{"id":"https://openalex.org/W4385225525","doi":"https://doi.org/10.1109/taslp.2023.3297954","title":"AmbiSep: Joint Ambisonic-to-Ambisonic Speech Separation and Noise Reduction","display_name":"AmbiSep: Joint Ambisonic-to-Ambisonic Speech Separation and Noise Reduction","publication_year":2023,"publication_date":"2023-01-01","ids":{"openalex":"https://openalex.org/W4385225525","doi":"https://doi.org/10.1109/taslp.2023.3297954"},"language":"en","primary_location":{"id":"doi:10.1109/taslp.2023.3297954","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taslp.2023.3297954","pdf_url":null,"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":null,"license_id":null,"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":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"]},{"id":"https://openalex.org/I4210124274","display_name":"Fraunhofer Institute for Integrated Circuits","ror":"https://ror.org/024ape423","country_code":"DE","type":"facility","lineage":["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 (A joint institution of the Friedrich Alexander Universität Erlangen-Nürnberg (FAU) and Fraunhofer IIS), Erlangen, Germany"],"raw_orcid":"https://orcid.org/0000-0003-0827-8333","affiliations":[{"raw_affiliation_string":"International Audio Laboratories Erlangen (A joint institution of the Friedrich Alexander Universität Erlangen-Nürnberg (FAU) and Fraunhofer IIS), Erlangen, Germany","institution_ids":["https://openalex.org/I4210123192","https://openalex.org/I4210124274"]}]},{"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"]},{"id":"https://openalex.org/I4210124274","display_name":"Fraunhofer Institute for Integrated Circuits","ror":"https://ror.org/024ape423","country_code":"DE","type":"facility","lineage":["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 (A joint institution of the Friedrich Alexander Universität Erlangen-Nürnberg (FAU) and Fraunhofer IIS), Erlangen, Germany"],"raw_orcid":"https://orcid.org/0000-0002-2186-5420","affiliations":[{"raw_affiliation_string":"International Audio Laboratories Erlangen (A joint institution of the Friedrich Alexander Universität Erlangen-Nürnberg (FAU) and Fraunhofer IIS), Erlangen, Germany","institution_ids":["https://openalex.org/I4210123192","https://openalex.org/I4210124274"]}]},{"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"]},{"id":"https://openalex.org/I4210124274","display_name":"Fraunhofer Institute for Integrated Circuits","ror":"https://ror.org/024ape423","country_code":"DE","type":"facility","lineage":["https://openalex.org/I4210124274","https://openalex.org/I4923324"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Emanu\u00ebl A. P. Habets","raw_affiliation_strings":["International Audio Laboratories Erlangen (A joint institution of the Friedrich Alexander Universität Erlangen-Nürnberg (FAU) and Fraunhofer IIS), Erlangen, Germany"],"raw_orcid":"https://orcid.org/0000-0002-2613-8046","affiliations":[{"raw_affiliation_string":"International Audio Laboratories Erlangen (A joint institution of the Friedrich Alexander Universität Erlangen-Nürnberg (FAU) and Fraunhofer IIS), Erlangen, Germany","institution_ids":["https://openalex.org/I4210123192","https://openalex.org/I4210124274"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.739,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.69357435,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":98},"biblio":{"volume":"31","issue":null,"first_page":"3081","last_page":"3094"},"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9993000030517578,"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/T11309","display_name":"Music and Audio Processing","score":0.998199999332428,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/ambisonics","display_name":"Ambisonics","score":0.9978693723678589},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6280848979949951},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5083207488059998},{"id":"https://openalex.org/keywords/reverberation","display_name":"Reverberation","score":0.5034741759300232},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.46131253242492676},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.4568222165107727},{"id":"https://openalex.org/keywords/loudspeaker","display_name":"Loudspeaker","score":0.3530508279800415},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.3362831473350525},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3100909888744354}],"concepts":[{"id":"https://openalex.org/C47726159","wikidata":"https://www.wikidata.org/wiki/Q457547","display_name":"Ambisonics","level":3,"score":0.9978693723678589},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6280848979949951},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5083207488059998},{"id":"https://openalex.org/C95851461","wikidata":"https://www.wikidata.org/wiki/Q468809","display_name":"Reverberation","level":2,"score":0.5034741759300232},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.46131253242492676},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.4568222165107727},{"id":"https://openalex.org/C157138929","wikidata":"https://www.wikidata.org/wiki/Q570","display_name":"Loudspeaker","level":2,"score":0.3530508279800415},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.3362831473350525},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3100909888744354},{"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/taslp.2023.3297954","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taslp.2023.3297954","pdf_url":null,"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":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE/ACM