{"id":"https://openalex.org/W4372267082","doi":"https://doi.org/10.1109/icassp49357.2023.10095821","title":"Real-Time Speech Enhancement with Dynamic Attention Span","display_name":"Real-Time Speech Enhancement with Dynamic Attention Span","publication_year":2023,"publication_date":"2023-05-05","ids":{"openalex":"https://openalex.org/W4372267082","doi":"https://doi.org/10.1109/icassp49357.2023.10095821"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49357.2023.10095821","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49357.2023.10095821","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2023 - 2023 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/A5026859339","display_name":"Chengyu Zheng","orcid":"https://orcid.org/0000-0001-7740-0457"},"institutions":[{"id":"https://openalex.org/I75689368","display_name":"Communication University of China","ror":"https://ror.org/04facbs33","country_code":"CN","type":"education","lineage":["https://openalex.org/I75689368"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Chengyu Zheng","raw_affiliation_strings":["Communication University of China,Beijing,China","Communication University of China, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Communication University of China,Beijing,China","institution_ids":["https://openalex.org/I75689368"]},{"raw_affiliation_string":"Communication University of China, Beijing, China","institution_ids":["https://openalex.org/I75689368"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5071613755","display_name":"Yuan Zhou","orcid":"https://orcid.org/0000-0001-9021-4667"},"institutions":[{"id":"https://openalex.org/I4210113369","display_name":"Microsoft Research Asia (China)","ror":"https://ror.org/0300m5276","country_code":"CN","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210113369"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuan Zhou","raw_affiliation_strings":["Microsoft Research Asia,Beijing,China","Microsoft Research Asia, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Microsoft Research Asia,Beijing,China","institution_ids":["https://openalex.org/I4210113369"]},{"raw_affiliation_string":"Microsoft Research Asia, Beijing, China","institution_ids":["https://openalex.org/I4210113369"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5024977056","display_name":"Xiulian Peng","orcid":"https://orcid.org/0000-0001-8213-4878"},"institutions":[{"id":"https://openalex.org/I4210113369","display_name":"Microsoft Research Asia (China)","ror":"https://ror.org/0300m5276","country_code":"CN","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210113369"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiulian Peng","raw_affiliation_strings":["Microsoft Research Asia,Beijing,China","Microsoft Research Asia, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Microsoft Research Asia,Beijing,China","institution_ids":["https://openalex.org/I4210113369"]},{"raw_affiliation_string":"Microsoft Research Asia, Beijing, China","institution_ids":["https://openalex.org/I4210113369"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100368686","display_name":"Yuan Zhang","orcid":"https://orcid.org/0000-0002-1335-2780"},"institutions":[{"id":"https://openalex.org/I75689368","display_name":"Communication University of China","ror":"https://ror.org/04facbs33","country_code":"CN","type":"education","lineage":["https://openalex.org/I75689368"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuan Zhang","raw_affiliation_strings":["Communication University of China,Beijing,China","Communication University of China, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Communication University of China,Beijing,China","institution_ids":["https://openalex.org/I75689368"]},{"raw_affiliation_string":"Communication University of China, Beijing, China","institution_ids":["https://openalex.org/I75689368"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100756584","display_name":"Yan Lu","orcid":"https://orcid.org/0000-0001-5383-6424"},"institutions":[{"id":"https://openalex.org/I4210113369","display_name":"Microsoft Research Asia (China)","ror":"https://ror.org/0300m5276","country_code":"CN","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210113369"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yan Lu","raw_affiliation_strings":["Microsoft Research Asia,Beijing,China","Microsoft Research Asia, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Microsoft Research Asia,Beijing,China","institution_ids":["https://openalex.org/I4210113369"]},{"raw_affiliation_string":"Microsoft Research Asia, Beijing, China","institution_ids":["https://openalex.org/I4210113369"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5026859339"],"corresponding_institution_ids":["https://openalex.org/I75689368"],"apc_list":null,"apc_paid":null,"fwci":1.188,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":{"value":0.78280515,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":95,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"5"},"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/T11233","display_name":"Advanced Adaptive Filtering Techniques","score":0.9990000128746033,"subfield":{"id":"https://openalex.org/subfields/2206","display_name":"Computational Mechanics"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10283","display_name":"Hearing Loss and Rehabilitation","score":0.9968000054359436,"subfield":{"id":"https://openalex.org/subfields/2805","display_name":"Cognitive Neuroscience"},"field":{"id":"https://openalex.org/fields/28","display_name":"Neuroscience"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7976888418197632},{"id":"https://openalex.org/keywords/speech-enhancement","display_name":"Speech