{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,27]],"date-time":"2025-03-27T14:29:44Z","timestamp":1743085784036,"version":"3.40.3"},"publisher-location":"Cham","reference-count":29,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783030026974"},{"type":"electronic","value":"9783030026981"}],"license":[{"start":{"date-parts":[[2018,1,1]],"date-time":"2018-01-01T00:00:00Z","timestamp":1514764800000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2018]]},"DOI":"10.1007\/978-3-030-02698-1_20","type":"book-chapter","created":{"date-parts":[[2018,11,8]],"date-time":"2018-11-08T16:46:59Z","timestamp":1541695619000},"page":"231-242","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":2,"title":["Covariance Based Deep Feature for Text-Dependent Speaker Verification"],"prefix":"10.1007","author":[{"given":"Shuai","family":"Wang","sequence":"first","affiliation":[]},{"given":"Heinrich","family":"Dinkel","sequence":"additional","affiliation":[]},{"given":"Yanmin","family":"Qian","sequence":"additional","affiliation":[]},{"given":"Kai","family":"Yu","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2018,11,9]]},"reference":[{"issue":"11","key":"20_CR1","doi-asserted-by":"publisher","first-page":"1744","DOI":"10.1109\/TNN.2011.2167240","volume":"22","author":"K Chen","year":"2011","unstructured":"Chen, K., Salman, A.: Learning speaker-specific characteristics with a deep neural architecture. IEEE Trans. Neural Netw. 22(11), 1744\u20131756 (2011)","journal-title":"IEEE Trans. Neural Netw."},{"key":"20_CR2","doi-asserted-by":"crossref","unstructured":"Heigold, G., Moreno, I., Bengio, S., Shazeer, N.: End-to-end text-dependent speaker verification. arXiv preprint arXiv:1509.08062 (2015)","DOI":"10.1109\/ICASSP.2016.7472652"},{"key":"20_CR3","doi-asserted-by":"crossref","unstructured":"Chen, Y.-H., Lopez-Moreno, I., Sainath, T.N., Visontai, M., Alvarez, R., Parada, C.: Locally-connected and convolutional neural networks for small footprint speaker recognition. In: INTERSPEECH (2015)","DOI":"10.21437\/Interspeech.2015-297"},{"key":"20_CR4","doi-asserted-by":"crossref","unstructured":"Lei, Y., Ferrer, L., McLaren, M., et al.: A novel scheme for speaker recognition using a phonetically-aware deep neural network. In: IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 1695\u20131699. IEEE (2014)","DOI":"10.21236\/ADA613971"},{"key":"20_CR5","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1016\/j.specom.2015.07.003","volume":"73","author":"Y Liu","year":"2015","unstructured":"Liu, Y., Qian, Y., Chen, N., Fu, T., Zhang, Y., Yu, K.: Deep feature for text-dependent speaker verification. Speech Commun. 73, 1\u201313 (2015)","journal-title":"Speech Commun."},{"issue":"5786","key":"20_CR6","doi-asserted-by":"publisher","first-page":"504","DOI":"10.1126\/science.1127647","volume":"313","author":"GE Hinton","year":"2006","unstructured":"Hinton, G.E., Salakhutdinov, R.R.: Reducing the dimensionality of data with neural networks. Science 313(5786), 504\u2013507 (2006)","journal-title":"Science"},{"issue":"7","key":"20_CR7","doi-asserted-by":"publisher","first-page":"1527","DOI":"10.1162\/neco.2006.18.7.1527","volume":"18","author":"GE Hinton","year":"2006","unstructured":"Hinton, G.E., Osindero, S., Teh, Y.-W.: A fast learning algorithm for deep belief nets. Neural Computat. 18(7), 1527\u20131554 (2006)","journal-title":"Neural Computat."