{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,2,22]],"date-time":"2025-02-22T00:18:01Z","timestamp":1740183481339,"version":"3.37.3"},"reference-count":27,"publisher":"World Scientific Pub Co Pte Ltd","issue":"02","funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"crossref","award":["U1836219"],"award-info":[{"award-number":["U1836219"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"crossref"}]},{"name":"National Key R&D Program of China","award":["2019GQG0001"],"award-info":[{"award-number":["2019GQG0001"]}]},{"DOI":"10.13039\/501100017582","name":"Beijing National Research Center for Information Science and Technology","doi-asserted-by":"crossref","award":["BNR2019TD01022"],"award-info":[{"award-number":["BNR2019TD01022"]}],"id":[{"id":"10.13039\/501100017582","id-type":"DOI","asserted-by":"crossref"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Int. J. As. Lang. Proc."],"published-print":{"date-parts":[[2020,6]]},"abstract":"<jats:p>In this paper, we propose a network for small footprint keyword spotting. It includes four parts, data augmentation, Time-Delay Neural Network (TDNN) and Convolutional Neural Network (CNN), Recurrent Neural Network (RNN), and attention mechanism. Data augmentation is Google SpecAugment with time warping and frequency mask and time mask to the spectrum on clean data set and noisy data set. TDNN and CNN model the spectrogram features from the time and space dimensions. RNN-type networks include RNN, Long Short-Term Memory network (LSTM), Gated Recurrent Unit (GRU), Bidirectional Long Short-Term Memory network (BiLSTM), and Bidirectional Gated Recurrent Unit (BiGRU). The RNN extracts hidden layer features and transforms them into high-level representations. The attention mechanism is selected to generate different weights and multiplied by the high-level representation generated by the RNN to obtain a fixed-length vector. Finally, we use a linear transformation and softmax function to generate scores. We also explored the size of attention mechanism, two attention mechanisms, rectified linear unit and hidden layer of RNN. Our model has achieved a true positive rate of 99.81% at a 5% false positive rate.<\/jats:p>","DOI":"10.1142\/s271755452050006x","type":"journal-article","created":{"date-parts":[[2020,9,28]],"date-time":"2020-09-28T11:21:56Z","timestamp":1601292116000},"page":"2050006","source":"Crossref","is-referenced-by-count":0,"title":["An End-to-End Model Based on Multiple Neural Networks with Data Augmentation for Keyword Spotting"],"prefix":"10.1142","volume":"30","author":[{"given":"Shuzhou","family":"Chai","sequence":"first","affiliation":[{"name":"Beijing National Research Center for Information Science and Technology, Department of Electronic Engineering, Tsinghua University, Beijing 10084, Haidian District, P. R. China"}]},{"given":"Wei-Qiang","family":"Zhang","sequence":"additional","affiliation":[{"name":"Beijing National Research Center for Information Science and Technology, Department of Electronic Engineering, Tsinghua University, Beijing 10084, Haidian District, P. R. China"}]},{"given":"Changsheng","family":"Lv","sequence":"additional","affiliation":[{"name":"School of Electronic Engineering, Beijing University of Posts and Telecommunications, Beijing 10084, Haidian District, P. R. China"}]},{"given":"Zhenye","family":"Yang","sequence":"additional","affiliation":[{"name":"Department of Electronic Engineering in Leeds Joint School, The Southwest Jiaotong University, Chengdu, Pidu District, P. R. China"}]}],"member":"219","published-online":{"date-parts":[[2020,9,25]]},"reference":[{"key":"S271755452050006XBIB001","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-4419-5951-5_4"},{"key":"S271755452050006XBIB002","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.1989.266505"},{"key":"S271755452050006XBIB003","first-page":"314","volume-title":"INTERSPEECH 2007, 8th Annual Conf. the Int. Speech Communication Association","author":"Miller D. R.","year":"2007"},{"key":"S271755452050006XBIB005","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2011.2134090"},{"key":"S271755452050006XBIB006","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2013.6639347"},{"key":"S271755452050006XBIB007","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2013.6638947"},{"key":"S271755452050006XBIB008","first-page":"1764","volume-title":"Int. Conf. Machine Learning (ICML)","author":"Graves A.","year":"2014"},{"key":"S271755452050006XBIB009","doi-asserted-by":"publisher","DOI":"10.1515\/jisys-2018-0372"},{"key":"S271755452050006XBIB010","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462105"},{"key":"S271755452050006XBIB011","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU.2013.6707748"},{"key":"S271755452050006XBIB013","first-page":"3586","volume-title":"INTERSPEECH 2015, 16th Annual Conf. the Int. Speech Communication Association","author":"Ko T.","year":"2015"},{"key":"S271755452050006XBIB014","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-1510"},{"key":"S271755452050006XBIB015","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178863"},{"key":"S271755452050006XBIB016","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00020"},{"key":"S271755452050006XBIB018","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.1990.115555"},{"key":"S271755452050006XBIB019","first-page":"1478","volume-title":"INTERSPEECH 2015, 16th Annual Conf. the Int. Speech Communication Association","author":"Sainath T. N.","year":"2015"},{"key":"S271755452050006XBIB020","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2014.6854370"},{"key":"S271755452050006XBIB021","doi-asserted-by":"publisher","DOI":"10.1109\/SLT.2016.7846306"},{"key":"S271755452050006XBIB022","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462688"},{"key":"S271755452050006XBIB023","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-1737"},{"key":"S271755452050006XBIB024","doi-asserted-by":"publisher","DOI":"10.1016\/0167-6393(86)90010-5"},{"key":"S271755452050006XBIB025","doi-asserted-by":"crossref","unstructured":"J. L. McClelland, D. E. Rumelhart, P. R. Group et\u00a0al., Parallel Distributed Processing: Explorations in the Microstructure of Cognition, Vol. 2 (MIT Press, 1986), pp. 216\u2013271.","DOI":"10.7551\/mitpress\/5237.001.0001"},{"key":"S271755452050006XBIB026","first-page":"338","volume-title":"INTERSPEECH 2014, 15th Annual Conf. the Int. Speech Communication Association","author":"Sak H.","year":"2014"},{"volume-title":"2nd Int. Conf. Learning Representations (ICLR)","year":"2013","author":"Pascanu R.","key":"S271755452050006XBIB027"},{"key":"S271755452050006XBIB028","first-page":"900","volume-title":"INTERSPEECH 2014, 15th Annual Conf. the Int. Speech Communication Association","author":"Sainath T. N.","year":"2014"},{"volume-title":"3rd Int. Conf. Learning Representations (ICLR)","year":"2015","author":"Bahdanau D.","key":"S271755452050006XBIB029"},{"volume-title":"3rd Int. Conf. Learning Representations (ICLR)","year":"2015","author":"Kingma D. P.","key":"S271755452050006XBIB030"}],"container-title":["International Journal of Asian Language Processing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.worldscientific.com\/doi\/pdf\/10.1142\/S271755452050006X","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,11,20]],"date-time":"2022-11-20T20:22:11Z","timestamp":1668975731000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.worldscientific.com\/doi\/abs\/10.1142\/S271755452050006X"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,6]]},"references-count":27,"journal-issue":{"issue":"02","published-print":{"date-parts":[[2020,6]]}},"alternative-id":["10.1142\/S271755452050006X"],"URL":"https:\/\/doi.org\/10.1142\/s271755452050006x","relation":{},"ISSN":["2717-5545","2424-791X"],"issn-type":[{"type":"print","value":"2717-5545"},{"type":"electronic","value":"2424-791X"}],"subject":[],"published":{"date-parts":[[2020,6]]}}}