{"id":"https://openalex.org/W4391021644","doi":"https://doi.org/10.1109/asru57964.2023.10389669","title":"On Time Domain Conformer Models for Monaural Speech Separation in Noisy Reverberant Acoustic Environments","display_name":"On Time Domain Conformer Models for Monaural Speech Separation in Noisy Reverberant Acoustic Environments","publication_year":2023,"publication_date":"2023-12-16","ids":{"openalex":"https://openalex.org/W4391021644","doi":"https://doi.org/10.1109/asru57964.2023.10389669"},"language":"en","primary_location":{"id":"doi:10.1109/asru57964.2023.10389669","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asru57964.2023.10389669","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5004802529","display_name":"William Ravenscroft","orcid":"https://orcid.org/0000-0002-0780-3303"},"institutions":[{"id":"https://openalex.org/I91136226","display_name":"University of Sheffield","ror":"https://ror.org/05krs5044","country_code":"GB","type":"education","lineage":["https://openalex.org/I91136226"]}],"countries":["GB"],"is_corresponding":true,"raw_author_name":"William Ravenscroft","raw_affiliation_strings":["The University of Sheffield,Speech and Hearing Group,Dept. of Computer Science,Sheffield,UK","Dept. of Computer Science, Speech and Hearing Group, The University of Sheffield, Sheffield, UK"],"affiliations":[{"raw_affiliation_string":"The University of Sheffield,Speech and Hearing Group,Dept. of Computer Science,Sheffield,UK","institution_ids":["https://openalex.org/I91136226"]},{"raw_affiliation_string":"Dept. of Computer Science, Speech and Hearing Group, The University of Sheffield, Sheffield, UK","institution_ids":["https://openalex.org/I91136226"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5027797344","display_name":"Stefan Goetze","orcid":"https://orcid.org/0000-0003-1044-7343"},"institutions":[{"id":"https://openalex.org/I91136226","display_name":"University of Sheffield","ror":"https://ror.org/05krs5044","country_code":"GB","type":"education","lineage":["https://openalex.org/I91136226"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Stefan Goetze","raw_affiliation_strings":["The University of Sheffield,Speech and Hearing Group,Dept. of Computer Science,Sheffield,UK","Dept. of Computer Science, Speech and Hearing Group, The University of Sheffield, Sheffield, UK"],"affiliations":[{"raw_affiliation_string":"The University of Sheffield,Speech and Hearing Group,Dept. of Computer Science,Sheffield,UK","institution_ids":["https://openalex.org/I91136226"]},{"raw_affiliation_string":"Dept. of Computer Science, Speech and Hearing Group, The University of Sheffield, Sheffield, UK","institution_ids":["https://openalex.org/I91136226"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5030528300","display_name":"Thomas Hain","orcid":"https://orcid.org/0000-0003-0939-3464"},"institutions":[{"id":"https://openalex.org/I91136226","display_name":"University of Sheffield","ror":"https://ror.org/05krs5044","country_code":"GB","type":"education","lineage":["https://openalex.org/I91136226"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Thomas Hain","raw_affiliation_strings":["The University of Sheffield,Speech and Hearing Group,Dept. of Computer Science,Sheffield,UK","Dept. of Computer Science, Speech and Hearing Group, The University of Sheffield, Sheffield, UK"],"affiliations":[{"raw_affiliation_string":"The University of Sheffield,Speech and Hearing Group,Dept. of Computer Science,Sheffield,UK","institution_ids":["https://openalex.org/I91136226"]},{"raw_affiliation_string":"Dept. of Computer Science, Speech and Hearing Group, The University of Sheffield, Sheffield, UK","institution_ids":["https://openalex.org/I91136226"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5004802529"],"corresponding_institution_ids":["https://openalex.org/I91136226"],"apc_list":null,"apc_paid":null,"fwci":1.0166,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.77511423,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":95,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"7"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":1.0,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":1.0,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9995999932289124,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9987000226974487,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/conformational-isomerism","display_name":"Conformational isomerism","score":0.7451726198196411},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6304605007171631},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.5301889777183533},{"id":"https://openalex.org/keywords/convolution","display_name":"Convolution (computer science)","score":0.4609738886356354},{"id":"https://openalex.org/keywords/time-domain","display_name":"Time domain","score":0.43966394662857056},{"id":"https://openalex.org/keywords/source-separation","display_name":"Source separation","score":0.42598575353622437},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.41949328780174255},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.379889577627182},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3383689522743225},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.1599164605140686},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.13407915830612183},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.1316492259502411}],"concepts":[{"id":"https://openalex.org/C18705241","wikidata":"https://www.wikidata.org/wiki/Q1128023","display_name":"Conformational