{"id":"https://openalex.org/W3099361421","doi":"https://doi.org/10.1109/slt48900.2021.9383492","title":"Multi-Channel Automatic Speech Recognition Using Deep Complex Unet","display_name":"Multi-Channel Automatic Speech Recognition Using Deep Complex Unet","publication_year":2021,"publication_date":"2021-01-19","ids":{"openalex":"https://openalex.org/W3099361421","doi":"https://doi.org/10.1109/slt48900.2021.9383492","mag":"3099361421"},"language":"en","primary_location":{"id":"doi:10.1109/slt48900.2021.9383492","is_oa":false,"landing_page_url":"https://doi.org/10.1109/slt48900.2021.9383492","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 IEEE Spoken Language Technology Workshop (SLT)","raw_type":"proceedings-article"},"type":"preprint","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2011.09081","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5087994947","display_name":"Yuxiang Kong","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":true,"raw_author_name":"Yuxiang Kong","raw_affiliation_strings":["Audio, Speech and Language Processing Group (ASLP@NPU), School of Computer Science, Northwestern Polytechnical University, Xi\u2019an, China","Xiaomi Inc, Beijing, China","Northwestern Polytechnical University,Audio, Speech and Language Processing Group (ASLP@NPU),School of Computer Science,Xi\u2019an,China"],"affiliations":[{"raw_affiliation_string":"Audio, Speech and Language Processing Group (ASLP@NPU), School of Computer Science, Northwestern Polytechnical University, Xi\u2019an, China","institution_ids":["https://openalex.org/I17145004"]},{"raw_affiliation_string":"Xiaomi Inc, Beijing, China","institution_ids":[]},{"raw_affiliation_string":"Northwestern Polytechnical University,Audio, Speech and Language Processing Group (ASLP@NPU),School of Computer Science,Xi\u2019an,China","institution_ids":["https://openalex.org/I17145004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101674460","display_name":"Jian Wu","orcid":"https://orcid.org/0000-0002-3101-7011"},"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":"Jian Wu","raw_affiliation_strings":["Audio, Speech and Language Processing Group (ASLP@NPU), School of Computer Science, Northwestern Polytechnical University, Xi\u2019an, China","Northwestern Polytechnical University,Audio, Speech and Language Processing Group (ASLP@NPU),School of Computer Science,Xi\u2019an,China"],"affiliations":[{"raw_affiliation_string":"Audio, Speech and Language Processing Group (ASLP@NPU), School of Computer Science, Northwestern Polytechnical University, Xi\u2019an, China","institution_ids":["https://openalex.org/I17145004"]},{"raw_affiliation_string":"Northwestern Polytechnical University,Audio, Speech and Language Processing Group (ASLP@NPU),School of Computer Science,Xi\u2019an,China","institution_ids":["https://openalex.org/I17145004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5013004114","display_name":"Quandong Wang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Quandong Wang","raw_affiliation_strings":["Xiaomi Inc, Beijing, China","Xiaomi Inc., Beijing, China#TAB#"],"affiliations":[{"raw_affiliation_string":"Xiaomi Inc, Beijing, China","institution_ids":[]},{"raw_affiliation_string":"Xiaomi Inc., Beijing, China#TAB#","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5106667221","display_name":"Peng Gao","orcid":"https://orcid.org/0009-0005-7881-712X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Peng Gao","raw_affiliation_strings":["Xiaomi Inc, Beijing, China","Xiaomi Inc., Beijing, China#TAB#"],"affiliations":[{"raw_affiliation_string":"Xiaomi Inc, Beijing, China","institution_ids":[]},{"raw_affiliation_string":"Xiaomi Inc., Beijing, China#TAB#","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5113987256","display_name":"Weiji Zhuang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Weiji Zhuang","raw_affiliation_strings":["Xiaomi Inc, Beijing, China","Xiaomi Inc., Beijing, China#TAB#"],"affiliations":[{"raw_affiliation_string":"Xiaomi Inc, Beijing, China","institution_ids":[]},{"raw_affiliation_string":"Xiaomi Inc., Beijing, China#TAB#","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100362606","display_name":"Yujun Wang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yujun Wang","raw_affiliation_strings":["Xiaomi Inc, Beijing, China","Xiaomi Inc., Beijing, China#TAB#"],"affiliations":[{"raw_affiliation_string":"Xiaomi Inc, Beijing, China","institution_ids":[]},{"raw_affiliation_string":"Xiaomi Inc., Beijing, China#TAB#","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":["Audio, Speech and Language Processing Group (ASLP@NPU), School of Computer Science, Northwestern Polytechnical University, Xi\u2019an, China","Northwestern Polytechnical University,Audio, Speech and Language Processing Group (ASLP@NPU),School of Computer Science,Xi\u2019an,China"],"affiliations":[{"raw_affiliation_string":"Audio, Speech and Language Processing Group (ASLP@NPU), School of Computer Science, Northwestern