{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,8]],"date-time":"2026-07-08T04:54:49Z","timestamp":1783486489505,"version":"3.55.0"},"reference-count":42,"publisher":"Springer Science and Business Media LLC","issue":"3","license":[{"start":{"date-parts":[[2021,3,14]],"date-time":"2021-03-14T00:00:00Z","timestamp":1615680000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2021,3,14]],"date-time":"2021-03-14T00:00:00Z","timestamp":1615680000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Sciences Foundation of China","doi-asserted-by":"crossref","award":["62072192"],"award-info":[{"award-number":["62072192"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"crossref"}]},{"name":"National Cryptography Development Fund","award":["MMJJ20180206"],"award-info":[{"award-number":["MMJJ20180206"]}]},{"name":"the Project of Science and Technology of Guangzhou","award":["201802010044"],"award-info":[{"award-number":["201802010044"]}]},{"DOI":"10.13039\/501100021171","name":"Guangdong Basic and Applied Basic Research Foundation","doi-asserted-by":"crossref","award":["2019A1515011797"],"award-info":[{"award-number":["2019A1515011797"]}],"id":[{"id":"10.13039\/501100021171","id-type":"DOI","asserted-by":"crossref"}]},{"name":"the Opening Project of GuangDong Province Key Laboratory of Information Security Technology","award":["2020B1212060078"],"award-info":[{"award-number":["2020B1212060078"]}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["J Ambient Intell Human Comput"],"published-print":{"date-parts":[[2022,3]]},"DOI":"10.1007\/s12652-021-03022-1","type":"journal-article","created":{"date-parts":[[2021,3,14]],"date-time":"2021-03-14T03:02:23Z","timestamp":1615690943000},"page":"1525-1535","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":17,"title":["EdgeCRNN: an edge-computing oriented model of acoustic feature enhancement for keyword spotting"],"prefix":"10.1007","volume":"13","author":[{"given":"Yungen","family":"Wei","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zheng","family":"Gong","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shunzhi","family":"Yang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Kai","family":"Ye","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yamin","family":"Wen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2021,3,14]]},"reference":[{"issue":"10","key":"3022_CR1","doi-asserted-by":"publisher","first-page":"1533","DOI":"10.1109\/TASLP.2014.2339736","volume":"22","author":"O Abdel-Hamid","year":"2014","unstructured":"Abdel-Hamid O, Ar Mohamed, Jiang H, Deng L, Penn G, Yu D (2014) Convolutional neural networks for speech recognition. IEEE\/ACM Trans Audio Speech Lang Process 22(10):1533\u20131545","journal-title":"IEEE\/ACM Trans Audio Speech Lang Process"},{"key":"3022_CR2","doi-asserted-by":"crossref","unstructured":"Anderson A, Su J, Dahyot R, Gregg D (2020) Performance-oriented neural architecture search. arXiv preprint arXiv:200102976","DOI":"10.1109\/HPCS48598.2019.9188213"},{"key":"3022_CR3","doi-asserted-by":"crossref","unstructured":"Arik SO, Kliegl M, Child R, Hestness J, Gibiansky A, Fougner C, Prenger R, Coates A (2017) Convolutional recurrent neural networks for small-footprint keyword spotting. arXiv preprint arXiv:170305390","DOI":"10.21437\/Interspeech.2017-1737"},{"key":"3022_CR4","doi-asserted-by":"crossref","unstructured":"Benelli G, Meoni G, Fanucci L (2018) A low power keyword spotting algorithm for memory constrained embedded systems. In: 2018 IFIP\/IEEE international conference on very large scale integration (VLSI-SoC). IEEE, pp 267\u2013272","DOI":"10.1109\/VLSI-SoC.2018.8644728"},{"key":"3022_CR5","doi-asserted-by":"crossref","unstructured":"Chen G, Parada C, Heigold G (2014) Small-footprint keyword spotting using deep neural networks. In: 2014 IEEE international conference on acoustics. speech and signal processing (ICASSP). IEEE, pp 4087\u20134091","DOI":"10.1109\/ICASSP.2014.6854370"},{"key":"3022_CR6","doi-asserted-by":"crossref","unstructured":"Cho