"given":"Hamilton Pereira","family":"da Silva","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5108-2630","authenticated-orcid":false,"given":"Sandra Maria","family":"Alu\u00edsio","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2059-9463","authenticated-orcid":false,"given":"Moacir Antonelli","family":"Ponti","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2021,11,28]]},"reference":[{"key":"39_CR1","unstructured":"Abadi, M., et al.: TensorFlow: large-scale machine learning on heterogeneous distributed systems. arXiv preprint arXiv:1603.04467 (2016)"},{"key":"39_CR2","unstructured":"Ardila, R., et al.: Common voice: a massively-multilingual speech corpus. In: Proceedings of the 12th Language Resources and Evaluation Conference, pp. 4218\u20134222 (2020)"},{"key":"39_CR3","unstructured":"Arik, S., Chen, J., Peng, K., Ping, W., Zhou, Y.: Neural voice cloning with a few samples. In: Advances in Neural Information Processing Systems, pp. 10019\u201310029 (2018)"},{"key":"39_CR4","unstructured":"Bowater, R.J., Porter, L.L.: Voice recognition of telephone conversations. US Patent 6,278,772 (21 August 2001)"},{"key":"39_CR5","doi-asserted-by":"crossref","unstructured":"Bredin, H.: TristouNet: triplet loss for speaker turn embedding. In: 2017 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 5430\u20135434. IEEE (2017)","DOI":"10.1109\/ICASSP.2017.7953194"},{"key":"39_CR6","unstructured":"Cheng, J.M., Wang, H.C.: A method of estimating the equal error rate for automatic speaker verification. In: 2004 International Symposium on Chinese Spoken Language Processing, pp. 285\u2013288. IEEE (2004)"},{"key":"39_CR7","doi-asserted-by":"crossref","unstructured":"Chopra, S., Hadsell, R., LeCun, Y.: Learning a similarity metric discriminatively, with application to face verification. In: 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, CVPR 2005, vol. 1, pp. 539\u2013546. IEEE (2005)","DOI":"10.1109\/CVPR.2005.202"},{"key":"39_CR8","doi-asserted-by":"crossref","unstructured":"Chung, J.S., et al.: In defence of metric learning for speaker recognition. In: Proceedings of the Interspeech 2020, pp. 2977\u20132981 (2020)","DOI":"10.21437\/Interspeech.2020-1064"},{"key":"39_CR9","doi-asserted-by":"crossref","unstructured":"Cooper, E., et al.: Zero-shot multi-speaker text-to-speech with state-of-the-art neural speaker embeddings. In: 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), ICASSP 2020, pp. 6184\u20136188. IEEE (2020)","DOI":"10.1109\/ICASSP40776.2020.9054535"},{"key":"39_CR10","doi-asserted-by":"crossref","unstructured":"Deng, J., Guo, J., Xue, N., Zafeiriou, S.: ArcFace: additive angular margin loss for deep face recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 4690\u20134699 (2019)","DOI":"10.1109\/CVPR.2019.00482"},{"key":"39_CR11","unstructured":"Erta\u015f, F.: Fundamentals of speaker recognition. Pamukkale \u00dcniversitesi M\u00fchendislik Bilimleri Dergisi 6(2\u20133) (2011)"},{"issue":"3","key":"39_CR12","first-page":"59","volume":"31","author":"D Ferrucci","year":"2010","unstructured":"Ferrucci, D., et al.: Building Watson: an overview of the DeepQA project. AI Mag. 31(3), 59\u201379 (2010)","journal-title":"AI Mag."},{"key":"39_CR13","unstructured":"Goodfellow, I., Bengio, Y., Courville, A.: Deep Learning. MIT Press (2016). http:\/\/www.deeplearningbook.org"},{"key":"39_CR14","unstructured":"Gruber, T.: Siri, a virtual personal assistant-bringing intelligence to the interface (2009)"},{"key":"39_CR15","unstructured":"Heo, H.S., Lee, B.J., Huh, J., Chung, J.S.: Clova baseline system for the VoxCeleb speaker recognition challenge 2020. arXiv preprint arXiv:2009.14153 (2020)"},{"key":"39_CR16","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"531","DOI":"10.1007\/11744085_41","volume-title":"Computer Vision \u2013 ECCV 2006","author":"S Ioffe","year":"2006","unstructured":"Ioffe, S.: Probabilistic linear discriminant analysis. In: Leonardis, A., Bischof, H., Pinz, A. (eds.) ECCV 2006. LNCS, vol. 3954, pp. 531\u2013542. Springer, Heidelberg (2006). https:\/\/doi.org\/10.1007\/11744085_41"},{"key":"39_CR17","doi-asserted-by":"crossref","unstructured":"Kekre, H., Kulkarni, V.: Closed set and open set speaker identification