{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,6,18]],"date-time":"2025-06-18T04:24:27Z","timestamp":1750220667180,"version":"3.41.0"},"publisher-location":"New York, NY, USA","reference-count":18,"publisher":"ACM","license":[{"start":{"date-parts":[[2020,10,30]],"date-time":"2020-10-30T00:00:00Z","timestamp":1604016000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2020,10,30]]},"DOI":"10.1145\/3436369.3437430","type":"proceedings-article","created":{"date-parts":[[2021,1,12]],"date-time":"2021-01-12T03:48:53Z","timestamp":1610423333000},"page":"479-483","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":1,"title":["Attention-Based End-to-End Keywords Spotting"],"prefix":"10.1145","author":[{"given":"Hengbo","family":"Hu","sequence":"first","affiliation":[{"name":"PLA Strategic Support Force Information Engineering, University Zhengzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Wenlin","family":"Zhang","sequence":"additional","affiliation":[{"name":"PLA Strategic Support Force Information Engineering, University Zhengzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Li","family":"Feng","sequence":"additional","affiliation":[{"name":"Beijing Institute of Remote Sensing Information, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ziwei","family":"Wei","sequence":"additional","affiliation":[{"name":"PLA Strategic Support Force Information Engineering, University Zhengzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Qi","family":"Chen","sequence":"additional","affiliation":[{"name":"PLA Strategic Support Force Information Engineering, University Zhengzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2021,1,11]]},"reference":[{"key":"e_1_3_2_1_1_1","volume-title":"Proceedings of the International Symposium on Chinese Spoken Language Processing","author":"Bai Y.","year":"2016","unstructured":"Bai , Y. , Yi , J. , Ni , H. , Wen , Z. , Liu , B. , Li , Y. , and Tao , J . 2016. End-to-end keywords spotting based on connectionist temporal classification for Mandarin . In Proceedings of the International Symposium on Chinese Spoken Language Processing ( Tianjin, China , Oct 17-20, 2016 ). ISCSLP'16. IEEE Computer Society, Los Alamitos, CA, 1--5.DOI= https:\/\/doi.org\/10.1109\/ISCSLP.2016.7918460 10.1109\/ISCSLP.2016.7918460 Bai, Y., Yi, J., Ni, H., Wen, Z., Liu, B., Li, Y., and Tao, J. 2016. End-to-end keywords spotting based on connectionist temporal classification for Mandarin. In Proceedings of the International Symposium on Chinese Spoken Language Processing (Tianjin, China, Oct 17-20, 2016). ISCSLP'16. IEEE Computer Society, Los Alamitos, CA, 1--5.DOI= https:\/\/doi.org\/10.1109\/ISCSLP.2016.7918460"},{"key":"e_1_3_2_1_2_1","volume-title":"Proceedings of the IEEE Workshop on Automatic Speech Recognition & Understanding","author":"Zhang Y","year":"2009","unstructured":"Zhang , Y and Glass , J. R . 2009.Unsupervised spoken keyword spotting via segmental DTW on Gaussian posteriorgrams . In Proceedings of the IEEE Workshop on Automatic Speech Recognition & Understanding ( Merano, Italy, Nov 13- Dec 17. 2009 ). ASRU'09. IEEE Computer Society, Los Alamitos, CA, 398--403. DOI= https:\/\/doi.org\/10.1109\/ASRU.2009.5372931. 10.1109\/ASRU.2009.5372931 Zhang, Y and Glass, J. R. 2009.Unsupervised spoken keyword spotting via segmental DTW on Gaussian posteriorgrams. In Proceedings of the IEEE Workshop on Automatic Speech Recognition & Understanding (Merano, Italy, Nov 13- Dec 17. 2009). ASRU'09. IEEE Computer Society, Los Alamitos, CA, 398--403. DOI= https:\/\/doi.org\/10.1109\/ASRU.2009.5372931."},{"key":"e_1_3_2_1_3_1","volume-title":"Proceedings of the IEEE International Conference on Acoustics, Speech and Signal Processing (Brisbane, QLD","author":"Chen G.","year":"2015","unstructured":"Chen , G. , Parada , C. , and Sainath , T. N . 