{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,10,19]],"date-time":"2024-10-19T04:03:56Z","timestamp":1729310636468,"version":"3.27.0"},"reference-count":30,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2024,10,18]],"date-time":"2024-10-18T00:00:00Z","timestamp":1729209600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,10,18]],"date-time":"2024-10-18T00:00:00Z","timestamp":1729209600000},"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":["J Supercomput"],"published-print":{"date-parts":[[2025,1]]},"DOI":"10.1007\/s11227-024-06497-9","type":"journal-article","created":{"date-parts":[[2024,10,18]],"date-time":"2024-10-18T07:03:13Z","timestamp":1729234993000},"update-policy":"http:\/\/dx.doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["A parallel computing approach to CNN-based QbE-STD using kernel-based matching"],"prefix":"10.1007","volume":"81","author":[{"given":"Manisha","family":"Naik Gaonkar","sequence":"first","affiliation":[]},{"given":"Veena","family":"Thenkanidiyoor","sequence":"additional","affiliation":[]},{"given":"Aroor Dinesh","family":"Dileep","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2024,10,18]]},"reference":[{"key":"6497_CR1","unstructured":"Anguera X, Rodriguez-Fuentes JL, Sz\u0151ke I, et\u00a0al (2014) Query-by-example Spoken Term Detection Evaluation on Low-resource Languages. In: Proceedings of the 4th international workshop on spoken language technologies for under\u2014resourced languages SLTU-2014. \u00c2 St. Petersburg, Russia. International Speech Communication Association, pp 24\u201331"},{"key":"6497_CR2","doi-asserted-by":"publisher","unstructured":"Benati N, Bahi H (2024) Self-supervised spoken term detection for query by example. Ing\u00e9nierie des Syst\u00e8mes d\u2019Information https:\/\/doi.org\/10.18280\/isi.290334","DOI":"10.18280\/isi.290334"},{"key":"6497_CR3","doi-asserted-by":"publisher","first-page":"357","DOI":"10.1109\/TASSP.1980.1163420","volume":"28","author":"S Davis","year":"1980","unstructured":"Davis S, Mermelstein P (1980) Comparison of parametric representations for monosyllabic word recognition in continuosly spoken sentences. IEEE Trans Acoust Speech Signal Process 28:357\u2013366","journal-title":"IEEE Trans Acoust Speech Signal Process"},{"key":"6497_CR4","unstructured":"Fayek HM (2016) Speech processing for machine learning: filter banks, mel-frequency cepstral coefficients (mfccs) and what\u2019s in-between. https:\/\/haythamfayek.com\/2016\/04\/21\/speech-processing-for-machine-learning.html"},{"key":"6497_CR5","doi-asserted-by":"publisher","DOI":"10.6028\/NIST.IR.4930","volume-title":"TIMIT acoustic-phonetic continuous speech corpus LDC93S1. Web Download","author":"J Garofolo","year":"1993","unstructured":"Garofolo J, Lamel L, Fisher W et al (1993) TIMIT acoustic-phonetic continuous speech corpus LDC93S1. Web Download. Linguistic Data Consortium, Philadelphia"},{"key":"6497_CR6","first-page":"1125","volume":"2011","author":"V Gupta","year":"2011","unstructured":"Gupta V, Ajmera J, Kumar A et al (2011) A language independent approach to audio search. Proc Interspeech 2011:1125\u20131128","journal-title":"Proc Interspeech"},{"key":"6497_CR7","doi-asserted-by":"crossref","unstructured":"Hazen TJ, Shen W, White C (2009) Query-by-example spoken term detection using phonetic posteriorgram templates. In: 2009 IEEE workshop on automatic speech recognition and understanding, pp 421\u2013426","DOI":"10.1109\/ASRU.2009.5372889"},{"key":"6497_CR8","doi-asserted-by":"publisher","first-page":"353","DOI":"10.1007\/s00034-020-01475-x","volume":"40","author":"P Kokil","year":"2021","unstructured":"Kokil P, Pratap T (2021) Additive white gaussian noise level estimation for natural images using linear scale-space features. Circuits Syst Signal Process 40:353. https:\/\/doi.org\/10.1007\/s00034-020-01475-x","journal-title":"Circuits Syst Signal Process"},{"key":"6497_CR9","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 (2017) Partial matching and search space reduction