using amplitude distribution of different transforms. In: 2013 International Conference on Advances in Technology and Engineering (ICATE), pp. 1\u20138. IEEE (2013)","DOI":"10.1109\/ICAdTE.2013.6524764"},{"key":"39_CR18","unstructured":"Kingma, D.P., Ba, J.: Adam: a method for stochastic optimization. arXiv preprint arXiv:1412.6980 (2014)"},{"key":"39_CR19","doi-asserted-by":"crossref","unstructured":"Liu, W., Wen, Y., Yu, Z., Li, M., Raj, B., Song, L.: SphereFace: deep hypersphere embedding for face recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 212\u2013220 (2017)","DOI":"10.1109\/CVPR.2017.713"},{"key":"39_CR20","unstructured":"Logan, B., et al.: Mel frequency cepstral coefficients for music modeling. In: ISMIR, vol. 270, pp. 1\u201311 (2000)"},{"key":"39_CR21","doi-asserted-by":"crossref","unstructured":"McFee, B., et al.: librosa: audio and music signal analysis in Python. In: Proceedings of the 14th Python in Science Conference, pp. 18\u201325 (2015)","DOI":"10.25080\/Majora-7b98e3ed-003"},{"key":"39_CR22","doi-asserted-by":"publisher","unstructured":"Michalski, R.S., Carbonell, J.G., Mitchell, T.M.: Machine learning: an artificial intelligence approach. Springer Science & Business Media (2013). https:\/\/doi.org\/10.1007\/978-3-662-12405-5","DOI":"10.1007\/978-3-662-12405-5"},{"key":"39_CR23","doi-asserted-by":"crossref","unstructured":"Nagrani, A., Chung, J.S., Zisserman, A.: VoxCeleb: a large-scale speaker identification dataset. In: Proceedings of the Interspeech 2017, pp. 2616\u20132620 (2017)","DOI":"10.21437\/Interspeech.2017-950"},{"key":"39_CR24","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"416","DOI":"10.1007\/978-3-319-75193-1_50","volume-title":"Progress in Pattern Recognition, Image Analysis, Computer Vision, and Applications","author":"TS Nazar\u00e9","year":"2018","unstructured":"Nazar\u00e9, T.S., da Costa, G.B.P., Contato, W.A., Ponti, M.: Deep convolutional neural networks and noisy images. In: Mendoza, M., Velast\u00edn, S. (eds.) CIARP 2017. LNCS, vol. 10657, pp. 416\u2013424. Springer, Cham (2018). https:\/\/doi.org\/10.1007\/978-3-319-75193-1_50"},{"key":"39_CR25","doi-asserted-by":"publisher","unstructured":"Nussbaumer, H.J.: The fast Fourier transform. In: Fast Fourier Transform and Convolution Algorithms, vol. 2, pp. 80\u2013111. Springer, Heidelberg (1981). https:\/\/doi.org\/10.1007\/978-3-662-00551-4_4","DOI":"10.1007\/978-3-662-00551-4_4"},{"key":"39_CR26","unstructured":"Ping, W., et al.: Deep Voice 3: scaling text-to-speech with convolutional sequence learning. In: International Conference on Learning Representations (2018)"},{"key":"39_CR27","doi-asserted-by":"crossref","unstructured":"Ramoji, S., Krishnan V, P., Singh, P., Ganapathy, S.: Pairwise discriminative neural PLDA for speaker verification. arXiv preprint arXiv:2001.07034 (2020)","DOI":"10.21437\/Odyssey.2020-29"},{"key":"39_CR28","doi-asserted-by":"crossref","unstructured":"Schroff, F., Kalenichenko, D., Philbin, J.: 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)","DOI":"10.1109\/CVPR.2015.7298682"},{"key":"39_CR29","unstructured":"Seara, I.: Estudo Estat\u00edstico dos Fonemas do Portugu\u00eas Brasileiro Falado na Capital de Santa Catarina para Elabora\u00e7\u00e3o de Frases Foneticamente Balanceadas. Ph.D. thesis, Disserta\u00e7\u00e3o de Mestrado, Universidade Federal de Santa Catarina ... (1994)"},{"key":"39_CR30","doi-asserted-by":"crossref","unstructured":"Snyder, D., Garcia-Romero, D., Povey, D., Khudanpur, S.: Deep neural network embeddings for text-independent speaker verification. In: Interspeech, pp. 999\u20131003 (2017)","DOI":"10.21437\/Interspeech.2017-620"},{"key":"39_CR31","doi-asserted-by":"crossref","unstructured":"Snyder, D., Garcia-Romero, D., Sell, G., Povey, D., Khudanpur, S.: 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)","DOI":"10.1109\/ICASSP.2018.8461375"},{"key":"39_CR32","unstructured":"Tang, Y.: TF.Learn: Tensorflow\u2019s high-level module for distributed machine learning. arXiv preprint arXiv:1612.04251 (2016)"},{"key":"39_CR33","unstructured":"Veaux, C., Yamagishi, J., MacDonald, K., et al.: Superseded-CSTR VCTK corpus: English multi-speaker corpus for CSTR voice cloning toolkit. University