Transactions on Audio, Speech, and Language Processing","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/10","score":0.6299999952316284,"display_name":"Reduced inequalities"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":57,"referenced_works":["https://openalex.org/W165956390","https://openalex.org/W1569827162","https://openalex.org/W1582950417","https://openalex.org/W1969110495","https://openalex.org/W1972978214","https://openalex.org/W1979601119","https://openalex.org/W1981755271","https://openalex.org/W2037814094","https://openalex.org/W2098795429","https://openalex.org/W2127851351","https://openalex.org/W2129501075","https://openalex.org/W2149648624","https://openalex.org/W2152632507","https://openalex.org/W2172491908","https://openalex.org/W2221409856","https://openalex.org/W2336857195","https://openalex.org/W2340354943","https://openalex.org/W2467338965","https://openalex.org/W2494085323","https://openalex.org/W2507219293","https://openalex.org/W2524249505","https://openalex.org/W2734774145","https://openalex.org/W2772289775","https://openalex.org/W2786625961","https://openalex.org/W2899838214","https://openalex.org/W2899857465","https://openalex.org/W2914584499","https://openalex.org/W2914801158","https://openalex.org/W2917254586","https://openalex.org/W2952218014","https://openalex.org/W2962866211","https://openalex.org/W3015199127","https://openalex.org/W3025423009","https://openalex.org/W3047232705","https://openalex.org/W3099330747","https://openalex.org/W3152352576","https://openalex.org/W3163652268","https://openalex.org/W3167533889","https://openalex.org/W3180342997","https://openalex.org/W3205004157","https://openalex.org/W3213661887","https://openalex.org/W4225632554","https://openalex.org/W4236344233","https://openalex.org/W4312245440","https://openalex.org/W4366503942","https://openalex.org/W4379797396","https://openalex.org/W4385245566","https://openalex.org/W6633823725","https://openalex.org/W6635083030","https://openalex.org/W6659849957","https://openalex.org/W6679329388","https://openalex.org/W6682325752","https://openalex.org/W6683587825","https://openalex.org/W6703583378","https://openalex.org/W6704119336","https://openalex.org/W6739901393","https://openalex.org/W6777639356"],"related_works":["https://openalex.org/W2184829026","https://openalex.org/W4317418940","https://openalex.org/W2072824490","https://openalex.org/W2013363868","https://openalex.org/W2038475054","https://openalex.org/W2241777496","https://openalex.org/W2237408746","https://openalex.org/W3113396598","https://openalex.org/W3199097733","https://openalex.org/W2586994231"],"abstract_inverted_index":{"Blind":[0],"separation":[1,32],"of":[2,19,33,82,90],"the":[3,16,88,121],"sounds":[4,21],"in":[5],"an":[6],"Ambisonic":[7,58,66,91,140],"sound":[8],"scene":[9],"is":[10,44,104],"a":[11,47],"challenging":[12],"problem,":[13],"especially":[14],"when":[15],"spatial":[17,74],"impression":[18],"these":[20],"needs":[22],"to":[23,135],"be":[24],"preserved.":[25],"In":[26],"this":[27,95],"work,":[28],"we":[29,97],"consider":[30],"Ambisonic-to-Ambisonic":[31],"reverberant":[34,129],"speech":[35,115,130],"mixtures,":[36,131],"optionally":[37],"containing":[38],"noise.":[39],"A":[40],"supervised":[41],"learning":[42],"approach":[43],"adopted":[45],"utilizing":[46],"transformer-based":[48],"deep":[49],"neural":[50],"network,":[51],"denoted":[52],"by":[53],"AmbiSep.":[54],"AmbiSep":[55,83],"takes":[56],"mutichannel":[57],"signals":[59,67],"as":[60],"input":[61],"and":[62,106,110,127,132],"estimates":[63],"separate":[64],"multichannel":[65],"for":[68,108],"each":[69],"speaker":[70],"while":[71],"preserving":[72],"their":[73],"images":[75],"including":[76],"reverberation.":[77],"The":[78,102],"GPU":[79],"memory":[80],"requirement":[81],"during":[84],"training":[85],"increases":[86],"with":[87,138],"number":[89],"channels.":[92],"To":[93],"overcome":[94],"issue,":[96],"propose":[98],"different":[99],"aggregation":[100],"methods.":[101],"model":[103,122],"trained":[105],"evaluated":[107],"first-order":[109],"second-order":[111],"Ambisonics":[112],"using":[113],"simulated":[114],"mixtures.":[116],"Experimental":[117],"results":[118],"show":[119],"that":[120],"performs":[123],"well":[124],"on":[125],"clean":[126],"noisy":[128],"also":[133],"generalizes":[134],"mixtures":[136],"generated":[137],"measured":[139],"impulse":[141],"responses.":[142]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":2}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}