for QbE-STD. Comput Speech Lang 45:58\u201382","journal-title":"Comput Speech Lang"},{"key":"6497_CR10","doi-asserted-by":"crossref","unstructured":"Mantena G, Prahallad K (2014) Use of articulatory bottle-neck features for Query-by-Example Spoken Term Detection in low resource scenarios. In: 2014 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp 7128\u20137132","DOI":"10.1109\/ICASSP.2014.6854983"},{"issue":"5","key":"6497_CR11","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 (2014) Query-by-example spoken term detection using frequency domain linear prediction and non-segmental dynamic time warping. IEEE\/ACM Trans Audio Speech Lang Process 22(5):946\u2013955","journal-title":"IEEE\/ACM Trans Audio Speech Lang Process"},{"key":"6497_CR12","doi-asserted-by":"crossref","unstructured":"Mary L, Deekshitha G (2019) Searching speech databases: features, techniques and evaluation measures. In: Springer briefs in speech technology","DOI":"10.1007\/978-3-319-97761-4"},{"key":"6497_CR13","first-page":"69","volume-title":"Dynamic time warping","author":"M Muller","year":"2007","unstructured":"Muller M (2007) Dynamic time warping. Springer, Berlin Heidelberg, Berlin, Heidelberg, pp 69\u201384"},{"key":"6497_CR14","doi-asserted-by":"crossref","unstructured":"Naik P, Naik\u00a0Gaonkar M, Thenkanidiyoor V, et\u00a0al (2020) Kernel based matching and a novel training approach for CNN-based QbE-STD. In: 2020 International Conference on Signal Processing and Communications (SPCOM), pp 1\u20135","DOI":"10.1109\/SPCOM50965.2020.9179588"},{"key":"6497_CR15","doi-asserted-by":"crossref","unstructured":"Popli A, Kumar A (2017) Capturing Indian phonemic diversity with multiple posteriorgrams for Multilingual Query-by-Example Spoken Term Detection. In: 2017 23rd National Conference on Communications (NCC), pp 1\u20136","DOI":"10.1109\/NCC.2017.8077115"},{"key":"6497_CR16","doi-asserted-by":"publisher","first-page":"131","DOI":"10.1007\/s10772-018-09585-3","volume":"22","author":"A Popli","year":"2019","unstructured":"Popli A, Kumar A (2019) Multilingual query-by-example spoken term detection in Indian languages. Int J Speech Technol 22:131\u2013141","journal-title":"Int J Speech Technol"},{"key":"6497_CR17","doi-asserted-by":"crossref","unstructured":"Ram D, Miculicich L, Bourlard H (2018) CNN based query by example spoken term detection. In: 17th Annual Conference of the International Speech Communication Association (INTERSPEECH), pp 92\u201396","DOI":"10.21437\/Interspeech.2018-1722"},{"key":"6497_CR18","doi-asserted-by":"crossref","unstructured":"Ram D, Miculicich L, Bourlard H (2019) Multilingual bottleneck features for query by example spoken term detection. In: 2019 IEEE automatic speech recognition and understanding workshop (ASRU), pp 621\u2013628","DOI":"10.1109\/ASRU46091.2019.9003752"},{"key":"6497_CR19","doi-asserted-by":"crossref","unstructured":"Rodr\u00edguez-Fuentes LJ, Varona A, Pe\u00f1agarikano M, et\u00a0al (2014) High-performance query-by-example spoken term detection on the SWS 2013 evaluation. 2014 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) pp 7819\u20137823","DOI":"10.1109\/ICASSP.2014.6855122"},{"key":"6497_CR20","doi-asserted-by":"crossref","unstructured":"Shankar R, Vikram C, Prasanna S (2018) Spoken keyword detection using joint DTW-CNN. In: 17th Annual Conference of the International Speech Communication Association (INTERSPEECH), pp 117\u2013121","DOI":"10.21437\/Interspeech.2018-1436"},{"key":"6497_CR21","doi-asserted-by":"crossref","unstructured":"Sharma A, Kumar A, Allappa S, et\u00a0al (2018) Modified time flexible kernel for video activity recognition using support vector machines. In: 7th International Conference on Pattern Recognition Applications and Methods (ICPRAM), pp 133\u2013140","DOI":"10.5220\/0006595501330140"},{"key":"6497_CR22","doi-asserted-by":"publisher","unstructured":"Singh A, Arora V, Chen YPP (2024) An efficient TF-IDF based query by example spoken term detection. In: 2024 IEEE Conference on Artificial