K, Van\u00a0Merri\u00ebnboer B, Gulcehre C, Bahdanau D, Bougares F, Schwenk H, Bengio Y (2014) Learning phrase representations using RNN encoder-decoder for statistical machine translation. arXiv preprint arXiv:14061078","DOI":"10.3115\/v1\/D14-1179"},{"key":"3022_CR7","doi-asserted-by":"crossref","unstructured":"Coucke A, Chlieh M, Gisselbrecht T, Leroy D, Poumeyrol M, Lavril T (2019) Efficient keyword spotting using dilated convolutions and gating. In: ICASSP 2019\u20132019 IEEE international conference on acoustics. speech and signal processing (ICASSP). IEEE, pp 6351\u20136355","DOI":"10.1109\/ICASSP.2019.8683474"},{"key":"3022_CR8","doi-asserted-by":"publisher","DOI":"10.1007\/978-94-6265-282-8","volume-title":"EU personal data protection in policy and practice","author":"B Custers","year":"2019","unstructured":"Custers B, Sears AM, Dechesne F, Georgieva I, Tani T, van der Hof S (2019) EU personal data protection in policy and practice. Springer, Berlin"},{"key":"3022_CR9","doi-asserted-by":"crossref","unstructured":"Dey R, Salemt FM (2017) Gate-variants of gated recurrent unit (GRU) neural networks. In: 2017 IEEE 60th international midwest symposium on circuits and systems (MWSCAS). IEEE, pp 1597\u20131600","DOI":"10.1109\/MWSCAS.2017.8053243"},{"key":"3022_CR10","doi-asserted-by":"publisher","first-page":"7218758","DOI":"10.1155\/2019\/7218758","volume":"2019","author":"G Dinelli","year":"2019","unstructured":"Dinelli G, Meoni G, Rapuano E, Benelli G, Fanucci L (2019) An FPGA-based hardware accelerator for CNNS using on-chip memories only: design and benchmarking with intel movidius neural compute stick. Int J Reconfigurable Comput 2019:7218758","journal-title":"Int J Reconfigurable Comput"},{"key":"3022_CR11","doi-asserted-by":"crossref","unstructured":"Du H, Li R, Kim D, Hirota K, Dai Y (2018) Low-latency convolutional recurrent neural network for keyword spotting. In: 2018 Joint 10th international conference on soft computing and intelligent systems (SCIS) and 19th International Symposium on Advanced Intelligent Systems (ISIS). IEEE, pp 802\u2013807","DOI":"10.1109\/SCIS-ISIS.2018.00133"},{"issue":"6","key":"3022_CR12","doi-asserted-by":"publisher","first-page":"7","DOI":"10.1109\/MC.2014.161","volume":"47","author":"BM Gaff","year":"2014","unstructured":"Gaff BM, Sussman HE, Geetter J (2014) Privacy and big data. Computer 47(6):7\u20139","journal-title":"Computer"},{"key":"3022_CR13","unstructured":"Glorot X, Bordes A, Bengio Y (2011) Deep sparse rectifier neural networks. In: Proceedings of the fourteenth international conference on artificial intelligence and statistics, pp 315\u2013323"},{"key":"3022_CR14","doi-asserted-by":"crossref","unstructured":"He K, Zhang X, Ren S, Sun J (2016) Deep residual learning for image recognition. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 770\u2013778","DOI":"10.1109\/CVPR.2016.90"},{"issue":"8","key":"3022_CR15","doi-asserted-by":"publisher","first-page":"1735","DOI":"10.1162\/neco.1997.9.8.1735","volume":"9","author":"S Hochreiter","year":"1997","unstructured":"Hochreiter S, Schmidhuber J (1997) Long short-term memory. Neural Comput 9(8):1735\u20131780","journal-title":"Neural Comput"},{"key":"3022_CR16","doi-asserted-by":"crossref","unstructured":"Howard A, Sandler M, Chu G, Chen LC, Chen B, Tan M, Wang W, Zhu Y, Pang R, Vasudevan V et\u00a0al (2019) Searching for mobilenetv3. In: Proceedings of the IEEE international conference on computer vision, pp 1314\u20131324","DOI":"10.1109\/ICCV.2019.00140"},{"key":"3022_CR17","unstructured":"Howard AG, Zhu M, Chen B, Kalenichenko D, Wang W, Weyand T, Andreetto M, Adam H (2017) Mobilenets: efficient convolutional neural networks for mobile vision applications. arXiv preprint arXiv:170404861"},{"key":"3022_CR18","unstructured":"Ioffe S, Szegedy C (2015) Batch normalization: accelerating deep network training by reducing internal covariate