{"id":"https://openalex.org/W4392903921","doi":"https://doi.org/10.1109/icassp48485.2024.10447563","title":"Automatic Channel Selection and Spatial Feature Integration for Multi-Channel Speech Recognition Across Various Array Topologies","display_name":"Automatic Channel Selection and Spatial Feature Integration for Multi-Channel Speech Recognition Across Various Array Topologies","publication_year":2024,"publication_date":"2024-03-18","ids":{"openalex":"https://openalex.org/W4392903921","doi":"https://doi.org/10.1109/icassp48485.2024.10447563"},"language":"en","primary_location":{"id":"doi:10.1109/icassp48485.2024.10447563","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp48485.2024.10447563","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/A5072425459","display_name":"Bingshen Mu","orcid":"https://orcid.org/0009-0009-7797-865X"},"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":"Bingshen Mu","raw_affiliation_strings":["Northwestern Polytechnical University,Audio, Speech and Language Processing Group (ASLP@NPU), School of Computer Science,Xian,China","Audio, Speech and Language Processing Group (ASLP@NPU), School of Computer Science, Northwestern Polytechnical University, Xian, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Northwestern Polytechnical University,Audio, Speech and Language Processing Group (ASLP@NPU), School of Computer Science,Xian,China","institution_ids":["https://openalex.org/I17145004"]},{"raw_affiliation_string":"Audio, Speech and Language Processing Group (ASLP@NPU), School of Computer Science, Northwestern Polytechnical University, Xian, China","institution_ids":["https://openalex.org/I17145004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101783173","display_name":"Pengcheng Guo","orcid":"https://orcid.org/0009-0001-2388-5935"},"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":"Pengcheng Guo","raw_affiliation_strings":["Northwestern Polytechnical University,Audio, Speech and Language Processing Group (ASLP@NPU), School of Computer Science,Xian,China","Audio, Speech and Language Processing Group (ASLP@NPU), School of Computer Science, Northwestern Polytechnical University, Xian, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Northwestern Polytechnical University,Audio, Speech and Language Processing Group (ASLP@NPU), School of Computer Science,Xian,China","institution_ids":["https://openalex.org/I17145004"]},{"raw_affiliation_string":"Audio, Speech and Language Processing Group (ASLP@NPU), School of Computer Science, Northwestern Polytechnical University, Xian, China","institution_ids":["https://openalex.org/I17145004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101377824","display_name":"Dake Guo","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":"Dake Guo","raw_affiliation_strings":["Northwestern Polytechnical University,Audio, Speech and Language Processing Group (ASLP@NPU), School of Computer Science,Xian,China","Audio, Speech and Language Processing Group (ASLP@NPU), School of Computer Science, Northwestern Polytechnical University, Xian, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Northwestern Polytechnical University,Audio, Speech and Language Processing Group (ASLP@NPU), School of Computer Science,Xian,China","institution_ids":["https://openalex.org/I17145004"]},{"raw_affiliation_string":"Audio, Speech and Language Processing Group (ASLP@NPU), School of Computer Science, Northwestern Polytechnical University, Xian, China","institution_ids":["https://openalex.org/I17145004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5010883708","display_name":"Pan Zhou","orcid":"https://orcid.org/0000-0003-3400-8943"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Pan Zhou","raw_affiliation_strings":["Space AI, Li Auto"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Space AI, Li Auto","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100344481","display_name":"Wei Chen","orcid":"https://orcid.org/0000-0002-7663-278X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wei Chen","raw_affiliation_strings":["Space AI, Li Auto"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Space AI, Li Auto","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,Xian,China","Audio, Speech and Language Processing Group (ASLP@NPU), School of Computer Science, Northwestern Polytechnical University, Xian, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Northwestern Polytechnical University,Audio, Speech and Language Processing Group (ASLP@NPU), School of Computer Science,Xian,China","institution_ids":["https://openalex.org/I17145004"]},{"raw_affiliation_string":"Audio, Speech and Language Processing Group (ASLP@NPU), School of Computer Science, Northwestern Polytechnical University, Xian, China","institution_ids":["https://openalex.org/I17145004"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":3.9116,"has_fulltext":false,"cited_by_count":11,"citation_normalized_percentile":{"value":0.94741258,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"11396","last_page":"11400"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":1.0,"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"}},"topics":[{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":1.0,"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/T10860","display_name":"Speech and Audio Processing","score":0.9998000264167786,"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/T11309","display_name":"Music and Audio Processing","score":0.9984999895095825,"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":0.7510256171226501},{"id":"https://openalex.org/keywords/network-topology","display_name":"Network topology","score":0.6793582439422607},{"id":"https://openalex.org/keywords/channel","display_name":"Channel (broadcasting)","score":0.6341325044631958},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5503626465797424},{"id":"https://openalex.org/keywords/oracle","display_name":"Oracle","score":0.47986310720443726},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.4665173292160034},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.41856902837753296},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.417484849691391},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.36957859992980957},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3690883219242096},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.12258809804916382},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.10082170367240906},{"id":"https://openalex.org/keywords/computer-network","display_name":"Computer