{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,7,27]],"date-time":"2025-07-27T07:52:30Z","timestamp":1753602750555,"version":"3.40.3"},"publisher-location":"Cham","reference-count":17,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783030638290"},{"type":"electronic","value":"9783030638306"}],"license":[{"start":{"date-parts":[[2020,1,1]],"date-time":"2020-01-01T00:00:00Z","timestamp":1577836800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2020,1,1]],"date-time":"2020-01-01T00:00:00Z","timestamp":1577836800000},"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":[[2020]]},"DOI":"10.1007\/978-3-030-63830-6_2","type":"book-chapter","created":{"date-parts":[[2020,11,18]],"date-time":"2020-11-18T10:08:18Z","timestamp":1605694098000},"page":"12-23","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":2,"title":["An Efficient Joint Training Framework for Robust Small-Footprint Keyword Spotting"],"prefix":"10.1007","author":[{"given":"Yue","family":"Gu","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhihao","family":"Du","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hui","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xueliang","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2020,11,19]]},"reference":[{"key":"2_CR1","doi-asserted-by":"crossref","unstructured":"Du, J., Wang, Q., Gao, T., Xu, Y., Dai, L.R., Lee, C.H.: Robust speech recognition with speech enhanced deep neural networks. In: INTERSPEECH (2014)","DOI":"10.21437\/Interspeech.2014-148"},{"key":"2_CR2","first-page":"448","volume":"37","author":"S Ioffe","year":"2015","unstructured":"Ioffe, S., Szegedy, C.: Batch normalization: Accelerating deep network training by reducing internal covariate shift. ICML 37, 448\u2013456 (2015)","journal-title":"ICML"},{"key":"2_CR3","unstructured":"Kingma, D.P., Ba, J.: Adam: A method for stochastic optimization. In: ICLR (Poster) (2015)"},{"key":"2_CR4","unstructured":"Nair, V., Hinton, G.E.: Rectified linear units improve restricted boltzmann machines. In: ICML. pp. 807\u2013814 (2010)"},{"key":"2_CR5","doi-asserted-by":"crossref","unstructured":"Narayanan, A., Wang, D.: Ideal ratio mask estimation using deep neural networks for robust speech recognition. In: ICASSP. pp. 7092\u20137096 (2013)","DOI":"10.1109\/ICASSP.2013.6639038"},{"key":"2_CR6","doi-asserted-by":"crossref","unstructured":"Prabhavalkar, R., Alvarez, R., Parada, C., Nakkiran, P., Sainath, T.N.: Automatic gain control and multi-style training for robust small-footprint keyword spotting with deep neural networks. In: ICASSP. pp. 4704\u20134708 (2015)","DOI":"10.1109\/ICASSP.2015.7178863"},{"key":"2_CR7","doi-asserted-by":"crossref","unstructured":"Sainath, T., Parada, C.: Convolutional neural networks for small-footprint keyword spotting. In: INTERSPEECH (2015)","DOI":"10.21437\/Interspeech.2015-352"},{"key":"2_CR8","doi-asserted-by":"crossref","unstructured":"Seltzer, M.L., Yu, D., Wang, Y.: An investigation of deep neural networks for noise robust speech recognition. In: ICASSP. pp. 7398\u20137402 (2013)","DOI":"10.1109\/ICASSP.2013.6639100"},{"key":"2_CR9","doi-asserted-by":"crossref","unstructured":"Shan, C., Zhang, J., Wang, Y., Xie, L.: Attention-based end-to-end models for small-footprint keyword spotting. pp. 2037\u20132041 (2018)","DOI":"10.21437\/Interspeech.2018-1777"},{"key":"2_CR10","doi-asserted-by":"crossref","unstructured":"Tan, K., Wang, D.: A convolutional recurrent neural network for real-time speech enhancement. In: INTERSPEECH. pp. 3229\u20133233 (2018)","DOI":"10.21437\/Interspeech.2018-1405"},{"key":"2_CR11","unstructured":"Tang, R., Lin, J.: Honk: A pytorch reimplementation of convolutional neural net- works for keyword spotting. arXiv preprint arXiv:1710.06554 (2017)"},{"key":"2_CR12","doi-asserted-by":"crossref","unstructured":"Tang, R., Lin, J.: Deep residual learning for small-footprint keyword spotting. In: ICASSP. pp. 5484\u20135488 (2018)","DOI":"10.1109\/ICASSP.2018.8462688"},{"issue":"10","key":"2_CR13","doi-asserted-by":"publisher","first-page":"1702","DOI":"10.1109\/TASLP.2018.2842159","volume":"26","author":"D Wang","year":"2018","unstructured":"Wang, D., Chen, J.: Supervised speech separation based on deep learning: an overview. IEEE\/ACM Trans. Audio, Speech, and Language Process. 26(10), 1702\u20131726 (2018)","journal-title":"IEEE\/ACM Trans. Audio, Speech, and Language Process."},{"issue":"12","key":"2_CR14","doi-asserted-by":"publisher","first-page":"1849","DOI":"10.1109\/TASLP.2014.2352935","volume":"22","author":"Y Wang","year":"2014","unstructured":"Wang, Y., Narayanan, A., Wang, D.: On training targets for supervised speech separation. IEEE\/ACM Trans. Audio, Speech, and Language Process. 22(12), 1849\u20131858 (2014)","journal-title":"IEEE\/ACM Trans. Audio, Speech, and Language Process."},{"issue":"4","key":"2_CR15","doi-asserted-by":"publisher","first-page":"796","DOI":"10.1109\/TASLP.2016.2528171","volume":"24","author":"ZQ Wang","year":"2016","unstructured":"Wang, Z.Q., Wang, D.: A joint training framework for robust automatic speech recognition. IEEE\/ACM Trans. Audio, Speech, and Language Process. 24(4), 796\u2013806 (2016)","journal-title":"IEEE\/ACM Trans. Audio, Speech, and Language Process."},{"key":"2_CR16","unstructured":"Warden, P.: Speech commands: A dataset for limited-vocabulary speech recognition. arXiv preprint arXiv:1804.03209 (2018)"},{"key":"2_CR17","doi-asserted-by":"crossref","unstructured":"Yu, M., et al.: Text-dependent speech enhancement for small-footprint robust keyword detection. In: Interspeech. pp. 2613\u20132617 (2018)","DOI":"10.21437\/Interspeech.2018-1668"}],"container-title":["Lecture Notes in Computer Science","Neural Information Processing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-030-63830-6_2","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,3,7]],"date-time":"2024-03-07T14:04:30Z","timestamp":1709820270000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-030-63830-6_2"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020]]},"ISBN":["9783030638290","9783030638306"],"references-count":17,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-63830-6_2","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2020]]},"assertion":[{"value":"19 November 2020","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ICONIP","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Neural Information Processing","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Bangkok","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Thailand","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2020","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"18 November 2020","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"22 November 2020","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":"iconip2020","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/www.apnns.org\/ICONIP2020","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":"CMT","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"618","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":"187","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":"189","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":"30% - 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":"3.18","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":"3.68","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":"Due to COVID-19 pandemic the conference was held virtually.","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)"}}]}}