{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,26]],"date-time":"2025-03-26T20:48:08Z","timestamp":1743022088411,"version":"3.40.3"},"publisher-location":"Singapore","reference-count":30,"publisher":"Springer Nature Singapore","isbn-type":[{"type":"print","value":"9789811989902"},{"type":"electronic","value":"9789811989919"}],"license":[{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2022]]},"DOI":"10.1007\/978-981-19-8991-9_2","type":"book-chapter","created":{"date-parts":[[2023,1,18]],"date-time":"2023-01-18T08:04:02Z","timestamp":1674029042000},"page":"18-28","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Text-Independent Speaker Identification Using a Single-Scale SincNet-DCGAN Model"],"prefix":"10.1007","author":[{"given":"Yanna","family":"Zhang","sequence":"first","affiliation":[]},{"given":"Guangcun","family":"Wei","sequence":"additional","affiliation":[]},{"given":"Hang","family":"Min","sequence":"additional","affiliation":[]},{"given":"Yunfei","family":"Xu","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2023,1,19]]},"reference":[{"key":"2_CR1","doi-asserted-by":"publisher","DOI":"10.1007\/978-0-387-77592-0","volume-title":"Fundamentals of Speaker Recognition","author":"H Beigi","year":"2011","unstructured":"Beigi, H.: Fundamentals of Speaker Recognition. Springer US, Boston, MA (2011). https:\/\/doi.org\/10.1007\/978-0-387-77592-0"},{"issue":"10","key":"2_CR2","doi-asserted-by":"publisher","first-page":"1533","DOI":"10.1109\/TASLP.2014.2339736","volume":"22","author":"O Abdel-Hamid","year":"2014","unstructured":"Abdel-Hamid, O., Mohamed, A.-R., Jiang, H., Deng, L., Penn, G., Yu, D.: Convolutional neural networks for speech recognition. IEEE\/ACM Trans. Audio Speech Lang. Process. 22(10), 1533\u20131545 (2014)","journal-title":"IEEE\/ACM Trans. Audio Speech Lang. Process."},{"key":"2_CR3","doi-asserted-by":"publisher","first-page":"114591","DOI":"10.1016\/j.eswa.2021.114591","volume":"171","author":"R Jahangir","year":"2021","unstructured":"Jahangir, R., Teh, Y.W., Nweke, H.F., Mujtaba, G., AlGaradi, M.A., Ali, I.: Speaker identification through artificial intelligence techniques: a comprehensive review and research challenges. Expert Syst. Appl. 171, 114591 (2021)","journal-title":"Expert Syst. Appl."},{"issue":"1\u20133","key":"2_CR4","doi-asserted-by":"publisher","first-page":"19","DOI":"10.1006\/dspr.1999.0361","volume":"10","author":"DA Reynolds","year":"2000","unstructured":"Reynolds, D.A., Quatieri, T.F., Dunn, R.B.: Speaker verification using adapted gaussian mixture models. Digital Signal Process. 10(1\u20133), 19\u201341 (2000)","journal-title":"Digital Signal Process."},{"issue":"5","key":"2_CR5","doi-asserted-by":"publisher","first-page":"308","DOI":"10.1109\/LSP.2006.870086","volume":"13","author":"WM Campbell","year":"2006","unstructured":"Campbell, W.M., Sturim, D.E., Reynolds, D.A.: Support vector machines using GMM supervectors for speaker verification. IEEE Signal Process. Lett. 13(5), 308\u2013311 (2006)","journal-title":"IEEE Signal Process. Lett."},{"issue":"4","key":"2_CR6","doi-asserted-by":"publisher","first-page":"1435","DOI":"10.1109\/TASL.2006.881693","volume":"15","author":"P Kenny","year":"2007","unstructured":"Kenny, P., Boulianne, G., Ouellet, P., Dumouchel, P.: Joint factor analysis versus eigenchannels in speaker recognition. IEEE Trans. Audio Speech Lang. Process. 15(4), 1435\u20131447 (2007)","journal-title":"IEEE Trans. Audio Speech Lang. Process."},{"issue":"4","key":"2_CR7","doi-asserted-by":"publisher","first-page":"788","DOI":"10.1109\/TASL.2010.2064307","volume":"19","author":"N Dehak","year":"2010","unstructured":"Dehak, N., Kenny, P.J., Dehak, R., Dumouchel, P., Ouellet, P.: Front-end factor analysis for speaker verification. IEEE Trans. Audio Speech Lang. Process. 19(4), 788\u2013798 (2010)","journal-title":"IEEE Trans. Audio Speech Lang. Process."