network","score":0.09372124075889587}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7510256171226501},{"id":"https://openalex.org/C199845137","wikidata":"https://www.wikidata.org/wiki/Q145490","display_name":"Network topology","level":2,"score":0.6793582439422607},{"id":"https://openalex.org/C127162648","wikidata":"https://www.wikidata.org/wiki/Q16858953","display_name":"Channel (broadcasting)","level":2,"score":0.6341325044631958},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5503626465797424},{"id":"https://openalex.org/C55166926","wikidata":"https://www.wikidata.org/wiki/Q2892946","display_name":"Oracle","level":2,"score":0.47986310720443726},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.4665173292160034},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.41856902837753296},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.417484849691391},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.36957859992980957},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3690883219242096},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.12258809804916382},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.10082170367240906},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.09372124075889587},{"id":"https://openalex.org/C115903868","wikidata":"https://www.wikidata.org/wiki/Q80993","display_name":"Software engineering","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp48485.2024.10447563","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp48485.2024.10447563","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":[{"score":0.4099999964237213,"id":"https://metadata.un.org/sdg/10","display_name":"Reduced inequalities"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":38,"referenced_works":["https://openalex.org/W1494198834","https://openalex.org/W1514905536","https://openalex.org/W1552282138","https://openalex.org/W1592062602","https://openalex.org/W1901129140","https://openalex.org/W1904457459","https://openalex.org/W1973787919","https://openalex.org/W2070707809","https://openalex.org/W2148575186","https://openalex.org/W2148613904","https://openalex.org/W2157331557","https://openalex.org/W2289394825","https://openalex.org/W2803322398","https://openalex.org/W2884797218","https://openalex.org/W2900212944","https://openalex.org/W2944972166","https://openalex.org/W2962780374","https://openalex.org/W3020336359","https://openalex.org/W3097263872","https://openalex.org/W3160207687","https://openalex.org/W3169722760","https://openalex.org/W3209984917","https://openalex.org/W4224916733","https://openalex.org/W4226390724","https://openalex.org/W4299838440","https://openalex.org/W4319862255","https://openalex.org/W4387799863","https://openalex.org/W4389315126","https://openalex.org/W4389315128","https://openalex.org/W4389315135","https://openalex.org/W6683785785","https://openalex.org/W6713671256","https://openalex.org/W6742632731","https://openalex.org/W6762182681","https://openalex.org/W6766380642","https://openalex.org/W6846236293","https://openalex.org/W6849552894","https://openalex.org/W6857062747"],"related_works":["https://openalex.org/W2073713056","https://openalex.org/W3110702597","https://openalex.org/W2078761926","https://openalex.org/W2110441383","https://openalex.org/W2125620709","https://openalex.org/W1498872724","https://openalex.org/W4233149903","https://openalex.org/W4293864700","https://openalex.org/W2524540579","https://openalex.org/W2326878701"],"abstract_inverted_index":{"Automatic":[0],"Speech":[1],"Recognition":[2],"(ASR)":[3],"has":[4],"shown":[5],"remarkable":[6],"progress,":[7],"yet":[8],"it":[9,118],"still":[10],"faces":[11],"challenges":[12],"in":[13,57,119,164,176],"real-world":[14,58],"distant":[15],"scenarios":[16],"across":[17,72],"various":[18,44,73],"array":[19,45,74],"topologies":[20,46],"each":[21,101],"with":[22,156],"multiple":[23,49,97],"recording":[24,50,98],"devices.":[25],"The":[26],"focal":[27],"point":[28],"of":[29,42,77,93,113,123,174],"the":[30,89,111,121,138,143,153,161,177,188,193],"CHiME-7":[31,154],"Distant":[32],"ASR":[33,66,167,190],"task":[34],"is":[35],"to":[36,87,109,141,170,187],"devise":[37],"a":[38,130,147,171],"unified":[39],"system":[40,67,168,191],"capable":[41],"generalizing":[43],"that":[47,68,160],"have":[48],"devices":[51,99],"and":[52],"offering":[53],"reliable":[54],"recognition":[55],"performance":[56,71],"environments.":[59],"Addressing":[60],"this":[61],"task,":[62],"we":[63,79,104,128],"introduce":[64,105],"an":[65],"demonstrates":[69],"exceptional":[70],"topologies.":[75],"First":[76],"all,":[78],"propose":[80,129],"two":[81],"attention-based":[82],"automatic":[83],"channel":[84],"selection":[85],"modules":[86],"select":[88],"most":[90],"advantageous":[91],"subset":[92],"multi-channel":[94,144],"signals":[95],"from":[96,137],"for":[100],"utterance.":[102],"Furthermore,":[103],"inter-channel":[106],"spatial":[107,124],"features":[108],"augment":[110],"effectiveness":[112],"multiframe":[114],"cross-channel":[115],"attention,":[116],"aiding":[117],"improving":[120],"capability":[122],"information":[125],"awareness.":[126],"Finally,":[127],"multi-layer":[131],"convolution":[132],"fusion":[133],"module":[134],"drawing":[135],"inspiration":[136],"U-Net":[139],"architecture":[140],"integrate":[142],"output":[145],"into":[146],"single-channel":[148],"output.":[149],"Experimental":[150],"results":[151],"on":[152,192],"corpus":[155],"oracle":[157],"segmentation":[158],"demonstrate":[159],"improvements":[162],"introduced":[163],"our":[165],"proposed":[166],"lead":[169],"relative":[172],"reduction":[173],"40.1%":[175],"Macro":[178],"Diarization":[179],"Attributed":[180],"Word":[181],"Error":[182],"Rates":[183],"(DA-WER)":[184],"when":[185],"compared":[186],"baseline":[189],"Eval":[194],"sets.":[195]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":9},{"year":2024,"cited_by_count":1}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}