{"id":"https://openalex.org/W4392903544","doi":"https://doi.org/10.1109/icassp48485.2024.10447153","title":"Real-Time Stereo Speech Enhancement with Spatial-Cue Preservation Based on Dual-Path Structure","display_name":"Real-Time Stereo Speech Enhancement with Spatial-Cue Preservation Based on Dual-Path Structure","publication_year":2024,"publication_date":"2024-03-18","ids":{"openalex":"https://openalex.org/W4392903544","doi":"https://doi.org/10.1109/icassp48485.2024.10447153"},"language":"en","primary_location":{"id":"doi:10.1109/icassp48485.2024.10447153","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp48485.2024.10447153","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2024 - 2024 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/A5021883714","display_name":"Masahito Togami","orcid":null},"institutions":[{"id":"https://openalex.org/I1311688040","display_name":"Amazon (United States)","ror":"https://ror.org/04mv4n011","country_code":"US","type":"company","lineage":["https://openalex.org/I1311688040"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Masahito Togami","raw_affiliation_strings":["Amazon Web Services,Palo Alto,CA,USA","Amazon Web Services, Palo Alto, CA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Amazon Web Services,Palo Alto,CA,USA","institution_ids":["https://openalex.org/I1311688040"]},{"raw_affiliation_string":"Amazon Web Services, Palo Alto, CA, USA","institution_ids":["https://openalex.org/I1311688040"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5021269794","display_name":"Jean-Marc Valin","orcid":"https://orcid.org/0000-0002-9883-6927"},"institutions":[{"id":"https://openalex.org/I1311688040","display_name":"Amazon (United States)","ror":"https://ror.org/04mv4n011","country_code":"US","type":"company","lineage":["https://openalex.org/I1311688040"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jean-Marc Valin","raw_affiliation_strings":["Amazon Web Services,Palo Alto,CA,USA","Amazon Web Services, Palo Alto, CA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Amazon Web Services,Palo Alto,CA,USA","institution_ids":["https://openalex.org/I1311688040"]},{"raw_affiliation_string":"Amazon Web Services, Palo Alto, CA, USA","institution_ids":["https://openalex.org/I1311688040"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5014282181","display_name":"Karim Helwani","orcid":null},"institutions":[{"id":"https://openalex.org/I1311688040","display_name":"Amazon (United States)","ror":"https://ror.org/04mv4n011","country_code":"US","type":"company","lineage":["https://openalex.org/I1311688040"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Karim Helwani","raw_affiliation_strings":["Amazon Web Services,Palo Alto,CA,USA","Amazon Web Services, Palo Alto, CA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Amazon Web Services,Palo Alto,CA,USA","institution_ids":["https://openalex.org/I1311688040"]},{"raw_affiliation_string":"Amazon Web Services, Palo Alto, CA, USA","institution_ids":["https://openalex.org/I1311688040"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5091775011","display_name":"Ritwik Giri","orcid":"https://orcid.org/0000-0002-8599-3229"},"institutions":[{"id":"https://openalex.org/I1311688040","display_name":"Amazon (United States)","ror":"https://ror.org/04mv4n011","country_code":"US","type":"company","lineage":["https://openalex.org/I1311688040"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ritwik Giri","raw_affiliation_strings":["Amazon Web Services,Palo Alto,CA,USA","Amazon Web Services, Palo Alto, CA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Amazon Web Services,Palo Alto,CA,USA","institution_ids":["https://openalex.org/I1311688040"]},{"raw_affiliation_string":"Amazon Web Services, Palo Alto, CA, USA","institution_ids":["https://openalex.org/I1311688040"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5036092393","display_name":"Umut Isik","orcid":null},"institutions":[{"id":"https://openalex.org/I1311688040","display_name":"Amazon (United States)","ror":"https://ror.org/04mv4n011","country_code":"US","type":"company","lineage":["https://openalex.org/I1311688040"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Umut Isik","raw_affiliation_strings":["Amazon Web Services,Palo Alto,CA,USA","Amazon Web Services, Palo Alto, CA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Amazon Web Services,Palo Alto,CA,USA","institution_ids":["https://openalex.org/I1311688040"]},{"raw_affiliation_string":"Amazon Web Services, Palo Alto, CA, USA","institution_ids":["https://openalex.org/I1311688040"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5028244782","display_name":"Michael M. Goodwin","orcid":null},"institutions":[{"id":"https://openalex.org/I1311688040","display_name":"Amazon (United States)","ror":"https://ror.org/04mv4n011","country_code":"US","type":"company","lineage":["https://openalex.org/I1311688040"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Michael M. Goodwin","raw_affiliation_strings":["Amazon Web Services,Palo Alto,CA,USA","Amazon Web Services, Palo Alto, CA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Amazon Web Services,Palo Alto,CA,USA","institution_ids":["https://openalex.org/I1311688040"]},{"raw_affiliation_string":"Amazon Web Services, Palo Alto, CA, USA","institution_ids":["https://openalex.org/I1311688040"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.5286,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.81477556,"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":"71","last_page":"75"},"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":0.9991999864578247,"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":0.9958000183105469,"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":0.7958232164382935},{"id":"https://openalex.org/keywords/beamforming","display_name":"Beamforming","score":0.6098523139953613},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5922700762748718},{"id":"https://openalex.org/keywords/speech-enhancement","display_name":"Speech