{"id":"https://openalex.org/W4312245440","doi":"https://doi.org/10.1109/iwaenc53105.2022.9914735","title":"AmbiSep: Ambisonic-to-Ambisonic Reverberant Speech Separation Using Transformer Networks","display_name":"AmbiSep: Ambisonic-to-Ambisonic Reverberant Speech Separation Using Transformer Networks","publication_year":2022,"publication_date":"2022-09-05","ids":{"openalex":"https://openalex.org/W4312245440","doi":"https://doi.org/10.1109/iwaenc53105.2022.9914735"},"language":"en","primary_location":{"id":"doi:10.1109/iwaenc53105.2022.9914735","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iwaenc53105.2022.9914735","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 International Workshop on Acoustic Signal Enhancement (IWAENC)","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/A5005446137","display_name":"Adrian Herzog","orcid":"https://orcid.org/0000-0003-0827-8333"},"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":"Adrian Herzog","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":"middle","author":{"id":"https://openalex.org/A5004929413","display_name":"Srikanth Raj Chetupalli","orcid":"https://orcid.org/0000-0002-2186-5420"},"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":"Srikanth Raj Chetupalli","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":1.3376,"has_fulltext":false,"cited_by_count":9,"citation_normalized_percentile":{"value":0.80460153,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"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/T11309","display_name":"Music and Audio Processing","score":0.9988999962806702,"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/T10283","display_name":"Hearing Loss and Rehabilitation","score":0.9976999759674072,"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/ambisonics","display_name":"Ambisonics","score":0.9555274248123169},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7145496606826782},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5899062156677246},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3969821333885193},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.32045215368270874},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.20866402983665466},{"id":"https://openalex.org/keywords/loudspeaker","display_name":"Loudspeaker","score":0.1636490821838379}],"concepts":[{"id":"https://openalex.org/C47726159","wikidata":"https://www.wikidata.org/wiki/Q457547","display_name":"Ambisonics","level":3,"score":0.9555274248123169},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7145496606826782},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5899062156677246},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3969821333885193},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.32045215368270874},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.20866402983665466},{"id":"https://openalex.org/C157138929","wikidata":"https://www.wikidata.org/wiki/Q570","display_name":"Loudspeaker","level":2,"score":0.1636490821838379},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/iwaenc53105.2022.9914735","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iwaenc53105.2022.9914735","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 International Workshop on Acoustic Signal Enhancement (IWAENC)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.41999998688697815,"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":31,"referenced_works":["https://openalex.org/W165956390","https://openalex.org/W1969110495","https://openalex.org/W1981755271","https://openalex.org/W2098795429","https://openalex.org/W2152632507","https://openalex.org/W2221409856","https://openalex.org/W2467338965","https://openalex.org/W2494085323","https://openalex.org/W2507219293","https://openalex.org/W2734774145","https://openalex.org/W2751323801","https://openalex.org/W2772289775","https://openalex.org/W2786625961","https://openalex.org/W2899838214","https://openalex.org/W2899857465","https://openalex.org/W2917254586","https://openalex.org/W2938751282","https://openalex.org/W2952218014","https://openalex.org/W2962866211","https://openalex.org/W3015199127","https://openalex.org/W3030781580","https://openalex.org/W3047232705","https://openalex.org/W3099330747","https://openalex.org/W3105931041","https://openalex.org/W3163652268","https://openalex.org/W3205004157","https://openalex.org/W4236344233","https://openalex.org/W6703583378","https://openalex.org/W6704119336","https://openalex.org/W6777639356","https://openalex.org/W6802884974"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2748952813","https://openalex.org/W62656364","https://openalex.org/W2403497458","https://openalex.org/W4387871131","https://openalex.org/W2305368260","https://openalex.org/W3108333885","https://openalex.org/W1978521983","https://openalex.org/W2033914206","https://openalex.org/W2042327336"],"abstract_inverted_index":{"Consider":[0],"a":[1,6,29,48,70,83,93],"multichannel":[2,94],"Ambisonic":[3,16],"recording":[4],"containing":[5],"mixture":[7,27],"of":[8,99,112],"several":[9],"reverberant":[10,15],"speech":[11,22],"signals.":[12],"Retrieving":[13],"the":[14,20,26,78,90,103,109,113],"signals":[17],"corresponding":[18],"to":[19,56],"individual":[21],"sources":[23],"blindly":[24],"from":[25],"is":[28],"challenging":[30],"task":[31],"as":[32],"it":[33],"requires":[34],"estimating":[35],"multiple":[36],"signal":[37],"channels":[38],"for":[39],"each":[40],"source.":[41],"In":[42],"this":[43,58],"work,":[44],"we":[45],"propose":[46],"AmbiSep,":[47],"deep":[49],"neural":[50],"network-based":[51],"plane-wave":[52],"domain":[53],"masking":[54,61],"approach":[55],"solve":[57],"task.":[59],"The":[60],"network":[62,80],"uses":[63],"learned":[64],"feature":[65],"representations":[66],"and":[67,76,87],"transformers":[68],"in":[69],"triple-path":[71],"processing":[72],"configuration.":[73],"We":[74],"train":[75],"evaluate":[77],"proposed":[79],"architecture":[81],"on":[82,102],"spatialized":[84],"WSJ0-2mix":[85],"dataset":[86],"show":[88],"that":[89],"method":[91],"achieves":[92],"scale-invariant":[95],"signal-to-distortion":[96],"ratio":[97],"improvement":[98],"17.7":[100],"dB":[101],"blind":[104],"test":[105],"set":[106],"while":[107],"preserving":[108],"spatial":[110],"characteristics":[111],"separated":[114],"sounds.":[115]},"counts_by_year":[{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":4},{"year":2023,"cited_by_count":2}],"updated_date":"2026-06-26T08:34:08.712188","created_date":"2025-10-10T00:00:00"}