enhancement","score":0.7239527702331543},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6851810216903687},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.5198086500167847},{"id":"https://openalex.org/keywords/sound-quality","display_name":"Sound quality","score":0.4968736469745636},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.467360258102417},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.4673350751399994},{"id":"https://openalex.org/keywords/limit","display_name":"Limit (mathematics)","score":0.45574358105659485},{"id":"https://openalex.org/keywords/signal","display_name":"SIGNAL (programming language)","score":0.43195271492004395},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.4128553867340088},{"id":"https://openalex.org/keywords/field","display_name":"Field (mathematics)","score":0.4105144143104553},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3434041142463684},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.21002689003944397}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7976888418197632},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.7239527702331543},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6851810216903687},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.5198086500167847},{"id":"https://openalex.org/C167310288","wikidata":"https://www.wikidata.org/wiki/Q7564808","display_name":"Sound quality","level":2,"score":0.4968736469745636},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.467360258102417},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.4673350751399994},{"id":"https://openalex.org/C151201525","wikidata":"https://www.wikidata.org/wiki/Q177239","display_name":"Limit (mathematics)","level":2,"score":0.45574358105659485},{"id":"https://openalex.org/C2779843651","wikidata":"https://www.wikidata.org/wiki/Q7390335","display_name":"SIGNAL (programming language)","level":2,"score":0.43195271492004395},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.4128553867340088},{"id":"https://openalex.org/C9652623","wikidata":"https://www.wikidata.org/wiki/Q190109","display_name":"Field (mathematics)","level":2,"score":0.4105144143104553},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3434041142463684},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.21002689003944397},{"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/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"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/C202444582","wikidata":"https://www.wikidata.org/wiki/Q837863","display_name":"Pure mathematics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49357.2023.10095821","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49357.2023.10095821","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","score":0.6499999761581421,"display_name":"Peace, Justice and strong institutions"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":23,"referenced_works":["https://openalex.org/W123803282","https://openalex.org/W1677182931","https://openalex.org/W2130222221","https://openalex.org/W2937484199","https://openalex.org/W2946567085","https://openalex.org/W3160115460","https://openalex.org/W3161480375","https://openalex.org/W3162348042","https://openalex.org/W3183654341","https://openalex.org/W3196995871","https://openalex.org/W3197034572","https://openalex.org/W3203083806","https://openalex.org/W3203616181","https://openalex.org/W4224919230","https://openalex.org/W4224932531","https://openalex.org/W4224933821","https://openalex.org/W4225304381","https://openalex.org/W4225905067","https://openalex.org/W4226357460","https://openalex.org/W4281484853","https://openalex.org/W6638667902","https://openalex.org/W6798138677","https://openalex.org/W6838838051"],"related_works":["https://openalex.org/W2120771489","https://openalex.org/W2051376034","https://openalex.org/W2955597484","https://openalex.org/W3110551121","https://openalex.org/W2089240210","https://openalex.org/W2131486661","https://openalex.org/W111365173","https://openalex.org/W2161396743","https://openalex.org/W2386453889","https://openalex.org/W3134790285"],"abstract_inverted_index":{"For":[0],"real-time":[1],"speech":[2,117],"enhancement":[3],"(SE)":[4],"including":[5],"noise":[6],"suppression,":[7],"dereverberation":[8],"and":[9,25,107,116],"acoustic":[10],"echo":[11],"cancellation,":[12],"the":[13,16,31,38,42,50,55,79,84,92],"time-variance":[14],"of":[15,86],"audio":[17],"signals":[18],"becomes":[19],"a":[20,70],"severe":[21],"challenge.":[22],"The":[23],"causality":[24],"memory":[26],"usage":[27],"limit":[28],"that":[29,98],"only":[30],"historical":[32,87],"information":[33],"can":[34,102],"be":[35],"used":[36,89],"for":[37,82,90],"system":[39],"to":[40,47,54,77,112],"capture":[41,108],"time-variant":[43,105],"characteristics.":[44],"We":[45],"propose":[46],"adaptively":[48],"change":[49],"receptive":[51],"field":[52],"according":[53],"input":[56],"signal":[57],"in":[58,66],"deep":[59],"neural":[60],"network":[61],"based":[62],"SE":[63],"model.":[64],"Specifically,":[65],"an":[67],"encoder-decoder":[68],"framework,":[69],"dynamic":[71,100],"attention":[72,80],"span":[73],"mechanism":[74,101],"is":[75],"introduced":[76],"all":[78],"modules":[81],"controlling":[83],"size":[85],"content":[88],"processing":[91],"current":[93],"frame.":[94],"Experimental":[95],"results":[96],"verify":[97],"this":[99],"better":[103],"track":[104],"factors":[106],"speech-related":[109],"characteristics,":[110],"benefiting":[111],"both":[113],"interference":[114],"removing":[115],"quality":[118],"retaining.":[119]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":4}],"updated_date":"2026-04-01T17:29:45.350535","created_date":"2025-10-10T00:00:00"}