{"id":"https://openalex.org/W4403126605","doi":"https://doi.org/10.1109/iwaenc61483.2024.10694612","title":"Interaural Time Difference Loss for Binaural Target Sound Extraction","display_name":"Interaural Time Difference Loss for Binaural Target Sound Extraction","publication_year":2024,"publication_date":"2024-09-09","ids":{"openalex":"https://openalex.org/W4403126605","doi":"https://doi.org/10.1109/iwaenc61483.2024.10694612"},"language":"en","primary_location":{"id":"doi:10.1109/iwaenc61483.2024.10694612","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iwaenc61483.2024.10694612","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 18th 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/A5048090174","display_name":"Carlos Hernandez-Olivan","orcid":"https://orcid.org/0000-0002-0235-2267"},"institutions":[{"id":"https://openalex.org/I2251713219","display_name":"NTT (Japan)","ror":"https://ror.org/00berct97","country_code":"JP","type":"company","lineage":["https://openalex.org/I2251713219"]}],"countries":["JP"],"is_corresponding":true,"raw_author_name":"Carlos Hernandez-Olivan","raw_affiliation_strings":["NTT Corporation,Japan"],"affiliations":[{"raw_affiliation_string":"NTT Corporation,Japan","institution_ids":["https://openalex.org/I2251713219"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5023868166","display_name":"Marc Delcroix","orcid":"https://orcid.org/0000-0002-5175-7834"},"institutions":[{"id":"https://openalex.org/I2251713219","display_name":"NTT (Japan)","ror":"https://ror.org/00berct97","country_code":"JP","type":"company","lineage":["https://openalex.org/I2251713219"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Marc Delcroix","raw_affiliation_strings":["NTT Corporation,Japan"],"affiliations":[{"raw_affiliation_string":"NTT Corporation,Japan","institution_ids":["https://openalex.org/I2251713219"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5070624983","display_name":"Tsubasa Ochiai","orcid":"https://orcid.org/0000-0002-2519-2032"},"institutions":[{"id":"https://openalex.org/I2251713219","display_name":"NTT (Japan)","ror":"https://ror.org/00berct97","country_code":"JP","type":"company","lineage":["https://openalex.org/I2251713219"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Tsubasa Ochiai","raw_affiliation_strings":["NTT Corporation,Japan"],"affiliations":[{"raw_affiliation_string":"NTT Corporation,Japan","institution_ids":["https://openalex.org/I2251713219"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5073111123","display_name":"Naohiro Tawara","orcid":null},"institutions":[{"id":"https://openalex.org/I2251713219","display_name":"NTT (Japan)","ror":"https://ror.org/00berct97","country_code":"JP","type":"company","lineage":["https://openalex.org/I2251713219"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Naohiro Tawara","raw_affiliation_strings":["NTT Corporation,Japan"],"affiliations":[{"raw_affiliation_string":"NTT Corporation,Japan","institution_ids":["https://openalex.org/I2251713219"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5021240106","display_name":"Tomohiro Nakatani","orcid":"https://orcid.org/0000-0002-7487-7150"},"institutions":[{"id":"https://openalex.org/I2251713219","display_name":"NTT (Japan)","ror":"https://ror.org/00berct97","country_code":"JP","type":"company","lineage":["https://openalex.org/I2251713219"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Tomohiro Nakatani","raw_affiliation_strings":["NTT Corporation,Japan"],"affiliations":[{"raw_affiliation_string":"NTT Corporation,Japan","institution_ids":["https://openalex.org/I2251713219"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5009309584","display_name":"Shoko Araki","orcid":"https://orcid.org/0000-0003-4363-4305"},"institutions":[{"id":"https://openalex.org/I2251713219","display_name":"NTT (Japan)","ror":"https://ror.org/00berct97","country_code":"JP","type":"company","lineage":["https://openalex.org/I2251713219"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Shoko Araki","raw_affiliation_strings":["NTT Corporation,Japan"],"affiliations":[{"raw_affiliation_string":"NTT Corporation,Japan","institution_ids":["https://openalex.org/I2251713219"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5048090174"],"corresponding_institution_ids":["https://openalex.org/I2251713219"],"apc_list":null,"apc_paid":null,"fwci":2.0527,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.85939923,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":97,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"210","last_page":"214"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11698","display_name":"Underwater Acoustics Research","score":0.9988999962806702,"subfield":{"id":"https://openalex.org/subfields/1910","display_name":"Oceanography"},"field":{"id":"https://openalex.org/fields/19","display_name":"Earth and Planetary Sciences"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T11698","display_name":"Underwater Acoustics Research","score":0.9988999962806702,"subfield":{"id":"https://openalex.org/subfields/1910","display_name":"Oceanography"},"field":{"id":"https://openalex.org/fields/19","display_name":"Earth and Planetary Sciences"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9919000267982483,"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":0.9611999988555908,"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/binaural-recording","display_name":"Binaural recording","score":0.7093420624732971},{"id":"https://openalex.org/keywords/extraction","display_name":"Extraction (chemistry)","score":0.6144147515296936},{"id":"https://openalex.org/keywords/sound-localization","display_name":"Sound localization","score":0.5497354865074158},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.5338135361671448},{"id":"https://openalex.org/keywords/sound","display_name":"Sound (geography)","score":0.5071909427642822},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5004167556762695},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.35283327102661133},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.15300434827804565},{"id":"https://openalex.org/keywords/chemistry","display_name":"Chemistry","score":0.0746803879737854}],"concepts":[{"id":"https://openalex.org/C201247586","wikidata":"https://www.wikidata.org/wiki/Q5612967","display_name":"Binaural recording","level":2,"score":0.7093420624732971},{"id":"https://openalex.org/C4725764","wikidata":"https://www.wikidata.org/wiki/Q844704","display_name":"Extraction (chemistry)","level":2,"score":0.6144147515296936},{"id":"https://openalex.org/C68236139","wikidata":"https://www.wikidata.org/wiki/Q765652","display_name":"Sound localization","level":2,"score":0.5497354865074158},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.5338135361671448},{"id":"https://openalex.org/C203718221","wikidata":"https://www.wikidata.org/wiki/Q491713","display_name":"Sound (geography)","level":2,"score":0.5071909427642822},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5004167556762695},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.35283327102661133},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.15300434827804565},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0746803879737854},{"id":"https://openalex.org/C43617362","wikidata":"https://www.wikidata.org/wiki/Q170050","display_name":"Chromatography","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/iwaenc61483.2024.10694612","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iwaenc61483.2024.10694612","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 18th International Workshop on Acoustic Signal Enhancement (IWAENC)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320338124","display_name":"Strategic International Collaborative Research Program","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":30,"referenced_works":["https://openalex.org/W1581848821","https://openalex.org/W1934547825","https://openalex.org/W1965159237","https://openalex.org/W2052666245","https://openalex.org/W2108668360","https://openalex.org/W2118323284","https://openalex.org/W2128974165","https://openalex.org/W2771361008","https://openalex.org/W2951130829","https://openalex.org/W2962865004","https://openalex.org/W2964058413","https://openalex.org/W3015279216","https://openalex.org/W3095263845","https://openalex.org/W3173852682","https://openalex.org/W4205689591","https://openalex.org/W4224929689","https://openalex.org/W4296070363","https://openalex.org/W4298310324","https://openalex.org/W4310873168","https://openalex.org/W4367597591","https://openalex.org/W4372260051","https://openalex.org/W4372348953","https://openalex.org/W4387835382","https://openalex.org/W4392911133","https://openalex.org/W4395471087","https://openalex.org/W6634794388","https://openalex.org/W6752516136","https://openalex.org/W6766320909","https://openalex.org/W6784775991","https://openalex.org/W7024468878"],"related_works":["https://openalex.org/W1991848873","https://openalex.org/W3004570917","https://openalex.org/W4389240440","https://openalex.org/W2084430325","https://openalex.org/W2041661331","https://openalex.org/W2539207221","https://openalex.org/W2045803470","https://openalex.org/W2242743481","https://openalex.org/W1571953124","https://openalex.org/W2622611424"],"abstract_inverted_index":{"Binaural":[0,46],"target":[1,32,117],"sound":[2,10,33,44,61,72],"extraction":[3],"(TSE)":[4],"aims":[5],"to":[6,56,109],"extract":[7],"a":[8,12,52,63],"desired":[9,25,60,71],"from":[11],"binaural":[13,64],"mixture":[14,65],"of":[15,23,115],"arbitrary":[16],"sounds":[17],"while":[18,156],"preserving":[19,126],"the":[20,24,31,43,59,70,86,89,95,112,116,127,158],"spatial":[21,37,107,113,143,154],"cues":[22,38,114,155],"sound.":[26,118],"Indeed,":[27],"for":[28,94],"many":[29],"applications,":[30],"signal":[34],"and":[35,66,91,97,133],"its":[36],"carry":[39],"important":[40],"information":[41],"about":[42],"source.":[45],"TSE":[47,77],"can":[48],"be":[49],"realized":[50],"with":[51],"neural":[53],"network":[54],"trained":[55,80],"output":[57],"only":[58],"given":[62],"an":[67],"embedding":[68],"characterizing":[69],"class":[73],"as":[74],"inputs.":[75],"Conventional":[76],"systems":[78],"are":[79],"using":[81],"signal-level":[82,159],"losses,":[83,144],"which":[84],"measure":[85],"difference":[87],"between":[88],"extracted":[90],"reference":[92],"signals":[93],"left":[96],"right":[98],"channels.":[99],"In":[100,119],"this":[101],"paper,":[102],"we":[103,121],"propose":[104],"adding":[105,141],"explicit":[106],"losses":[108,123],"better":[110,153],"preserve":[111,152],"particular,":[120],"explore":[122],"aiming":[124],"at":[125],"interaural":[128],"level":[129],"(ILD),":[130],"phase":[131],"(IPD),":[132],"time":[134],"differences":[135],"(ITD).":[136],"We":[137],"show":[138],"experimentally":[139],"that":[140],"such":[142],"particularly":[145],"our":[146],"newly":[147],"proposed":[148],"ITD":[149],"loss,":[150],"helps":[151],"maintaining":[157],"metrics.":[160]},"counts_by_year":[{"year":2025,"cited_by_count":4}],"updated_date":"2025-12-22T23:10:17.713674","created_date":"2025-10-10T00:00:00"}
