{"id":"https://openalex.org/W4403126614","doi":"https://doi.org/10.1109/iwaenc61483.2024.10694503","title":"LASER: Language-Queried Speech Enhancer","display_name":"LASER: Language-Queried Speech Enhancer","publication_year":2024,"publication_date":"2024-09-09","ids":{"openalex":"https://openalex.org/W4403126614","doi":"https://doi.org/10.1109/iwaenc61483.2024.10694503"},"language":"en","primary_location":{"id":"doi:10.1109/iwaenc61483.2024.10694503","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iwaenc61483.2024.10694503","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 18th International Workshop on Acoustic Signal Enhancement (IWAENC)","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/A5102520429","display_name":"Danilo de Oliveira","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Danilo de Oliveira","raw_affiliation_strings":["Universität Hamburg,Signal Processing,Germany"],"affiliations":[{"raw_affiliation_string":"Universität Hamburg,Signal Processing,Germany","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5011673214","display_name":"Eric Grinstein","orcid":"https://orcid.org/0000-0003-4502-5407"},"institutions":[{"id":"https://openalex.org/I47508984","display_name":"Imperial College London","ror":"https://ror.org/041kmwe10","country_code":"GB","type":"education","lineage":["https://openalex.org/I47508984"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Eric Grinstein","raw_affiliation_strings":["Imperial College London,Electric and Electronic Eng.,United Kingdom"],"affiliations":[{"raw_affiliation_string":"Imperial College London,Electric and Electronic Eng.,United Kingdom","institution_ids":["https://openalex.org/I47508984"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5016227729","display_name":"Patrick A. Naylor","orcid":"https://orcid.org/0000-0001-8546-8013"},"institutions":[{"id":"https://openalex.org/I47508984","display_name":"Imperial College London","ror":"https://ror.org/041kmwe10","country_code":"GB","type":"education","lineage":["https://openalex.org/I47508984"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Patrick A. Naylor","raw_affiliation_strings":["Imperial College London,Electric and Electronic Eng.,United Kingdom"],"affiliations":[{"raw_affiliation_string":"Imperial College London,Electric and Electronic Eng.,United Kingdom","institution_ids":["https://openalex.org/I47508984"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5087022569","display_name":"Timo Gerkmann","orcid":"https://orcid.org/0000-0002-8678-4699"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Timo Gerkmann","raw_affiliation_strings":["Universität Hamburg,Signal Processing,Germany"],"affiliations":[{"raw_affiliation_string":"Universität Hamburg,Signal Processing,Germany","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5102520429"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.3735,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.57498528,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"90","last_page":"94"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.995199978351593,"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":0.995199978351593,"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":0.9828000068664551,"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"}},{"id":"https://openalex.org/T11398","display_name":"Hand Gesture Recognition Systems","score":0.9254999756813049,"subfield":{"id":"https://openalex.org/subfields/1709","display_name":"Human-Computer Interaction"},"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/computer-science","display_name":"Computer science","score":0.629944920539856},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.43459299206733704},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3401334285736084}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.629944920539856},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.43459299206733704},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3401334285736084}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/iwaenc61483.2024.10694503","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iwaenc61483.2024.10694503","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 18th International Workshop on Acoustic Signal Enhancement (IWAENC)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":24,"referenced_works":["https://openalex.org/W1510355813","https://openalex.org/W1552314771","https://openalex.org/W2020997493","https://openalex.org/W2103934944","https://openalex.org/W2130476329","https://openalex.org/W2291877678","https://openalex.org/W2408688265","https://openalex.org/W2516001803","https://openalex.org/W2603567530","https://openalex.org/W2760103357","https://openalex.org/W2918296821","https://openalex.org/W2963341071","https://openalex.org/W2964058413","https://openalex.org/W3015537910","https://openalex.org/W3096408984","https://openalex.org/W3161480375","https://openalex.org/W4224871700","https://openalex.org/W4232282348","https://openalex.org/W4312711418","https://openalex.org/W4365512576","https://openalex.org/W4372260310","https://openalex.org/W6675521023","https://openalex.org/W6791353385","https://openalex.org/W6801426729"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W4396696052","https://openalex.org/W4402327032","https://openalex.org/W2382290278"],"abstract_inverted_index":{"The":[0],"performance":[1],"of":[2,12,50],"speech":[3,73,81],"enhancement":[4,74,110],"systems":[5],"may":[6],"be":[7],"improved":[8],"by":[9],"the":[10,48,68,72,88,98],"introduction":[11],"prior":[13],"signal":[14],"and":[15,36,76,83,113],"noise":[16,84],"information":[17,23,100],"into":[18],"their":[19],"operation.":[20],"Including":[21],"this":[22,57],"as":[24],"a":[25,33,62],"textual":[26],"query":[27],"is":[28,32],"desirable,":[29],"since":[30],"it":[31],"flexible,":[34],"intuitive":[35],"interpretable":[37],"interface":[38],"for":[39],"human-machine":[40],"interaction.":[41],"This":[42],"has":[43],"recently":[44],"gained":[45],"attention":[46],"in":[47,102,106],"field":[49],"Language-queried":[51],"Audio":[52],"Source":[53],"Separation":[54],"(LASS).":[55],"In":[56],"work,":[58],"we":[59],"propose":[60],"LASER,":[61],"LAnguage-queried":[63],"Speech":[64],"EnhanceR":[65],"that":[66,92],"extends":[67],"LASS":[69],"framework":[70],"to":[71,96,108],"task":[75],"operates":[77],"on":[78,87],"commands":[79],"including":[80],"transcription":[82],"information.":[85],"Experiments":[86],"VoiceBank-DEMAND":[89],"dataset":[90],"confirm":[91],"an":[93],"appropriate":[94],"approach":[95],"include":[97],"aforementioned":[99],"results":[101],"increased":[103],"perceptual":[104],"quality":[105],"comparison":[107],"baseline":[109],"approaches,":[111],"with":[112],"without":[114],"text":[115],"conditioning.":[116]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2025-12-23T23:11:35.936235","created_date":"2025-10-10T00:00:00"}