{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,23]],"date-time":"2026-07-23T20:14:04Z","timestamp":1784837644080,"version":"3.55.0"},"reference-count":43,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2027,1,1]],"date-time":"2027-01-01T00:00:00Z","timestamp":1798761600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2027,1,1]],"date-time":"2027-01-01T00:00:00Z","timestamp":1798761600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2027,1,1]],"date-time":"2027-01-01T00:00:00Z","timestamp":1798761600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-017"},{"start":{"date-parts":[[2027,1,1]],"date-time":"2027-01-01T00:00:00Z","timestamp":1798761600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"},{"start":{"date-parts":[[2027,1,1]],"date-time":"2027-01-01T00:00:00Z","timestamp":1798761600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-012"},{"start":{"date-parts":[[2027,1,1]],"date-time":"2027-01-01T00:00:00Z","timestamp":1798761600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2027,1,1]],"date-time":"2027-01-01T00:00:00Z","timestamp":1798761600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-004"}],"funder":[{"DOI":"10.13039\/501100017596","name":"Natural Science Basic Research Program of Shaanxi Province","doi-asserted-by":"publisher","award":["2022JQ-627"],"award-info":[{"award-number":["2022JQ-627"]}],"id":[{"id":"10.13039\/501100017596","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Computer Speech & Language"],"published-print":{"date-parts":[[2027,1]]},"DOI":"10.1016\/j.csl.2026.102018","type":"journal-article","created":{"date-parts":[[2026,6,12]],"date-time":"2026-06-12T15:40:09Z","timestamp":1781278809000},"page":"102018","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":0,"special_numbering":"C","title":["A lightweight query-by-example keyword spotting system for IoT devices"],"prefix":"10.1016","volume":"101","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-7785-7323","authenticated-orcid":false,"given":"Meirong","family":"Li","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Wen","family":"Xu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhouzhou","family":"Liu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Nan","family":"Chen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"78","reference":[{"key":"10.1016\/j.csl.2026.102018_bib0001","series-title":"Proc. O-COCOSDA","first-page":"1","article-title":"AISHELL-1: an open-source Mandarin speech corpus and a speech recognition baseline","author":"Bu","year":"2017"},{"key":"10.1016\/j.csl.2026.102018_bib0002","series-title":"Proc. ICASSP","first-page":"5549","article-title":"Temporal modeling using dilated convolution and gating for voice-activity-detection","author":"Chang","year":"2018"},{"key":"10.1016\/j.csl.2026.102018_bib0003","series-title":"Proc. ICASSP, South","first-page":"5236","article-title":"Query-by-example keyword spotting using long short-term memory networks","author":"Chen","year":"2015"},{"key":"10.1016\/j.csl.2026.102018_bib0004","series-title":"Proc. INTERSPEECH","first-page":"2663","article-title":"Compact Feedforward sequential memory networks for small-footprint keyword spotting","author":"Chen","year":"2018"},{"key":"10.1016\/j.csl.2026.102018_bib0005","series-title":"Proc. INTERSPEECH","first-page":"3372","article-title":"Temporal convolution for real-time keyword spotting on mobile devices","author":"Choi","year":"2019"},{"key":"10.1016\/j.csl.2026.102018_bib0006","author":"Du"},{"key":"10.1016\/j.csl.2026.102018_bib0008","series-title":"Proc. NIPS","first-page":"1135","article-title":"Learning both weights and connections for efficient neural networks","author":"Han","year":"2015"},{"key":"10.1016\/j.csl.2026.102018_bib0009","series-title":"Proc. ASRU","first-page":"421","article-title":"Query-by-example spoken term detection using phonetic posteriorgram templates","author":"Hazen","year":"2009"},{"key":"10.1016\/j.csl.2026.102018_bib0010","author":"Hinton"},{"key":"10.1016\/j.csl.2026.102018_bib0011","series-title":"Proc. 10th International Symposium on Chinese Spoken Language