{"id":"https://openalex.org/W4392904458","doi":"https://doi.org/10.1109/icassp48485.2024.10448072","title":"UniX-Encoder: A Universal X-Channel Speech Encoder for AD-HOC Microphone Array Speech Processing","display_name":"UniX-Encoder: A Universal X-Channel Speech Encoder for AD-HOC Microphone Array Speech Processing","publication_year":2024,"publication_date":"2024-03-18","ids":{"openalex":"https://openalex.org/W4392904458","doi":"https://doi.org/10.1109/icassp48485.2024.10448072"},"language":"en","primary_location":{"id":"doi:10.1109/icassp48485.2024.10448072","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp48485.2024.10448072","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5101592613","display_name":"Zili Huang","orcid":"https://orcid.org/0000-0003-4260-8033"},"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":"Zili Huang","raw_affiliation_strings":["Johns Hopkins University,Center for Language and Speech Processing,Baltimore,MD,USA","Center for Language and Speech Processing, Johns Hopkins University, Baltimore, MD, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Johns Hopkins University,Center for Language and Speech Processing,Baltimore,MD,USA","institution_ids":["https://openalex.org/I145311948"]},{"raw_affiliation_string":"Center for Language and Speech Processing, Johns Hopkins University, Baltimore, MD, USA","institution_ids":["https://openalex.org/I145311948"]}]},{"author_position":"middle","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":false,"raw_author_name":"Yiwen Shao","raw_affiliation_strings":["Johns Hopkins University,Center for Language and Speech Processing,Baltimore,MD,USA","Center for Language and Speech Processing, Johns Hopkins University, Baltimore, MD, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Johns Hopkins University,Center for Language and Speech Processing,Baltimore,MD,USA","institution_ids":["https://openalex.org/I145311948"]},{"raw_affiliation_string":"Center for Language and Speech Processing, Johns Hopkins University, Baltimore, MD, USA","institution_ids":["https://openalex.org/I145311948"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5056567731","display_name":"Shixiong Zhang","orcid":"https://orcid.org/0000-0002-0314-9199"},"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":"Shi-Xiong Zhang","raw_affiliation_strings":["Tencent AI Lab,Bellevue,WA,USA","Tencent AI Lab, Bellevue, WA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tencent AI Lab,Bellevue,WA,USA","institution_ids":["https://openalex.org/I4210108985"]},{"raw_affiliation_string":"Tencent AI Lab, Bellevue, WA, USA","institution_ids":["https://openalex.org/I4210108985"]}]},{"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","Tencent AI Lab, Bellevue, WA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tencent AI Lab,Bellevue,WA,USA","institution_ids":["https://openalex.org/I4210108985"]},{"raw_affiliation_string":"Tencent AI Lab, Bellevue, WA, USA","institution_ids":["https://openalex.org/I4210108985"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"11991","last_page":"11995"},"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9998000264167786,"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":0.9986000061035156,"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":0.7981120944023132},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.7654559016227722},{"id":"https://openalex.org/keywords/unix","display_name":"Unix","score":0.5901131629943848},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5634612441062927},{"id":"https://openalex.org/keywords/microphone","display_name":"Microphone","score":0.5534492135047913},{"id":"https://openalex.org/keywords/channel","display_name":"Channel (broadcasting)","score":0.5096249580383301},{"id":"https://openalex.org/keywords/microphone-array","display_name":"Microphone array","score":0.4451342523097992},{"id":"https://openalex.org/keywords/voice-activity-detection","display_name":"Voice activity detection","score":0.43278640508651733},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.41445210576057434},{"id":"https://openalex.org/keywords/computer-network","display_name":"Computer network","score":0.09620362520217896},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.07385396957397461}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7981120944023132},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.7654559016227722},{"id":"https://openalex.org/C112968700","wikidata":"https://www.wikidata.org/wiki/Q11368","display_name":"Unix","level":3,"score":0.5901131629943848},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5634612441062927},{"id":"https://openalex.org/C2778263558","wikidata":"https://www.wikidata.org/wiki/Q46384","display_name":"Microphone","level":3,"score":0.5534492135047913},{"id":"https://openalex.org/C127162648","wikidata":"https://www.wikidata.org/wiki/Q16858953","display_name":"Channel (broadcasting)","level":2,"score":0.5096249580383301},{"id":"https://openalex.org/C2778806681","wikidata":"https://www.wikidata.org/wiki/Q907293","display_name":"Microphone array","level":4,"score":0.4451342523097992},{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.43278640508651733},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.41445210576057434},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.09620362520217896},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.07385396957397461},{"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/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.0},{"id":"https://openalex.org/C68115822","wikidata":"https://www.wikidata.org/wiki/Q1068172","display_name":"Sound pressure","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp48485.2024.10448072","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp48485.2024.10448072","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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":37,"referenced_works":["https://openalex.org/W262275730","https://openalex.org/W1494198834","https://openalex.org/W1522301498","https://openalex.org/W2127141656","https://openalex.org/W2148613904","https://openalex.org/W2299467264","https://openalex.org/W2460742184","https://openalex.org/W2763188033","https://openalex.org/W2842511635","https://openalex.org/W2972541922","https://openalex.org/W2972943112","https://openalex.org/W2972949456","https://openalex.org/W3008762051","https://openalex.org/W3013139777","https://openalex.org/W3016232124","https://openalex.org/W3020336359","https://openalex.org/W3025260599","https://openalex.org/W3036601975","https://openalex.org/W3094831814","https://openalex.org/W3094893851","https://openalex.org/W3133848124","https://openalex.org/W3162341667","https://openalex.org/W3162358523","https://openalex.org/W3197042120","https://openalex.org/W3197580070","https://openalex.org/W3207360934","https://openalex.org/W3207570488","https://openalex.org/W3207841327","https://openalex.org/W3209059054","https://openalex.org/W3209984917","https://openalex.org/W4226491018","https://openalex.org/W4297808394","https://openalex.org/W4372348115","https://openalex.org/W4375868938","https://openalex.org/W6631190155","https://openalex.org/W6678914141","https://openalex.org/W6780218876"],"related_works":["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/W2011788874","https://openalex.org/W2043735059","https://openalex.org/W2041060376","https://openalex.org/W2122030153"],"abstract_inverted_index":{"The":[0,39,121],"speech":[1,37,48,68,116],"field":[2],"is":[3,41,87,123],"evolving":[4],"to":[5,20,44,80,137],"solve":[6],"more":[7],"challenging":[8],"scenarios,":[9],"such":[10,186],"as":[11,105,187],"multi-channel":[12,36,67,130,167],"recordings":[13],"with":[14,53,191],"multiple":[15],"simultaneous":[16],"talkers.":[17],"In":[18,135],"response":[19],"the":[21,30,102,126,162,170,188,192],"diversity":[22],"of":[23,47,111],"microphone":[24,55,82],"configurations":[25],"in":[26,58,71],"use,":[27],"we":[28,160],"introduce":[29],"UniX-Encoder,":[31],"a":[32,45,106,165],"universal":[33],"encoder":[34,86,146,182],"for":[35,99,114,128],"recordings.":[38],"UniX-Encoder":[40,103,122,163],"versatile,":[42],"catering":[43],"variety":[46],"tasks,":[49,175],"and":[50,178],"seamlessly":[51],"integrates":[52],"any":[54],"array,":[56],"whether":[57],"single-talker":[59],"or":[60,154],"multi-talker":[61],"environments.":[62],"Our":[63],"research":[64],"enhances":[65],"previous":[66,94],"processing":[69],"efforts":[70],"four":[72],"aspects:":[73],"1)":[74],"Adaptability:":[75],"Contrasting":[76,93],"traditional":[77],"models":[78,138],"constrained":[79],"certain":[81],"array":[83],"configurations,":[84],"our":[85,145,181],"universally":[88],"compatible.":[89],"2)":[90],"Multi-Task":[91],"Capability:":[92],"systems":[95],"that":[96,139],"were":[97],"designed":[98],"single-task":[100],"applications,":[101],"serves":[104],"versatile":[107],"upstream":[108],"model,":[109],"capable":[110],"extracting":[112],"features":[113],"diverse":[115],"tasks.":[117],"3)":[118],"Self-Supervised":[119],"Training:":[120],"pretrained":[124],"without":[125],"need":[127],"labeled":[129],"data.":[131],"4)":[132],"End-to-End":[133],"Integration:":[134],"contrast":[136],"first":[140],"beamform":[141],"then":[142],"process":[143],"single-channels,":[144],"offers":[147],"an":[148],"end-to-end":[149],"solution,":[150],"bypassing":[151],"explicit":[152],"beamforming":[153],"separation.":[155],"To":[156],"validate":[157],"its":[158],"effectiveness,":[159],"tested":[161],"on":[164],"synthetic":[166],"dataset":[168],"from":[169],"LibriSpeech":[171],"corpus.":[172],"Across":[173],"various":[174],"including":[176],"ASR":[177],"speaker":[179],"diarization,":[180],"consistently":[183],"outperformed":[184],"combinations":[185],"WavLM":[189],"model":[190],"BeamformIt":[193],"frontend.":[194]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}