isomerism","level":3,"score":0.7451726198196411},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6304605007171631},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.5301889777183533},{"id":"https://openalex.org/C45347329","wikidata":"https://www.wikidata.org/wiki/Q5166604","display_name":"Convolution (computer science)","level":3,"score":0.4609738886356354},{"id":"https://openalex.org/C103824480","wikidata":"https://www.wikidata.org/wiki/Q185889","display_name":"Time domain","level":2,"score":0.43966394662857056},{"id":"https://openalex.org/C2776864781","wikidata":"https://www.wikidata.org/wiki/Q52617913","display_name":"Source separation","level":2,"score":0.42598575353622437},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.41949328780174255},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.379889577627182},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3383689522743225},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.1599164605140686},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.13407915830612183},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.1316492259502411},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C32909587","wikidata":"https://www.wikidata.org/wiki/Q11369","display_name":"Molecule","level":2,"score":0.0},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/asru57964.2023.10389669","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asru57964.2023.10389669","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions","score":0.5600000023841858}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":40,"referenced_works":["https://openalex.org/W1904365287","https://openalex.org/W2734774145","https://openalex.org/W2952218014","https://openalex.org/W2962715207","https://openalex.org/W2962834855","https://openalex.org/W2962935966","https://openalex.org/W2964058413","https://openalex.org/W2981976899","https://openalex.org/W3015191643","https://openalex.org/W3015199127","https://openalex.org/W3086154751","https://openalex.org/W3096893582","https://openalex.org/W3097777922","https://openalex.org/W3099330747","https://openalex.org/W3163652268","https://openalex.org/W3163842642","https://openalex.org/W3167533889","https://openalex.org/W3185109982","https://openalex.org/W3191469971","https://openalex.org/W3197729725","https://openalex.org/W3213661887","https://openalex.org/W4224938485","https://openalex.org/W4250482878","https://openalex.org/W4280557595","https://openalex.org/W4296068774","https://openalex.org/W4300978696","https://openalex.org/W4312257080","https://openalex.org/W4312580459","https://openalex.org/W4312878242","https://openalex.org/W4372260572","https://openalex.org/W4372271367","https://openalex.org/W4375869348","https://openalex.org/W4385245566","https://openalex.org/W4385756463","https://openalex.org/W4388117238","https://openalex.org/W6640036494","https://openalex.org/W6702735670","https://openalex.org/W6739901393","https://openalex.org/W6780226713","https://openalex.org/W6844662008"],"related_works":["https://openalex.org/W2023036309","https://openalex.org/W1972863456","https://openalex.org/W2089371831","https://openalex.org/W4385077663","https://openalex.org/W2052399476","https://openalex.org/W2077273959","https://openalex.org/W2810163160","https://openalex.org/W4220905048","https://openalex.org/W2037964119","https://openalex.org/W1494829770"],"abstract_inverted_index":{"Speech":[0],"separation":[1,33,39],"remains":[2],"an":[3,66],"important":[4],"topic":[5],"for":[6,17,26,93,104],"multispeaker":[7],"technology":[8],"researchers.":[9],"Convolution":[10],"augmented":[11],"transformers":[12],"(conformers)":[13],"have":[14,23,35,47,83],"performed":[15],"well":[16],"many":[18],"speech":[19,27],"processing":[20],"tasks":[21],"but":[22,82],"been":[24,36],"under-researched":[25],"separation.":[28],"Most":[29],"recent":[30],"state-of-the-art":[31],"(SOTA)":[32],"models":[34,46],"time-domain":[37],"audio":[38],"networks":[40,53],"(TasNets).":[41],"A":[42],"number":[43],"of":[44,50,68],"successful":[45],"made":[48],"use":[49],"dual-path":[51],"(DP)":[52],"which":[54],"sequentially":[55,81],"process":[56,76],"local":[57,77],"and":[58,78,122,130],"global":[59,79],"information.":[60],"Time":[61],"domain":[62],"conformers":[63,98],"(TD-Conformers)":[64],"are":[65,99,109],"analogue":[67],"the":[69,128],"DP":[70],"approach":[71],"in":[72],"that":[73,92],"they":[74],"also":[75],"context":[80],"a":[84],"different":[85],"time":[86],"complexity":[87],"function.":[88],"It":[89],"is":[90],"shown":[91],"realistic":[94],"shorter":[95],"signal":[96],"lengths,":[97],"more":[100],"efficient":[101],"when":[102],"controlling":[103],"feature":[105],"dimension.":[106],"Subsampling":[107],"layers":[108],"proposed":[110],"to":[111],"further":[112],"improve":[113],"computational":[114],"efficiency.":[115],"The":[116],"best":[117],"TD-Conformer":[118],"achieves":[119],"$14.6":[120],"\\mathrm{~dB}$":[121,124],"$21.2":[123],"SISDR":[125],"improvement":[126],"on":[127],"WHAMR":[129],"WSJO2Mix":[131],"benchmarks,":[132],"respectively.":[133]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":3}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}