shift. arXiv preprint arXiv:150203167"},{"key":"3022_CR19","unstructured":"Luo R, Sun T, Wang C, Du M, Tang Z, Zhou K, Gong X, Yang X (2019) Multi-layer attention mechanism for speech keyword recognition. arXiv preprint arXiv:190704536"},{"key":"3022_CR20","doi-asserted-by":"crossref","unstructured":"Ma N, Zhang X, Zheng HT, Sun J (2018) Shufflenet v2: practical guidelines for efficient CNN architecture design. In: Proceedings of the European conference on computer vision (ECCV), pp 116\u2013131","DOI":"10.1007\/978-3-030-01264-9_8"},{"key":"3022_CR21","doi-asserted-by":"crossref","unstructured":"Mazzawi H, Gonzalvo X, Kracun A, Sridhar P, Subrahmanya N, Moreno IL, Park HJ, Violette P (2019) Improving keyword spotting and language identification via neural architecture search at scale. In: Proc Interspeech, vol 2019, pp 1278\u20131282","DOI":"10.21437\/Interspeech.2019-1916"},{"key":"3022_CR22","doi-asserted-by":"crossref","unstructured":"McFee B, Raffel C, Liang D, Ellis DP, McVicar M, Battenberg E, Nieto O (2015) Librosa: audio and music signal analysis in python. In: Proceedings of the 14th python in science conference, vol\u00a08","DOI":"10.25080\/Majora-7b98e3ed-003"},{"key":"3022_CR23","doi-asserted-by":"crossref","unstructured":"Mishchenko Y, Goren Y, Sun M, Beauchene C, Matsoukas S, Rybakov O, Vitaladevuni SNP (2019) Low-bit quantization and quantization-aware training for small-footprint keyword spotting. In: 2019 18th IEEE international conference on machine learning and applications (ICMLA). IEEE, pp 706\u2013711","DOI":"10.1109\/ICMLA.2019.00127"},{"key":"3022_CR24","doi-asserted-by":"crossref","unstructured":"Nakkiran P, Alvarez R, Prabhavalkar R and Parada C (2015) Compressing deep neural networks using a rank-constrained topology, In: Proceedings of annual conference of the international speech communication association (Interspeech). pp 1473\u20131477","DOI":"10.21437\/Interspeech.2015-351"},{"key":"3022_CR25","doi-asserted-by":"crossref","unstructured":"Sainath TN, Parada C (2015) Convolutional neural networks for small-footprint keyword spotting. In: Proceeding of the Sixteenth Annual Conference of the International Speech Communication Association (Interspeech). pp 1478\u20131482","DOI":"10.21437\/Interspeech.2015-352"},{"key":"3022_CR26","doi-asserted-by":"crossref","unstructured":"Sandler M, Howard A, Zhu M, Zhmoginov A, Chen LC (2018) Mobilenetv2: Inverted residuals and linear bottlenecks. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 4510\u20134520","DOI":"10.1109\/CVPR.2018.00474"},{"key":"3022_CR27","unstructured":"Sifre L, Mallat S (2014) Rigid-motion scattering for image classification. Ph.D. Thesis"},{"key":"3022_CR28","unstructured":"Silaghi MC (2005) Spotting subsequences matching an hmm using the average observation probability criteria with application to keyword spotting. In: AAAI, pp 1118\u20131123"},{"key":"3022_CR29","unstructured":"Silaghi MC, Bourlard H (1999) Iterative posterior-based keyword spotting without filler models. In: Proceedings of the IEEE automatic speech recognition and understanding workshop. Citeseer, pp 213\u2013216"},{"key":"3022_CR30","doi-asserted-by":"crossref","unstructured":"Sun M, Raju A, Tucker G, Panchapagesan S, Fu G, Mandal A, Matsoukas S, Strom N, Vitaladevuni S (2016) Max-pooling loss training of long short-term memory networks for small-footprint keyword spotting. In: 2016 IEEE spoken language technology workshop (SLT). IEEE, pp 474\u2013480","DOI":"10.1109\/SLT.2016.7846306"},{"key":"3022_CR31","doi-asserted-by":"crossref","unstructured":"Sun M, Snyder D, Gao Y, Nagaraja VK, Rodehorst M, Panchapagesan S, Strom N, Matsoukas S, Vitaladevuni S (2017) Compressed time delay neural network for small-footprint keyword spotting. In: INTERSPEECH, pp 3607\u20133611","DOI":"10.21437\/Interspeech.2017-480"},{"key":"3022_CR32","unstructured":"Tan M, Chen B, Pang R, Vasudevan V, Sandler M, Howard A, Le QV (2018) Resource-efficient neural architect. arXiv preprint arXiv:180607912"},{"key":"3022_CR33","doi-asserted-by":"crossref","unstructured":"Tang R, Lin J (2018) Deep residual learning for small-footprint keyword spotting. 