{"id":"https://openalex.org/W4408353984","doi":"https://doi.org/10.1109/icassp49660.2025.10887894","title":"How much to Dereverberate? Low-Latency Single-Channel Speech Enhancement in Distant Microphone Scenarios","display_name":"How much to Dereverberate? Low-Latency Single-Channel Speech Enhancement in Distant Microphone Scenarios","publication_year":2025,"publication_date":"2025-03-12","ids":{"openalex":"https://openalex.org/W4408353984","doi":"https://doi.org/10.1109/icassp49660.2025.10887894"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49660.2025.10887894","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10887894","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"type":"article","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2505.01338","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5059641673","display_name":"Satvik Venkatesh","orcid":"https://orcid.org/0000-0001-5244-3020"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Satvik Venkatesh","raw_affiliation_strings":["L-Acoustics,London,United Kingdom"],"affiliations":[{"raw_affiliation_string":"L-Acoustics,London,United Kingdom","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5054599395","display_name":"Peter John Cusack Coleman","orcid":"https://orcid.org/0000-0002-3266-7358"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Philip Coleman","raw_affiliation_strings":["L-Acoustics,London,United Kingdom"],"affiliations":[{"raw_affiliation_string":"L-Acoustics,London,United Kingdom","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5081766976","display_name":"A. Benilov","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Arthur Benilov","raw_affiliation_strings":["L-Acoustics,London,United Kingdom"],"affiliations":[{"raw_affiliation_string":"L-Acoustics,London,United Kingdom","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5033346395","display_name":"Simon Brown","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Simon Brown","raw_affiliation_strings":["L-Acoustics,London,United Kingdom"],"affiliations":[{"raw_affiliation_string":"L-Acoustics,London,United Kingdom","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5116594468","display_name":"Selim Sheta","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Selim Sheta","raw_affiliation_strings":["L-Acoustics,London,United Kingdom"],"affiliations":[{"raw_affiliation_string":"L-Acoustics,London,United Kingdom","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5082006647","display_name":"Frederic Roskam","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Frederic Roskam","raw_affiliation_strings":["L-Acoustics,London,United Kingdom"],"affiliations":[{"raw_affiliation_string":"L-Acoustics,London,United Kingdom","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5059641673"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.05572163,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"5"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9998999834060669,"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":0.9998999834060669,"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/T11233","display_name":"Advanced Adaptive Filtering Techniques","score":0.9976999759674072,"subfield":{"id":"https://openalex.org/subfields/2206","display_name":"Computational Mechanics"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9776999950408936,"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/computer-science","display_name":"Computer science","score":0.6935825943946838},{"id":"https://openalex.org/keywords/microphone","display_name":"Microphone","score":0.6900207996368408},{"id":"https://openalex.org/keywords/latency","display_name":"Latency (audio)","score":0.6205919981002808},{"id":"https://openalex.org/keywords/channel","display_name":"Channel (broadcasting)","score":0.5277531743049622},{"id":"https://openalex.org/keywords/speech-enhancement","display_name":"Speech enhancement","score":0.5144631862640381},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4999985694885254},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.1891096532344818},{"id":"https://openalex.org/keywords/background-noise","display_name":"Background noise","score":0.1004699170589447}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6935825943946838},{"id":"https://openalex.org/C2778263558","wikidata":"https://www.wikidata.org/wiki/Q46384","display_name":"Microphone","level":3,"score":0.6900207996368408},{"id":"https://openalex.org/C82876162","wikidata":"https://www.wikidata.org/wiki/Q17096504","display_name":"Latency (audio)","level":2,"score":0.6205919981002808},{"id":"https://openalex.org/C127162648","wikidata":"https://www.wikidata.org/wiki/Q16858953","display_name":"Channel (broadcasting)","level":2,"score":0.5277531743049622},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.5144631862640381},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4999985694885254},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.1891096532344818},{"id":"https://openalex.org/C100675267","wikidata":"https://www.wikidata.org/wiki/Q1371624","display_name":"Background