{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,2,21]],"date-time":"2025-02-21T21:14:06Z","timestamp":1740172446921,"version":"3.37.3"},"reference-count":62,"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":"am","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":[{"DOI":"10.13039\/100000001","name":"National Science Foundation","doi-asserted-by":"publisher","award":["IIS-1618061","IIS-1750383"],"award-info":[{"award-number":["IIS-1618061","IIS-1750383"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]}],"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.2020.3040545","type":"journal-article","created":{"date-parts":[[2020,11,25]],"date-time":"2020-11-25T21:46:11Z","timestamp":1606340771000},"page":"312-323","source":"Crossref","is-referenced-by-count":8,"title":["Directly Comparing the Listening Strategies of Humans and Machines"],"prefix":"10.1109","volume":"29","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-1660-6627","authenticated-orcid":false,"given":"Viet Anh","family":"Trinh","sequence":"first","affiliation":[]},{"given":"Michael","family":"Mandel","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0130140"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1145\/2939672.2939778"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1121\/1.5101576"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1121\/1.3295689"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1177\/2331216519886707"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1152\/jn.00088.2002"},{"article-title":"Deep inside convolutional networks: Visualising image classification models and saliency maps","year":"2013","author":"simonyan","key":"ref37"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.319"},{"key":"ref35","first-page":"818","article-title":"Visualizing and understanding convolutional networks","author":"zeiler","year":"0","journal-title":"Proc Eur Conf Comput Vis"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1121\/1.5101104"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461704"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.7551\/mitpress\/1072.001.0001"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/89.759034"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.3389\/fnhum.2013.00865"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1121\/1.4730905"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1121\/1.4960544"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1121\/1.2166600"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1016\/j.csl.2018.04.003"},{"key":"ref20","first-page":"1912","article-title":"Exploring how deep neural networks form phonemic categories","author":"nagamine","year":"0","journal-title":"Proc INTERSPEECH"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-2377"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1126\/science.1245994"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1121\/1.424370"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1121\/1.417336"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1121\/1.2722211"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1121\/1.1781329"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2013.6637622"},{"key":"ref51","first-page":"109","article-title":"Improved feature processing for deep neural networks","author":"rath","year":"0","journal-title":"Proc INTERSPEECH"},{"key":"ref59","article-title":"Interpolated estimation of Markov source parameters from sparse data","author":"jelinek","year":"0","journal-title":"Proc Workshop Pattern Recognit Pract"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.1995.479394"},{"key":"ref57","article-title":"SRILM-an extensible language modeling toolkit","author":"stolcke","year":"0","journal-title":"Proc Int Conf Spoken Lang Process"},{"key":"ref56","first-page":"25","article-title":"The TUM+TUT+KUL approach to the 2nd CHiME challenge: Multi-stream ASR exploiting BLSTM networks and sparse NMF","author":"geiger","year":"0","journal-title":"Proc Int Conf Acoust Speech and Signal Process"},{"key":"ref55","first-page":"6159","article-title":"Learning recurrent neural network language models with context-sensitive label smoothing for automatic speech recognition","author":"song","year":"0","journal-title":"Proc IEEE Int Conf Acoust Speech Signal Process"},{"key":"ref54","first-page":"338","article-title":"Long short-term memory recurrent neural network architectures for large scale acoustic modeling","author":"sak","year":"0","journal-title":"Proc 15th Annu Conf Int Speech Commun Assoc"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-129"},{"key":"ref52","first-page":"3214","article-title":"A time delay neural network architecture for efficient modeling of long temporal contexts","author":"peddinti","year":"0","journal-title":"Proc 16th Annu Conf Int Speech Commun Assoc"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1121\/1.2229005"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1007\/11677482_3"},{"article-title":"Smoothgrad: Removing noise by adding noise","year":"2017","author":"smilkov","key":"ref40"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2016-932"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1121\/1.3514525"},{"key":"ref14","first-page":"1273","article-title":"Oldenburg logatome speech corpus (OLLO) for speech recognition experiments with humans and machines","author":"wesker","year":"0","journal-title":"Proc 9th Eur Conf Speech Commun Technol"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.1995.479404"},{"article-title":"Error-responsive feedback mechanisms for speech recognizers","year":"1997","author":"chase","key":"ref16"},{"key":"ref17","first-page":"71","article-title":"Don’t multiply lightly: Quantifying problems with the acoustic model assumptions in speech recognition","author":"gillick","year":"0","journal-title":"Proc IEEE ASRU"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2012.6288979"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2013.6638970"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2007.01.009"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1016\/S0167-6393(97)00021-6"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1121\/1.3684744"},{"key":"ref5","first-page":"95","article-title":"A human-machine comparison in speech recognition based on a logatome corpus","author":"meyer","year":"0","journal-title":"Proc Speech Recognition and Intrinsic Variation Workshop"},{"key":"ref8","first-page":"2016","article-title":"Generalizing time-frequency importance functions across noises, talkers, and phonemes","author":"mandel","year":"0","journal-title":"Proc INTERSPEECH"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/WASPAA.2013.6701835"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1016\/j.csl.2012.10.004"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1121\/1.4964102"},{"journal-title":"Statistical Methods for Speech Recognition","year":"1997","author":"jelinek","key":"ref46"},{"key":"ref45","article-title":"The Kaldi speech recognition toolkit","author":"povey","year":"0","journal-title":"Proc ASRU"},{"journal-title":"Automatic Speech Recognition","year":"2016","author":"yu","key":"ref48"},{"journal-title":"Speech and Language Processing","year":"2009","author":"jurafsky","key":"ref47"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1016\/0378-5955(90)90170-T"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1016\/S0042-6989(01)00097-9"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1121\/1.1907526"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.3758\/BF03214307"}],"container-title":["IEEE\/ACM Transactions on Audio, Speech, and Language Processing"],"original-title":[],"link":[{"URL":"https:\/\/ieeexplore.ieee.org\/ielam\/6570655\/9289074\/9271908-aam.pdf","content-type":"application\/pdf","content-version":"am","intended-application":"syndication"},{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6570655\/9289074\/09271908.pdf?arnumber=9271908","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,5,10]],"date-time":"2022-05-10T14:54:01Z","timestamp":1652194441000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9271908\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021]]},"references-count":62,"URL":"https:\/\/doi.org\/10.1109\/taslp.2020.3040545","relation":{},"ISSN":["2329-9290","2329-9304"],"issn-type":[{"type":"print","value":"2329-9290"},{"type":"electronic","value":"2329-9304"}],"subject":[],"published":{"date-parts":[[2021]]}}}