2018 IEEE International Conference on Acoustics. Speech and Signal Processing (ICASSP). IEEE, pp 5484\u20135488","DOI":"10.1109\/ICASSP.2018.8462688"},{"key":"3022_CR34","doi-asserted-by":"crossref","unstructured":"Tang R, Wang W, Tu Z, Lin J (2018) An experimental analysis of the power consumption of convolutional neural networks for keyword spotting. In: 2018 IEEE international conference on acoustics. speech and signal processing (ICASSP). IEEE, pp 5479\u20135483","DOI":"10.1109\/ICASSP.2018.8461624"},{"key":"3022_CR35","doi-asserted-by":"crossref","unstructured":"Tucker G, Wu M, Sun M, Panchapagesan S, Fu G, Vitaladevuni S (2016) Model compression applied to small-footprint keyword spotting. In: INTERSPEECH, pp 1878\u20131882","DOI":"10.21437\/Interspeech.2016-1393"},{"key":"3022_CR36","doi-asserted-by":"crossref","unstructured":"V\u00e9niat T, Schwander O, Denoyer L (2019) Stochastic adaptive neural architecture search for keyword spotting. In: ICASSP 2019\u20132019 IEEE international conference on acoustics. speech and signal processing (ICASSP). IEEE, pp 2842\u20132846","DOI":"10.1109\/ICASSP.2019.8683305"},{"key":"3022_CR37","unstructured":"Warden P (2018) Speech commands: A dataset for limited-vocabulary speech recognition. arXiv preprint arXiv:180403209"},{"key":"3022_CR38","doi-asserted-by":"crossref","unstructured":"Wilpon J, Miller L, Modi P (1991) Improvements and applications for key word recognition using hidden markov modeling techniques. In: 1991 international conference on acoustics, speech, and signal processing. IEEE, pp 309\u2013312","DOI":"10.1109\/ICASSP.1991.150338"},{"key":"3022_CR39","doi-asserted-by":"publisher","first-page":"10767","DOI":"10.1109\/ACCESS.2019.2891838","volume":"7","author":"M Zeng","year":"2019","unstructured":"Zeng M, Xiao N (2019) Effective combination of DenseNet and BiLSTM for keyword spotting. IEEE Access 7:10767\u201310775","journal-title":"IEEE Access"},{"key":"3022_CR40","doi-asserted-by":"crossref","unstructured":"Zhang B, Li W, Li Q, Zhuang W, Chu X, Wang Y (2020) Autokws: keyword spotting with differentiable architecture search. arXiv preprint arXiv:200903658","DOI":"10.1109\/ICASSP39728.2021.9414848"},{"key":"3022_CR41","doi-asserted-by":"crossref","unstructured":"Zhang X, Zhou X, Lin M, Sun J (2018) Shufflenet: An extremely efficient convolutional neural network for mobile devices. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 6848\u20136856","DOI":"10.1109\/CVPR.2018.00716"},{"key":"3022_CR42","unstructured":"Zhang Y, Suda N, Lai L, Chandra V (2017) Hello edge: keyword spotting on microcontrollers. arXiv preprint arXiv:171107128"}],"container-title":["Journal of Ambient Intelligence and Humanized Computing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s12652-021-03022-1.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s12652-021-03022-1\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s12652-021-03022-1.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,3,1]],"date-time":"2022-03-01T10:37:05Z","timestamp":1646131025000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s12652-021-03022-1"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,3,14]]},"references-count":42,"journal-issue":{"issue":"3","published-print":{"date-parts":[[2022,3]]}},"alternative-id":["3022"],"URL":"https:\/\/doi.org\/10.1007\/s12652-021-03022-1","relation":{},"ISSN":["1868-5137","1868-5145"],"issn-type":[{"value":"1868-5137","type":"print"},{"value":"1868-5145","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021,3,14]]},"assertion":[{"value":"12 October 2020","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"1 March 2021","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"14 March 2021","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}]}}