{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,9,24]],"date-time":"2025-09-24T10:25:57Z","timestamp":1758709557716,"version":"3.28.0"},"reference-count":41,"publisher":"IEEE","license":[{"start":{"date-parts":[[2020,7,1]],"date-time":"2020-07-01T00:00:00Z","timestamp":1593561600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2020,7,1]],"date-time":"2020-07-01T00:00:00Z","timestamp":1593561600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2020,7,1]],"date-time":"2020-07-01T00:00:00Z","timestamp":1593561600000},"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":[[2020,7]]},"DOI":"10.1109\/ijcnn48605.2020.9206817","type":"proceedings-article","created":{"date-parts":[[2020,9,30]],"date-time":"2020-09-30T00:40:33Z","timestamp":1601426433000},"page":"1-7","source":"Crossref","is-referenced-by-count":7,"title":["Using Deep Speech Recognition to Evaluate Speech Enhancement Methods"],"prefix":"10.1109","author":[{"given":"Shamoon","family":"Siddiqui","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ghulam","family":"Rasool","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ravi P.","family":"Ramachandran","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Nidhal C.","family":"Bouaynaya","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1016\/0167-6393(93)90095-3"},{"key":"ref38","doi-asserted-by":"crossref","first-page":"4214","DOI":"10.1109\/ICASSP.2010.5495701","article-title":"A SHORT-TIME OBJECTIVE INTELLIGIBILITY MEASURE FOR TIME-FREQUENCY WEIGHTED NOISY SPEECH Signal Information & Processing Lab, 2628 CD Delft, The Netherlands Oticon A \/ S 2765 Smørum, Denmark","author":"taal","year":"2010","journal-title":"IEEE International Conference on Acoustics Speech and Signal Processing"},{"journal-title":"Vocabulary for Performance and Quality of Service","year":"2006","key":"ref33"},{"journal-title":"ITU-T Rec P 862","article-title":"Perceptual evaluation of speech quality (pesq): An objective method for end-to-end speech quality assessment of narrow-band telephone networks and speech codecs","year":"2001","key":"ref32"},{"key":"ref31","doi-asserted-by":"crossref","DOI":"10.21437\/Interspeech.2017-1428","article-title":"Segan: Speech enhancement generative adversarial network","author":"pascual","year":"2017"},{"key":"ref30","article-title":"Recent developments in speech enhancement in the short-time fourier transform domain","author":"panchami","year":"2016","journal-title":"IEEE Circuits and Systems Magazine"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461671"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1007\/s00530-014-0446-1"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1155\/2009\/942617"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462417"},{"key":"ref10","first-page":"1","article-title":"Gansynth: Adversarial neural audio synthesis","author":"engel","year":"2019","journal-title":"7th International Conference on Learning Representations ICLR 2019"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.7551\/mitpress\/2946.001.0001"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462091"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.1992.225858"},{"key":"ref13","first-page":"2672","article-title":"Generative adversarial nets","author":"goodfellow","year":"2014","journal-title":"Advances in neural information processing systems"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2007.911054"},{"key":"ref15","first-page":"749","article-title":"Perceptual evaluation of speech quality (PESQ)","volume":"862","year":"2001","journal-title":"Networks"},{"journal-title":"ITU-T Recommendation","article-title":"ITU-T. P.862.1: Mapping function for transforming P.862 raw result scores to MOS-LQO","year":"2003","key":"ref16"},{"key":"ref17","article-title":"A style-based generator architecture for generative adversarial networks","author":"karras","year":"2018","journal-title":"CoRR"},{"journal-title":"Auto-encoding variational bayes","year":"2013","author":"kingma","key":"ref18"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/IWQOS.1999.766473"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1007\/s11265-016-1200-z"},{"key":"ref4","doi-asserted-by":"crossref","first-page":"880","DOI":"10.1109\/JRPROC.1947.229647","article-title":"the design of speech communication systems","volume":"35","author":"beranek","year":"1947","journal-title":"Proceedings of the IRE"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1007\/s00034-019-01157-3"},{"article-title":"Data augmentation generative adversarial networks","year":"2017","author":"antoniou","key":"ref3"},{"key":"ref6","first-page":"1","author":"case","year":"0","journal-title":"Deep speech Scaling up end-to-end speech recognition"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178964"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1809"},{"key":"ref8","article-title":"Adversarial audio synthesis","author":"donahue","year":"2019","journal-title":"ICLRE"},{"key":"ref7","article-title":"The fisher corpus: a resource for the next generations of speech-to-text","author":"cieri","year":"2004","journal-title":"LREC"},{"key":"ref2","first-page":"173","article-title":"Deep speech 2: End-to-end speech recognition in english and mandarin","author":"amodei","year":"2016","journal-title":"International Conference on Machine Learning"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TAU.1968.1161979"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.2528\/PIERM08061206"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8682546"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.21236\/ADA073139"},{"key":"ref21","first-page":"707","article-title":"Binary codes capable of correcting deletions, insertions, and reversals","volume":"10","author":"levenshtein","year":"1966","journal-title":"Soviet Physics Doklady"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1201\/b14529"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2006.1659980"},{"key":"ref23","article-title":"Two-dimensional signal and image processing","volume":"710","author":"lim","year":"1990"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2018.2871419"},{"key":"ref25","first-page":"436","article-title":"Speech enhancement based on deep denoising autoencoder","author":"lu","year":"2013","journal-title":"InterSpeech"}],"event":{"name":"2020 International Joint Conference on Neural Networks (IJCNN)","start":{"date-parts":[[2020,7,19]]},"location":"Glasgow, United Kingdom","end":{"date-parts":[[2020,7,24]]}},"container-title":["2020 International Joint Conference on Neural Networks (IJCNN)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9200848\/9206590\/09206817.pdf?arnumber=9206817","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,11,21]],"date-time":"2022-11-21T06:23:33Z","timestamp":1669011813000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9206817\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,7]]},"references-count":41,"URL":"https:\/\/doi.org\/10.1109\/ijcnn48605.2020.9206817","relation":{},"subject":[],"published":{"date-parts":[[2020,7]]}}}