{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,5,14]],"date-time":"2025-05-14T05:47:24Z","timestamp":1747201644205,"version":"3.28.0"},"reference-count":25,"publisher":"IEEE","license":[{"start":{"date-parts":[[2021,6,6]],"date-time":"2021-06-06T00:00:00Z","timestamp":1622937600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2021,6,6]],"date-time":"2021-06-06T00:00:00Z","timestamp":1622937600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2021,6,6]]},"DOI":"10.1109\/icassp39728.2021.9414577","type":"proceedings-article","created":{"date-parts":[[2021,5,13]],"date-time":"2021-05-13T19:53:45Z","timestamp":1620935625000},"page":"6853-6857","source":"Crossref","is-referenced-by-count":7,"title":["CNN-Based Spoken Term Detection and Localization without Dynamic Programming"],"prefix":"10.1109","author":[{"given":"Tzeviya Sylvia","family":"Fuchs","sequence":"first","affiliation":[{"name":"BarIlan University,Ramat Gan,Israel"}]},{"given":"Yael","family":"Segal","sequence":"additional","affiliation":[{"name":"BarIlan University,Ramat Gan,Israel"}]},{"given":"Joseph","family":"Keshet","sequence":"additional","affiliation":[{"name":"BarIlan University,Ramat Gan,Israel"}]}],"member":"263","reference":[{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1788"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1749"},{"key":"ref12","first-page":"779","article-title":"You only look once: Unified, real-time object detection","author":"redmon","year":"2016","journal-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition"},{"key":"ref13","first-page":"21","article-title":"SSD: Single shot multibox detector","author":"liu","year":"2016","journal-title":"European Conference on Computer Vision"},{"key":"ref14","article-title":"Zero-shot object detection by hybrid region embed-ding","author":"demirel","year":"2018","journal-title":"BMVC"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/SLT.2014.7078558"},{"key":"ref16","article-title":"Very deep convolutional networks for large-scale image recognition","author":"simonyan","year":"2015","journal-title":"International Conference on Learning Representations (ICLR)"},{"key":"ref17","article-title":"Adam: A method for stochastic optimization","author":"kingma","year":"2015","journal-title":"3rd International Conference for Learning Representations San Diego"},{"article-title":"Speech commands: A dataset for limited-vocabulary speech recognition","year":"2018","author":"warden","key":"ref18"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178964"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2017.2764268"},{"key":"ref3","article-title":"Mul-tilingual bottleneck features for query by example spoken term detection","author":"ram","year":"2019","journal-title":"IEEE Workshop on Automatic Speech Recognition and Unde rstanding"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2413"},{"key":"ref5","article-title":"Discriminative spoken term detection with limited data","author":"prabhavalkar","year":"2012","journal-title":"Symposium on Machine Learning in Speech and Language Processing"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2016.7472619"},{"key":"ref7","article-title":"Multi-view recurrent neural acoustic word embeddings","author":"he","year":"2017","journal-title":"Proc ICLR"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2019.2911164"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/SLT.2016.7846310"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1722"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-1386"},{"key":"ref22","article-title":"Darpa timit acoustic-phonetic continous speech corpus cd-rom. nist speech disc 1-1.1","volume":"93","author":"garofolo","year":"1993","journal-title":"NASA STI\/Recon Technical Report N"},{"article-title":"librosa\/librosa: 0.6.3","year":"2019","author":"mcfee","key":"ref21"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-1592"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2008.10.002"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7179089"}],"event":{"name":"ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","start":{"date-parts":[[2021,6,6]]},"location":"Toronto, ON, Canada","end":{"date-parts":[[2021,6,11]]}},"container-title":["ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9413349\/9413350\/09414577.pdf?arnumber=9414577","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,8,3]],"date-time":"2022-08-03T00:19:06Z","timestamp":1659485946000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9414577\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,6,6]]},"references-count":25,"URL":"https:\/\/doi.org\/10.1109\/icassp39728.2021.9414577","relation":{},"subject":[],"published":{"date-parts":[[2021,6,6]]}}}