{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,15]],"date-time":"2026-03-15T22:59:26Z","timestamp":1773615566242,"version":"3.50.1"},"reference-count":10,"publisher":"Allerton Press","issue":"4","license":[{"start":{"date-parts":[[2024,8,1]],"date-time":"2024-08-01T00:00:00Z","timestamp":1722470400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,8,1]],"date-time":"2024-08-01T00:00:00Z","timestamp":1722470400000},"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":["Aut. Control Comp. Sci."],"published-print":{"date-parts":[[2024,8]]},"DOI":"10.3103\/s0146411624700561","type":"journal-article","created":{"date-parts":[[2024,8,28]],"date-time":"2024-08-28T06:02:32Z","timestamp":1724824952000},"page":"454-458","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Building a Production-Ready Keyword Detection System on a Real-World Audio"],"prefix":"10.3103","volume":"58","author":[{"family":"Eugene Zhmakin","sequence":"first","affiliation":[]},{"family":"Grach Mkrtchian","sequence":"additional","affiliation":[]}],"member":"1627","published-online":{"date-parts":[[2024,8,28]]},"reference":[{"key":"7717_CR1","doi-asserted-by":"publisher","first-page":"361","DOI":"10.1109\/tassp.1977.1162983","volume":"25","author":"R. Christiansen","year":"1977","unstructured":"Christiansen, R. and Rushforth, C., Detecting and locating key words in continuous speech using linear predictive coding, IEEE Trans. Acoust., Speech, Signal Process., 1977, vol. 25, no. 5, pp. 361\u2013367. https:\/\/doi.org\/10.1109\/tassp.1977.1162983","journal-title":"IEEE Trans. Acoust., Speech, Signal Process."},{"key":"7717_CR2","doi-asserted-by":"publisher","unstructured":"Shrivastava, A., Kundu, A., Dhir, Ch., Naik, D., and Tuzel, O., Optimize what matters: Training DNN-Hmm keyword spotting model using end metric, ICASSP 2021\u20132021 IEEE Int. Conf. on Acoustics, Speech and Signal Processing (ICASSP), Toronto, 2021, IEEE, 2021, pp. 4000\u20134004. https:\/\/doi.org\/10.1109\/icassp39728.2021.9414797","DOI":"10.1109\/icassp39728.2021.9414797"},{"key":"7717_CR3","doi-asserted-by":"publisher","unstructured":"Warden, P., Speech commands: A dataset for limited-vocabulary speech recognition, arXiv Preprint, 2018. https:\/\/doi.org\/10.48550\/arXiv.1804.03209","DOI":"10.48550\/arXiv.1804.03209"},{"key":"7717_CR4","doi-asserted-by":"publisher","unstructured":"Ardila, R., Branson, M., Davis, K., Henretty, M., Kohler, M., Meyer, J., Morais, R., Saunders, L., Tyers, F.M., and Weber, G., Common voice: A massively-multilingual speech corpus, arXiv Preprint, 2020. https:\/\/doi.org\/10.48550\/arXiv.1912.06670","DOI":"10.48550\/arXiv.1912.06670"},{"key":"7717_CR5","doi-asserted-by":"publisher","unstructured":"Kim, B., Chang, S., Lee, J., and Sung, D., Broadcasted residual learning for efficient keyword spotting, Proc. Interspeech 2021, ISCA, 2023, pp. 4538\u20134542. https:\/\/doi.org\/10.21437\/interspeech.2021-383","DOI":"10.21437\/interspeech.2021-383"},{"key":"7717_CR6","doi-asserted-by":"publisher","unstructured":"Berg, A., O\u2019Connor, M., and Cruz, M.T., Keyword transformer: A self-attention model for keyword spotting, Proc. Interspeech 2021, ISCA, 2021. https:\/\/doi.org\/10.21437\/interspeech.2021-1286","DOI":"10.21437\/interspeech.2021-1286"},{"key":"7717_CR7","doi-asserted-by":"publisher","unstructured":"Howard, A., Sandler, M., Chen, B., Wang, W., Chen, L.-C., Tan, M., Chu, G., Vasudevan, V., Zhu, Yu., Pang, R., Adam, H., and Le, Q., Searching for MobileNetV3, 2019 IEEE\/CVF Int. Conf. on Computer Vision (ICCV), Seoul, 2019, IEEE, 2019, pp. 1314\u20131324. https:\/\/doi.org\/10.1109\/iccv.2019.00140","DOI":"10.1109\/iccv.2019.00140"},{"key":"7717_CR8","doi-asserted-by":"publisher","unstructured":"Simonyan, K. and Zisserman, A., Very deep convolutional networks for large-scale image recognition, arXiv Preprint, 2015. https:\/\/doi.org\/10.48550\/arXiv.1409.1556","DOI":"10.48550\/arXiv.1409.1556"},{"key":"7717_CR9","doi-asserted-by":"publisher","unstructured":"Park, D.S., Chan, W., Zhang, Yu., Chiu, C.-C., Zoph, B., Cubuk, E.D., and Le, Q.V., SpecAugment: A simple data augmentation method for automatic speech recognition, Proc. Interspeech 2019, ISCA, 2019, pp. 2613\u20132617. https:\/\/doi.org\/10.21437\/interspeech.2019-2680","DOI":"10.21437\/interspeech.2019-2680"},{"key":"7717_CR10","unstructured":"S. Team, Silero VAD: Pretrained enterprise-grade voice activity detector (VAD), number detector, and language classifier, GitHub, 2021. https:\/\/github.com\/snakers4\/silero-vad."}],"container-title":["Automatic Control and Computer Sciences"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.3103\/S0146411624700561.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.3103\/S0146411624700561","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.3103\/S0146411624700561.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,15]],"date-time":"2026-03-15T22:01:38Z","timestamp":1773612098000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.3103\/S0146411624700561"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,8]]},"references-count":10,"journal-issue":{"issue":"4","published-print":{"date-parts":[[2024,8]]}},"alternative-id":["7717"],"URL":"https:\/\/doi.org\/10.3103\/s0146411624700561","relation":{},"ISSN":["0146-4116","1558-108X"],"issn-type":[{"value":"0146-4116","type":"print"},{"value":"1558-108X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,8]]},"assertion":[{"value":"24 July 2023","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"25 October 2023","order":2,"name":"revised","label":"Revised","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"25 October 2023","order":3,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"28 August 2024","order":4,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"The authors of this work declare that they have no conflicts of interest.","order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"CONFLICT OF INTEREST"}}]}}