{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,22]],"date-time":"2026-04-22T18:35:09Z","timestamp":1776882909754,"version":"3.51.2"},"reference-count":54,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2021,1,1]],"date-time":"2021-01-01T00:00:00Z","timestamp":1609459200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2021,1,1]],"date-time":"2021-01-01T00:00:00Z","timestamp":1609459200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2021,1,1]],"date-time":"2021-01-01T00:00:00Z","timestamp":1609459200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"Demant Foundation"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE\/ACM Trans. Audio Speech Lang. Process."],"published-print":{"date-parts":[[2021]]},"DOI":"10.1109\/taslp.2021.3092567","type":"journal-article","created":{"date-parts":[[2021,6,28]],"date-time":"2021-06-28T21:37:27Z","timestamp":1624916247000},"page":"2254-2266","source":"Crossref","is-referenced-by-count":22,"title":["A Novel Loss Function and Training Strategy for Noise-Robust Keyword Spotting"],"prefix":"10.1109","volume":"29","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-8634-7897","authenticated-orcid":false,"given":"Iv\u00e1n","family":"L\u00f3pez-Espejo","sequence":"first","affiliation":[{"name":"Department of Electronic Systems, Aalborg University, Aalborg, Denmark"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6856-8928","authenticated-orcid":false,"given":"Zheng-Hua","family":"Tan","sequence":"additional","affiliation":[{"name":"Department of Electronic Systems, Aalborg University, Aalborg, Denmark"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1478-622X","authenticated-orcid":false,"given":"Jesper","family":"Jensen","sequence":"additional","affiliation":[{"name":"Department of Electronic Systems, Aalborg University, Aalborg, Denmark"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1016\/j.csl.2016.10.005"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU.2015.7404837"},{"key":"ref33","first-page":"35","article-title":"Modern information retrieval: A brief overview","volume":"24","author":"singhal","year":"2001","journal-title":"Bull IEEE Comput Soc Tech Committee Data Eng"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1017\/S0373463309990415"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU.2017.8268989"},{"key":"ref30","article-title":"Context-aware recommendations for televisions using deep embeddings with relaxed n-pairs loss objective","author":"kristoffersen","year":"2020"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1016\/0167-6393(93)90095-3"},{"key":"ref36","first-page":"29","article-title":"The AURORA experimental framework for the performance evaluation of speech recognition systems under noisy conditions","author":"pearce","year":"0","journal-title":"Proc Int Conf Spoken Lang Process"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.309"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33015361"},{"key":"ref28","article-title":"In defense of the triplet loss for person re-identification","author":"hermans","year":"2017"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2005.202"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.145"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1145\/3178115"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1080\/02763869.2018.1404391"},{"key":"ref20","first-page":"1857","article-title":"Improved deep metric learning with multi-class n-pair loss objective","author":"sohn","year":"0","journal-title":"Proc 30th Int Conf Neural Inf Process Syst"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU46091.2019.9003781"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1846"},{"key":"ref24","article-title":"Speech commands: A dataset for limited-vocabulary speech recognition","author":"warden","year":"2018"},{"key":"ref23","first-page":"133","article-title":"Metric learning for keyword spotting","author":"huh","year":"0","journal-title":"Proc IEEE Spoken Lang Technol Workshop"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2017.2732900"},{"key":"ref25","doi-asserted-by":"crossref","first-page":"227","DOI":"10.1007\/978-3-642-76153-9_28","article-title":"Probabilistic interpretation of feedforward classification network outputs, with relationships to statistical pattern recognition","volume":"68","author":"bridle","year":"1990","journal-title":"Neurocomputing"},{"key":"ref50","first-page":"5998","article-title":"Attention is all you need","author":"vaswani","year":"0","journal-title":"Proc 31st Int Conf Neural Inf Process Syst"},{"key":"ref51","article-title":"Hello edge: Keyword spotting on microcontrollers","author":"zhang","year":"2018"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683474"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU46091.2019.9004014"},{"key":"ref52","first-page":"220","article-title":"An application of recurrent neural networks to discriminative keyword spotting","author":"fern\u00e1ndez","year":"0","journal-title":"Proc 17th Int Conf Artif Neural Netw"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7953242"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053313"},{"key":"ref40","author":"hirsch","year":"2005","journal-title":"Fant - filtering and noise adding tool"},{"key":"ref12","first-page":"1606","article-title":"Convolutional recurrent neural networks for small-footprint keyword spotting","author":"arik","year":"0","journal-title":"Proc 18th Annu Conf Int Speech Commun Assoc"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1777"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462688"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1363"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2010"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2020.2984089"},{"key":"ref18","first-page":"331","article-title":"Exploring filterbank learning for keyword spotting","author":"l\u00f3pez-espejo","year":"0","journal-title":"Proc 28th Eur Signal Process Conf"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298682"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462346"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1668"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8682682"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054538"},{"key":"ref8","first-page":"6475","article-title":"Improving noise robustness of automatic speech recognition via parallel data and teacher-student learning","author":"mo\u0161ner","year":"0","journal-title":"Proc 44th IEEE Int Conf Acoust Speech Signal Process"},{"key":"ref7","doi-asserted-by":"crossref","first-page":"251","DOI":"10.1007\/978-3-030-27947-9_21","article-title":"On practical aspects of multi-condition training based on augmentation for reverberation-\/noise-robust speech recognition","volume":"11697","author":"malek","year":"2019","journal-title":"Lecture Notes Comput Sci"},{"key":"ref49","article-title":"A neural attention model for speech command recognition","author":"andrade","year":"2018"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1495"},{"key":"ref46","author":"van rijsbergen","year":"1979","journal-title":"Information Retrieval Butterworth-Heinemann"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/TIT.1987.1057306"},{"key":"ref48","first-page":"2277","article-title":"Streaming keyword spotting on mobile devices","author":"rybakov","year":"0","journal-title":"Proc 21st Annu Conf Int Speech Commun Assoc"},{"key":"ref47","first-page":"2579","article-title":"Visualizing data using t-SNE","volume":"9","author":"maaten","year":"2008","journal-title":"J Mach Learn Res"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1142\/9789814415729_0012"},{"key":"ref41","article-title":"Adam: A method for stochastic optimization","author":"kingma","year":"0","journal-title":"Proc 3rd Int Conf Learn Representations"},{"key":"ref44","article-title":"TensorFlow: Large-scale machine learning on heterogeneous systems","author":"abadi","year":"2015"},{"key":"ref43","article-title":"Keras","author":"chollet","year":"2015"}],"container-title":["IEEE\/ACM Transactions on Audio, Speech, and Language Processing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6570655\/9289074\/09465680.pdf?arnumber=9465680","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,12,3]],"date-time":"2024-12-03T19:09:43Z","timestamp":1733252983000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9465680\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021]]},"references-count":54,"URL":"https:\/\/doi.org\/10.1109\/taslp.2021.3092567","relation":{},"ISSN":["2329-9290","2329-9304"],"issn-type":[{"value":"2329-9290","type":"print"},{"value":"2329-9304","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021]]}}}