{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,5,24]],"date-time":"2025-05-24T04:09:07Z","timestamp":1748059747497,"version":"3.41.0"},"reference-count":16,"publisher":"Springer Science and Business Media LLC","issue":"5","license":[{"start":{"date-parts":[[2025,5,23]],"date-time":"2025-05-23T00:00:00Z","timestamp":1747958400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,5,23]],"date-time":"2025-05-23T00:00:00Z","timestamp":1747958400000},"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":["SN COMPUT. SCI."],"DOI":"10.1007\/s42979-025-04023-z","type":"journal-article","created":{"date-parts":[[2025,5,23]],"date-time":"2025-05-23T12:43:48Z","timestamp":1748004228000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Exploring the Impact of Different Similarity Measures on Query-by-Example Spoken Term Detection"],"prefix":"10.1007","volume":"6","author":[{"ORCID":"https:\/\/orcid.org\/0009-0004-1090-7666","authenticated-orcid":false,"given":"Manisha Naik","family":"Gaonkar","sequence":"first","affiliation":[]},{"given":"Veena","family":"Thenkanidiyoor","sequence":"additional","affiliation":[]},{"given":"A. D.","family":"Dileep","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2025,5,23]]},"reference":[{"key":"4023_CR1","unstructured":"Garofolo J, Lamel L, Fisher W, et\u00a0al. TIMIT Acoustic-Phonetic Continuous Speech Corpus 1993."},{"key":"4023_CR2","doi-asserted-by":"publisher","unstructured":"Kokil P, Pratap T. Additive white gaussian noise level estimation for natural images using linear scale-space features. Circuits, Systems, and Signal Processing. 2021;40. https:\/\/doi.org\/10.1007\/s00034-020-01475-x.","DOI":"10.1007\/s00034-020-01475-x"},{"key":"4023_CR3","doi-asserted-by":"publisher","first-page":"58","DOI":"10.1016\/j.csl.2017.03.004","volume":"45","author":"M Madhavi","year":"2017","unstructured":"Madhavi M, Patil H. Partial matching and search space reduction for QbE-STD. Comput Speech Lang. 2017;45:58\u201382.","journal-title":"Comput Speech Lang"},{"key":"4023_CR4","doi-asserted-by":"publisher","first-page":"41","DOI":"10.1016\/j.csl.2018.04.006","volume":"52","author":"M Madhavi","year":"2018","unstructured":"Madhavi M, Patil H. Design of mixture of GMMs for Query-by-Example Spoken Term Detection. Comput Speech Lang. 2018;52:41\u201355.","journal-title":"Comput Speech Lang"},{"key":"4023_CR5","doi-asserted-by":"publisher","first-page":"175","DOI":"10.1016\/j.csl.2019.03.005","volume":"58","author":"M Madhavi","year":"2019","unstructured":"Madhavi M, Patil H. Vocal Tract Length Normalization using a Gaussian Mixture Model framework for Query-by-Example Spoken Term Detection. Comput Speech Lang. 2019;58:175\u2013202.","journal-title":"Comput Speech Lang"},{"key":"4023_CR6","unstructured":"Mantena G, Prahallad K. Use of GPU and Feature Reduction for Fast Query-by-Example Spoken Term Detection. In: Proceedings of the 11th International Conference on Natural Language Processing. NLP Association of India, Goa, India, 2014;56\u201362."},{"issue":"5","key":"4023_CR7","doi-asserted-by":"publisher","first-page":"946","DOI":"10.1109\/TASLP.2014.2311322","volume":"22","author":"G Mantena","year":"2014","unstructured":"Mantena G, Achanta S, Prahallad K. Query-by-Example Spoken Term Detection using Frequency Domain Linear Prediction and Non-Segmental Dynamic Time Warping. IEEE\/ACM Transactions on Audio, Speech, and Language Processing. 