Processing","first-page":"1","article-title":"Investigating neural network based query-by-example keyword spotting approach for personalized wake-up word detection in Mandarin Chinese","author":"Hou","year":"2016"},{"key":"10.1016\/j.csl.2026.102018_bib0012","series-title":"Proc. ICCV, Seoul, South Korea","first-page":"1314","article-title":"Searching for Mobilenetv3","author":"Howard","year":"2019"},{"key":"10.1016\/j.csl.2026.102018_bib0013","series-title":"Proc. ICASSP","first-page":"6858","article-title":"Query-by-example keyword spotting system using multi-head attention and soft-triple loss","author":"Huang","year":"2021"},{"issue":"1","key":"10.1016\/j.csl.2026.102018_bib0014","doi-asserted-by":"crossref","first-page":"341","DOI":"10.2991\/ijcis.d.200316.001","article-title":"End-to-End sequence labeling via convolutional recurrent neural network with a connectionist temporal classification layer","volume":"13","author":"Huang","year":"2020","journal-title":"Int. J. Comput. Intell. Syst."},{"key":"10.1016\/j.csl.2026.102018_bib0015","series-title":"Proc. INTERSPEECH","first-page":"4538","article-title":"Broadcasted residual learning for efficient keyword spotting","author":"Kim","year":"2021"},{"key":"10.1016\/j.csl.2026.102018_bib0016","series-title":"Proc. ASRU","first-page":"532","article-title":"Query-by-example on-device keyword spotting","author":"Kim","year":"2019"},{"key":"10.1016\/j.csl.2026.102018_bib0017","series-title":"Proc. INTERSPEECH","first-page":"4568","article-title":"PQK: model compression via pruning, quantization, and knowledge distillation","author":"Kim","year":"2021"},{"key":"10.1016\/j.csl.2026.102018_bib0018","author":"Krishnamoorthi"},{"key":"10.1016\/j.csl.2026.102018_bib0019","author":"Krishnamoorthi"},{"key":"10.1016\/j.csl.2026.102018_bib0020","author":"Lengerich"},{"key":"10.1016\/j.csl.2026.102018_bib0021","doi-asserted-by":"crossref","first-page":"4169","DOI":"10.1109\/ACCESS.2021.3139508","article-title":"Deep spoken keyword spotting: an overview","volume":"10","author":"L\u00f3pez-Espejo","year":"2022","journal-title":"IEEe Access."},{"key":"10.1016\/j.csl.2026.102018_bib0022","series-title":"Proc. NeurIPS","first-page":"1","article-title":"Donut: ctc-based query-by-example keyword spotting","author":"Lugosch","year":"2018"},{"key":"10.1016\/j.csl.2026.102018_bib0023","series-title":"Proc. ISCSLP, Hong Kong","first-page":"1","article-title":"Acoustic word embedding system for code-switching query-by-example spoken term detection","author":"Ma","year":"2021"},{"key":"10.1016\/j.csl.2026.102018_bib0024","series-title":"Proc. ECCV","first-page":"116","article-title":"Shufflenet v2: practical guidelines for efficient CNN architecture design","author":"Ma","year":"2018"},{"key":"10.1016\/j.csl.2026.102018_bib0025","series-title":"Proc. ICASSP, Rhodes Island","first-page":"1","article-title":"Fixed-point quantization Aware training for on-device keyword-spotting","author":"Macha","year":"2023"},{"key":"10.1016\/j.csl.2026.102018_bib0026","series-title":"Proc. ICASSP","first-page":"5955","article-title":"Personalized speech recognition on mobile devices","author":"McGraw","year":"2016"},{"key":"10.1016\/j.csl.2026.102018_bib0027","series-title":"Proc. IJCAI","first-page":"4331","article-title":"BiFSMN: binary neural network for keyword spotting","author":"Qin","year":"2022"},{"key":"10.1016\/j.csl.2026.102018_bib0028","doi-asserted-by":"crossref","first-page":"1416","DOI":"10.1109\/TASLP.2020.2988788","article-title":"Neural network based end-to-end query by example spoken term detection","volume":"28","author":"Ram","year":"2020","journal-title":"IEEE\/ACM. Trans. Audio Speech. Lang. Process."