{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,1]],"date-time":"2026-04-01T18:40:00Z","timestamp":1775068800002,"version":"3.50.1"},"publisher-location":"Cham","reference-count":25,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031781216","type":"print"},{"value":"9783031781223","type":"electronic"}],"license":[{"start":{"date-parts":[[2024,12,5]],"date-time":"2024-12-05T00:00:00Z","timestamp":1733356800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,12,5]],"date-time":"2024-12-05T00:00:00Z","timestamp":1733356800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025]]},"DOI":"10.1007\/978-3-031-78122-3_7","type":"book-chapter","created":{"date-parts":[[2024,12,4]],"date-time":"2024-12-04T07:16:40Z","timestamp":1733296600000},"page":"98-112","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":20,"title":["CAB-KWS : Contrastive Augmentation: An Unsupervised Learning Approach for\u00a0Keyword Spotting in\u00a0Speech Technology"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0009-0004-1201-3471","authenticated-orcid":false,"given":"Weinan","family":"Dai","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0008-9534-0185","authenticated-orcid":false,"given":"Yifeng","family":"Jiang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0002-9636-2526","authenticated-orcid":false,"given":"Yuanjing","family":"Liu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-5792-2097","authenticated-orcid":false,"given":"Jinkun","family":"Chen","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-4333-3990","authenticated-orcid":false,"given":"Xin","family":"Sun","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-4709-4302","authenticated-orcid":false,"given":"Jinglei","family":"Tao","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2024,12,5]]},"reference":[{"key":"7_CR1","doi-asserted-by":"crossref","unstructured":"Chung, Y.A., Hsu, W.N., Tang, H., Glass, J.: An unsupervised autoregressive model for speech representation learning. arXiv preprint arXiv:1904.03240 (2019)","DOI":"10.21437\/Interspeech.2019-1473"},{"key":"7_CR2","unstructured":"De\u00a0Andrade, D.C., Leo, S., Viana, M.L.D.S., Bernkopf, C.: A neural attention model for speech command recognition. arXiv preprint arXiv:1808.08929 (2018)"},{"key":"7_CR3","doi-asserted-by":"crossref","unstructured":"Garcia, A., Gish, H.: Keyword spotting of arbitrary words using minimal speech resources. In: 2006 IEEE International Conference on Acoustics Speech and Signal Processing Proceedings, vol.\u00a01, pp.\u00a0I\u2013I. IEEE (2006)","DOI":"10.1109\/ICASSP.2006.1660179"},{"key":"7_CR4","unstructured":"Hannun, A., et\u00a0al.: Deep speech: scaling up end-to-end speech recognition. arXiv preprint arXiv:1412.5567 (2014)"},{"key":"7_CR5","unstructured":"Jaitly, N., Hinton, G.E.: Vocal tract length perturbation (VTLP) improves speech recognition. In: Proc. ICML Workshop on Deep Learning for Audio, Speech and Language, vol.\u00a0117, pp.\u00a021 (2013)"},{"key":"7_CR6","unstructured":"Jiang, D., et al.: Improving transformer-based speech recognition using unsupervised pre-training. arXiv preprint arXiv:1910.09932 (2019)"},{"key":"7_CR7","doi-asserted-by":"crossref","unstructured":"Kharitonov, E., et al.: Data augmenting contrastive learning of speech representations in the time domain. In: 2021 IEEE Spoken Language Technology Workshop (SLT), pp. 215\u2013222. IEEE (2021)","DOI":"10.1109\/SLT48900.2021.9383605"},{"key":"7_CR8","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":"7_CR9","doi-asserted-by":"crossref","unstructured":"Li, B., et\u00a0al.: Acoustic modeling for google home. In: Interspeech, pp. 399\u2013403 (2017)","DOI":"10.21437\/Interspeech.2017-234"},{"key":"7_CR10","doi-asserted-by":"crossref","unstructured":"Li, P., Liang, J., Xu, B.: A novel instance matching based unsupervised keyword spotting system. In: Second International Conference on Innovative Computing, Informatio and Control (ICICIC 2007), pp. 550\u2013550. IEEE (2007)","DOI":"10.1109\/ICICIC.2007.65"},{"key":"7_CR11","doi-asserted-by":"crossref","unstructured":"Luo, J., Wang, J., Cheng, N., Jiang, G., Xiao, J.: End-to-end silent speech recognition with acoustic sensing. In: 2021 IEEE Spoken Language Technology Workshop (SLT), pp. 606\u2013612. IEEE (2021)","DOI":"10.1109\/SLT48900.2021.9383622"},{"key":"7_CR12","doi-asserted-by":"crossref","unstructured":"Majumdar, S., Ginsburg, B.: MatchboxNet: 1D time-channel separable convolutional neural network architecture for speech commands recognition. arXiv preprint arXiv:2004.08531 (2020)","DOI":"10.21437\/Interspeech.2020-1058"},{"key":"7_CR13","unstructured":"Oord, A.v.d., Li, Y., Vinyals, O.: Representation learning with contrastive predictive coding. arXiv preprint arXiv:1807.03748 (2018)"},{"key":"7_CR14","doi-asserted-by":"crossref","unstructured":"Panayotov, V., Chen, G., Povey, D., Khudanpur, S.: Librispeech: an ASR corpus based on public domain audio books. In: 2015 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 5206\u20135210. IEEE (2015)","DOI":"10.1109\/ICASSP.2015.7178964"},{"key":"7_CR15","doi-asserted-by":"crossref","unstructured":"Park, D.S., et al.: SpecAugment: a simple data augmentation method for automatic speech recognition. arXiv preprint arXiv:1904.08779 (2019)","DOI":"10.21437\/Interspeech.2019-2680"},{"key":"7_CR16","doi-asserted-by":"crossref","unstructured":"Park, D.S., et al.: Improved noisy student training for automatic speech recognition. arXiv preprint arXiv:2005.09629 (2020)","DOI":"10.21437\/Interspeech.2020-1470"},{"key":"7_CR17","doi-asserted-by":"crossref","unstructured":"Park, H.J., Zhu, P., Moreno, I.L., Subrahmanya, N.: Noisy student-teacher training for robust keyword spotting. arXiv preprint arXiv:2106.01604 (2021)","DOI":"10.21437\/Interspeech.2021-72"},{"key":"7_CR18","doi-asserted-by":"crossref","unstructured":"Schalkwyk, J., et al.: \u201cyour word is my command\u201d: Google search by voice: a case study. Adv. Speech Recogn. Mob. Environ. Call Centers Clin. 61\u201390 (2010)","DOI":"10.1007\/978-1-4419-5951-5_4"},{"issue":"1","key":"7_CR19","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1186\/s13636-016-0080-2","volume":"2019","author":"J Tejedor","year":"2019","unstructured":"Tejedor, J., et al.: Search on speech from spoken queries: the multi-domain international albayzin 2018 query-by-example spoken term detection evaluation. EURASIP J. Audio Speech Music Process. 2019(1), 1\u201329 (2019)","journal-title":"EURASIP J. Audio Speech Music Process."},{"key":"7_CR20","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1186\/s13636-018-0125-9","volume":"2018","author":"J Tejedor","year":"2018","unstructured":"Tejedor, J., et al.: Albayzin query-by-example spoken term detection 2016 evaluation. EURASIP J. Audio Speech Music Process. 2018, 1\u201325 (2018)","journal-title":"EURASIP J. Audio Speech Music Process."},{"issue":"6","key":"7_CR21","doi-asserted-by":"publisher","first-page":"1416","DOI":"10.1007\/s11263-022-01589-6","volume":"130","author":"G Varol","year":"2022","unstructured":"Varol, G., Momeni, L., Albanie, S., Afouras, T., Zisserman, A.: Scaling up sign spotting through sign language dictionaries. Int. J. Comput. Vision 130(6), 1416\u20131439 (2022)","journal-title":"Int. J. Comput. Vision"},{"key":"7_CR22","doi-asserted-by":"crossref","unstructured":"Vygon, R., Mikhaylovskiy, N.: Learning efficient representations for keyword spotting with triplet loss. In: Speech and Computer: 23rd International Conference, SPECOM 2021, St. Petersburg, Russia, September 27\u201330, 2021, Proceedings 23, pp. 773\u2013785. Springer (2021)","DOI":"10.1007\/978-3-030-87802-3_69"},{"key":"7_CR23","unstructured":"Warden, P.: Speech commands: a dataset for limited-vocabulary speech recognition. arXiv preprint arXiv:1804.03209 (2018)"},{"key":"7_CR24","unstructured":"Wei, Y., Gong, Z., Yang, S., Ye, K., Wen, Y.: EdgeCRNN: an edge-computing oriented model of acoustic feature enhancement for keyword spotting. J. Ambient Intell. Humanized Comput. 1\u201311 (2022)"},{"key":"7_CR25","doi-asserted-by":"crossref","unstructured":"Zhang, Y., Glass, J.R.: Unsupervised spoken keyword spotting via segmental DTW on Gaussian posteriorgrams. In: 2009 IEEE Workshop on Automatic Speech Recognition & Understanding, pp. 398\u2013403. IEEE (2009)","DOI":"10.1109\/ASRU.2009.5372931"}],"container-title":["Lecture Notes in Computer Science","Pattern Recognition"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-78122-3_7","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,12,4]],"date-time":"2024-12-04T08:08:20Z","timestamp":1733299700000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-78122-3_7"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,12,5]]},"ISBN":["9783031781216","9783031781223"],"references-count":25,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-78122-3_7","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,12,5]]},"assertion":[{"value":"5 December 2024","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ICPR","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Pattern Recognition","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Kolkata","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"India","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2024","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"1 December 2024","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"5 December 2024","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":"icpr2024","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/icpr2024.org\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}