2014;22(5):946\u201355.","journal-title":"IEEE\/ACM Transactions on Audio, Speech, and Language Processing"},{"key":"4023_CR8","doi-asserted-by":"crossref","unstructured":"Naik P, Naik\u00a0Gaonkar M, Thenkanidiyoor V, et\u00a0al. Kernel based Matching and a Novel training approach for CNN-based QbE-STD. In: 2020 International Conference on Signal Processing and Communications (SPCOM), 2020;1\u20135.","DOI":"10.1109\/SPCOM50965.2020.9179588"},{"key":"4023_CR9","doi-asserted-by":"crossref","unstructured":"Ram D, Miculicich L, Bourlard H. CNN based Query by Example Spoken Term Detection. In: Seventeenth Annual Conference of the International Speech Communication Association (INTERSPEECH), 2018;92\u201396.","DOI":"10.21437\/Interspeech.2018-1722"},{"key":"4023_CR10","doi-asserted-by":"publisher","first-page":"1416","DOI":"10.1109\/TASLP.2020.2988788","volume":"28","author":"D Ram","year":"2020","unstructured":"Ram D, Miculicich L, Bourlard H. Neural Network Based End-to-End Query by Example Spoken Term Detection. IEEE\/ACM Transactions on Audio, Speech, and Language Processing (ASLP). 2020;28:1416\u201327.","journal-title":"IEEE\/ACM Transactions on Audio, Speech, and Language Processing (ASLP)"},{"key":"4023_CR11","doi-asserted-by":"crossref","unstructured":"Rodr\u00edguez-Fuentes LJ, Varona A, Pe\u00f1agarikano M, et\u00a0al. High-performance Query-by-Example Spoken Term Detection on the SWS 2013 evaluation. 2014 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) 2014;7819\u20137823.","DOI":"10.1109\/ICASSP.2014.6855122"},{"key":"4023_CR12","doi-asserted-by":"crossref","unstructured":"Shankar R, Vikram C, Prasanna S. Spoken Keyword Detection using joint DTW-CNN. In: Seventeenth Annual Conference of the International Speech Communication Association (INTERSPEECH), 2018;117\u2013121.","DOI":"10.21437\/Interspeech.2018-1436"},{"key":"4023_CR13","doi-asserted-by":"crossref","unstructured":"Sharma A, Kumar A, Allappa S, et\u00a0al. Modified time flexible kernel for video activity recognition using support vector machines. In: 7th International Conference on Pattern Recognition Applications and Methods (ICPRAM), 2018;133\u2013140.","DOI":"10.5220\/0006595501330140"},{"key":"4023_CR14","doi-asserted-by":"crossref","unstructured":"Zhang Y, Glass JR. Unsupervised spoken keyword spotting via segmental DTW on Gaussian posteriorgrams. In: IEEE Workshop on Automatic Speech Recognition and Understanding (ASRU), 2009;398\u2013403.","DOI":"10.1109\/ASRU.2009.5372931"},{"key":"4023_CR15","doi-asserted-by":"crossref","unstructured":"Zhu Z, Wu Z, Li R, et\u00a0al. Siamese Recurrent Auto-Encoder Representation for Query-by-Example Spoken Term Detection. In: Seventeenth Annual Conference of the International Speech Communication Association (INTERSPEECH), 2018;102\u2013106.","DOI":"10.21437\/Interspeech.2018-1788"},{"key":"4023_CR16","doi-asserted-by":"crossref","unstructured":"\u0160vec J, \u0160m\u00eddl L, Lehecka J. Transformer-based encoder-encoder architecture for spoken term detection. arXiv:2211.01089 2022.","DOI":"10.1007\/978-3-031-47665-5_28"}],"container-title":["SN Computer Science"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s42979-025-04023-z.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s42979-025-04023-z\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s42979-025-04023-z.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,5,23]],"date-time":"2025-05-23T12:43:52Z","timestamp":1748004232000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s42979-025-04023-z"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,5,23]]},"references-count":16,"journal-issue":{"issue":"5","published-online":{"date-parts":[[2025,6]]}},"alternative-id":["4023"],"URL":"https:\/\/doi.org\/10.1007\/s42979-025-04023-z","relation":{},"ISSN":["2661-8907"],"issn-type":[{"value":"2661-8907","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,5,23]]},"assertion":[{"value":"8 July 2024","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"6 May 2025","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"23 May 2025","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"On behalf of all authors, the corresponding author states that there is no conflict of interest.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}},{"value":"This article does not contain any studies with human participants or animals performed by any of the authors.","order":3,"name":"Ethics","group":{"name":"EthicsHeading","label":"Ethics approval"}}],"article-number":"491"}}