{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,23]],"date-time":"2026-01-23T10:00:56Z","timestamp":1769162456815,"version":"3.49.0"},"reference-count":24,"publisher":"Springer Science and Business Media LLC","issue":"4","license":[{"start":{"date-parts":[[2023,11,11]],"date-time":"2023-11-11T00:00:00Z","timestamp":1699660800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2023,11,11]],"date-time":"2023-11-11T00:00:00Z","timestamp":1699660800000},"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":["Int J Speech Technol"],"published-print":{"date-parts":[[2023,12]]},"DOI":"10.1007\/s10772-023-10067-4","type":"journal-article","created":{"date-parts":[[2023,11,11]],"date-time":"2023-11-11T05:01:40Z","timestamp":1699678900000},"page":"919-931","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["Robust and efficient keyword spotting using a bidirectional attention LSTM"],"prefix":"10.1007","volume":"26","author":[{"given":"Om Prakash","family":"Swain","sequence":"first","affiliation":[]},{"given":"H.","family":"Hemanth","sequence":"additional","affiliation":[]},{"given":"Puneet","family":"Saran","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3938-7495","authenticated-orcid":false,"given":"Mohanaprasad","family":"Kothandaraman","sequence":"additional","affiliation":[]},{"given":"Logesh","family":"Ravi","sequence":"additional","affiliation":[]},{"given":"Hardik","family":"Sailor","sequence":"additional","affiliation":[]},{"given":"K. S.","family":"Rajesh","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2023,11,11]]},"reference":[{"key":"10067_CR1","doi-asserted-by":"crossref","unstructured":"Arik, S. O., Kliegl, M., Child, R., Hestness, J., Gibiansky, A., Fougner, C., Prenger, R., & Coates, A. (2017). Convolutional recurrent neural networks for small-footprint keyword spotting. Preprint at https:\/\/arXiv.org\/\/1703.05390","DOI":"10.21437\/Interspeech.2017-1737"},{"key":"10067_CR2","doi-asserted-by":"crossref","unstructured":"Berg, A., O\u2019Connor, M., & Cruz, M. T. (2021). Keyword transformer: A self-attention model for keyword spotting. Preprint at https:\/\/arXiv.org\/2104.00769","DOI":"10.21437\/Interspeech.2021-1286"},{"key":"10067_CR3","unstructured":"Bluche, T., Primet, M., & Gisselbrecht, T. (2020). Small-footprint open-vocabulary keyword spotting with quantized LSTM networks. Preprint at https:\/\/arXiv.org\/2002.10851"},{"key":"10067_CR5","doi-asserted-by":"crossref","unstructured":"Chen, G., Parada, C., & Sainath, T. N. (2015). Query-by-example keyword spotting using long short-term memory networks. In 2015 IEEE international conference on acoustics, speech and signal processing (ICASSP) (pp. 5236\u20135240). IEEE.","DOI":"10.1109\/ICASSP.2015.7178970"},{"key":"10067_CR4","doi-asserted-by":"crossref","unstructured":"Chen, X., Yin, S., Song, D., Ouyang, P., Liu, L., & Wei, S. (2019). Small-footprint keyword spotting with graph convolutional network. In 2019 IEEE automatic speech recognition and understanding workshop (ASRU) (pp. 539\u2013546). IEEE.","DOI":"10.1109\/ASRU46091.2019.9004005"},{"key":"10067_CR6","doi-asserted-by":"crossref","unstructured":"Choi, S., Seo, S., Shin, B., Byun, H., Kersner, M., Kim, B., Kim, D., & Ha, S. (2019). Temporal convolution for real-time keyword spotting on mobile devices. Preprint at https:\/\/arXiv.org\/2008.00209","DOI":"10.21437\/Interspeech.2019-1363"},{"key":"10067_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 2019 IEEE international conference on acoustics, speech and signal processing (ICASSP) (pp. 6351\u20136355). IEEE.","DOI":"10.1109\/ICASSP.2019.8683474"},{"key":"10067_CR8","unstructured":"Fuketa, H., & Morita, Y. (2020). Neural ODE with temporal convolution and time delay neural networks for small-footprint keyword spotting. Preprint https:\/\/arXiv.org\/2008.00209"},{"key":"10067_CR9","doi-asserted-by":"crossref","unstructured":"Higuchi, T., Ghasemzadeh, M., You, K., & Dhir, C. (2020). Stacked 1D convolutional networks for end-to-end small footprint voice trigger detection. Preprint at https:\/\/arXiv.org\/2008.03405","DOI":"10.21437\/Interspeech.2020-2763"},{"key":"10067_CR10","doi-asserted-by":"crossref","unstructured":"Hou, J., Xie, L., & Fu, Z. (2016). Investigating neural network based query-by-example keyword spotting approach for personalized wake-up word detection in Mandarin Chinese. In 2016 10th international symposium on Chinese spoken language processing (ISCSLP) (pp. 1\u20135). IEEE.","DOI":"10.1109\/ISCSLP.2016.7918366"},{"key":"10067_CR12","doi-asserted-by":"crossref","unstructured":"Kim, B., Lee, M., Lee, J., Kim, Y., & Hwang, K. (2019). Query-by-example on-device keyword spotting. In 2019 IEEE automatic speech recognition and understanding workshop (ASRU) (pp. 532\u2013538). IEEE.","DOI":"10.1109\/ASRU46091.2019.9004014"},{"key":"10067_CR11","doi-asserted-by":"crossref","unstructured":"Kim, T., & Nam, J. (2022). Temporal feedback convolutional recurrent neural networks for speech command recognition. In 2022 Asia-Pacific signal and information processing association annual summit and conference (APSIPA ASC) (pp. 