{"id":"https://openalex.org/W7164667751","doi":"https://doi.org/10.21437/chime.2026-13","title":"A Multichannel Band-split Recurrent Architecture for Real-time Speaker-conditioned Speech Enhancement","display_name":"A Multichannel Band-split Recurrent Architecture for Real-time Speaker-conditioned Speech Enhancement","publication_year":2026,"publication_date":"2026-05-04","ids":{"openalex":"https://openalex.org/W7164667751","doi":"https://doi.org/10.21437/chime.2026-13"},"language":"en","primary_location":{"id":"doi:10.21437/chime.2026-13","doi":"https://doi.org/10.21437/chime.2026-13","is_oa":true,"landing_page_url":"https://doi.org/10.21437/chime.2026-13","pdf_url":"https://www.isca-archive.org/chime_2026/jhou26_chime.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"9th CHiME Speech Separation and Recognition Challenge (CHiME 2026)","raw_type":"proceedings-article"},"volume":null,"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.isca-archive.org/chime_2026/jhou26_chime.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5138585088","display_name":"Zeen Jhou","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I16733864","display_name":"National Taiwan University","ror":"https://ror.org/05bqach95","country_code":"TW","type":"education","lineage":["https://openalex.org/I16733864"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Zeen Jhou","raw_affiliation_strings":["National Taiwan University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Taiwan University","institution_ids":["https://openalex.org/I16733864"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5138557790","display_name":"Rong Chao","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Rong Chao","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5110692834","display_name":"You-Jin Li","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"You-Jin Li","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5138567587","display_name":"Yu Tsao","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I84653119","display_name":"Academia Sinica","ror":"https://ror.org/05bxb3784","country_code":"TW","type":"facility","lineage":["https://openalex.org/I84653119"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Yu Tsao","raw_affiliation_strings":["Academia Sinica"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Academia Sinica","institution_ids":["https://openalex.org/I84653119"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.44139834,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"58","last_page":"60"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9990000128746033,"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":0.9990000128746033,"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":0.000699999975040555,"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/T11309","display_name":"Music and Audio Processing","score":0.0,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/multichannel-speech-enhancement","display_name":"multichannel speech enhancement","score":0.9649999737739563},{"id":"https://openalex.org/keywords/recurrent-neural-networks","display_name":"recurrent neural networks","score":0.8259999752044678},{"id":"https://openalex.org/keywords/film","display_name":"cinema","score":0.5320000052452087},{"id":"https://openalex.org/keywords/lstm","display_name":"LSTM","score":0.7089999914169312},{"id":"https://openalex.org/keywords/speaker-extraction","display_name":"speaker extraction","score":0.6710000038146973},{"id":"https://openalex.org/keywords/real-time-inference","display_name":"real-time inference","score":0.7139999866485596},{"id":"https://openalex.org/keywords/noise-robust-speech-enhancement","display_name":"noise-robust speech enhancement","score":0.5720000267028809}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6273000240325928},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.6154999732971191},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.49570000171661377},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.40380001068115234},{"id":"https://openalex.org/C163258240","wikidata":"https://www.wikidata.org/wiki/Q25342","display_name":"Power (physics)","level":2,"score":0.3310999870300293},{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.3154999911785126},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.29980000853538513},{"id":"https://openalex.org/C123657996","wikidata":"https://www.wikidata.org/wiki/Q12271","display_name":"Architecture","level":2,"score":0.2842000126838684},{"id":"https://openalex.org/C9652623","wikidata":"https://www.wikidata.org/wiki/Q190109","display_name":"Field (mathematics)","level":2,"score":0.27070000767707825},{"id":"https://openalex.org/C104267543","wikidata":"https://www.wikidata.org/wiki/Q208163","display_name":"Signal processing","level":3,"score":0.2671000063419342},{"id":"https://openalex.org/C2780009758","wikidata":"https://www.wikidata.org/wiki/Q6804172","display_name":"Measure (data warehouse)","level":2,"score":0.26660001277923584},{"id":"https://openalex.org/C100675267","wikidata":"https://www.wikidata.org/wiki/Q1371624","display_name":"Background noise","level":2,"score":0.2635999917984009},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.26249998807907104},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.25940001010894775}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21437/chime.2026-13","doi":"https://doi.org/10.21437/chime.2026-13","is_oa":true,"landing_page_url":"https://doi.org/10.21437/chime.2026-13","pdf_url":"https://www.isca-archive.org/chime_2026/jhou26_chime.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"9th CHiME Speech Separation and Recognition Challenge (CHiME 2026)","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.21437/chime.2026-13","doi":"https://doi.org/10.21437/chime.2026-13","is_oa":true,"landing_page_url":"https://doi.org/10.21437/chime.2026-13","pdf_url":"https://www.isca-archive.org/chime_2026/jhou26_chime.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"9th CHiME Speech Separation and Recognition Challenge (CHiME 2026)","raw_type":"proceedings-article"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7164667751.pdf","grobid_xml":"https://content.openalex.org/works/W7164667751.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4385822305","https://openalex.org/W4406298889","https://openalex.org/W3109458322","https://openalex.org/W3160973314","https://openalex.org/W3143523846","https://openalex.org/W4319862661","https://openalex.org/W4225323964","https://openalex.org/W3167217740","https://openalex.org/W6921330492","https://openalex.org/W4408354537"],"abstract_inverted_index":{"This":[0],"paper":[1],"presents":[2],"MBSRNN,":[3],"a":[4,77,82],"real-time":[5,110],"multichannel":[6],"speech":[7,34,102],"enhancement":[8],"and":[9,22],"speaker":[10,46,52],"extraction":[11],"system":[12],"developed":[13],"for":[14,71],"the":[15,32,49,57,92],"CHiME-9":[16,93],"ECHI":[17],"challenge.MBSRNN":[18],"efficiently":[19],"leverages":[20],"spatial":[21],"phase":[23],"information":[24,53],"across":[25],"microphones.Unlike":[26],"traditional":[27],"methods,":[28],"bandsplit":[29],"processing":[30],"to":[31,38,43],"enrollment":[33],"is":[35,54],"applied":[36],"prior":[37],"encoding,":[39],"which":[40],"allows":[41],"us":[42],"capture":[44],"fine-grained":[45],"characteristics":[47],"at":[48],"subband":[50],"level.This":[51],"integrated":[55],"into":[56],"network":[58],"via":[59],"Feature-wise":[60],"Linear":[61],"Modulation":[62],"(FiLM)":[63],"interleaved":[64],"with":[65,81],"LSTM":[66],"blocks.To":[67],"ensure":[68],"online-streaming":[69],"capability":[70],"hearing":[72],"assistive":[73],"devices,":[74],"we":[75],"employ":[76],"chunk-based":[78],"inference":[79],"strategy":[80],"strict":[83],"maximum":[84],"algorithmic":[85],"latency":[86],"of":[87],"20":[88],"ms.Experimental":[89],"results":[90],"on":[91],"development":[94],"set":[95],"demonstrate":[96],"that":[97],"MBSRNN":[98],"effectively":[99],"extracts":[100],"target":[101],"in":[103],"highly":[104],"noisy":[105],"environments":[106],"while":[107],"maintaining":[108],"robust":[109],"performance.":[111]},"counts_by_year":[],"updated_date":"2026-10-28T10:33:24.094632","created_date":"2026-06-14T00:00:00"}