{"id":"https://openalex.org/W4385486329","doi":"https://doi.org/10.1109/taslp.2023.3301223","title":"Deep Latent Fusion Layers for Binaural Speech Enhancement","display_name":"Deep Latent Fusion Layers for Binaural Speech Enhancement","publication_year":2023,"publication_date":"2023-01-01","ids":{"openalex":"https://openalex.org/W4385486329","doi":"https://doi.org/10.1109/taslp.2023.3301223"},"language":"en","primary_location":{"id":"doi:10.1109/taslp.2023.3301223","is_oa":true,"landing_page_url":"https://doi.org/10.1109/taslp.2023.3301223","pdf_url":"https://ieeexplore.ieee.org/ielx7/6570655/6633080/10202199.pdf","source":{"id":"https://openalex.org/S4210169297","display_name":"IEEE/ACM Transactions on Audio Speech and Language Processing","issn_l":"2329-9290","issn":["2329-9290","2329-9304"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE/ACM Transactions on Audio, Speech, and Language Processing","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://ieeexplore.ieee.org/ielx7/6570655/6633080/10202199.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5060096422","display_name":"Tom Gaj\u0229cki","orcid":"https://orcid.org/0000-0002-1904-1836"},"institutions":[{"id":"https://openalex.org/I4210144375","display_name":"Hearing4all","ror":"https://ror.org/0393vzh87","country_code":"DE","type":"facility","lineage":["https://openalex.org/I4210144375"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Tom Gajecki","raw_affiliation_strings":["Department of Otolaryngology, Medical University of Hannover and Cluster of Excellence “Hearing4all,”, Hannover, Germany"],"raw_orcid":"https://orcid.org/0000-0002-1904-1836","affiliations":[{"raw_affiliation_string":"Department of Otolaryngology, Medical University of Hannover and Cluster of Excellence “Hearing4all,”, Hannover, Germany","institution_ids":["https://openalex.org/I4210144375"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5055615467","display_name":"Waldo Nogueira","orcid":"https://orcid.org/0000-0001-7224-7617"},"institutions":[{"id":"https://openalex.org/I4210144375","display_name":"Hearing4all","ror":"https://ror.org/0393vzh87","country_code":"DE","type":"facility","lineage":["https://openalex.org/I4210144375"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Waldo Nogueira","raw_affiliation_strings":["Department of Otolaryngology, Medical University of Hannover and Cluster of Excellence “Hearing4all,”, Hannover, Germany"],"raw_orcid":"https://orcid.org/0000-0001-7224-7617","affiliations":[{"raw_affiliation_string":"Department of Otolaryngology, Medical University of Hannover and Cluster of Excellence “Hearing4all,”, Hannover, Germany","institution_ids":["https://openalex.org/I4210144375"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I4210144375"],"apc_list":null,"apc_paid":null,"fwci":1.2178,"has_fulltext":true,"cited_by_count":7,"citation_normalized_percentile":{"value":0.79717133,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":95,"max":98},"biblio":{"volume":"31","issue":null,"first_page":"3127","last_page":"3138"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9998999834060669,"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":0.9998999834060669,"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"}},{"id":"https://openalex.org/T10863","display_name":"Voice and Speech Disorders","score":0.9894000291824341,"subfield":{"id":"https://openalex.org/subfields/2737","display_name":"Physiology"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/binaural-recording","display_name":"Binaural recording","score":0.567013144493103},{"id":"https://openalex.org/keywords/fusion","display_name":"Fusion","score":0.5088363289833069},{"id":"https://openalex.org/keywords/speech-enhancement","display_name":"Speech