},{"key":"20_CR8","doi-asserted-by":"crossref","unstructured":"Yu, D., Seltzer, M.L.: Improved bottleneck features using pretrained deep neural networks. In: INTERSPEECH, vol. 237, p. 240 (2011)","DOI":"10.21437\/Interspeech.2011-91"},{"key":"20_CR9","doi-asserted-by":"crossref","unstructured":"Gr\u00e9zl, F., Karafi\u00e1t, M., Kont\u00e1r, S., Cernocky, J.: Probabilistic and bottle-neck features for lvcsr of meetings. In: IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), vol. 4, pp. IV\u2013757. IEEE (2007)","DOI":"10.1109\/ICASSP.2007.367023"},{"key":"20_CR10","doi-asserted-by":"crossref","unstructured":"Matejka, P., et al.: Neural network bottleneck features for language identification. In: Proceedings of IEEE Odyssey, pp. 299\u2013304 (2014)","DOI":"10.21437\/Odyssey.2014-45"},{"key":"20_CR11","doi-asserted-by":"crossref","unstructured":"Fu, T., Qian, Y., Liu, Y., Yu, K.: Tandem deep features for text-dependent speaker verification. In: INTERSPEECH, pp. 1327\u20131331 (2014)","DOI":"10.21437\/Interspeech.2014-329"},{"issue":"10","key":"20_CR12","doi-asserted-by":"publisher","first-page":"1671","DOI":"10.1109\/LSP.2015.2420092","volume":"22","author":"F Richardson","year":"2015","unstructured":"Richardson, F., Reynolds, D., Dehak, N.: Deep neural network approaches to speaker and language recognition. IEEE Sig. Process. Lett. 22(10), 1671\u20131675 (2015)","journal-title":"IEEE Sig. Process. Lett."},{"key":"20_CR13","doi-asserted-by":"crossref","unstructured":"Variani, E., Lei, X., McDermott, E., Lopez Moreno, I., Gonzalez-Dominguez, J.: Deep neural networks for small footprint text-dependent speaker verification. In: IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 4052\u20134056. IEEE (2014)","DOI":"10.1109\/ICASSP.2014.6854363"},{"key":"20_CR14","doi-asserted-by":"crossref","unstructured":"Chen, N., Qian, Y., Yu, K.: Multi-task learning for text-dependent speaker verification. In: INTERSPEECH (2015)","DOI":"10.21437\/Interspeech.2015-81"},{"key":"20_CR15","doi-asserted-by":"publisher","first-page":"56","DOI":"10.1016\/j.specom.2014.03.001","volume":"60","author":"A Larcher","year":"2014","unstructured":"Larcher, A., Lee, K.A., Ma, B., Li, H.: Text-dependent speaker verification: classifiers, databases and RSR2015. Speech Commun. 60, 56\u201377 (2014)","journal-title":"Speech Commun."},{"key":"20_CR16","doi-asserted-by":"crossref","unstructured":"Lee, K.A., et al.: The RedDots data collection for speaker recognition. In: INTERSPEECH (2015)","DOI":"10.21437\/Interspeech.2015-95"},{"key":"20_CR17","unstructured":"Hain, T., Johnson, S., Tuerk, A., Woodland, P., Young, S.: Segment generation and clustering in the HTK broadcast news transcription system. In: Proceedings of 1998 DARPA Broadcast News Transcription and Understanding Workshop, pp. 133\u2013137 (1998)"},{"issue":"8","key":"20_CR18","doi-asserted-by":"publisher","first-page":"2280","DOI":"10.1109\/TASL.2012.2201472","volume":"20","author":"PL De Leon","year":"2012","unstructured":"De Leon, P.L., Pucher, M., Yamagishi, J., Hernaez, I., Saratxaga, I.: Evaluation of speaker verification security and detection of hmm-based synthetic speech. IEEE Trans. Audio Speech Lang. Process. 20(8), 2280\u20132290 (2012)","journal-title":"IEEE Trans. Audio Speech Lang. Process."},{"key":"20_CR19","doi-asserted-by":"crossref","unstructured":"Chen, L.-W., Guo, W., Dai, L.-R.: Speaker verification against synthetic speech. In: 7th International Symposium on Chinese Spoken Language Processing (ISCSLP), pp. 309\u2013312. IEEE (2010)","DOI":"10.1109\/ISCSLP.2010.5684887"},{"key":"20_CR20","doi-asserted-by":"crossref","unstructured":"Tuzel, O., Porikli, F., Meer, P.: Human detection via classification on Riemannian manifolds. In: IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2007, pp. 1\u20138. IEEE (2007)","DOI":"10.1109\/CVPR.2007.383197"},{"key":"20_CR21","unstructured":"Yao, J., Odobez, J.-M.: Fast human detection from videos using covariance features. Technical report, Idiap (2007)"},{"issue":"4","key":"20_CR22","doi-asserted-by":"publisher","first-page":"788","DOI":"10.1109\/TASL.2010.2064307","volume":"19","author":"N Dehak","year":"2011","unstructured":"Dehak, N., Kenny, P., Dehak, R., Dumouchel, P., Ouellet, P.: Front-end factor analysis for speaker verification. IEEE Trans. Audio Speech Lang. Process. 