{"id":"https://openalex.org/W4406461901","doi":"https://doi.org/10.1109/slt61566.2024.10832223","title":"Dualsep: A Light-Weight Dual-Encoder Convolutional Recurrent Network For Real-Time In-Car Speech Separation","display_name":"Dualsep: A Light-Weight Dual-Encoder Convolutional Recurrent Network For Real-Time In-Car Speech Separation","publication_year":2024,"publication_date":"2024-12-02","ids":{"openalex":"https://openalex.org/W4406461901","doi":"https://doi.org/10.1109/slt61566.2024.10832223"},"language":"en","primary_location":{"id":"doi:10.1109/slt61566.2024.10832223","is_oa":false,"landing_page_url":"https://doi.org/10.1109/slt61566.2024.10832223","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE Spoken Language Technology Workshop (SLT)","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/A5100332232","display_name":"Ziqian Wang","orcid":"https://orcid.org/0009-0006-9496-2244"},"institutions":[{"id":"https://openalex.org/I17145004","display_name":"Northwestern Polytechnical University","ror":"https://ror.org/01y0j0j86","country_code":"CN","type":"education","lineage":["https://openalex.org/I17145004"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Ziqian Wang","raw_affiliation_strings":["Northwestern Polytechnical University,Audio, Speech and Language Processing Group (ASLP@NPU), School of Computer Science,Xi’an,China"],"affiliations":[{"raw_affiliation_string":"Northwestern Polytechnical University,Audio, Speech and Language Processing Group (ASLP@NPU), School of Computer Science,Xi’an,China","institution_ids":["https://openalex.org/I17145004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5032074032","display_name":"Jiayao Sun","orcid":null},"institutions":[{"id":"https://openalex.org/I17145004","display_name":"Northwestern Polytechnical University","ror":"https://ror.org/01y0j0j86","country_code":"CN","type":"education","lineage":["https://openalex.org/I17145004"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiayao Sun","raw_affiliation_strings":["Northwestern Polytechnical University,Audio, Speech and Language Processing Group (ASLP@NPU), School of Computer Science,Xi’an,China"],"affiliations":[{"raw_affiliation_string":"Northwestern Polytechnical University,Audio, Speech and Language Processing Group (ASLP@NPU), School of Computer Science,Xi’an,China","institution_ids":["https://openalex.org/I17145004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100410545","display_name":"Zihan Zhang","orcid":"https://orcid.org/0000-0002-0415-7721"},"institutions":[{"id":"https://openalex.org/I17145004","display_name":"Northwestern Polytechnical University","ror":"https://ror.org/01y0j0j86","country_code":"CN","type":"education","lineage":["https://openalex.org/I17145004"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zihan Zhang","raw_affiliation_strings":["Northwestern Polytechnical University,Audio, Speech and Language Processing Group (ASLP@NPU), School of Computer Science,Xi’an,China"],"affiliations":[{"raw_affiliation_string":"Northwestern Polytechnical University,Audio, Speech and Language Processing Group (ASLP@NPU), School of Computer Science,Xi’an,China","institution_ids":["https://openalex.org/I17145004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100749621","display_name":"Xingchen Li","orcid":"https://orcid.org/0000-0002-2786-5392"},"institutions":[{"id":"https://openalex.org/I17145004","display_name":"Northwestern Polytechnical University","ror":"https://ror.org/01y0j0j86","country_code":"CN","type":"education","lineage":["https://openalex.org/I17145004"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xingchen Li","raw_affiliation_strings":["Northwestern Polytechnical University,Audio, Speech and Language Processing Group (ASLP@NPU), School of Computer Science,Xi’an,China"],"affiliations":[{"raw_affiliation_string":"Northwestern Polytechnical University,Audio, Speech and Language Processing Group (ASLP@NPU), School of Computer Science,Xi’an,China","institution_ids":["https://openalex.org/I17145004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100454011","display_name":"Jie Liu","orcid":"https://orcid.org/0000-0001-6912-0797"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jie Liu","raw_affiliation_strings":["Huawei Cloud"],"affiliations":[{"raw_affiliation_string":"Huawei Cloud","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100668966","display_name":"Lei Xie","orcid":"https://orcid.org/0000-0001-8234-0823"},"institutions":[{"id":"https://openalex.org/I17145004","display_name":"Northwestern Polytechnical University","ror":"https://ror.org/01y0j0j86","country_code":"CN","type":"education","lineage":["https://openalex.org/I17145004"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lei Xie","raw_affiliation_strings":["Northwestern Polytechnical University,Audio, Speech and Language Processing Group (ASLP@NPU), School of Computer Science,Xi’an,China"],"affiliations":[{"raw_affiliation_string":"Northwestern Polytechnical University,Audio, Speech and Language Processing Group (ASLP@NPU), School of Computer Science,Xi’an,China","institution_ids":["https://openalex.org/I17145004"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5100332232"],"corresponding_institution_ids":["https://openalex.org/I17145004"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.29373026,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"286","last_page":"293"},"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9994000196456909,"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":0.9940000176429749,"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/computer-science","display_name":"Computer science","score":0.7223885655403137},{"id":"https://openalex.org/keywords/dual","display_name":"Dual (grammatical number)","score":0.7157706022262573},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.6861885786056519},{"id":"https://openalex.org/keywords/separation","display_name":"Separation (statistics)","score":0.5455533862113953},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.47619521617889404},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.34873223304748535},{"id":"https://openalex.org/keywords/real-time-computing","display_name":"Real-time computing","score":0.3280028700828552},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.10303172469139099}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7223885655403137},{"id":"https://openalex.org/C2780980858","wikidata":"https://www.wikidata.org/wiki/Q110022","display_name":"Dual (grammatical number)","level":2,"score":0.7157706022262573},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.6861885786056519},{"id":"https://openalex.org/C2776061190","wikidata":"https://www.wikidata.org/wiki/Q7451805","display_name":"Separation (statistics)","level":2,"score":0.5455533862113953},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.47619521617889404},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.34873223304748535},{"id":"https://openalex.org/C79403827","wikidata":"https://www.wikidata.org/wiki/Q3988","display_name":"Real-time computing","level":1,"score":0.3280028700828552},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.10303172469139099},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C124952713","wikidata":"https://www.wikidata.org/wiki/Q8242","display_name":"Literature","level":1,"score":0.0},{"id":"https://openalex.org/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/slt61566.2024.10832223","is_oa":false,"landing_page_url":"https://doi.org/10.1109/slt61566.2024.10832223","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE Spoken Language Technology Workshop (SLT)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":35,"referenced_works":["https://openalex.org/W1901129140","https://openalex.org/W2058079016","https://openalex.org/W2060108923","https://openalex.org/W2064675550","https://openalex.org/W2147665979","https://openalex.org/W2194775991","https://openalex.org/W2402526332","https://openalex.org/W2539141352","https://openalex.org/W2568308529","https://openalex.org/W2714487941","https://openalex.org/W2803583024","https://openalex.org/W2889442120","https://openalex.org/W2952218014","https://openalex.org/W2962760690","https://openalex.org/W2963242190","https://openalex.org/W2970618241","https://openalex.org/W3015199127","https://openalex.org/W3032514799","https://openalex.org/W3043534594","https://openalex.org/W3097173744","https://openalex.org/W3097643313","https://openalex.org/W3099330747","https://openalex.org/W3162341667","https://openalex.org/W3171278394","https://openalex.org/W3194303810","https://openalex.org/W3196360884","https://openalex.org/W3207841327","https://openalex.org/W4292971627","https://openalex.org/W4310638450","https://openalex.org/W4312356750","https://openalex.org/W4372267870","https://openalex.org/W4375869228","https://openalex.org/W4385822364","https://openalex.org/W6628802962","https://openalex.org/W6757817989"],"related_works":["https://openalex.org/W2071676784","https://openalex.org/W4292513318","https://openalex.org/W4390516098","https://openalex.org/W2181948922","https://openalex.org/W2384362569","https://openalex.org/W4308092240","https://openalex.org/W2287611352","https://openalex.org/W320684304","https://openalex.org/W2142795561","https://openalex.org/W1509352139"],"abstract_inverted_index":{"Advancements":[0],"in":[1,20,39],"deep":[2],"learning":[3],"and":[4,51,80,93,115,130,150],"voice-activated":[5],"technologies":[6],"have":[7],"driven":[8],"the":[9,28,37,40,47,67,136,139],"development":[10],"of":[11,30,42,55,138],"human-vehicle":[12],"interaction.":[13],"Distributed":[14],"microphone":[15],"arrays":[16],"are":[17,173],"widely":[18],"used":[19],"incar":[21],"scenarios":[22],"because":[23],"they":[24],"can":[25],"accurately":[26],"capture":[27],"voices":[29],"passengers":[31],"from":[32],"different":[33],"speech":[34,63,166,169],"zones.":[35,170],"However,":[36],"increase":[38],"number":[41],"audio":[43],"channels,":[44],"coupled":[45],"with":[46,109],"limited":[48],"computational":[49,91],"resources":[50],"low":[52],"latency":[53],"requirements":[54],"in-car":[56,61],"systems,":[57],"presents":[58],"challenges":[59],"for":[60,106],"multi-channel":[62],"separation.":[64],"To":[65],"migrate":[66],"problems,":[68],"we":[69],"propose":[70],"a":[71],"lightweight":[72],"framework":[73],"that":[74],"cascades":[75],"digital":[76],"signal":[77],"processing":[78],"(DSP)":[79],"neural":[81],"networks":[82],"(NN).":[83],"We":[84,102],"utilize":[85],"fixed":[86],"beamforming":[87],"(BF)":[88],"to":[89,98],"reduce":[90],"costs":[92],"independent":[94],"vector":[95],"analysis":[96],"(IVA)":[97],"provide":[99],"spatial":[100,110,113],"prior.":[101],"employ":[103],"dual":[104],"encoders":[105],"dual-branch":[107],"modeling,":[108],"encoder":[111,117],"capturing":[112],"cues":[114],"spectral":[116,119],"preserving":[118],"information,":[120],"facilitating":[121],"spatial-spectral":[122],"fusion.":[123],"Our":[124,171],"proposed":[125,140],"system":[126,141],"supports":[127],"both":[128],"streaming":[129],"non-streaming":[131],"modes.":[132],"Experimental":[133],"results":[134],"demonstrate":[135],"superiority":[137],"across":[142],"various":[143],"metrics.":[144],"With":[145],"only":[146],"0.83":[147],"M":[148],"parameters":[149],"0.39":[151],"real-time":[152],"factor":[153],"(RTF)":[154],"on":[155],"an":[156],"Intel":[157],"Core":[158],"i7":[159],"$(2.6":[160],"\\mathrm{GHz})":[161],"\\mathrm{CPU}$,":[162],"it":[163],"effectively":[164],"separates":[165],"into":[167],"distinct":[168],"demos":[172],"available":[174],"at":[175],"https://honeew.github.io/DualSep/.":[176]},"counts_by_year":[],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}