{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,28]],"date-time":"2025-03-28T05:51:15Z","timestamp":1743141075955,"version":"3.40.3"},"publisher-location":"Cham","reference-count":23,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783030121761"},{"type":"electronic","value":"9783030121778"}],"license":[{"start":{"date-parts":[[2019,1,1]],"date-time":"2019-01-01T00:00:00Z","timestamp":1546300800000},"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":[[2019]]},"DOI":"10.1007\/978-3-030-12177-8_4","type":"book-chapter","created":{"date-parts":[[2019,1,18]],"date-time":"2019-01-18T12:13:44Z","timestamp":1547813624000},"page":"35-47","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Effective SVD-Based Deep Network Compression for Automatic Speech Recognition"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-3755-8756","authenticated-orcid":false,"given":"Hao","family":"Fu","sequence":"first","affiliation":[]},{"given":"Yue","family":"Ming","sequence":"additional","affiliation":[]},{"given":"Yibo","family":"Jiang","sequence":"additional","affiliation":[]},{"given":"Chunxiao","family":"Fan","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2019,1,19]]},"reference":[{"key":"4_CR1","doi-asserted-by":"crossref","unstructured":"Bu, H., Du, J., Na, X., Wu, B., Zheng, H.: Aishell-1: An open-source mandarin speech corpus and a speech recognition baseline. arXiv preprint arXiv:1709.05522 (2017)","DOI":"10.1109\/ICSDA.2017.8384449"},{"key":"4_CR2","doi-asserted-by":"crossref","unstructured":"Bucilu, C., Caruana, R., Niculescu-Mizil, A.: Model compression. In: Proceedings of the 12th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, pp. 535\u2013541. ACM (2006)","DOI":"10.1145\/1150402.1150464"},{"key":"4_CR3","unstructured":"Denton, E.L., Zaremba, W., Bruna, J., LeCun, Y., Fergus, R.: Exploiting linear structure within convolutional networks for efficient evaluation. In: Advances in Neural Information Processing Systems, pp. 1269\u20131277 (2014)"},{"key":"4_CR4","unstructured":"Han, S., Pool, J., Tran, J., Dally, W.: Learning both weights and connections for efficient neural network. In: Advances in Neural Information Processing Systems, pp. 1135\u20131143 (2015)"},{"key":"4_CR5","unstructured":"Hinton, G., Vinyals, O., Dean, J.: Distilling the knowledge in a neural network. arXiv preprint arXiv:1503.02531 (2015)"},{"key":"4_CR6","doi-asserted-by":"crossref","unstructured":"Jacob, B., et al.: Quantization and training of neural networks for efficient integer-arithmetic-only inference. arXiv preprint arXiv:1712.05877 (2017)","DOI":"10.1109\/CVPR.2018.00286"},{"key":"4_CR7","doi-asserted-by":"crossref","unstructured":"Jaderberg, M., Vedaldi, A., Zisserman, A.: Speeding up convolutional neural networks with low rank expansions. arXiv preprint arXiv:1405.3866 (2014)","DOI":"10.5244\/C.28.88"},{"key":"4_CR8","doi-asserted-by":"crossref","unstructured":"Kim, S., Hori, T., Watanabe, S.: Joint CTC-attention based end-to-end speech recognition using multi-task learning. In: 2017 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 4835\u20134839. IEEE (2017)","DOI":"10.1109\/ICASSP.2017.7953075"},{"key":"4_CR9","doi-asserted-by":"crossref","unstructured":"Ko, T., Peddinti, V., Povey, D., Khudanpur, S.: Audio augmentation for speech recognition. In: Sixteenth Annual Conference of the International Speech Communication Association (2015)","DOI":"10.21437\/Interspeech.2015-711"},{"key":"4_CR10","unstructured":"Krizhevsky, A., Sutskever, I., Hinton, G.E.: Imagenet classification with deep convolutional neural networks. In: Advances in Neural Information Processing Systems, pp. 1097\u20131105 (2012)"},{"key":"4_CR11","unstructured":"LeCun, Y., Denker, J.S., Solla, S.A.: Optimal brain damage. In: Advances in Neural Information Processing Systems, pp. 598\u2013605 (1990)"},{"key":"4_CR12","unstructured":"Li, F., Zhang, B., Liu, B.: Ternary weight networks. arXiv preprint arXiv:1605.04711 (2016)"},{"key":"4_CR13","unstructured":"Lin, S., Ji, R., Guo, X., Li, X., et al.: Towards convolutional neural networks compression via global error reconstruction. In: IJCAI, pp. 1753\u20131759 (2016)"},{"key":"4_CR14","doi-asserted-by":"publisher","first-page":"195","DOI":"10.1016\/j.csl.2016.06.007","volume":"41","author":"AL Maas","year":"2017","unstructured":"Maas, A.L., et al.: Building DNN acoustic models for large vocabulary speech recognition. Comput. Speech Lang. 41, 195\u2013213 (2017)","journal-title":"Comput. Speech Lang."},{"key":"4_CR15","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"525","DOI":"10.1007\/978-3-319-46493-0_32","volume-title":"Computer Vision \u2013 ECCV 2016","author":"M Rastegari","year":"2016","unstructured":"Rastegari, M., Ordonez, V., Redmon, J., Farhadi, A.: XNOR-Net: imagenet classification using binary convolutional neural networks. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9908, pp. 525\u2013542. Springer, Cham (2016). https:\/\/doi.org\/10.1007\/978-3-319-46493-0_32"},{"key":"4_CR16","unstructured":"Simonyan, K., Zisserman, A.: Very deep convolutional networks for large-scale image recognition. arXiv preprint arXiv:1409.1556 (2014)"},{"key":"4_CR17","unstructured":"Sindhwani, V., Sainath, T., Kumar, S.: Structured transforms for small-footprint deep learning. In: Advances in Neural Information Processing Systems, pp. 3088\u20133096 (2015)"},{"key":"4_CR18","doi-asserted-by":"crossref","unstructured":"Xiong, W., et al.: The microsoft 2016 conversational speech recognition system. In: 2017 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 5255\u20135259. IEEE (2017)","DOI":"10.1109\/ICASSP.2017.7953159"},{"key":"4_CR19","doi-asserted-by":"crossref","unstructured":"Xue, J., Li, J., Gong, Y.: Restructuring of deep neural network acoustic models with singular value decomposition. In: Interspeech, pp. 2365\u20132369 (2013)","DOI":"10.21437\/Interspeech.2013-552"},{"key":"4_CR20","doi-asserted-by":"crossref","unstructured":"Yu, D., Seide, F., Li, G., Deng, L.: Exploiting sparseness in deep neural networks for large vocabulary speech recognition. In: 2012 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 4409\u20134412. IEEE (2012)","DOI":"10.1109\/ICASSP.2012.6288897"},{"key":"4_CR21","doi-asserted-by":"crossref","unstructured":"Zeyer, A., Doetsch, P., Voigtlaender, P., Schl\u00fcter, R., Ney, H.: A comprehensive study of deep bidirectional LSTM RNNs for acoustic modeling in speech recognition. In: 2017 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 2462\u20132466. IEEE (2017)","DOI":"10.1109\/ICASSP.2017.7952599"},{"key":"4_CR22","doi-asserted-by":"crossref","unstructured":"Zhang, Y., Chan, W., Jaitly, N.: Very deep convolutional networks for end-to-end speech recognition. In: 2017 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 4845\u20134849. IEEE (2017)","DOI":"10.1109\/ICASSP.2017.7953077"},{"key":"4_CR23","unstructured":"Zhou, A., Yao, A., Guo, Y., Xu, L., Chen, Y.: Incremental network quantization: Towards lossless CNNs with low-precision weights. arXiv preprint arXiv:1702.03044 (2017)"}],"container-title":["Lecture Notes in Computer Science","Video Analytics. Face and Facial Expression Recognition"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-030-12177-8_4","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,9,10]],"date-time":"2022-09-10T16:52:10Z","timestamp":1662828730000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-030-12177-8_4"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019]]},"ISBN":["9783030121761","9783030121778"],"references-count":23,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-12177-8_4","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2019]]},"assertion":[{"value":"19 January 2019","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"FFER","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Workshop on Face and Facial Expression Recognition from Real World Videos","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":"2018","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"20 August 2018","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"20 August 2018","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"3","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"ffer2018","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/ffer.aau.dk\/","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"}},{"value":"CMT","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information"}},{"value":"9","order":3,"name":"number_of_submissions_sent_for_review","label":"Number of Submissions Sent for Review","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information"}},{"value":"7","order":4,"name":"number_of_full_papers_accepted","label":"Number of Full Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information"}},{"value":"0","order":5,"name":"number_of_short_papers_accepted","label":"Number of Short Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information"}},{"value":"78% - 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"}},{"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"}},{"value":"1","order":8,"name":"average_number_of_papers_per_reviewer","label":"Average Number of Papers per Reviewer","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information"}},{"value":"Yes","order":9,"name":"external_reviewers_involved","label":"External Reviewers Involved","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information"}},{"value":"The peer review information is combined from the workshops FFER 2018 and DLPR 2018.","order":10,"name":"additional_info_on_review_process","label":"Additional Info on Review Process","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information"}}]}}