of Edinburgh, The Centre for Speech Technology Research (CSTR) (2016)"},{"key":"39_CR34","doi-asserted-by":"crossref","unstructured":"Wan, L., Wang, Q., Papir, A., Moreno, I.L.: Generalized end-to-end loss for speaker verification. In: 2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 4879\u20134883. IEEE (2018)","DOI":"10.1109\/ICASSP.2018.8462665"},{"issue":"7","key":"39_CR35","doi-asserted-by":"publisher","first-page":"926","DOI":"10.1109\/LSP.2018.2822810","volume":"25","author":"F Wang","year":"2018","unstructured":"Wang, F., Cheng, J., Liu, W., Liu, H.: Additive margin Softmax for face verification. IEEE Sig. Process. Lett. 25(7), 926\u2013930 (2018)","journal-title":"IEEE Sig. Process. Lett."},{"key":"39_CR36","doi-asserted-by":"crossref","unstructured":"Wang, J., Wang, K.C., Law, M.T., Rudzicz, F., Brudno, M.: Centroid-based deep metric learning for speaker recognition. In: 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), ICASSP 2019, pp. 3652\u20133656. IEEE (2019)","DOI":"10.1109\/ICASSP.2019.8683393"},{"key":"39_CR37","doi-asserted-by":"crossref","unstructured":"Zhou, Y., Tian, X., Xu, H., Das, R.K., Li, H.: Cross-lingual voice conversion with bilingual Phonetic PosteriorGram and average modeling. In: 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), ICASSP 2019, pp. 6790\u20136794. IEEE (2019)","DOI":"10.1109\/ICASSP.2019.8683746"}],"container-title":["Lecture Notes in Computer Science","Intelligent Systems"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-030-91699-2_39","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,9,13]],"date-time":"2024-09-13T03:49:12Z","timestamp":1726199352000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-030-91699-2_39"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021]]},"ISBN":["9783030916985","9783030916992"],"references-count":37,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-91699-2_39","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2021]]},"assertion":[{"value":"28 November 2021","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"BRACIS","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Brazilian Conference on Intelligent Systems","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2021","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"29 November 2021","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"3 December 2021","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"10","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"bracis2021","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/c4ai.inova.usp.br\/bracis\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Double-blind","order":1,"name":"type","label":"Type","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"JEMS","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"192","order":3,"name":"number_of_submissions_sent_for_review","label":"Number of Submissions Sent for Review","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"77","order":4,"name":"number_of_full_papers_accepted","label":"Number of Full Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"0","order":5,"name":"number_of_short_papers_accepted","label":"Number of Short Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"40% - The value is computed by the equation \"Number of Full Papers Accepted \/ Number of Submissions Sent for Review * 100\" and then rounded to a whole number.","order":6,"name":"acceptance_rate_of_full_papers","label":"Acceptance Rate of Full Papers","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"3","order":7,"name":"average_number_of_reviews_per_paper","label":"Average Number of Reviews per Paper","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"3.1","order":8,"name":"average_number_of_papers_per_reviewer","label":"Average Number of Papers per Reviewer","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"Yes","order":9,"name":"external_reviewers_involved","label":"External Reviewers Involved","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"Due to COVID-19, the conference was held as an online event.","order":10,"name":"additional_info_on_review_process","label":"Additional Info on Review Process","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}}]}}