{"id":"https://openalex.org/W2909607850","doi":"https://doi.org/10.1109/slt.2018.8639593","title":"Multi-Channel Overlapped Speech Recognition with Location Guided Speech Extraction Network","display_name":"Multi-Channel Overlapped Speech Recognition with Location Guided Speech Extraction Network","publication_year":2018,"publication_date":"2018-12-01","ids":{"openalex":"https://openalex.org/W2909607850","doi":"https://doi.org/10.1109/slt.2018.8639593","mag":"2909607850"},"language":"en","primary_location":{"id":"doi:10.1109/slt.2018.8639593","is_oa":false,"landing_page_url":"https://doi.org/10.1109/slt.2018.8639593","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 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/A5100345092","display_name":"Zhuo Chen","orcid":"https://orcid.org/0000-0002-9011-7928"},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Zhuo Chen","raw_affiliation_strings":["Microsoft Corporation, USA"],"affiliations":[{"raw_affiliation_string":"Microsoft Corporation, USA","institution_ids":["https://openalex.org/I1290206253"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101602536","display_name":"Xiong Xiao","orcid":"https://orcid.org/0009-0001-5128-6518"},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Xiong Xiao","raw_affiliation_strings":["Microsoft Corporation, USA"],"affiliations":[{"raw_affiliation_string":"Microsoft Corporation, USA","institution_ids":["https://openalex.org/I1290206253"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101618071","display_name":"Takuya Yoshioka","orcid":"https://orcid.org/0009-0003-7791-3545"},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Takuya Yoshioka","raw_affiliation_strings":["Microsoft Corporation, USA"],"affiliations":[{"raw_affiliation_string":"Microsoft Corporation, USA","institution_ids":["https://openalex.org/I1290206253"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5065994318","display_name":"Hakan Erdo\u011fan","orcid":"https://orcid.org/0000-0003-3140-8642"},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Hakan Erdogan","raw_affiliation_strings":["Microsoft Corporation, USA"],"affiliations":[{"raw_affiliation_string":"Microsoft Corporation, USA","institution_ids":["https://openalex.org/I1290206253"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100365053","display_name":"Jinyu Li","orcid":"https://orcid.org/0000-0002-1089-9748"},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jinyu Li","raw_affiliation_strings":["Microsoft Corporation, USA"],"affiliations":[{"raw_affiliation_string":"Microsoft Corporation, USA","institution_ids":["https://openalex.org/I1290206253"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5077401426","display_name":"Yifan Gong","orcid":"https://orcid.org/0000-0001-8786-3391"},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yifan Gong","raw_affiliation_strings":["Microsoft Corporation, USA"],"affiliations":[{"raw_affiliation_string":"Microsoft Corporation, USA","institution_ids":["https://openalex.org/I1290206253"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5100345092"],"corresponding_institution_ids":["https://openalex.org/I1290206253"],"apc_list":null,"apc_paid":null,"fwci":12.3081,"has_fulltext":false,"cited_by_count":141,"citation_normalized_percentile":{"value":0.99140681,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":99,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"558","last_page":"565"},"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":0.9991000294685364,"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":0.9988999962806702,"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":0.8061106204986572},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7755297422409058},{"id":"https://openalex.org/keywords/beamforming","display_name":"Beamforming","score":0.6712096333503723},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.6280015707015991},{"id":"https://openalex.org/keywords/speech-enhancement","display_name":"Speech enhancement","score":0.527228832244873},{"id":"https://openalex.org/keywords/reverberation","display_name":"Reverberation","score":0.5202221274375916},{"id":"https://openalex.org/keywords/oracle","display_name":"Oracle","score":0.4753151535987854},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4505109488964081},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.42649421095848083},{"id":"https://openalex.org/keywords/channel","display_name":"Channel (broadcasting)","score":0.42154625058174133},{"id":"https://openalex.org/keywords/reduction","display_name":"Reduction (mathematics)","score":0.41323134303092957},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3711281716823578},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.31600555777549744},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.1131303608417511},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.10265231132507324},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.09270301461219788}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8061106204986572},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7755297422409058},{"id":"https://openalex.org/C54197355","wikidata":"https://www.wikidata.org/wiki/Q5782992","display_name":"Beamforming","level":2,"score":0.6712096333503723},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.6280015707015991},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.527228832244873},{"id":"https://openalex.org/C95851461","wikidata":"https://www.wikidata.org/wiki/Q468809","display_name":"Reverberation","level":2,"score":0.5202221274375916},{"id":"https://openalex.org/C55166926","wikidata":"https://www.wikidata.org/wiki/Q2892946","display_name":"Oracle","level":2,"score":0.4753151535987854},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4505109488964081},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.42649421095848083},{"id":"https://openalex.org/C127162648","wikidata":"https://www.wikidata.org/wiki/Q16858953","display_name":"Channel (broadcasting)","level":2,"score":0.42154625058174133},{"id":"https://openalex.org/C111335779","wikidata":"https://www.wikidata.org/wiki/Q3454686","display_name":"Reduction (mathematics)","level":2,"score":0.41323134303092957},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3711281716823578},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.31600555777549744},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.1131303608417511},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.10265231132507324},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.09270301461219788},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C115903868","wikidata":"https://www.wikidata.org/wiki/Q80993","display_name":"Software engineering","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/slt.2018.8639593","is_oa":false,"landing_page_url":"https://doi.org/10.1109/slt.2018.8639593","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 IEEE Spoken Language Technology Workshop (SLT)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions","score":0.8199999928474426}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":40,"referenced_works":["https://openalex.org/W262275730","https://openalex.org/W1494198834","https://openalex.org/W1603075283","https://openalex.org/W1897240248","https://openalex.org/W1983812858","https://openalex.org/W2030486566","https://openalex.org/W2042860487","https://openalex.org/W2046869671","https://openalex.org/W2144600569","https://openalex.org/W2219249508","https://openalex.org/W2221409856","https://openalex.org/W2289394825","https://openalex.org/W2460742184","https://openalex.org/W2517616541","https://openalex.org/W2551990143","https://openalex.org/W2558649592","https://openalex.org/W2589857635","https://openalex.org/W2622203030","https://openalex.org/W2714487941","https://openalex.org/W2734774145","https://openalex.org/W2749510669","https://openalex.org/W2749588430","https://openalex.org/W2759071281","https://openalex.org/W2786625961","https://openalex.org/W2787692317","https://openalex.org/W2801798988","https://openalex.org/W2803322398","https://openalex.org/W2804228164","https://openalex.org/W2889503488","https://openalex.org/W2890489755","https://openalex.org/W2891833136","https://openalex.org/W2892163332","https://openalex.org/W2962715207","https://openalex.org/W2963266252","https://openalex.org/W2963301902","https://openalex.org/W2964171275","https://openalex.org/W4289665794","https://openalex.org/W6688816777","https://openalex.org/W6726313835","https://openalex.org/W6751765566"],"related_works":["https://openalex.org/W1491017269","https://openalex.org/W2337992322","https://openalex.org/W2185164075","https://openalex.org/W4288357365","https://openalex.org/W4224931722","https://openalex.org/W2949386652","https://openalex.org/W2911603104","https://openalex.org/W2081983610","https://openalex.org/W2543816751","https://openalex.org/W2909607850"],"abstract_inverted_index":{"Although":[0],"advances":[1],"in":[2,8,16,125],"close-talk":[3],"speech":[4,30,45,60,78,114],"recognition":[5,14],"have":[6],"resulted":[7],"relatively":[9],"low":[10,24],"error":[11,164],"rates,":[12],"the":[13,81,112,116,127,155,190],"performance":[15],"far-field":[17,76],"environments":[18],"is":[19,35,103,123,187],"still":[20],"limited":[21,62],"due":[22],"to":[23,54,181],"signal-to-noise":[25],"ratio,":[26],"reverberation,":[27],"and":[28,44,96,130],"overlapped":[29,77],"from":[31,56,179],"simultaneous":[32],"speakers":[33],"which":[34,126],"especially":[36],"more":[37,159],"difficult.":[38],"To":[39],"solve":[40],"these":[41],"problems,":[42],"beamforming":[43,129,170],"separation":[46],"networks":[47],"were":[48,139],"previously":[49],"proposed.":[50],"However,":[51],"they":[52],"tend":[53],"suffer":[55],"leakage":[57],"of":[58,111,115,148],"interfering":[59],"or":[61],"generalizability.":[63],"In":[64,80],"this":[65],"work,":[66],"we":[67],"propose":[68],"a":[69,100,109],"simple":[70],"yet":[71],"effective":[72],"method":[73],"for":[74,89,189],"multi-channel":[75],"recognition.":[79],"proposed":[82,124,137,156,191],"system,":[83],"three":[84],"different":[85,146],"features":[86,107],"are":[87,133],"formed":[88],"each":[90],"target":[91,110],"speaker,":[92],"namely,":[93],"spectral,":[94],"spatial,":[95],"angle":[97],"features.":[98],"Then":[99],"neural":[101],"network":[102],"trained":[104],"using":[105],"all":[106],"with":[108,141,145,171],"clean":[113],"required":[117],"speaker.":[118],"An":[119],"iterative":[120],"update":[121],"procedure":[122],"mask-based":[128],"mask":[131],"estimation":[132],"performed":[134],"alternatively.":[135],"The":[136,151],"system":[138,157],"evaluated":[140],"real":[142],"recorded":[143],"meetings":[144],"levels":[147],"overlapping":[149],"ratios.":[150],"results":[152],"show":[153],"that":[154],"achieves":[158],"than":[160,168],"24%":[161],"relative":[162],"word":[163],"rate":[165],"(WER)":[166],"reduction":[167],"fixed":[169],"oracle":[172],"selection.":[173],"Moreover,":[174],"as":[175],"overlap":[176],"ratio":[177],"rises":[178],"20%":[180],"70+%,":[182],"only":[183],"3.8%":[184],"WER":[185],"increase":[186],"observed":[188],"system.":[192]},"counts_by_year":[{"year":2025,"cited_by_count":8},{"year":2024,"cited_by_count":17},{"year":2023,"cited_by_count":18},{"year":2022,"cited_by_count":24},{"year":2021,"cited_by_count":28},{"year":2020,"cited_by_count":31},{"year":2019,"cited_by_count":15}],"updated_date":"2026-04-03T22:45:19.894376","created_date":"2025-10-10T00:00:00"}