enhancement","score":0.42634445428848267},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.4250231981277466},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.40397393703460693},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.2816770374774933},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.10005620121955872},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.07641047239303589}],"concepts":[{"id":"https://openalex.org/C201247586","wikidata":"https://www.wikidata.org/wiki/Q5612967","display_name":"Binaural recording","level":2,"score":0.567013144493103},{"id":"https://openalex.org/C158525013","wikidata":"https://www.wikidata.org/wiki/Q2593739","display_name":"Fusion","level":2,"score":0.5088363289833069},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.42634445428848267},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.4250231981277466},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.40397393703460693},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2816770374774933},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.10005620121955872},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.07641047239303589},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/taslp.2023.3301223","is_oa":true,"landing_page_url":"https://doi.org/10.1109/taslp.2023.3301223","pdf_url":"https://ieeexplore.ieee.org/ielx7/6570655/6633080/10202199.pdf","source":{"id":"https://openalex.org/S4210169297","display_name":"IEEE/ACM Transactions on Audio Speech and Language Processing","issn_l":"2329-9290","issn":["2329-9290","2329-9304"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE/ACM Transactions on Audio, Speech, and Language Processing","raw_type":"journal-article"},{"id":"pmh:oai:zenodo.org:12657007","is_oa":true,"landing_page_url":"https://doi.org/10.1109/TASLP.2023.3301223","pdf_url":null,"source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"IEEE/ACM Transactions on Audio, Speech, and Language Processing, 31, 3127-3138, (2023)","raw_type":"info:eu-repo/semantics/article"}],"best_oa_location":{"id":"doi:10.1109/taslp.2023.3301223","is_oa":true,"landing_page_url":"https://doi.org/10.1109/taslp.2023.3301223","pdf_url":"https://ieeexplore.ieee.org/ielx7/6570655/6633080/10202199.pdf","source":{"id":"https://openalex.org/S4210169297","display_name":"IEEE/ACM Transactions on Audio Speech and Language Processing","issn_l":"2329-9290","issn":["2329-9290","2329-9304"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE/ACM Transactions on Audio, Speech, and Language Processing","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G684888348","display_name":"Music4u: Personalisierte objektive Deep Learning Modelle zur Verbesserung der Musikwahrnehmung von Cochlea ImplantatTr\u00e4gern","funder_award_id":"446611346","funder_id":"https://openalex.org/F4320320879","funder_display_name":"Deutsche Forschungsgemeinschaft"}],"funders":[{"id":"https://openalex.org/F4320320879","display_name":"Deutsche Forschungsgemeinschaft","ror":"https://ror.org/018mejw64"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4385486329.pdf","grobid_xml":"https://content.openalex.org/works/W4385486329.grobid-xml"},"referenced_works_count":50,"referenced_works":["https://openalex.org/W1522301498","https://openalex.org/W1533861849","https://openalex.org/W1594560367","https://openalex.org/W1973746598","https://openalex.org/W1985638656","https://openalex.org/W1986423218","https://openalex.org/W2007217741","https://openalex.org/W2091432990","https://openalex.org/W2108598243","https://openalex.org/W2114218864","https://openalex.org/W2117130368","https://openalex.org/W2118323284","https://openalex.org/W2138927287","https://openalex.org/W2141998673","https://openalex.org/W2143156057","https://openalex.org/W2144980666","https://openalex.org/W2147101913","https://openalex.org/W2260826958","https://openalex.org/W2577762507","https://openalex.org/W2753709519","https://openalex.org/W2797579321","https://openalex.org/W2801271919","https://openalex.org/W2810434345","https://openalex.org/W2890718122","https://openalex.org/W2912581782","https://openalex.org/W2913340405","https://openalex.org/W2935873029","https://openalex.org/W2952218014","https://openalex.org/W2953343412","https://openalex.org/W2963103134","https://openalex.org/W2963216850","https://openalex.org/W2963877604","https://openalex.org/W2964058413","https://openalex.org/W2966182616","https://openalex.org/W3015279216","https://openalex.org/W3016257794","https://openalex.org/W3099330747","https://openalex.org/W3132455321","https://openalex.org/W3160071434","https://openalex.org/W3161565382","https://openalex.org/W3162133351","https://openalex.org/W3185109982","https://openalex.org/W3197832224","https://openalex.org/W3211408542","https://openalex.org/W4205437463","https://openalex.org/W4232282348","https://openalex.org/W6631190155","https://openalex.org/W6631943919","https://openalex.org/W6634537576","https://openalex.org/W6772750526"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2766995619","https://openalex.org/W4224270619","https://openalex.org/W2579722767","https://openalex.org/W2168148781","https://openalex.org/W1991848873","https://openalex.org/W3096184950","https://openalex.org/W4231424160"],"abstract_inverted_index":{"This":[0,100],"work":[1],"addresses":[2],"the":[3,33,84,89,96,134,140,195,223],"issue":[4],"of":[5,35,95,142,225],"enhancing":[6],"speech":[7,29,147,176,192,229,239],"in":[8,148],"binaural":[9,19,97,149,238],"hearing":[10,98],"scenarios.":[11],"Specifically,":[12],"we":[13],"present":[14],"a":[15,104,187],"method":[16,154],"to":[17,111,117,132,145,162,206,236],"improve":[18,133,237],"noise":[20,159],"reduction":[21,160],"by":[22,27],"integrating":[23],"latent":[24,44,81,204],"features":[25,184],"produced":[26],"monaural":[28],"enhancement":[30,230,240],"algorithms":[31],"through":[32,232],"use":[34],"\u201cFusion":[36],"layers.\u201d":[37],"These":[38,50],"layers":[39,52,73,144,200,235],"perform":[40,74],"Hadamard":[41],"products":[42,77],"between":[43,78,124,228],"spaces":[45],"at":[46,68,83],"specific":[47],"processing":[48,86],"stages.":[49],"fusion":[51,106,143,172,199,234],"draw":[53],"inspiration":[54],"from":[55,210],"multi-task":[56],"learning":[57,125],"techniques,":[58],"which":[59],"involve":[60],"sharing":[61,226],"model":[62],"weights":[63],"across":[64],"various":[65],"models":[66],"aimed":[67],"handling":[69],"interconnected":[70],"tasks.":[71],"The":[72,152,166],"element-wise":[75],"dot":[76],"tensors":[79],"representing":[80],"representations":[82,205],"same":[85],"stage,":[87],"mimicking":[88],"physiological":[90],"excitatory":[91],"and":[92,127,178,246],"inhibitory":[93],"mechanisms":[94],"system.":[99],"study":[101,167,221],"initially":[102],"presents":[103],"general":[105],"model,":[107],"demonstrating":[108],"its":[109],"ability":[110],"better":[112],"fit":[113],"synthetic":[114],"data":[115,130],"compared":[116,161],"independent":[118],"linear":[119],"models,":[120],"equalize":[121],"activation":[122],"variance":[123],"modules,":[126],"exploit":[128],"input":[129],"redundancy":[131],"training":[135],"error.":[136],"We":[137],"then":[138],"apply":[139],"concept":[141],"enhance":[146,174],"listening":[150,212],"conditions.":[151],"proposed":[153],"shows":[155],"promise":[156],"for":[157],"improved":[158],"other":[163],"feature-sharing":[164],"approaches.":[165],"also":[168],"suggests":[169],"that":[170,198],"including":[171],"can":[173],"predicted":[175],"intelligibility":[177],"quality,":[179],"but":[180],"too":[181],"many":[182],"fused":[183],"may":[185],"have":[186],"negative":[188],"impact":[189],"on":[190],"expected":[191],"intelligibility.":[193],"Furthermore,":[194],"results":[196],"suggest":[197],"should":[201],"share":[202],"parameterized":[203],"effectively":[207],"utilize":[208],"information":[209,227],"each":[211],"side,":[213],"rather":[214],"than":[215],"using":[216],"deterministic":[217],"representations.":[218],"Overall,":[219],"this":[220],"highlights":[222],"potential":[224],"modules":[231],"deep":[233],"while":[241],"maintaining":[242],"constant":[243],"trainable":[244],"parameters":[245],"improving":[247],"generalization.":[248]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":3}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}