},{"key":"10.1016\/j.csl.2026.102018_bib0029","series-title":"Proc. ICASSP","first-page":"1","article-title":"Multilingual query-by-example keyword spotting with metric learning and phoneme-to-embedding mapping","author":"Reuter","year":"2023"},{"key":"10.1016\/j.csl.2026.102018_bib0030","series-title":"Proc. ICASSP","first-page":"7819","article-title":"High-performance query-by-example spoken term detection on the SWS 2013 evaluation","author":"Rodriguez-Fuentes","year":"2014"},{"issue":"6","key":"10.1016\/j.csl.2026.102018_bib0031","doi-asserted-by":"crossref","first-page":"50","DOI":"10.1109\/MM.2023.3311826","article-title":"On-device customization of tiny deep learning models for keyword spotting with few examples","volume":"43","author":"Rusci","year":"2023","journal-title":"IEEe Micro"},{"key":"10.1016\/j.csl.2026.102018_bib0032","series-title":"Proc. ICASSP","first-page":"6655","article-title":"Low-rank matrix factorization for Deep Neural Network training with high-dimensional output targets","author":"Sainath","year":"2013"},{"issue":"11","key":"10.1016\/j.csl.2026.102018_bib0033","doi-asserted-by":"crossref","first-page":"2298","DOI":"10.1109\/TPAMI.2016.2646371","article-title":"An end-to-end trainable neural network for image-based sequence recognition and its application to scene text recognition","volume":"39","author":"Shi","year":"2017","journal-title":"IEEe Trans. Pattern. Anal. Mach. Intell."},{"key":"10.1016\/j.csl.2026.102018_bib0034","series-title":"Proc. INTERSPEECH","first-page":"774","article-title":"An investigation into on-device personalization of end-to-end automatic speech recognition models","author":"Sim","year":"2019"},{"key":"10.1016\/j.csl.2026.102018_bib0035","series-title":"Proc. INTERSPEECH, Incheon, Korea","first-page":"4128","article-title":"Knowledge distillation for In-memory keyword spotting model","author":"Song","year":"2022"},{"key":"10.1016\/j.csl.2026.102018_bib0036","series-title":"Proc. ICML","first-page":"6105","article-title":"Efficientnet: rethinking model scaling for convolutional neural networks","author":"Tan","year":"2019"},{"key":"10.1016\/j.csl.2026.102018_bib0037","series-title":"Proc. INTERSPEECH","first-page":"1878","article-title":"Model compression applied to small-footprint keyword spotting","author":"Tucker","year":"2016"},{"key":"10.1016\/j.csl.2026.102018_bib0038","series-title":"Proc. INTERSPEECH","first-page":"1878","article-title":"Model compression applied to small-footprint keyword spotting","author":"Tucker","year":"2016"},{"key":"10.1016\/j.csl.2026.102018_bib0039","author":"Wang"},{"key":"10.1016\/j.csl.2026.102018_bib0040","series-title":"Proc. ICASSP","first-page":"7489","article-title":"Crnn-ctc based Mandarin keywords spotting","author":"Yan","year":"2020"},{"key":"10.1016\/j.csl.2026.102018_bib0041","author":"Yan"},{"key":"10.1016\/j.csl.2026.102018_bib0042","series-title":"Proc. INTERSPEECH","first-page":"97","article-title":"Learning acoustic word embeddings with temporal context for query-by-example speech search","author":"Yuan","year":"2018"},{"key":"10.1016\/j.csl.2026.102018_bib0043","series-title":"Proc. ASRU","first-page":"398","article-title":"Unsupervised spoken keyword spotting via segmental DTW on gaussian posteriorgrams","author":"Zhang","year":"2009"},{"key":"10.1016\/j.csl.2026.102018_bib0044","author":"Zhang"}],"container-title":["Computer Speech & Language"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0885230826000811?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0885230826000811?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,7,23]],"date-time":"2026-07-23T19:45:39Z","timestamp":1784835939000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S0885230826000811"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2027,1]]},"references-count":43,"alternative-id":["S0885230826000811"],"URL":"https:\/\/doi.org\/10.1016\/j.csl.2026.102018","relation":{},"ISSN":["0885-2308"],"issn-type":[{"value":"0885-2308","type":"print"}],"subject":[],"published":{"date-parts":[[2027,1]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"A lightweight query-by-example keyword spotting system for IoT devices","name":"articletitle","label":"Article Title"},{"value":"Computer Speech & Language","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.csl.2026.102018","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2026 Elsevier Ltd. All rights are reserved, including those for text and data mining, AI training, and similar technologies.","name":"copyright","label":"Copyright"}],"article-number":"102018"}}