Polytechnical University, Xi\u2019an, China","institution_ids":["https://openalex.org/I17145004"]},{"raw_affiliation_string":"Northwestern Polytechnical University,Audio, Speech and Language Processing Group (ASLP@NPU),School of Computer Science,Xi\u2019an,China","institution_ids":["https://openalex.org/I17145004"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5087994947"],"corresponding_institution_ids":["https://openalex.org/I17145004"],"apc_list":null,"apc_paid":null,"fwci":0.3078,"has_fulltext":true,"cited_by_count":2,"citation_normalized_percentile":{"value":0.50530344,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"104","last_page":"110"},"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":0.9993000030517578,"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":0.996999979019165,"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":0.7557070255279541},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6770462393760681},{"id":"https://openalex.org/keywords/reverberation","display_name":"Reverberation","score":0.6329488754272461},{"id":"https://openalex.org/keywords/beamforming","display_name":"Beamforming","score":0.625625491142273},{"id":"https://openalex.org/keywords/channel","display_name":"Channel (broadcasting)","score":0.5957915782928467},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.5014088153839111},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.4995253086090088},{"id":"https://openalex.org/keywords/microphone","display_name":"Microphone","score":0.49295473098754883},{"id":"https://openalex.org/keywords/speech-enhancement","display_name":"Speech enhancement","score":0.47736501693725586},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.46823400259017944},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.46398213505744934},{"id":"https://openalex.org/keywords/signal-processing","display_name":"Signal processing","score":0.43860742449760437},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.4119125008583069},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.1973017156124115},{"id":"https://openalex.org/keywords/digital-signal-processing","display_name":"Digital signal processing","score":0.18863776326179504},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.1328134834766388}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7557070255279541},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6770462393760681},{"id":"https://openalex.org/C95851461","wikidata":"https://www.wikidata.org/wiki/Q468809","display_name":"Reverberation","level":2,"score":0.6329488754272461},{"id":"https://openalex.org/C54197355","wikidata":"https://www.wikidata.org/wiki/Q5782992","display_name":"Beamforming","level":2,"score":0.625625491142273},{"id":"https://openalex.org/C127162648","wikidata":"https://www.wikidata.org/wiki/Q16858953","display_name":"Channel (broadcasting)","level":2,"score":0.5957915782928467},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.5014088153839111},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.4995253086090088},{"id":"https://openalex.org/C2778263558","wikidata":"https://www.wikidata.org/wiki/Q46384","display_name":"Microphone","level":3,"score":0.49295473098754883},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.47736501693725586},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.46823400259017944},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.46398213505744934},{"id":"https://openalex.org/C104267543","wikidata":"https://www.wikidata.org/wiki/Q208163","display_name":"Signal processing","level":3,"score":0.43860742449760437},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.4119125008583069},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.1973017156124115},{"id":"https://openalex.org/C84462506","wikidata":"https://www.wikidata.org/wiki/Q173142","display_name":"Digital signal processing","level":2,"score":0.18863776326179504},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.1328134834766388},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0},{"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/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.0},{"id":"https://openalex.org/C9390403","wikidata":"https://www.wikidata.org/wiki/Q3966","display_name":"Computer hardware","level":1,"score":0.0},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.0},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.0}],"mesh":[],"locations_count":5,"locations":[{"id":"doi:10.1109/slt48900.2021.9383492","is_oa":false,"landing_page_url":"https://doi.org/10.1109/slt48900.2021.9383492","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 IEEE Spoken Language Technology Workshop (SLT)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2011.09081","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2011.09081","pdf_url":"https://arxiv.org/pdf/2011.09081","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"text"},{"id":"mag:3099361421","is_oa":true,"landing_page_url":"https://arxiv.org/pdf/2011.09081.pdf","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"arXiv (Cornell University)","raw_type":null},{"id":"doi:10.48550/arxiv.2011.09081","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2011.09081","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article"},{"id":"doi:10.17023/s99d-dm68","is_oa":true,"landing_page_url":"https://doi.org/10.17023/s99d-dm68","pdf_url":null,"source":{"id":"https://openalex.org/S7407051697","display_name":"IEEE RESOURCE CENTERS","issn_l":null,"issn":[],"is_oa":false,"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":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2011.09081","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2011.09081","pdf_url":"https://arxiv.org/pdf/2011.09081","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"text"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3099361421.pdf","grobid_xml":"https://content.openalex.org/works/W3099361421.grobid-xml"},"referenced_works_count":33,"referenced_works":["https://openalex.org/W1499999342","https://openalex.org/W1901129140","https://openalex.org/W2041768951","https://openalex.org/W2113556376","https://openalex.org/W2119203697","https://openalex.org/W2127141656","https://openalex.org/W2291877678","https://openalex.org/W2327501763","https://openalex.org/W2346842942","https://openalex.org/W2398972335","https://openalex.org/W2514741789","https://openalex.org/W2589857635","https://openalex.org/W2640112133","https://openalex.org/W2749980185","https://openalex.org/W2755891984","https://openalex.org/W2889282842","https://openalex.org/W2891997645","https://openalex.org/W2921496354","https://openalex.org/W2943554574","https://openalex.org/W2963403868","https://openalex.org/W2963504687","https://openalex.org/W2963747784","https://openalex.org/W2973130159","https://openalex.org/W2991361823","https://openalex.org/W3008400075","https://openalex.org/W3096408984","https://openalex.org/W6639824700","https://openalex.org/W6704747704","https://openalex.org/W6739901393","https://openalex.org/W6744261651","https://openalex.org/W6757632829","https://openalex.org/W6763847309","https://openalex.org/W6770282137"],"related_works":["https://openalex.org/W2591810467","https://openalex.org/W3179150334","https://openalex.org/W3102070904","https://openalex.org/W2221901388","https://openalex.org/W2345067732","https://openalex.org/W2996935789","https://openalex.org/W2564155414","https://openalex.org/W2803583024","https://openalex.org/W2902894493","https://openalex.org/W2764005420","https://openalex.org/W3005525822","https://openalex.org/W3027465796","https://openalex.org/W2797972631","https://openalex.org/W2963177459","https://openalex.org/W3163346546","https://openalex.org/W3199713199","https://openalex.org/W2914445497","https://openalex.org/W2264763718","https://openalex.org/W2996820600","https://openalex.org/W2765386274"],"abstract_inverted_index":{"The":[0],"front-end":[1,31,67],"module":[2],"in":[3,19,76],"multi-channel":[4,70],"automatic":[5],"speech":[6,61],"recognition":[7,101],"(ASR)":[8],"systems":[9],"mainly":[10],"use":[11],"microphone":[12],"array":[13,135],"techniques":[14],"to":[15,47,98],"produce":[16],"enhanced":[17],"signals":[18],"noisy":[20],"conditions":[21],"with":[22,83,94,111,130,134],"reverberation":[23],"and":[24,73],"echos.":[25,112],"Recently,":[26],"neural":[27,150],"network":[28],"(NN)":[29],"based":[30],"has":[32],"shown":[33],"promising":[34],"improvement":[35],"over":[36],"the":[37,49,66,69,91,100,104,131,147],"conventional":[38],"signal":[39],"processing":[40,136],"methods.":[41],"In":[42],"this":[43],"paper,":[44],"we":[45,89],"propose":[46],"adopt":[48],"architecture":[50],"of":[51,68],"deep":[52],"complex":[53],"Unet":[54],"(DCUnet)":[55],"-":[56,64],"a":[57,77],"powerful":[58],"complex-valued":[59],"Unet-structured":[60],"enhancement":[62],"model":[63],"as":[65],"acoustic":[71,139],"model,":[72],"integrate":[74],"them":[75],"multi-task":[78],"learning":[79],"(MTL)":[80],"framework":[81,85],"along":[82],"cascaded":[84],"for":[86],"comparison.":[87],"Meanwhile,":[88],"investigate":[90],"proposed":[92,117,149],"methods":[93],"several":[95],"training":[96],"strategies":[97],"improve":[99],"accuracy":[102],"on":[103],"1000-hours":[105],"real-world":[106],"XiaoMi":[107],"smart":[108],"speaker":[109],"data":[110],"Experiments":[113],"show":[114],"that":[115],"our":[116],"DCUnet-MTL":[118],"method":[119],"brings":[120],"about":[121],"12.2%":[122],"relative":[123],"character":[124],"error":[125],"rate":[126],"(CER)":[127],"reduction":[128],"compared":[129],"traditional":[132],"approach":[133],"plus":[137],"single-channel":[138],"model.":[140],"It":[141],"also":[142],"achieves":[143],"superior":[144],"performance":[145],"than":[146],"recently":[148],"beamforming":[151],"method.":[152]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2022,"cited_by_count":1}],"updated_date":"2026-03-10T16:38:18.471706","created_date":"2025-10-10T00:00:00"}
