{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,25]],"date-time":"2025-03-25T23:23:46Z","timestamp":1742945026781,"version":"3.40.3"},"publisher-location":"Cham","reference-count":21,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783030866075"},{"type":"electronic","value":"9783030866082"}],"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\/978-3-030-86608-2_53","type":"book-chapter","created":{"date-parts":[[2021,9,9]],"date-time":"2021-09-09T05:02:56Z","timestamp":1631163776000},"page":"483-490","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Explore the Use of Self-supervised Pre-trained Acoustic Features on Disguised Speech Detection"],"prefix":"10.1007","author":[{"given":"Jie","family":"Quan","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yingchun","family":"Yang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2021,9,8]]},"reference":[{"key":"53_CR1","doi-asserted-by":"crossref","unstructured":"Perrot, P., Aversano, G., Chollet, G.: Voice disguise and automatic detection: review and perspectives. Prog. Nonlinear Speech Process. 101\u2013117 (2007)","DOI":"10.1007\/978-3-540-71505-4_7"},{"key":"53_CR2","unstructured":"Kaur, H., Singh, A.G.: Speaker identification of disguised voices using MFCC statistical moment and SVM classifier (2017)"},{"key":"53_CR3","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"336","DOI":"10.1007\/978-3-642-40099-5_28","volume-title":"Digital Forensics and Watermaking","author":"Y Wang","year":"2013","unstructured":"Wang, Y., Deng, Y., Wu, H., Huang, J.: Blind detection of electronic voice transformation with natural disguise. In: Shi, Y.Q., Kim, H.-J., P\u00e9rez-Gonz\u00e1lez, F. (eds.) IWDW 2012. LNCS, vol. 7809, pp. 336\u2013343. Springer, Heidelberg (2013). https:\/\/doi.org\/10.1007\/978-3-642-40099-5_28"},{"key":"53_CR4","doi-asserted-by":"crossref","unstructured":"Wu, H., Wang, Y., Huang, J.: Blind detection of electronic disguised voice. In: 2013 IEEE International Conference on Acoustics, Speech and Signal Processing, IEEE, pp. 3013\u20133017 (2013)","DOI":"10.1109\/ICASSP.2013.6638211"},{"key":"53_CR5","doi-asserted-by":"crossref","unstructured":"Ma, D., Ryant, N., Liberman, M.: Probing acoustic representations for phonetic properties. In: ICASSP 2021\u20132021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 311\u2013315. IEEE (2021)","DOI":"10.1109\/ICASSP39728.2021.9414776"},{"key":"53_CR6","doi-asserted-by":"crossref","unstructured":"Schneider, S., Baevski, A., Collobert, R., et al.: wav2vec: unsupervised pre-training for speech recognition. arXiv preprint arXiv:1904.05862 (2019)","DOI":"10.21437\/Interspeech.2019-1873"},{"key":"53_CR7","unstructured":"Baevski, A,. Schneider, S., Auli, M.: vq-wav2vec: self-supervised learning of discrete speech representations. arXiv preprint arXiv:1910.05453 (2019)"},{"key":"53_CR8","doi-asserted-by":"crossref","unstructured":"Liu, A.T., Yang, S., Chi, P.H., et al.: Mockingjay: unsupervised speech representation learning with deep bidirectional transformer encoders. In: ICASSP 2020\u20132020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 6419\u20136423. IEEE (2020)","DOI":"10.1109\/ICASSP40776.2020.9054458"},{"key":"53_CR9","doi-asserted-by":"crossref","unstructured":"Ling, S., Liu, Y., Salazar, J., et al.: Deep contextualized acoustic representations for semi-supervised speech recognition. In: ICASSP 2020\u20132020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 6429\u20136433. IEEE (2020)","DOI":"10.1109\/ICASSP40776.2020.9053176"},{"issue":"6","key":"53_CR10","doi-asserted-by":"publisher","first-page":"345","DOI":"10.1007\/s00530-010-0182-0","volume":"16","author":"PK Atrey","year":"2010","unstructured":"Atrey, P.K., Hossain, M.A., El Saddik, A., et al.: Multimodal fusion for multimedia analysis: a survey. Multimed. Syst. 16(6), 345\u2013379 (2010)","journal-title":"Multimed. Syst."},{"issue":"8","key":"53_CR11","doi-asserted-by":"publisher","first-page":"1798","DOI":"10.1109\/TPAMI.2013.50","volume":"35","author":"Y Bengio","year":"2013","unstructured":"Bengio, Y., Courville, A., Vincent, P.: Representation learning: a review and new perspectives. IEEE Trans. Pattern Anal. Mach. Intell. 