{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,7]],"date-time":"2026-07-07T15:14:57Z","timestamp":1783437297416,"version":"3.54.6"},"reference-count":65,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"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":["IEEE\/ACM Trans. Audio Speech Lang. Process."],"published-print":{"date-parts":[[2023]]},"DOI":"10.1109\/taslp.2022.3224285","type":"journal-article","created":{"date-parts":[[2022,11,24]],"date-time":"2022-11-24T19:39:47Z","timestamp":1669318787000},"page":"397-410","source":"Crossref","is-referenced-by-count":42,"title":["STFT-Domain Neural Speech Enhancement With Very Low Algorithmic Latency"],"prefix":"10.1109","volume":"31","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-4204-9430","authenticated-orcid":false,"given":"Zhong-Qiu","family":"Wang","sequence":"first","affiliation":[{"name":"Language Technologies Institute, Carnegie Mellon University, Pittsburgh, PA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8597-6795","authenticated-orcid":false,"given":"Gordon","family":"Wichern","sequence":"additional","affiliation":[{"name":"Mitsubishi Electric Research Laboratories, Cambridge, MA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5970-8631","authenticated-orcid":false,"given":"Shinji","family":"Watanabe","sequence":"additional","affiliation":[{"name":"Language Technologies Institute, Carnegie Mellon University, Pittsburgh, PA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3451-171X","authenticated-orcid":false,"given":"Jonathan","family":"Le Roux","sequence":"additional","affiliation":[{"name":"Mitsubishi Electric Research Laboratories, Cambridge, MA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref39","first-page":"222","article-title":"A low delay, variable resolution, perfect reconstruction spectral analysis-synthesis system for speech enhancement","author":"mauler","year":"0","journal-title":"Proc Eur Signal Process Conf"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-230"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/WASPAA52581.2021.9632720"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9052981"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053833"},{"key":"ref30","first-page":"6","article-title":"Binaural speech enhancement based on deep attention layers","author":"gajecki","year":"0","journal-title":"Proc Clarity"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053575"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2016.2647702"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/JPROC.2020.3018668"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2012.2205029"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414062"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2011.2114881"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683855"},{"key":"ref63","article-title":"P.862.1: Mapping function for transforming P.862 raw result scores to MOS-LQO","year":"2003"},{"key":"ref28","first-page":"3","article-title":"A two-stage end-to-end system for speech-in-noise hearing aid processing","author":"tu","year":"0","journal-title":"Proc Clarity"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3078640"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053602"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461824"},{"key":"ref29","first-page":"1","article-title":"BUT system for the first clarity enhancement challenge","author":"zmolikova","year":"0","journal-title":"Proc Clarity"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2013.2250961"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2018.2842159"},{"key":"ref20","article-title":"Clarity challenge: Machine learning challenges for hearing devices","year":"2021"},{"key":"ref22","first-page":"2","article-title":"Combining binaural LCMP beamforming and deep multi-frame filtering for joint dereverberation and interferer reduction in the Clarity-2021 challenge","author":"gode","year":"0","journal-title":"Proc Clarity"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2011.2174226"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.23919\/EUSIPCO54536.2021.9616165"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/SLT48900.2021.9383522"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-540-70602-1_2"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1121\/10.0014875"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/PROC.1978.10837"},{"key":"ref51","author":"oppenheim","year":"1999","journal-title":"Discrete-Time Signal Processing"},{"key":"ref59","first-page":"1210","article-title":"Reducing algorithmic delay using low-overlap window for online Wave-U-net","author":"nakaoka","year":"0","journal-title":"Proc IEEE Asia-Pacific Signal Inf Process Assoc Annu Summit Conf"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414774"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461310"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/WASPAA52581.2021.9632783"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7952261"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3133208"},{"key":"ref53","first-page":"81","article-title":"WSJCAM0: A British english speech corpus for large vocabulary continuous speech recognition","volume":"1","author":"robinson","year":"0","journal-title":"Proc IEEE Int Conf Acoust Speech Signal Process"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/TASSP.1984.1164317"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9413901"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2019.2909193"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3129363"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/IWAENC.2018.8521347"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054536"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2537"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053215"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3082318"},{"key":"ref17","article-title":"WaveNet: A generative model for raw audio","author":"oord","year":"2016"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462417"},{"key":"ref19","first-page":"2492","article-title":"The INTERSPEECH 2020 deep noise suppression challenge: Datasets, subjective speech quality and testing framework","author":"reddy","year":"0","journal-title":"Proc Annu Conf Int Speech Commun Assoc"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2019.2904183"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2014.2364452"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-1428"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2015.2512042"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2019.2955276"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2019.2915167"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461850"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054266"},{"key":"ref46","first-page":"234","article-title":"U-Net: Convolutional networks for biomedical image segmentation","author":"ronneberger","year":"0","journal-title":"Proc Int Conf Med Image Comput Comput Assist Interv"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2021.3116502"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2020.2975902"},{"key":"ref47","article-title":"Leveraging low-distortion target estimates for improved speech enhancement","author":"wang","year":"2021"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2020.2998279"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053610"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746931"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3083405"}],"container-title":["IEEE\/ACM Transactions on Audio, Speech, and Language Processing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6570655\/9970249\/09961936.pdf?arnumber=9961936","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,12,26]],"date-time":"2022-12-26T19:27:16Z","timestamp":1672082836000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9961936\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023]]},"references-count":65,"URL":"https:\/\/doi.org\/10.1109\/taslp.2022.3224285","relation":{},"ISSN":["2329-9290","2329-9304"],"issn-type":[{"value":"2329-9290","type":"print"},{"value":"2329-9304","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023]]}}}