437\u2013441). IEEE.","DOI":"10.23919\/APSIPAASC55919.2022.9979907"},{"key":"10067_CR13","doi-asserted-by":"crossref","unstructured":"Kreuk, F., Sheena, Y., Keshet, J., & Adi, Y. (2020). Phoneme boundary detection using learnable segmental features. In 2020 IEEE international conference on acoustics, speech and signal processing (ICASSP) (pp. 8089\u20138093). IEEE.","DOI":"10.1109\/ICASSP40776.2020.9053053"},{"issue":"2","key":"10067_CR14","doi-asserted-by":"publisher","first-page":"18","DOI":"10.3390\/jlpea11020018","volume":"11","author":"J Lei","year":"2021","unstructured":"Lei, J., Rahman, T., Shafik, R., Wheeldon, A., Yakovlev, A., Granmo, O. C., Kawsar, F., & Mathur, A. (2021). Low-power audio keyword spotting using tsetlin machines. Journal of Low Power Electronics and Applications, 11(2), 18.","journal-title":"Journal of Low Power Electronics and Applications"},{"key":"10067_CR15","unstructured":"Lengerich, C., & Hannun, A. (2016). An end-to-end architecture for keyword spotting and voice activity detection. Preprint at https:\/\/arXiv.org\/1611.09405"},{"key":"10067_CR16","unstructured":"Lugosch, L., Myer, S., & Tomar, V. S. (2018). DONUT: CTC-based query-by-example keyword spotting. Preprint at https:\/\/arXiv.org\/1811.10736"},{"issue":"1","key":"10067_CR17","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3530989","volume":"22","author":"E Rajalakshmi","year":"2022","unstructured":"Rajalakshmi, E., Elakkiya, R., Prikhodko, A. L., Grif, M. G., Bakaev, M. A., Saini, J. R., Kotecha, K., & Subramaniyaswamy, V. (2022). Static and dynamic isolated Indian and Russian sign language recognition with spatial and temporal feature detection using hybrid neural network. ACM Transactions on Asian and Low-Resource Language Information Processing, 22(1), 1\u201323.","journal-title":"ACM Transactions on Asian and Low-Resource Language Information Processing"},{"key":"10067_CR18","doi-asserted-by":"publisher","first-page":"2226","DOI":"10.1109\/ACCESS.2022.3233671","volume":"11","author":"E Rajalakshmi","year":"2023","unstructured":"Rajalakshmi, E., Elakkiya, R., Subramaniyaswamy, V., Alexey, L. P., Mikhail, G., Bakaev, M., Kotecha, K., Gabralla, L. A., & Abraham, A. (2023). Multi-semantic discriminative feature learning for sign gesture recognition using hybrid deep neural architecture. IEEE Access, 11, 2226\u20132238.","journal-title":"IEEE Access"},{"key":"10067_CR19","doi-asserted-by":"crossref","unstructured":"Tang, R., & Lin, J. (2018). Deep residual learning for small-footprint keyword spotting. In 2018 IEEE international conference on acoustics, speech and signal processing (ICASSP) (pp. 5484\u20135488). IEEE.","DOI":"10.1109\/ICASSP.2018.8462688"},{"key":"10067_CR20","doi-asserted-by":"crossref","unstructured":"V\u00e9niat, T., Schwander, O., & Denoyer, L. (2019). Stochastic adaptive neural architecture search for keyword spotting. In 2019 IEEE international conference on acoustics, speech and signal processing (ICASSP) (pp. 2842\u20132846). IEEE.","DOI":"10.1109\/ICASSP.2019.8683305"},{"key":"10067_CR21","unstructured":"Wang, Z., Li, X., & Zhou, J. (2017). Small-footprint keyword spotting using deep neural network and connectionist temporal classifier. Preprint at https:\/\/arXiv.org\/1709.03665"},{"key":"10067_CR22","unstructured":"Warden, P. (2018). Speech commands: A dataset for limited-vocabulary speech recognition. Preprint at https:\/\/arXiv.org\/1804.03209"},{"key":"10067_CR23","doi-asserted-by":"crossref","unstructured":"Xu, M., & Zhang, X. L. (2020). Depthwise separable convolutional resnet with squeeze-and-excitation blocks for small-footprint keyword spotting. Preprint at https:\/\/arXiv.org\/2004.12200","DOI":"10.21437\/Interspeech.2020-1045"},{"key":"10067_CR24","doi-asserted-by":"crossref","unstructured":"Zhuang, Y., Chang, X., Qian, Y., & Yu, K. (2016). Unrestricted vocabulary keyword spotting using LSTM-CTC. In Interspeech (pp. 938\u2013942).","DOI":"10.21437\/Interspeech.2016-753"}],"container-title":["International Journal of Speech Technology"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10772-023-10067-4.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s10772-023-10067-4\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10772-023-10067-4.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,1,11]],"date-time":"2024-01-11T10:13:45Z","timestamp":1704968025000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s10772-023-10067-4"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,11,11]]},"references-count":24,"journal-issue":{"issue":"4","published-print":{"date-parts":[[2023,12]]}},"alternative-id":["10067"],"URL":"https:\/\/doi.org\/10.1007\/s10772-023-10067-4","relation":{},"ISSN":["1381-2416","1572-8110"],"issn-type":[{"value":"1381-2416","type":"print"},{"value":"1572-8110","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,11,11]]},"assertion":[{"value":"21 April 2023","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"31 October 2023","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"11 November 2023","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}]}}