{"id":"https://openalex.org/W4225272028","doi":"https://doi.org/10.1109/icassp43922.2022.9746328","title":"DP-DWA: Dual-Path Dynamic Weight Attention Network With Streaming Dfsmn-San For Automatic Speech Recognition","display_name":"DP-DWA: Dual-Path Dynamic Weight Attention Network With Streaming Dfsmn-San For Automatic Speech Recognition","publication_year":2022,"publication_date":"2022-04-27","ids":{"openalex":"https://openalex.org/W4225272028","doi":"https://doi.org/10.1109/icassp43922.2022.9746328"},"language":"en","primary_location":{"id":"doi:10.1109/icassp43922.2022.9746328","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp43922.2022.9746328","pdf_url":null,"source":{"id":"https://openalex.org/S4363607702","display_name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","issn_l":null,"issn":null,"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":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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/A5082253092","display_name":"Dongpeng Ma","orcid":null},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Dongpeng Ma","raw_affiliation_strings":["Tencent AI Lab,Shenzhen,China","Tencent AI Lab, Shenzhen, China"],"affiliations":[{"raw_affiliation_string":"Tencent AI Lab,Shenzhen,China","institution_ids":["https://openalex.org/I2250653659"]},{"raw_affiliation_string":"Tencent AI Lab, Shenzhen, China","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5118899892","display_name":"Yiwen Wang","orcid":"https://orcid.org/0000-0002-4531-2222"},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yiwen Wang","raw_affiliation_strings":["Tencent AI Lab,Shenzhen,China","Tencent AI Lab, Shenzhen, China"],"affiliations":[{"raw_affiliation_string":"Tencent AI Lab,Shenzhen,China","institution_ids":["https://openalex.org/I2250653659"]},{"raw_affiliation_string":"Tencent AI Lab, Shenzhen, China","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5074469791","display_name":"Liqiang He","orcid":"https://orcid.org/0000-0001-9179-6398"},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Liqiang He","raw_affiliation_strings":["Tencent AI Lab,Shenzhen,China","Tencent AI Lab, Shenzhen, China"],"affiliations":[{"raw_affiliation_string":"Tencent AI Lab,Shenzhen,China","institution_ids":["https://openalex.org/I2250653659"]},{"raw_affiliation_string":"Tencent AI Lab, Shenzhen, China","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5052541894","display_name":"Mingjie Jin","orcid":null},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Mingjie Jin","raw_affiliation_strings":["Tencent AI Lab,Shenzhen,China","Tencent AI Lab, Shenzhen, China"],"affiliations":[{"raw_affiliation_string":"Tencent AI Lab,Shenzhen,China","institution_ids":["https://openalex.org/I2250653659"]},{"raw_affiliation_string":"Tencent AI Lab, Shenzhen, China","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5075183307","display_name":"Dan Su","orcid":"https://orcid.org/0000-0001-5746-9545"},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Dan Su","raw_affiliation_strings":["Tencent AI Lab,Shenzhen,China","Tencent AI Lab, Shenzhen, China"],"affiliations":[{"raw_affiliation_string":"Tencent AI Lab,Shenzhen,China","institution_ids":["https://openalex.org/I2250653659"]},{"raw_affiliation_string":"Tencent AI Lab, Shenzhen, China","institution_ids":["https://openalex.org/I2250653659"]}]},{"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"],"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":2,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5082253092"],"corresponding_institution_ids":["https://openalex.org/I2250653659"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.01737757,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":97,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"7692","last_page":"7696"},"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/T11309","display_name":"Music and Audio Processing","score":0.9993000030517578,"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":0.9991999864578247,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8059045076370239},{"id":"https://openalex.org/keywords/microphone","display_name":"Microphone","score":0.6755081415176392},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6095137000083923},{"id":"https://openalex.org/keywords/echo","display_name":"Echo (communications protocol)","score":0.545806348323822},{"id":"https://openalex.org/keywords/distortion","display_name":"Distortion (music)","score":0.5193844437599182},{"id":"https://openalex.org/keywords/path","display_name":"Path (computing)","score":0.49432969093322754},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.4889141619205475},{"id":"https://openalex.org/keywords/signal","display_name":"SIGNAL (programming language)","score":0.47323521971702576},{"id":"https://openalex.org/keywords/dual","display_name":"Dual (grammatical number)","score":0.41848036646842957},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.34636104106903076},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.11810475587844849},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.10669165849685669}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8059045076370239},{"id":"https://openalex.org/C2778263558","wikidata":"https://www.wikidata.org/wiki/Q46384","display_name":"Microphone","level":3,"score":0.6755081415176392},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6095137000083923},{"id":"https://openalex.org/C2779426996","wikidata":"https://www.wikidata.org/wiki/Q18389128","display_name":"Echo (communications protocol)","level":2,"score":0.545806348323822},{"id":"https://openalex.org/C126780896","wikidata":"https://www.wikidata.org/wiki/Q899871","display_name":"Distortion (music)","level":4,"score":0.5193844437599182},{"id":"https://openalex.org/C2777735758","wikidata":"https://www.wikidata.org/wiki/Q817765","display_name":"Path (computing)","level":2,"score":0.49432969093322754},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.4889141619205475},{"id":"https://openalex.org/C2779843651","wikidata":"https://www.wikidata.org/wiki/Q7390335","display_name":"SIGNAL (programming language)","level":2,"score":0.47323521971702576},{"id":"https://openalex.org/C2780980858","wikidata":"https://www.wikidata.org/wiki/Q110022","display_name":"Dual (grammatical number)","level":2,"score":0.41848036646842957},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.34636104106903076},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.11810475587844849},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.10669165849685669},{"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/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","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/C194257627","wikidata":"https://www.wikidata.org/wiki/Q211554","display_name":"Amplifier","level":3,"score":0.0},{"id":"https://openalex.org/C2776257435","wikidata":"https://www.wikidata.org/wiki/Q1576430","display_name":"Bandwidth (computing)","level":2,"score":0.0},{"id":"https://openalex.org/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"score":0.0},{"id":"https://openalex.org/C124952713","wikidata":"https://www.wikidata.org/wiki/Q8242","display_name":"Literature","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp43922.2022.9746328","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp43922.2022.9746328","pdf_url":null,"source":{"id":"https://openalex.org/S4363607702","display_name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","issn_l":null,"issn":null,"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":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.5,"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":19,"referenced_works":["https://openalex.org/W2039553327","https://openalex.org/W2119203697","https://openalex.org/W2139737683","https://openalex.org/W2405883473","https://openalex.org/W2586584460","https://openalex.org/W2589857635","https://openalex.org/W2767071179","https://openalex.org/W2786031273","https://openalex.org/W2921496354","https://openalex.org/W2952218014","https://openalex.org/W2991361823","https://openalex.org/W3015199127","https://openalex.org/W3015492205","https://openalex.org/W3016218307","https://openalex.org/W3095057960","https://openalex.org/W3099330747","https://openalex.org/W3162341667","https://openalex.org/W3197260772","https://openalex.org/W6797438204"],"related_works":["https://openalex.org/W1473737476","https://openalex.org/W2949162897","https://openalex.org/W2061432289","https://openalex.org/W2276571074","https://openalex.org/W4300003799","https://openalex.org/W1500087777","https://openalex.org/W2357191878","https://openalex.org/W2158582019","https://openalex.org/W2156216981","https://openalex.org/W2039189137"],"abstract_inverted_index":{"In":[0,30,121],"multi-channel":[1],"far-field":[2,40],"automatic":[3],"speech":[4,13],"recognition":[5,24],"(ASR)":[6],"scenarios,":[7],"distortion":[8],"is":[9,15,90,126],"introduced":[10],"when":[11],"the":[12,18,23,27,39,94,130],"signal":[14,48,54],"processed":[16],"by":[17,129],"front":[19],"end,":[20],"which":[21,43,146],"damages":[22],"performance":[25],"for":[26,38,66,85],"ASR":[28],"tasks.":[29],"this":[31],"paper,":[32],"we":[33,58,71,103],"propose":[34],"a":[35,60,106,116,138,143],"dual-path":[36,101],"network":[37,79],"acoustic":[41,50,83],"model,":[42],"uses":[44],"voice":[45],"processing":[46],"(VP)":[47],"and":[49],"echo":[51],"cancellation":[52],"(AEC)":[53],"as":[55],"input.":[56],"Specifically,":[57],"design":[59],"dynamic":[61],"weight":[62],"attention":[63],"(DWA)":[64],"module":[65],"combining":[67],"two":[68,151],"signals.":[69],"Besides,":[70],"streamline":[72],"our":[73,123],"best":[74],"deep":[75],"feed-forward":[76],"sequential":[77],"memory":[78],"with":[80,100,150],"self-attention":[81],"(DFSMN-SAN)":[82],"model":[84],"real-time":[86],"requirements.":[87],"Joint-training":[88],"strategy":[89],"adopted":[91],"to":[92],"optimize":[93],"proposed":[95,124],"approach.":[96],"We":[97,136],"find":[98],"that":[99],"network,":[102],"can":[104],"achieve":[105,137],"54.5%":[107],"relative":[108,140],"improvement":[109,141],"in":[110],"character":[111],"error":[112],"rate":[113],"(CER)":[114],"on":[115,142],"10,000-hour":[117],"online":[118],"conference":[119],"task.":[120],"addition,":[122],"method":[125],"not":[127],"affected":[128],"arrangement":[131],"of":[132],"different":[133],"microphone":[134],"arrays.":[135],"23.56%":[139],"vehicle":[144],"task,":[145],"has":[147],"an":[148],"array":[149],"microphones.":[152]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}