{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,8,30]],"date-time":"2025-08-30T16:37:06Z","timestamp":1756571826385,"version":"3.28.0"},"reference-count":35,"publisher":"IEEE","license":[{"start":{"date-parts":[[2021,11,18]],"date-time":"2021-11-18T00:00:00Z","timestamp":1637193600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2021,11,18]],"date-time":"2021-11-18T00:00:00Z","timestamp":1637193600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2021,11,18]],"date-time":"2021-11-18T00:00:00Z","timestamp":1637193600000},"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":[[2021,11,18]]},"DOI":"10.1109\/o-cocosda202152914.2021.9660563","type":"proceedings-article","created":{"date-parts":[[2022,1,3]],"date-time":"2022-01-03T20:19:17Z","timestamp":1641241157000},"page":"7-12","source":"Crossref","is-referenced-by-count":2,"title":["Investigation of a Single-Channel Frequency-Domain Speech Enhancement Network to Improve End-to-End Bengali Automatic Speech Recognition Under Unseen Noisy Conditions"],"prefix":"10.1109","author":[{"given":"Md Mahbub E","family":"Noor","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yen-Ju","family":"Lu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Syu-Siang","family":"Wang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Supratip","family":"Ghose","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Chia-Yu","family":"Chang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ryandhimas E.","family":"Zezario","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shafique","family":"Ahmed","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Wei-Ho","family":"Chung","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yu","family":"Tsao","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hsin-Min","family":"Wang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2011.2114881"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2001.941023"},{"key":"ref31","article-title":"Improved speech enhancement with the wave-u-net","author":"macartney","year":"2018","journal-title":"ArXiv Preprint"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2013-130"},{"journal-title":"Fundamentals of Noise Reduction in Spring Handbook of Speech Processing Chapter 43","year":"2008","author":"chen","key":"ref35"},{"key":"ref34","doi-asserted-by":"crossref","first-page":"1218","DOI":"10.1109\/TSA.2005.860851","article-title":"New insights into the noise reduction Wiener filter","volume":"14","author":"chen","year":"2006","journal-title":"IEEE\/ACM Trans on Audio Speech and Language Processing"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2016.7472621"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2017.2763455"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2013.6638947"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU46091.2019.9003750"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2020.3036783"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1456"},{"key":"ref16","article-title":"The Kaldi speech recognition toolkit","author":"povey","year":"0","journal-title":"Proc ASRU"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2680"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-1296"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-1400"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1201\/b14529"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053266"},{"key":"ref27","doi-asserted-by":"crossref","first-page":"2067","DOI":"10.1109\/TASL.2010.2041110","article-title":"A tandem algorithm for pitch estimation and voiced speech segregation","volume":"18","author":"hu","year":"2010","journal-title":"IEEE\/ACM Trans on Audio Speech and Language Processing"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1270"},{"key":"ref6","first-page":"4375","article-title":"Joint training of frontend and back-end deep neural networks for robust speech recognition","author":"gao","year":"0","journal-title":"Proc ICASSP"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/89.902276"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2015-659"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-540-49127-9"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8682460"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.findings-emnlp.169"},{"key":"ref9","first-page":"577","article-title":"Attention-based models for speech recognition","author":"chorowski","year":"0","journal-title":"Proc NIPS"},{"key":"ref1","first-page":"51","article-title":"Bengali speech corpus for continuous automatic speech recognition system","author":"das","year":"0","journal-title":"Proc Oriental COCOSDA"},{"key":"ref20","first-page":"455","article-title":"Boosting Objective Scores of a Speech Enhancement Model by MetricGAN Post-processing","author":"fu","year":"0","journal-title":"Proc APSIPA ASC"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683169"},{"key":"ref21","first-page":"1","article-title":"Attention is all you need","author":"vaswani","year":"0","journal-title":"Proc NeurIPS"},{"key":"ref24","article-title":"Layer normalization","author":"ba","year":"2016","journal-title":"ArXiv Preprint"},{"key":"ref23","first-page":"181","article-title":"Speech enhancement using self-adaptation and multi-head selfattention","author":"koizumi","year":"0","journal-title":"Proc ICASSP"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.21437\/SLTU.2018-11"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/MVIP49855.2020.9116923"}],"event":{"name":"2021 24th Conference of the Oriental COCOSDA International Committee for the Co-ordination and Standardisation of Speech Databases and Assessment Techniques (O-COCOSDA)","start":{"date-parts":[[2021,11,18]]},"location":"Singapore, Singapore","end":{"date-parts":[[2021,11,20]]}},"container-title":["2021 24th Conference of the Oriental COCOSDA International Committee for the Co-ordination and Standardisation of Speech Databases and Assessment Techniques (O-COCOSDA)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9660212\/9660400\/09660563.pdf?arnumber=9660563","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,5,10]],"date-time":"2022-05-10T16:56:38Z","timestamp":1652201798000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9660563\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,11,18]]},"references-count":35,"URL":"https:\/\/doi.org\/10.1109\/o-cocosda202152914.2021.9660563","relation":{},"subject":[],"published":{"date-parts":[[2021,11,18]]}}}