{"id":"https://openalex.org/W4406461609","doi":"https://doi.org/10.1109/slt61566.2024.10832166","title":"Spatialemb: Extract and Encode Spatial Information for 1-Stage Multi-Channel Multi-Speaker ASR on Arbitrary Microphone Arrays","display_name":"Spatialemb: Extract and Encode Spatial Information for 1-Stage Multi-Channel Multi-Speaker ASR on Arbitrary Microphone Arrays","publication_year":2024,"publication_date":"2024-12-02","ids":{"openalex":"https://openalex.org/W4406461609","doi":"https://doi.org/10.1109/slt61566.2024.10832166"},"language":"en","primary_location":{"id":"doi:10.1109/slt61566.2024.10832166","is_oa":false,"landing_page_url":"https://doi.org/10.1109/slt61566.2024.10832166","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":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2601.18037","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5078423590","display_name":"Yiwen Shao","orcid":null},"institutions":[{"id":"https://openalex.org/I145311948","display_name":"Johns Hopkins University","ror":"https://ror.org/00za53h95","country_code":"US","type":"education","lineage":["https://openalex.org/I145311948"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Yiwen Shao","raw_affiliation_strings":["Johns Hopkins University,Center for Language and Speech Processing,Baltimore,MD,USA"],"affiliations":[{"raw_affiliation_string":"Johns Hopkins University,Center for Language and Speech Processing,Baltimore,MD,USA","institution_ids":["https://openalex.org/I145311948"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101467338","display_name":"Yong Xu","orcid":"https://orcid.org/0000-0003-4944-6890"},"institutions":[{"id":"https://openalex.org/I4210108985","display_name":"Bellevue Hospital Center","ror":"https://ror.org/01ky34z31","country_code":"US","type":"healthcare","lineage":["https://openalex.org/I1283621791","https://openalex.org/I4210086933","https://openalex.org/I4210108985"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yong Xu","raw_affiliation_strings":["Tencent AI Lab,Bellevue,WA,USA"],"affiliations":[{"raw_affiliation_string":"Tencent AI Lab,Bellevue,WA,USA","institution_ids":["https://openalex.org/I4210108985"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5014580424","display_name":"Sanjeev Khudanpur","orcid":"https://orcid.org/0000-0001-5976-0897"},"institutions":[{"id":"https://openalex.org/I145311948","display_name":"Johns Hopkins University","ror":"https://ror.org/00za53h95","country_code":"US","type":"education","lineage":["https://openalex.org/I145311948"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Sanjeev Khudanpur","raw_affiliation_strings":["Johns Hopkins University,Center for Language and Speech Processing,Baltimore,MD,USA"],"affiliations":[{"raw_affiliation_string":"Johns Hopkins University,Center for Language and Speech Processing,Baltimore,MD,USA","institution_ids":["https://openalex.org/I145311948"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5034476404","display_name":"Dong Yu","orcid":"https://orcid.org/0000-0003-0520-6844"},"institutions":[{"id":"https://openalex.org/I4210108985","display_name":"Bellevue Hospital Center","ror":"https://ror.org/01ky34z31","country_code":"US","type":"healthcare","lineage":["https://openalex.org/I1283621791","https://openalex.org/I4210086933","https://openalex.org/I4210108985"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Dong Yu","raw_affiliation_strings":["Tencent AI Lab,Bellevue,WA,USA"],"affiliations":[{"raw_affiliation_string":"Tencent AI Lab,Bellevue,WA,USA","institution_ids":["https://openalex.org/I4210108985"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5078423590"],"corresponding_institution_ids":["https://openalex.org/I145311948"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.294357,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"56","last_page":"63"},"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":0.9988999962806702,"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":0.9973000288009644,"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/encode","display_name":"ENCODE","score":0.8182970285415649},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.717534601688385},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6399632692337036},{"id":"https://openalex.org/keywords/channel","display_name":"Channel (broadcasting)","score":0.6117697954177856},{"id":"https://openalex.org/keywords/microphone","display_name":"Microphone","score":0.6078391075134277},{"id":"https://openalex.org/keywords/microphone-array","display_name":"Microphone array","score":0.49752286076545715},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3445946276187897},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.19167983531951904}],"concepts":[{"id":"https://openalex.org/C66746571","wikidata":"https://www.wikidata.org/wiki/Q1134833","display_name":"ENCODE","level":3,"score":0.8182970285415649},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.717534601688385},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6399632692337036},{"id":"https://openalex.org/C127162648","wikidata":"https://www.wikidata.org/wiki/Q16858953","display_name":"Channel (broadcasting)","level":2,"score":0.6117697954177856},{"id":"https://openalex.org/C2778263558","wikidata":"https://www.wikidata.org/wiki/Q46384","display_name":"Microphone","level":3,"score":0.6078391075134277},{"id":"https://openalex.org/C2778806681","wikidata":"https://www.wikidata.org/wiki/Q907293","display_name":"Microphone array","level":4,"score":0.49752286076545715},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3445946276187897},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.19167983531951904},{"id":"https://openalex.org/C68115822","wikidata":"https://www.wikidata.org/wiki/Q1068172","display_name":"Sound pressure","level":2,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/slt61566.2024.10832166","is_oa":false,"landing_page_url":"https://doi.org/10.1109/slt61566.2024.10832166","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"},{"id":"pmh:oai:arXiv.org:2601.18037","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2601.18037","pdf_url":"https://arxiv.org/pdf/2601.18037","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:2601.18037","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2601.18037","pdf_url":"https://arxiv.org/pdf/2601.18037","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":32,"referenced_works":["https://openalex.org/W2460742184","https://openalex.org/W2563666542","https://openalex.org/W2884797218","https://openalex.org/W2909607850","https://openalex.org/W2972492143","https://openalex.org/W3015372568","https://openalex.org/W3097777922","https://openalex.org/W3160207687","https://openalex.org/W3160348851","https://openalex.org/W3162341667","https://openalex.org/W3169722760","https://openalex.org/W3196360884","https://openalex.org/W3196845798","https://openalex.org/W3205567090","https://openalex.org/W3207360934","https://openalex.org/W3207834622","https://openalex.org/W3217643883","https://openalex.org/W4221165341","https://openalex.org/W4221165543","https://openalex.org/W4283700324","https://openalex.org/W4312443924","https://openalex.org/W4312806213","https://openalex.org/W4319862214","https://openalex.org/W4319862656","https://openalex.org/W4387799863","https://openalex.org/W4388275000","https://openalex.org/W4392904458","https://openalex.org/W4402111750","https://openalex.org/W6838690662","https://openalex.org/W6847967951","https://openalex.org/W6857062747","https://openalex.org/W6857515838"],"related_works":["https://openalex.org/W107154053","https://openalex.org/W1879255185","https://openalex.org/W2120442551","https://openalex.org/W2769861442","https://openalex.org/W1980506188","https://openalex.org/W2900122540","https://openalex.org/W4240587264","https://openalex.org/W2043735059","https://openalex.org/W2149163000","https://openalex.org/W2041060376"],"abstract_inverted_index":{"Spatial":[0],"information":[1,110],"is":[2],"a":[3,93,99,129,171],"critical":[4],"clue":[5],"for":[6,112,139],"multi-channel":[7,14],"multispeaker":[8],"target":[9],"speech":[10,26],"recognition.":[11],"Most":[12],"state-of-the-art":[13,173],"Automatic":[15],"Speech":[16],"Recognition":[17],"(ASR)":[18],"systems":[19,76],"extract":[20],"spatial":[21,60,109],"features":[22],"only":[23],"during":[24],"the":[25,35,52,66,75,113,135,165,176],"separation":[27],"stage,":[28],"followed":[29],"by":[30],"standard":[31],"single-channel":[32],"ASR":[33,48,114],"on":[34,65,78,127,164],"separated":[36],"speech.":[37],"This":[38],"approach":[39],"results":[40],"in":[41,141],"an":[42],"inefficient,":[43],"lengthy":[44],"pipeline":[45],"and":[46,71,81,107,119,146,158,167],"sub-optimal":[47],"performance":[49,145],"due":[50],"to":[51,83,85,95,133],"accumulated":[53],"errors":[54],"from":[55],"preprocessing":[56],"modules.":[57],"Furthermore,":[58],"most":[59],"feature":[61],"extraction":[62],"methods":[63],"depend":[64],"knowledge":[67],"of":[68,143],"speaker":[69],"positions":[70],"microphone":[72,121],"topology,":[73],"making":[74],"reliant":[77],"specific":[79],"settings":[80],"challenging":[82],"adapt":[84],"new":[86,172],"equipment.":[87],"In":[88],"this":[89],"work,":[90],"we":[91],"propose":[92],"solution":[94],"these":[96],"issues":[97],"with":[98,152,175],"lightweight":[100],"embedding":[101],"module":[102],"named":[103],"SpatialEmb,":[104],"which":[105],"extracts":[106],"encodes":[108],"directly":[111],"model,":[115],"supporting":[116],"both":[117,144],"fixed":[118],"arbitrary":[120],"topology.":[122],"We":[123],"conduct":[124],"comprehensive":[125],"experiments":[126],"AliMeeting,":[128],"real":[130],"meeting":[131],"corpus,":[132],"determine":[134],"optimal":[136],"model":[137,150],"design":[138],"SpatialEmb":[140],"terms":[142],"efficiency.":[147],"Our":[148],"best":[149],"trained":[151],"105":[153],"hours":[154],"Train-Ali-far":[155],"achieves":[156],"17.04%":[157],"20.32%":[159],"character":[160],"error":[161],"rates":[162],"(CER)":[163],"Eval":[166],"Test":[168],"sets,":[169],"establishing":[170],"result":[174],"same":[177],"training":[178],"data.":[179]},"counts_by_year":[],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}