{"id":"https://openalex.org/W4319862216","doi":"https://doi.org/10.1109/slt54892.2023.10023206","title":"A Hybrid Acoustic Echo Reduction Approach Using Kalman Filtering and Informed Source Extraction with Improved Training","display_name":"A Hybrid Acoustic Echo Reduction Approach Using Kalman Filtering and Informed Source Extraction with Improved Training","publication_year":2023,"publication_date":"2023-01-09","ids":{"openalex":"https://openalex.org/W4319862216","doi":"https://doi.org/10.1109/slt54892.2023.10023206"},"language":"en","primary_location":{"id":"doi:10.1109/slt54892.2023.10023206","is_oa":false,"landing_page_url":"https://doi.org/10.1109/slt54892.2023.10023206","pdf_url":null,"source":{"id":"https://openalex.org/S4363605953","display_name":"2022 IEEE Spoken Language Technology Workshop (SLT)","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":"2022 IEEE Spoken Language Technology Workshop (SLT)","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/A5049026973","display_name":"Wolfgang Mack","orcid":"https://orcid.org/0000-0002-8489-7382"},"institutions":[{"id":"https://openalex.org/I4210123192","display_name":"International Audio Laboratories Erlangen","ror":"https://ror.org/02mkz3e80","country_code":"DE","type":"facility","lineage":["https://openalex.org/I181369854","https://openalex.org/I4210123192","https://openalex.org/I4210124274","https://openalex.org/I4923324"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Wolfgang Mack","raw_affiliation_strings":["International Audio Laboratories Erlangen*,Erlangen,Germany,91058"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"International Audio Laboratories Erlangen*,Erlangen,Germany,91058","institution_ids":["https://openalex.org/I4210123192"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5031626756","display_name":"Emanu\u00ebl A. P. Habets","orcid":"https://orcid.org/0000-0002-2613-8046"},"institutions":[{"id":"https://openalex.org/I4210123192","display_name":"International Audio Laboratories Erlangen","ror":"https://ror.org/02mkz3e80","country_code":"DE","type":"facility","lineage":["https://openalex.org/I181369854","https://openalex.org/I4210123192","https://openalex.org/I4210124274","https://openalex.org/I4923324"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Emanuel A. P. Habets","raw_affiliation_strings":["International Audio Laboratories Erlangen*,Erlangen,Germany,91058"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"International Audio Laboratories Erlangen*,Erlangen,Germany,91058","institution_ids":["https://openalex.org/I4210123192"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I4210123192"],"apc_list":null,"apc_paid":null,"fwci":0.4607,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.53777778,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":"13","issue":null,"first_page":"502","last_page":"508"},"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":0.9990000128746033,"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":0.9983000159263611,"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":0.8179694414138794},{"id":"https://openalex.org/keywords/echo","display_name":"Echo (communications protocol)","score":0.814110279083252},{"id":"https://openalex.org/keywords/reduction","display_name":"Reduction (mathematics)","score":0.7446523308753967},{"id":"https://openalex.org/keywords/kalman-filter","display_name":"Kalman filter","score":0.5926833748817444},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.5852891206741333},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4934040606021881},{"id":"https://openalex.org/keywords/distortion","display_name":"Distortion (music)","score":0.47922831773757935},{"id":"https://openalex.org/keywords/signal","display_name":"SIGNAL (programming language)","score":0.4545705318450928},{"id":"https://openalex.org/keywords/filter","display_name":"Filter (signal processing)","score":0.43318212032318115},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.4212478995323181},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.41642510890960693},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.344184011220932},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.11671361327171326},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.09977996349334717},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.07232415676116943}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8179694414138794},{"id":"https://openalex.org/C2779426996","wikidata":"https://www.wikidata.org/wiki/Q18389128","display_name":"Echo (communications protocol)","level":2,"score":0.814110279083252},{"id":"https://openalex.org/C111335779","wikidata":"https://www.wikidata.org/wiki/Q3454686","display_name":"Reduction (mathematics)","level":2,"score":0.7446523308753967},{"id":"https://openalex.org/C157286648","wikidata":"https://www.wikidata.org/wiki/Q846780","display_name":"Kalman filter","level":2,"score":0.5926833748817444},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.5852891206741333},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4934040606021881},{"id":"https://openalex.org/C126780896","wikidata":"https://www.wikidata.org/wiki/Q899871","display_name":"Distortion (music)","level":4,"score":0.47922831773757935},{"id":"https://openalex.org/C2779843651","wikidata":"https://www.wikidata.org/wiki/Q7390335","display_name":"SIGNAL (programming language)","level":2,"score":0.4545705318450928},{"id":"https://openalex.org/C106131492","wikidata":"https://www.wikidata.org/wiki/Q3072260","display_name":"Filter (signal processing)","level":2,"score":0.43318212032318115},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.4212478995323181},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.41642510890960693},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.344184011220932},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.11671361327171326},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.09977996349334717},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.07232415676116943},{"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/C194257627","wikidata":"https://www.wikidata.org/wiki/Q211554","display_name":"Amplifier","level":3,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","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/C2776257435","wikidata":"https://www.wikidata.org/wiki/Q1576430","display_name":"Bandwidth (computing)","level":2,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/slt54892.2023.10023206","is_oa":false,"landing_page_url":"https://doi.org/10.1109/slt54892.2023.10023206","pdf_url":null,"source":{"id":"https://openalex.org/S4363605953","display_name":"2022 IEEE Spoken Language Technology Workshop (SLT)","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":"2022 IEEE Spoken Language Technology Workshop (SLT)","raw_type":"proceedings-article"},{"id":"pmh:oai:publica.fraunhofer.de:publica/448513","is_oa":false,"landing_page_url":"https://publica.fraunhofer.de/handle/publica/448513","pdf_url":null,"source":{"id":"https://openalex.org/S4306400318","display_name":"Fraunhofer-Publica (Fraunhofer-Gesellschaft)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I4923324","host_organization_name":"Fraunhofer-Gesellschaft","host_organization_lineage":["https://openalex.org/I4923324"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"conference paper"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":33,"referenced_works":["https://openalex.org/W1494198834","https://openalex.org/W1973524311","https://openalex.org/W1975244201","https://openalex.org/W2032676419","https://openalex.org/W2065804682","https://openalex.org/W2888860279","https://openalex.org/W2951130829","https://openalex.org/W2963859210","https://openalex.org/W2964054038","https://openalex.org/W3015199127","https://openalex.org/W3015636705","https://openalex.org/W3086154751","https://openalex.org/W3111182274","https://openalex.org/W3167533889","https://openalex.org/W3187990717","https://openalex.org/W3188042919","https://openalex.org/W3195156220","https://openalex.org/W3196995871","https://openalex.org/W3198575250","https://openalex.org/W3203083806","https://openalex.org/W3210390090","https://openalex.org/W4224919230","https://openalex.org/W4224931234","https://openalex.org/W4225873749","https://openalex.org/W4252684946","https://openalex.org/W4287601764","https://openalex.org/W6629717138","https://openalex.org/W6754161426","https://openalex.org/W6757510380","https://openalex.org/W6773173422","https://openalex.org/W6786498588","https://openalex.org/W6803183793","https://openalex.org/W6811120794"],"related_works":["https://openalex.org/W1473737476","https://openalex.org/W2061432289","https://openalex.org/W2276571074","https://openalex.org/W4300003799","https://openalex.org/W2158582019","https://openalex.org/W1500087777","https://openalex.org/W1970204757","https://openalex.org/W4214513620","https://openalex.org/W2791548713","https://openalex.org/W4230145862"],"abstract_inverted_index":{"State-of-the-art":[0],"acoustic":[1],"echo":[2,45,110,123],"and":[3,39,65],"noise":[4],"reduction":[5,46],"combines":[6],"adaptive":[7],"filters":[8],"with":[9],"a":[10,42,59,63,66],"deep":[11],"neural":[12],"network-based":[13],"postfilter.":[14],"While":[15],"the":[16,75,78,83,91,95,99,115],"signal-to-distortion":[17],"ratio":[18],"is":[19,25,49],"often":[20],"used":[21],"for":[22,28,37],"training,":[23],"it":[24,113],"not":[26],"well-defined":[27,34],"all":[29,126],"echo-reduction":[30],"scenarios.":[31],"We":[32],"propose":[33],"loss":[35],"functions":[36],"training":[38],"modifications":[40,56,73],"of":[41,82],"recently":[43],"proposed":[44,72,96],"system":[47,97],"that":[48,94],"based":[50],"on":[51,77],"informed":[52],"source":[53],"extraction.":[54],"The":[55,71],"include":[57],"using":[58],"Kalman":[60],"filter":[61],"as":[62],"prefilter":[64],"cyclical":[67],"learning":[68],"rate":[69],"scheduler.":[70],"improve":[74],"performance":[76],"blind":[79],"test":[80],"set":[81],"Interspeech":[84],"2021":[85],"AEC":[86],"challenge.":[87],"A":[88],"comparison":[89],"to":[90],"challenge-winner":[92],"shows":[93],"underperforms":[98],"winner":[100,116],"by":[101,117],"0.1":[102],"mean":[103],"opinion":[104],"score":[105],"(MOS)":[106],"points":[107,120],"in":[108,121],"double-talk":[109],"reduction.":[111,124],"However,":[112],"outperforms":[114],"0.3":[118],"MOS":[119],"echo-only":[122],"In":[125],"other":[127],"scenarios,":[128],"both":[129],"algorithms":[130],"perform":[131],"comparably.":[132]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1}],"updated_date":"2026-08-26T07:47:46.906454","created_date":"2025-10-10T00:00:00"}