{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,30]],"date-time":"2025-12-30T23:44:37Z","timestamp":1767138277218,"version":"build-2238731810"},"publisher-location":"Cham","reference-count":13,"publisher":"Springer International Publishing","isbn-type":[{"value":"9783030678319","type":"print"},{"value":"9783030678326","type":"electronic"}],"license":[{"start":{"date-parts":[[2021,1,1]],"date-time":"2021-01-01T00:00:00Z","timestamp":1609459200000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/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":"http:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2021]]},"DOI":"10.1007\/978-3-030-67832-6_1","type":"book-chapter","created":{"date-parts":[[2021,1,22]],"date-time":"2021-01-22T12:44:48Z","timestamp":1611319488000},"page":"1-10","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":2,"title":["Crossed-Time Delay Neural Network for Speaker Recognition"],"prefix":"10.1007","author":[{"given":"Liang","family":"Chen","sequence":"first","affiliation":[]},{"given":"Yanchun","family":"Liang","sequence":"additional","affiliation":[]},{"given":"Xiaohu","family":"Shi","sequence":"additional","affiliation":[]},{"given":"You","family":"Zhou","sequence":"additional","affiliation":[]},{"given":"Chunguo","family":"Wu","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2021,1,21]]},"reference":[{"key":"1_CR1","doi-asserted-by":"crossref","unstructured":"Snyder, D., Garcia-Romero, D., Sell, G., Povey, D., Khudanpur, S.: X-vectors\u202f: robust dnn embeddings for speaker recognition. In: Center for Language and Speech Processing & Human Language Technology, Center of Excellence the Johns Hopkins Un, Icassp 2018, pp. 5329\u20135333 (2018)","DOI":"10.1109\/ICASSP.2018.8461375"},{"key":"1_CR2","doi-asserted-by":"publisher","unstructured":"Jin, M., Yoo, C.D.: Speaker verification and identification. Behav. Biometrics Hum. Identif. Intell. Appl., 264\u2013289 (2009). https:\/\/doi.org\/10.4018\/978-1-60566-725-6.ch013","DOI":"10.4018\/978-1-60566-725-6.ch013"},{"key":"1_CR3","doi-asserted-by":"crossref","unstructured":"Karaali, O., Corrigan, G., Gerson, I., Massey, N.: Text-to-speech conversion with neural networks: a recurrent TDNN approach. In: Proceedings of Eurospeech 1997, Rhodes, Greece, pp. 561\u2013564 (1997)","DOI":"10.21437\/Eurospeech.1997-209"},{"key":"1_CR4","doi-asserted-by":"crossref","unstructured":"Peddinti, V., Povey, D., Khudanpur, S.: A time delay neural network architecture for efficient modeling of long temporal contexts.pdf. In: Proceedings of the Annual Conference of the International Speech Communication Association, INTERSPEECH 2015, vol. 2015-Janua, pp. 2\u20136 (2015)","DOI":"10.21437\/Interspeech.2015-647"},{"key":"1_CR5","doi-asserted-by":"publisher","unstructured":"Liu, B., Zhang, W., Xu, X., Chen, D.: Time delay recurrent neural network for speech recognition. J. Phys. Conf. Ser. 1229(1) (2019). https:\/\/doi.org\/10.1088\/1742-6596\/1229\/1\/012078","DOI":"10.1088\/1742-6596\/1229\/1\/012078"},{"key":"1_CR6","doi-asserted-by":"publisher","unstructured":"Qin, Y., Lee, T., Feng, S., Hin Kong, A.P.: Automatic speech assessment for people with aphasia using TDNN-BLSTM with multi-task learning. In: Proceedings of Annual Conference of International Speech Communication Association, INTERSPEECH, vol. 2018-Septe, no. September, pp. 3418\u20133422 (2018). https:\/\/doi.org\/10.21437\/Interspeech.2018-1630","DOI":"10.21437\/Interspeech.2018-1630"},{"key":"1_CR7","doi-asserted-by":"publisher","unstructured":"Miao, X., McLoughlin, I., Yan, Y.: A new time-frequency attention mechanism for TDNN and CNN-LSTM-TDNN, with application to language identification. In: Proceedings of Annual Conference International Speech Communication Association, INTERSPEECH, vol. 2019-Septe, pp. 4080\u20134084 (2019). https:\/\/doi.org\/10.21437\/Interspeech.2019-1256","DOI":"10.21437\/Interspeech.2019-1256"},{"key":"1_CR8","doi-asserted-by":"publisher","unstructured":"Povey, D., et al.: Semi-orthogonal low-rank matrix factorization for deep neural networks. In: Proceedings of Annual Conference International Speech Communication Association, INTERSPEECH, vol. 2018-Septe, no. 2, pp. 3743\u20133747 (2018). https:\/\/doi.org\/10.21437\/Interspeech.2018-1417","DOI":"10.21437\/Interspeech.2018-1417"},{"key":"1_CR9","doi-asserted-by":"publisher","unstructured":"He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: Proceedings of IEEE Computer Society Conference Computer Vision Pattern Recognition, vol. 2016-December, pp. 770\u2013778 (2016). https:\/\/doi.org\/10.1109\/CVPR.2016.90.","DOI":"10.1109\/CVPR.2016.90"},{"issue":"6","key":"1_CR10","doi-asserted-by":"publisher","first-page":"829","DOI":"10.1142\/S0219530516400042","volume":"14","author":"HN Mhaskar","year":"2016","unstructured":"Mhaskar, H.N., Poggio, T.: Deep vs. shallow networks: an approximation theory perspective. Anal. Appl. 14(6), 829\u2013848 (2016). https:\/\/doi.org\/10.1142\/S0219530516400042","journal-title":"Anal. Appl."},{"key":"1_CR11","unstructured":"He, F., Liu, T., Tao, D.: control batch size and learning rate to generalize well: theoretical and empirical evidence. In: Nips, no. NeurIPS, p. 10 (2019)"},{"key":"1_CR12","doi-asserted-by":"publisher","unstructured":"Nagrani, A., Chung, J.S., Zisserman, A.: VoxCeleb: a large-scale speaker identification dataset. In: Interspeech 2017, pp. 2616\u20132620 (2017). https:\/\/doi.org\/10.21437\/Interspeech.2017-950.","DOI":"10.21437\/Interspeech.2017-950"},{"key":"1_CR13","doi-asserted-by":"publisher","unstructured":"Toda, T., et al.: The Voice Conversion Challenge 2016, pp. 1632\u20131636 (2016). https:\/\/doi.org\/10.21437\/Interspeech.2016-1066.","DOI":"10.21437\/Interspeech.2016-1066"}],"updated-by":[{"DOI":"10.1007\/978-3-030-67832-6_59","type":"correction","label":"Correction","source":"publisher","updated":{"date-parts":[[2021,1,21]],"date-time":"2021-01-21T00:00:00Z","timestamp":1611187200000}}],"container-title":["Lecture Notes in Computer Science","MultiMedia Modeling"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-030-67832-6_1","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,12,12]],"date-time":"2022-12-12T17:27:47Z","timestamp":1670866067000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-030-67832-6_1"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021]]},"ISBN":["9783030678319","9783030678326"],"references-count":13,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-67832-6_1","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021]]},"assertion":[{"value":"21 January 2021","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"21 January 2021","order":2,"name":"change_date","label":"Change Date","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"Correction","order":3,"name":"change_type","label":"Change Type","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"A correction has been published.","order":4,"name":"change_details","label":"Change Details","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"MMM","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Multimedia Modeling","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Prague","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Czech Republic","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":"22 June 2021","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"24 June 2021","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"27","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"mmm2021","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/mmm2021.cz\/","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":"easychair","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"211","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":"73","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":"35% - 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":"2,63","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":"2,5","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)"}}]}}