},{"issue":"22","key":"2_CR8","doi-asserted-by":"publisher","first-page":"22184","DOI":"10.1109\/JIOT.2021.3103138","volume":"9","author":"M JiweiZhang","year":"2022","unstructured":"JiweiZhang, M., et al.: AntiConcealer: reliable detection of adversary concealed behaviors in EdgeAI-assisted IoT. IEEE Internet of Things J. 9(22), 22184\u201322193 (2022). https:\/\/doi.org\/10.1109\/JIOT.2021.3103138","journal-title":"IEEE Internet of Things J."},{"issue":"2","key":"2_CR9","doi-asserted-by":"publisher","first-page":"1301","DOI":"10.1109\/TII.2021.3098317","volume":"18","author":"J Zhang","year":"2021","unstructured":"Zhang, J., Bhuiyan, M.Z.A., Yang, X., Singh, A.K., Hsu, D.F., Luo, E.: Trustworthy target tracking with collaborative deep reinforcement learning in EdgeAI-aided IoT. IEEE Trans. Industr. Inf. 18(2), 1301\u20131309 (2021)","journal-title":"IEEE Trans. Industr. Inf."},{"key":"2_CR10","doi-asserted-by":"crossref","unstructured":"Prince, S.J., Elder, J.H.: Probabilistic linear discriminant analysis for inferences about identity. In: 2007 IEEE 11th International Conference on Computer Vision, pp. 1\u20138. IEEE (2007)","DOI":"10.1109\/ICCV.2007.4409052"},{"key":"2_CR11","doi-asserted-by":"crossref","unstructured":"Variani, E., Lei, X., McDermott, E., Moreno, I.L., Gonzalez-Dominguez, J.: Deep neural networks for small footprint text-dependent speaker verification. In: 2014 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 4052\u20134056. IEEE (2014)","DOI":"10.1109\/ICASSP.2014.6854363"},{"key":"2_CR12","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":"2_CR13","doi-asserted-by":"crossref","unstructured":"Chen, N., Qian, Y., Yu, K.: Multi-task learning for text-dependent speaker verification. In: Sixteenth Annual Conference of The International Speech Communication Association (2015)","DOI":"10.21437\/Interspeech.2015-81"},{"issue":"9","key":"2_CR14","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, J.H.: Text-independent speaker verification based on triplet convolutional neural network embeddings. IEEE\/ACM Trans Audio Speech Lang. Process. 26(9), 1633\u20131644 (2018)","journal-title":"IEEE\/ACM Trans Audio Speech Lang. Process."},{"key":"2_CR15","doi-asserted-by":"crossref","unstructured":"Ravanelli, M., Bengio, Y.: Speaker recognition from raw waveform with SincNet. In: 2018 IEEE Spoken Language Technology Workshop (SLT), pp. 1021\u20131028. IEEE (2018)","DOI":"10.1109\/SLT.2018.8639585"},{"key":"2_CR16","doi-asserted-by":"crossref","unstructured":"Adiga, N., Pantazis, Y., Tsiaras, V., Stylianou, Y.: Speech enhancement for noise-robust speech synthesis using Wasserstein GAN. In: Interspeech, pp. 1821\u20131825 (2019)","DOI":"10.21437\/Interspeech.2019-2648"},{"key":"2_CR17","doi-asserted-by":"crossref","unstructured":"Fang, F., Yamagishi, J., Echizen, I., Lorenzo-Trueba, J.: High-quality nonparallel voice conversion based on cycle-consistent adversarial network. In: 2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 5279\u20135283. IEEE (2018)","DOI":"10.1109\/ICASSP.2018.8462342"},{"key":"2_CR18","doi-asserted-by":"crossref","unstructured":"Hono, Y., Hashimoto, K., Oura, K., Nankaku, Y., Tokuda, K.: Singing voice synthesis based on generative adversarial networks. In: ICASSP 2019\u20132019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 6955\u20136959. IEEE (2019)","DOI":"10.1109\/ICASSP.2019.8683154"},{"key":"2_CR19","unstructured":"Springenberg, J.T.: Unsupervised and Semi-Supervised Learning with Categorical Generative Adversarial Networks. arXiv preprint arXiv:1511.06390 (2015)"},{"key":"2_CR20","unstructured":"Odena, A.: Semi-Supervised Learning with Generative Adversarial Networks. arXiv preprint arXiv:1606.01583 (2016)"},{"key":"2_CR21","doi-asserted-by":"crossref","unstructured":"Nidadavolu, P.S., Kataria, S., Villalba, J., Dehak, N.: Low-resource domain adaptation for speaker recognition using cycle-GANs. In: 2019 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU), pp. 710\u2013717. IEEE (2019)","DOI":"10.1109\/ASRU46091.2019.9003748"},{"key":"2_CR22","doi-asserted-by":"publisher","first-page":"211","DOI":"10.1016\/j.neucom.2020.08.040","volume":"418","author":"L Chen","year":"2020","unstructured":"Chen, L., Liu, Y., Xiao, W., Wang, Y., Xie, H.: SpeakerGAN: speaker identification with conditional generative adversarial network. Neurocomputing 418, 211\u2013220 (2020)","journal-title":"Neurocomputing"},{"key":"2_CR23","volume-title":"Theory and Applications of Digital Speech Processing","author":"L Rabiner","year":"2010","unstructured":"Rabiner, L., Schafer, R.: Theory and Applications of Digital Speech Processing. Prentice Hall Press, Hoboken (2010)"},{"issue":"1","key":"2_CR24","first-page":"167","volume":"57","author":"W Fang","year":"2018","unstructured":"Fang, W., Zhang, F., Sheng, V.S., Ding, Y.: A method for improving CNN-based image recognition using DCGAN. Comput. Mater. Cont. 57(1), 167\u2013178 (2018)","journal-title":"Comput. Mater. Cont."},{"key":"2_CR25","unstructured":"Goodfellow, I., et al.: Generative adversarial nets. In: Advances in Neural Information Processing Systems, vol. 27 (2014)"},{"key":"2_CR26","doi-asserted-by":"crossref","unstructured":"Shen, P., Lu, X., Li, S., Kawai, H.: Conditional generative adversarial nets classifier for spoken language identification. In: Interspeech, pp. 2814\u20132818 (2017)","DOI":"10.21437\/Interspeech.2017-553"},{"key":"2_CR27","unstructured":"Gulrajani, I., Ahmed, F., Arjovsky, M., Dumoulin, V., Courville, A.C.: Improved Training of Wasserstein GANs. In: Advances in Neural Information Processing Systems, vol. 30 (2017)"},{"key":"2_CR28","doi-asserted-by":"crossref","unstructured":"Panayotov, V., Chen, G., Povey, D., Khudanpur, S.:Librispeech: An Asr corpus based on public domain audio books. In: 2015 IEEE international conference on acoustics, speech and signal processing (ICASSP), pp. 5206\u20135210. IEEE (2015)","DOI":"10.1109\/ICASSP.2015.7178964"},{"key":"2_CR29","doi-asserted-by":"crossref","unstructured":"You, L., Guo, W., Dai, L., Du, J.: Multi-task learning with high-order statistics for x-vector based text-independent speaker verification. arXiv preprint arXiv:1903.12058 (2019)","DOI":"10.21437\/Interspeech.2019-2264"},{"key":"2_CR30","doi-asserted-by":"crossref","unstructured":"Muckenhirn, H., Magimai-Doss, M., Marcel, S.: On learning vocal tract system related speaker discriminative information from raw signal Using CNNs. In: Interspeech, pp. 1116\u20131120 (2018)","DOI":"10.21437\/Interspeech.2018-1696"}],"container-title":["Communications in Computer and Information Science","Data Mining and Big Data"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-981-19-8991-9_2","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,1,18]],"date-time":"2023-01-18T08:09:37Z","timestamp":1674029377000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-19-8991-9_2"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022]]},"ISBN":["9789811989902","9789811989919"],"references-count":30,"URL":"https:\/\/doi.org\/10.1007\/978-981-19-8991-9_2","relation":{},"ISSN":["1865-0929","1865-0937"],"issn-type":[{"type":"print","value":"1865-0929"},{"type":"electronic","value":"1865-0937"}],"subject":[],"published":{"date-parts":[[2022]]},"assertion":[{"value":"19 January 2023","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"DMBD","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Data Mining and Big Data","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Beijing","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"China","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2022","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"21 November 2022","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"24 November 2022","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"dmbd2022","order":10,"name":"conference_id","label":"Conference ID","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":"Easychair","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"135","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":"62","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":"46% - 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":"2.8","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":"2-3","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)"}}]}}