enhancement","score":0.5232885479927063},{"id":"https://openalex.org/keywords/monaural","display_name":"Monaural","score":0.5085562467575073},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.500408411026001},{"id":"https://openalex.org/keywords/path","display_name":"Path (computing)","score":0.4527982175350189},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4433925747871399},{"id":"https://openalex.org/keywords/spatial-filter","display_name":"Spatial filter","score":0.4221703112125397},{"id":"https://openalex.org/keywords/spatial-analysis","display_name":"Spatial analysis","score":0.4150998294353485},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.36048638820648193},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.09341630339622498},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.07910779118537903}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7958232164382935},{"id":"https://openalex.org/C54197355","wikidata":"https://www.wikidata.org/wiki/Q5782992","display_name":"Beamforming","level":2,"score":0.6098523139953613},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5922700762748718},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.5232885479927063},{"id":"https://openalex.org/C102894143","wikidata":"https://www.wikidata.org/wiki/Q1323979","display_name":"Monaural","level":2,"score":0.5085562467575073},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.500408411026001},{"id":"https://openalex.org/C2777735758","wikidata":"https://www.wikidata.org/wiki/Q817765","display_name":"Path (computing)","level":2,"score":0.4527982175350189},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4433925747871399},{"id":"https://openalex.org/C121475858","wikidata":"https://www.wikidata.org/wiki/Q2735911","display_name":"Spatial filter","level":2,"score":0.4221703112125397},{"id":"https://openalex.org/C159620131","wikidata":"https://www.wikidata.org/wiki/Q1938983","display_name":"Spatial analysis","level":2,"score":0.4150998294353485},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.36048638820648193},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.09341630339622498},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.07910779118537903},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","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},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp48485.2024.10447153","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp48485.2024.10447153","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Sustainable cities and communities","id":"https://metadata.un.org/sdg/11","score":0.5600000023841858}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":29,"referenced_works":["https://openalex.org/W1482149378","https://openalex.org/W1494198834","https://openalex.org/W1910234244","https://openalex.org/W2044893557","https://openalex.org/W2128653836","https://openalex.org/W2143156057","https://openalex.org/W2221409856","https://openalex.org/W2289394825","https://openalex.org/W2310962060","https://openalex.org/W2398042854","https://openalex.org/W2460742184","https://openalex.org/W2765794762","https://openalex.org/W2890553422","https://openalex.org/W2937235446","https://openalex.org/W2952218014","https://openalex.org/W2963341071","https://openalex.org/W2973084105","https://openalex.org/W3015279216","https://openalex.org/W3025844872","https://openalex.org/W3095248373","https://openalex.org/W3097906045","https://openalex.org/W3099330747","https://openalex.org/W3147539069","https://openalex.org/W3162133351","https://openalex.org/W4225282374","https://openalex.org/W4253928870","https://openalex.org/W6684450716","https://openalex.org/W6697270792","https://openalex.org/W6754904195"],"related_works":["https://openalex.org/W2036157531","https://openalex.org/W2056406069","https://openalex.org/W1974981856","https://openalex.org/W1518859147","https://openalex.org/W2045506488","https://openalex.org/W1983045063","https://openalex.org/W2538939196","https://openalex.org/W3045520545","https://openalex.org/W4233867831","https://openalex.org/W3126337586"],"abstract_inverted_index":{"We":[0],"introduce":[1],"a":[2,31,133],"real-time,":[3],"multichannel":[4],"speech":[5,18,54,144],"enhancement":[6,41],"algorithm":[7,125],"which":[8],"maintains":[9],"the":[10,35,57,75,93,104,108,118,122],"spatial":[11,26,36,72,94,105,147],"cues":[12,37,148],"of":[13,92,107,121,136],"stereo":[14,62,67,98],"recordings":[15],"including":[16],"two":[17],"sources.":[19],"Recognizing":[20],"that":[21],"each":[22,79],"source":[23,80],"has":[24],"unique":[25],"information,":[27],"our":[28],"method":[29,48],"utilizes":[30],"dual-path":[32],"structure,":[33],"ensuring":[34],"remain":[38],"unaffected":[39],"during":[40],"by":[42,102],"applying":[43],"source-specific":[44],"common-band":[45],"gain.":[46],"This":[47,88],"also":[49],"seamlessly":[50],"integrates":[51],"pretrained":[52],"monaural":[53],"enhancement,":[55],"eliminating":[56],"need":[58],"for":[59,78],"retraining":[60],"on":[61,117,129],"inputs.":[63],"Source":[64],"separation":[65,119],"from":[66],"mixtures":[68],"is":[69,100],"achieved":[70],"via":[71],"beamforming,":[73],"with":[74,111,132],"steering":[76],"vector":[77],"being":[81],"adaptively":[82],"updated":[83],"using":[84],"post-enhancement":[85],"output":[86,99],"signal.":[87],"ensures":[89],"accurate":[90],"tracking":[91],"information.":[95],"The":[96,124],"final":[97],"derived":[101],"merging":[103],"images":[106],"enhanced":[109],"sources,":[110],"its":[112,140],"efficacy":[113],"not":[114],"heavily":[115],"reliant":[116],"performance":[120],"beamforming.":[123],"runs":[126],"in":[127,142,149],"real-time":[128],"10-ms":[130],"frames":[131],"40":[134],"ms":[135],"look-ahead.":[137],"Evaluations":[138],"reveal":[139],"effectiveness":[141],"enhancing":[143],"and":[145,152],"preserving":[146],"both":[150],"fully":[151],"sparsely":[153],"overlapped":[154],"mixtures.":[155]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":4}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}