35(8), 1798\u20131828 (2013)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"53_CR12","unstructured":"Mikolov, T., Sutskever, I., Chen, K., et al.: Distributed representations of words and phrases and their compositionality. arXiv preprint arXiv:1310.4546 (2013)"},{"key":"53_CR13","doi-asserted-by":"crossref","unstructured":"Pascual, S., Ravanelli, M., Serra, J., et al.: Learning problem-agnostic speech representations from multiple self-supervised tasks. arXiv preprint arXiv:1904.03416 (2019)","DOI":"10.21437\/Interspeech.2019-2605"},{"key":"53_CR14","unstructured":"Baevski, A., Zhou, H., Mohamed, A., et al.: wav2vec 2.0: a framework for self-supervised learning of speech representations. arXiv preprint arXiv:2006.11477 (2020)"},{"key":"53_CR15","doi-asserted-by":"crossref","unstructured":"Zadeh, A., Chen, M., Poria, S., et al.: Tensor fusion network for multimodal sentiment analysis. arXiv preprint arXiv:1707.07250 (2017)","DOI":"10.18653\/v1\/D17-1115"},{"key":"53_CR16","doi-asserted-by":"crossref","unstructured":"Liu, Z., Shen, Y., Lakshminarasimhan, V.B., et al.: Efficient low-rank multimodal fusion with modality-specific factors. arXiv preprint arXiv:1806.00064 (2018)","DOI":"10.18653\/v1\/P18-1209"},{"issue":"11","key":"53_CR17","doi-asserted-by":"publisher","first-page":"2884","DOI":"10.1109\/TIFS.2018.2833032","volume":"13","author":"X Wu","year":"2018","unstructured":"Wu, X., He, R., Sun, Z., et al.: A light CNN for deep face representation with noisy labels. IEEE Trans. Inf. Forensics Secur. 13(11), 2884\u20132896 (2018)","journal-title":"IEEE Trans. Inf. Forensics Secur."},{"key":"53_CR18","doi-asserted-by":"crossref","unstructured":"Lavrentyeva, G., Novoselov, S., Malykh, E., et al.: Audio replay attack detection with deep learning frameworks. In: Interspeech, pp. 82\u201386 (2017)","DOI":"10.21437\/Interspeech.2017-360"},{"key":"53_CR19","unstructured":"Ba, J.L., Kiros, J.R., Hinton, G.E.: Layer normalization. arXiv preprint arXiv:1607.06450 (2016)"},{"key":"53_CR20","unstructured":"Ioffe, S., Szegedy, C.: Batch normalization: accelerating deep network training by reducing internal covariate shift. In: International Conference on Machine Learning. PMLR, pp. 448\u2013456 (2015)"},{"key":"53_CR21","unstructured":"Garofolo, J.S.: TIMIT acoustic phonetic continuous speech corpus. Linguistic Data Consortium, 1993 (1993)"}],"container-title":["Lecture Notes in Computer Science","Biometric Recognition"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-030-86608-2_53","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2021,9,9]],"date-time":"2021-09-09T05:16:02Z","timestamp":1631164562000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-030-86608-2_53"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021]]},"ISBN":["9783030866075","9783030866082"],"references-count":21,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-86608-2_53","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":"8 September 2021","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"CCBR","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Chinese Conference on Biometric Recognition","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Shanghai","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":"2021","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"10 September 2021","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"12 September 2021","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"15","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"ccbr2021","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/www.ccbr99.cn\/","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":"CMT","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"72","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":"53","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":"74% - 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":"2.3","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":"2.1","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":"No","order":9,"name":"external_reviewers_involved","label":"External Reviewers Involved","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"Full papers are up to 11 pages long.","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)"}}]}}