19(4), 788\u2013798 (2011)","journal-title":"IEEE Trans. Audio Speech Lang. Process."},{"issue":"3","key":"20_CR23","doi-asserted-by":"publisher","first-page":"345","DOI":"10.1109\/TSA.2004.840940","volume":"13","author":"P Kenny","year":"2005","unstructured":"Kenny, P., Boulianne, G., Dumouchel, P.: Eigenvoice modeling with sparse training data. IEEE Trans. Speech Audio Process. 13(3), 345\u2013354 (2005)","journal-title":"IEEE Trans. Speech Audio Process."},{"key":"20_CR24","unstructured":"Kenny, P.: A small footprint i-vector extractor. In: Odyssey, pp. 1\u20136 (2012)"},{"key":"20_CR25","doi-asserted-by":"crossref","unstructured":"Prince, S.J., Elder, J.H.: Probabilistic linear discriminant analysis for inferences about identity. In: IEEE 11th International Conference on Computer Vision, ICCV 2007, pp. 1\u20138. IEEE (2007)","DOI":"10.1109\/ICCV.2007.4409052"},{"key":"20_CR26","doi-asserted-by":"crossref","unstructured":"Kenny, P., Stafylakis, T., Ouellet, P., Alam, M.J., Dumouchel, P.: PLDA for speaker verification with utterances of arbitrary duration. In: IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 7649\u20137653. IEEE (2013)","DOI":"10.1109\/ICASSP.2013.6639151"},{"key":"20_CR27","doi-asserted-by":"crossref","unstructured":"Mat\u011bjka, P., et al.: Full-covariance UBM and heavy-tailed PLDA in i-vector speaker verification. In: IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 4828\u20134831. IEEE (2011)","DOI":"10.1109\/ICASSP.2011.5947436"},{"issue":"1","key":"20_CR28","doi-asserted-by":"publisher","first-page":"42","DOI":"10.1006\/dspr.1999.0360","volume":"10","author":"R Auckenthaler","year":"2000","unstructured":"Auckenthaler, R., Carey, M., Lloyd-Thomas, H.: Score normalization for text-independent speaker verification systems. Digit. Sig. Process. 10(1), 42\u201354 (2000)","journal-title":"Digit. Sig. Process."},{"issue":"1","key":"20_CR29","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. Digit. Sig. Process. 10(1), 19\u201341 (2000)","journal-title":"Digit. Sig. Process."}],"container-title":["Lecture Notes in Computer Science","Intelligence Science and Big Data Engineering"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-030-02698-1_20","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,3,12]],"date-time":"2024-03-12T11:43:52Z","timestamp":1710243832000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-030-02698-1_20"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018]]},"ISBN":["9783030026974","9783030026981"],"references-count":29,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-02698-1_20","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2018]]},"assertion":[{"value":"9 November 2018","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"IScIDE","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Intelligent Science and Big Data Engineering","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Lanzhou","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":"2018","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"18 August 2018","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"19 August 2018","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"8","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"iscide2018","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/iscide.lzu.edu.cn\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Single-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":"121","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":"59","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":"49% - 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":"2.7","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":"4.9","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)"}}]}}