2015. Query-by-example keyword spotting using long short-term memory networks . In Proceedings of the IEEE International Conference on Acoustics, Speech and Signal Processing (Brisbane, QLD , Australia , April 19-24, 2015 ). ICASSP'15. IEEE Computer Society, Los Alamitos, CA, 5236--5240. DOI= https:\/\/doi.org\/10.1109\/ICASSP.2015.7178970 10.1109\/ICASSP.2015.7178970 Chen, G., Parada, C., and Sainath, T. N. 2015. Query-by-example keyword spotting using long short-term memory networks. In Proceedings of the IEEE International Conference on Acoustics, Speech and Signal Processing (Brisbane, QLD, Australia, April 19-24, 2015). ICASSP'15. IEEE Computer Society, Los Alamitos, CA, 5236--5240. DOI= https:\/\/doi.org\/10.1109\/ICASSP.2015.7178970"},{"key":"e_1_3_2_1_4_1","first-page":"2","article-title":"Recent developments in spoken term detection: a survey","volume":"17","author":"Anupam Mandal K. R.","year":"2014","unstructured":"Anupam Mandal , K. R. Prasanna Kumar , and Pabitra Mitra. 2014 . Recent developments in spoken term detection: a survey . Int. J. Speech Technol. 17 , 2 (June 2014), 183--198. DOI=https:\/\/doi.org\/10.1007\/s10772-013-9217-1 10.1007\/s10772-013-9217-1 Anupam Mandal, K. R. Prasanna Kumar, and Pabitra Mitra. 2014. Recent developments in spoken term detection: a survey. Int. J. Speech Technol. 17, 2 (June 2014), 183--198. DOI=https:\/\/doi.org\/10.1007\/s10772-013-9217-1","journal-title":"Int. J. Speech Technol."},{"key":"e_1_3_2_1_5_1","volume-title":"Proceedings of the IEEE International Conference on Acoustics, Speech and Signal Processing","author":"Chen G.","year":"2014","unstructured":"Chen , G. , Parada , C. , and Heigold , G . 2014. Small-footprint keyword spotting using deep neural networks . In Proceedings of the IEEE International Conference on Acoustics, Speech and Signal Processing ( Florence, Italy , May 4-9, 2014 ). ICASSP'14. IEEE Computer Society, Los Alamitos, CA, 4087--4091. DOI= https:\/\/doi.org\/10.1109\/ICASSP.2014.6854370 10.1109\/ICASSP.2014.6854370 Chen, G., Parada, C., and Heigold, G. 2014. Small-footprint keyword spotting using deep neural networks. In Proceedings of the IEEE International Conference on Acoustics, Speech and Signal Processing (Florence, Italy, May 4-9, 2014). ICASSP'14. IEEE Computer Society, Los Alamitos, CA, 4087--4091. DOI= https:\/\/doi.org\/10.1109\/ICASSP.2014.6854370"},{"unstructured":"De Andrade D. C. Leo S. Viana M. L. D. S. and Bernkopf C. 2018. A neural attention model for speech command recognition ArXiv preprint arXiv: 1808.08929 2018.  De Andrade D. C. Leo S. Viana M. L. D. S. and Bernkopf C. 2018. A neural attention model for speech command recognition ArXiv preprint arXiv: 1808.08929 2018.","key":"e_1_3_2_1_6_1"},{"key":"e_1_3_2_1_7_1","volume-title":"Proceedings of the Annual Conference of the International Speech Communication Association","author":"Sainath T. N.","year":"2015","unstructured":"Sainath , T. N. , and Parada , C . 2015. Convolutional neural networks for small-footprint keyword spotting , in Proceedings of the Annual Conference of the International Speech Communication Association ( Dresden, Germany , September 6-10, 2015 ). INTERSPEECH'16, 1478--1482. Sainath, T. N., and Parada, C. 2015. Convolutional neural networks for small-footprint keyword spotting, in Proceedings of the Annual Conference of the International Speech Communication Association (Dresden, Germany, September 6-10, 2015). INTERSPEECH'16, 1478--1482."},{"doi-asserted-by":"publisher","key":"e_1_3_2_1_8_1","DOI":"10.21437\/Interspeech.2017-1737"},{"doi-asserted-by":"publisher","key":"e_1_3_2_1_9_1","DOI":"10.1109\/ASRU.2017.8268974"},{"key":"e_1_3_2_1_10_1","volume-title":"Proceedings of the Annual Conference of the International Speech Communication Association","author":"Mikolov T.","year":"2010","unstructured":"Mikolov , T. , Karafi' M. , Burget , L. , \u010cernock\u00fd , J. , and Khudanpur , S . 