noise","level":2,"score":0.1004699170589447},{"id":"https://openalex.org/C68115822","wikidata":"https://www.wikidata.org/wiki/Q1068172","display_name":"Sound pressure","level":2,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/icassp49660.2025.10887894","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10887894","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2505.01338","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2505.01338","pdf_url":"https://arxiv.org/pdf/2505.01338","source":{"id":"https://openalex.org/S4393918464","display_name":"ArXiv.org","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2505.01338","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2505.01338","pdf_url":"https://arxiv.org/pdf/2505.01338","source":{"id":"https://openalex.org/S4393918464","display_name":"ArXiv.org","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":38,"referenced_works":["https://openalex.org/W2009197094","https://openalex.org/W2058079016","https://openalex.org/W2168610508","https://openalex.org/W2242685705","https://openalex.org/W2403891086","https://openalex.org/W2535255545","https://openalex.org/W2559260703","https://openalex.org/W2763188033","https://openalex.org/W2889540509","https://openalex.org/W2898268964","https://openalex.org/W2990594533","https://openalex.org/W2998572311","https://openalex.org/W3015191643","https://openalex.org/W3092864146","https://openalex.org/W3097627357","https://openalex.org/W3097945073","https://openalex.org/W3104196160","https://openalex.org/W3160129476","https://openalex.org/W3163464523","https://openalex.org/W3182322695","https://openalex.org/W3205004157","https://openalex.org/W4221149546","https://openalex.org/W4224133928","https://openalex.org/W4224917453","https://openalex.org/W4224932531","https://openalex.org/W4225905067","https://openalex.org/W4251345346","https://openalex.org/W4312570973","https://openalex.org/W4321608474","https://openalex.org/W4372263902","https://openalex.org/W4376877074","https://openalex.org/W4385823401","https://openalex.org/W4389315128","https://openalex.org/W4392693577","https://openalex.org/W4392903460","https://openalex.org/W6633301432","https://openalex.org/W6690849574","https://openalex.org/W6798679764"],"related_works":["https://openalex.org/W2357191878","https://openalex.org/W1997078944","https://openalex.org/W1968065688","https://openalex.org/W1552846815","https://openalex.org/W2142945567","https://openalex.org/W107154053","https://openalex.org/W2396048001","https://openalex.org/W3096184950","https://openalex.org/W1559044324","https://openalex.org/W4231424160"],"abstract_inverted_index":{"Dereverberation":[0],"is":[1,23,101,125],"an":[2],"important":[3],"sub-task":[4],"of":[5,51,166],"Speech":[6],"Enhancement":[7],"(SE)":[8],"to":[9,62,81,111],"improve":[10],"the":[11,21,27,30,130,163,167],"signal\u2019s":[12],"intelligibility":[13],"and":[14,57,84,89,95,110,135,138],"quality.":[15,172],"However,":[16],"it":[17],"remains":[18],"challenging":[19,123],"because":[20],"reverberation":[22,96,136],"highly":[24],"correlated":[25],"with":[26,39,91,154],"signal.":[28],"Furthermore,":[29],"single-channel":[31,72,119],"SE":[32,73,120],"literature":[33],"has":[34],"predominantly":[35],"focused":[36],"on":[37,86],"rooms":[38,48,88],"short":[40,59,155],"reverb":[41],"times":[42],"(typically":[43],"under":[44,74],"1":[45],"s),":[46],"smaller":[47],"(under":[49],"volumes":[50],"10<sup":[52],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[53,55],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">3</sup>m<sup":[54],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">3</sup>)":[56],"relatively":[58],"distances":[60],"(up":[61],"2":[63],"meters).":[64],"In":[65],"this":[66],"paper,":[67],"we":[68,116,128,149],"explore":[69],"real-time":[70],"low-latency":[71],"distant":[75],"microphone":[76],"scenarios,":[77],"such":[78,105,122],"as":[79,106],"5":[80],"10":[82],"meters,":[83],"focus":[85],"conference":[87],"theatres,":[90],"larger":[92],"room":[93,133,145,168],"dimensions":[94],"times.":[97],"Such":[98],"a":[99],"setup":[100],"useful":[102],"for":[103,152],"applications":[104],"lecture":[107],"demonstrations,":[108],"drama,":[109],"enhance":[112],"stage":[113],"acoustics.":[114],"First,":[115],"show":[117,150],"that":[118,151],"in":[121],"scenarios":[124],"feasible.":[126],"Second,":[127],"investigate":[129],"relationship":[131],"between":[132],"volume":[134],"time,":[137],"demonstrate":[139],"its":[140],"importance":[141],"when":[142],"randomly":[143],"simulating":[144],"impulse":[146],"responses.":[147],"Lastly,":[148],"dereverberation":[153],"decay":[156],"times,":[157],"preserving":[158],"early":[159],"reflections":[160],"before":[161],"decaying":[162],"transfer":[164],"function":[165],"improves":[169],"overall":[170],"signal":[171]},"counts_by_year":[],"updated_date":"2025-12-21T01:58:51.020947","created_date":"2025-10-10T00:00:00"}