Intelligence (CAI), pp 170\u2013175, https:\/\/doi.org\/10.1109\/CAI59869.2024.00039","DOI":"10.1109\/CAI59869.2024.00039"},{"key":"6497_CR23","doi-asserted-by":"publisher","DOI":"10.1007\/s42979-023-01754-9","author":"P Sudhakar","year":"2023","unstructured":"Sudhakar P, Sreenivasa Rao K, Mitra P (2023a) A novel zero-resource spoken term detection using affinity Kernel propagation with acoustic feature map. SN Comput Sci. https:\/\/doi.org\/10.1007\/s42979-023-01754-9","journal-title":"SN Comput Sci"},{"key":"6497_CR24","doi-asserted-by":"crossref","unstructured":"Sudhakar P, Sreenivasa Rao K, Mitra P (2023b) Unsupervised discovery of recurring spoken terms using diagonal patterns. In: International Conference on Pattern Recognition and Machine Intelligence, Kolkata, India, pp 61\u201369","DOI":"10.1007\/978-3-031-45170-6_7"},{"key":"6497_CR25","doi-asserted-by":"crossref","unstructured":"Yuan Y, Leung CC, Xie L, et\u00a0al (2017) Pairwise learning using multi-lingual bottleneck features for low-resource Query-by-example spoken term detection. In: 2017 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp 5645\u20135649","DOI":"10.1109\/ICASSP.2017.7953237"},{"key":"6497_CR26","doi-asserted-by":"crossref","unstructured":"Yuan Y, Leung CC, Xie L, et\u00a0al (2018) Learning acoustic word embeddings with temporal context for query-by-example speech search. In 17th Annual Conference of the International Speech Communication Association (INTERSPEECH), pp 97\u2013101","DOI":"10.21437\/Interspeech.2018-1010"},{"key":"6497_CR27","doi-asserted-by":"publisher","first-page":"67656","DOI":"10.1109\/ACCESS.2019.2918638","volume":"7","author":"Y Yuan","year":"2019","unstructured":"Yuan Y, Leung CC, Xie L et al (2019) Query-by-Example Speech Search Using Recurrent Neural Acoustic Word Embeddings With Temporal Context. IEEE Access 7:67656\u201367665","journal-title":"IEEE Access"},{"key":"6497_CR28","doi-asserted-by":"crossref","unstructured":"Zhang Y, Glass JR (2009) Unsupervised spoken keyword spotting via segmental DTW on Gaussian posteriorgrams. In: IEEE workshop on automatic speech recognition and understanding (ASRU), pp 398\u2013403","DOI":"10.1109\/ASRU.2009.5372931"},{"key":"6497_CR29","doi-asserted-by":"crossref","unstructured":"Zhu Z, Wu Z, Li R, et\u00a0al (2018) Siamese recurrent auto-encoder representation for query-by-example spoken term detection. In: 17th Annual Conference of the International Speech Communication Association (INTERSPEECH), pp 102\u2013106","DOI":"10.21437\/Interspeech.2018-1788"},{"key":"6497_CR30","doi-asserted-by":"crossref","unstructured":"\u0160vec J, \u0160m\u00eddl L, Lehe\u010dka J (2022) Transformer-based encoder-encoder architecture for spoken term detection. arXiv:2211.01089","DOI":"10.1007\/978-3-031-47665-5_28"}],"container-title":["The Journal of Supercomputing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11227-024-06497-9.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s11227-024-06497-9\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11227-024-06497-9.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,10,18]],"date-time":"2024-10-18T07:20:44Z","timestamp":1729236044000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s11227-024-06497-9"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,10,18]]},"references-count":30,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2025,1]]}},"alternative-id":["6497"],"URL":"https:\/\/doi.org\/10.1007\/s11227-024-06497-9","relation":{},"ISSN":["0920-8542","1573-0484"],"issn-type":[{"value":"0920-8542","type":"print"},{"value":"1573-0484","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,10,18]]},"assertion":[{"value":"2 October 2024","order":1,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"18 October 2024","order":2,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"The authors have no conflict of interest to declare that are relevant to the content of this article.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}}],"article-number":"24"}}