2010. Recurrent neural network based language model , In Proceedings of the Annual Conference of the International Speech Communication Association ( Makuhari, Chiba, Japan , September 26-30, 2010 ). INTERSPEECH'11. 1045--1048 Mikolov, T., Karafi'M., Burget, L., \u010cernock\u00fd, J., and Khudanpur, S. 2010. Recurrent neural network based language model, In Proceedings of the Annual Conference of the International Speech Communication Association ( Makuhari, Chiba, Japan, September 26-30, 2010). INTERSPEECH'11. 1045--1048"},{"key":"e_1_3_2_1_11_1","volume-title":"Proceedings of the IEEE International Conference on Acoustics, Speech and Signal Processing","author":"Yan H.","year":"2020","unstructured":"Yan , H. , He , Q. , and Xie , W . 2020. Crnn-Ctc Based Mandarin Keywords Spotting . In Proceedings of the IEEE International Conference on Acoustics, Speech and Signal Processing ( Barcelona, Spain, Spain , May 4-8, 2020 ). ICASSP'20. IEEE Computer Society, Los Alamitos, CA. DOI=10.1109\/icassp40776.2020.9054618 Yan, H., He, Q., and Xie, W. 2020. Crnn-Ctc Based Mandarin Keywords Spotting. In Proceedings of the IEEE International Conference on Acoustics, Speech and Signal Processing (Barcelona, Spain, Spain, May 4-8, 2020). ICASSP'20. IEEE Computer Society, Los Alamitos, CA. DOI=10.1109\/icassp40776.2020.9054618"},{"doi-asserted-by":"publisher","key":"e_1_3_2_1_12_1","DOI":"10.21437\/Interspeech.2016-753"},{"key":"e_1_3_2_1_13_1","volume-title":"ArXiveprints","author":"Hwang K.","year":"2015","unstructured":"Hwang , K. , Lee , M. , and Sung , W . Online keyword spotting with a character-level recurrent neural network , ArXiveprints , December 2015 Hwang, K., Lee, M., and Sung, W. Online keyword spotting with a character-level recurrent neural network, ArXiveprints, December 2015"},{"key":"e_1_3_2_1_14_1","volume-title":"ArXiv e-prints","author":"Lengerich C.","year":"2016","unstructured":"Lengerich , C. , and Hannun , A. , An end-to-end architecture for keyword spotting and voice activity detection , ArXiv e-prints , November 2016 Lengerich, C., and Hannun, A., An end-to-end architecture for keyword spotting and voice activity detection, ArXiv e-prints, November 2016"},{"doi-asserted-by":"publisher","key":"e_1_3_2_1_15_1","DOI":"10.1109\/JSTSP.2017.2759726"},{"doi-asserted-by":"publisher","key":"e_1_3_2_1_16_1","DOI":"10.21437\/Interspeech.2018-1777"},{"doi-asserted-by":"publisher","key":"e_1_3_2_1_17_1","DOI":"10.21437\/Interspeech.2019-1676"},{"key":"e_1_3_2_1_18_1","volume-title":"ArXiv preprint arXiv:1808.10583","author":"Du J.","year":"2018","unstructured":"Du , J. , Na , X. , Liu , X. , and , Aishell-2: Transforming mandarin asr research into industrial scale , ArXiv preprint arXiv:1808.10583 , 2018 . Du, J., Na, X., Liu, X., and et al., Aishell-2: Transforming mandarin asr research into industrial scale, ArXiv preprint arXiv:1808.10583, 2018."}],"event":{"sponsor":["Beijing University of Technology"],"acronym":"ICCPR 2020","name":"ICCPR 2020: 2020 9th International Conference on Computing and Pattern Recognition","location":"Xiamen China"},"container-title":["Proceedings of the 2020 9th International Conference on Computing and Pattern Recognition"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3436369.3437430","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3436369.3437430","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T22:02:53Z","timestamp":1750197773000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3436369.3437430"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,10,30]]},"references-count":18,"alternative-id":["10.1145\/3436369.3437430","10.1145\/3436369"],"URL":"https:\/\/doi.org\/10.1145\/3436369.3437430","relation":{},"subject":[],"published":{"date-parts":[[2020,10,30]]},"assertion":[{"value":"2021-01-11","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}