{"id":"https://openalex.org/W3160970338","doi":"https://doi.org/10.1109/icassp39728.2021.9414750","title":"Implicit HRTF Modeling Using Temporal Convolutional Networks","display_name":"Implicit HRTF Modeling Using Temporal Convolutional Networks","publication_year":2021,"publication_date":"2021-05-13","ids":{"openalex":"https://openalex.org/W3160970338","doi":"https://doi.org/10.1109/icassp39728.2021.9414750","mag":"3160970338"},"language":"en","primary_location":{"id":"doi:10.1109/icassp39728.2021.9414750","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp39728.2021.9414750","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2021 - 2021 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/A5072548521","display_name":"Israel D. Gebru","orcid":null},"institutions":[{"id":"https://openalex.org/I2252078561","display_name":"Meta (Israel)","ror":"https://ror.org/02388em19","country_code":"IL","type":"company","lineage":["https://openalex.org/I2252078561","https://openalex.org/I4210114444"]},{"id":"https://openalex.org/I4210114444","display_name":"Meta (United States)","ror":"https://ror.org/01zbnvs85","country_code":"US","type":"company","lineage":["https://openalex.org/I4210114444"]}],"countries":["IL","US"],"is_corresponding":true,"raw_author_name":"Israel D. Gebru","raw_affiliation_strings":["Facebook Reality Labs Research,Pittsburgh,PA,USA","Facebook Reality Labs Research, Pittsburgh, PA, USA"],"affiliations":[{"raw_affiliation_string":"Facebook Reality Labs Research,Pittsburgh,PA,USA","institution_ids":["https://openalex.org/I2252078561"]},{"raw_affiliation_string":"Facebook Reality Labs Research, Pittsburgh, PA, USA","institution_ids":["https://openalex.org/I4210114444"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5003700236","display_name":"Dejan Markovi\u0107","orcid":"https://orcid.org/0000-0002-6744-7531"},"institutions":[{"id":"https://openalex.org/I2252078561","display_name":"Meta (Israel)","ror":"https://ror.org/02388em19","country_code":"IL","type":"company","lineage":["https://openalex.org/I2252078561","https://openalex.org/I4210114444"]},{"id":"https://openalex.org/I4210114444","display_name":"Meta (United States)","ror":"https://ror.org/01zbnvs85","country_code":"US","type":"company","lineage":["https://openalex.org/I4210114444"]}],"countries":["IL","US"],"is_corresponding":false,"raw_author_name":"Dejan Markovic","raw_affiliation_strings":["Facebook Reality Labs Research,Pittsburgh,PA,USA","Facebook Reality Labs Research, Pittsburgh, PA, USA"],"affiliations":[{"raw_affiliation_string":"Facebook Reality Labs Research,Pittsburgh,PA,USA","institution_ids":["https://openalex.org/I2252078561"]},{"raw_affiliation_string":"Facebook Reality Labs Research, Pittsburgh, PA, USA","institution_ids":["https://openalex.org/I4210114444"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5108760515","display_name":"Alexander Richard","orcid":"https://orcid.org/0009-0000-5173-6438"},"institutions":[{"id":"https://openalex.org/I2252078561","display_name":"Meta (Israel)","ror":"https://ror.org/02388em19","country_code":"IL","type":"company","lineage":["https://openalex.org/I2252078561","https://openalex.org/I4210114444"]},{"id":"https://openalex.org/I4210114444","display_name":"Meta (United States)","ror":"https://ror.org/01zbnvs85","country_code":"US","type":"company","lineage":["https://openalex.org/I4210114444"]}],"countries":["IL","US"],"is_corresponding":false,"raw_author_name":"Alexander Richard","raw_affiliation_strings":["Facebook Reality Labs Research,Pittsburgh,PA,USA","Facebook Reality Labs Research, Pittsburgh, PA, USA"],"affiliations":[{"raw_affiliation_string":"Facebook Reality Labs Research,Pittsburgh,PA,USA","institution_ids":["https://openalex.org/I2252078561"]},{"raw_affiliation_string":"Facebook Reality Labs Research, Pittsburgh, PA, USA","institution_ids":["https://openalex.org/I4210114444"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5002770382","display_name":"Steven Krenn","orcid":null},"institutions":[{"id":"https://openalex.org/I2252078561","display_name":"Meta (Israel)","ror":"https://ror.org/02388em19","country_code":"IL","type":"company","lineage":["https://openalex.org/I2252078561","https://openalex.org/I4210114444"]},{"id":"https://openalex.org/I4210114444","display_name":"Meta (United States)","ror":"https://ror.org/01zbnvs85","country_code":"US","type":"company","lineage":["https://openalex.org/I4210114444"]}],"countries":["IL","US"],"is_corresponding":false,"raw_author_name":"Steven Krenn","raw_affiliation_strings":["Facebook Reality Labs Research,Pittsburgh,PA,USA","Facebook Reality Labs Research, Pittsburgh, PA, USA"],"affiliations":[{"raw_affiliation_string":"Facebook Reality Labs Research,Pittsburgh,PA,USA","institution_ids":["https://openalex.org/I2252078561"]},{"raw_affiliation_string":"Facebook Reality Labs Research, Pittsburgh, PA, USA","institution_ids":["https://openalex.org/I4210114444"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5089311602","display_name":"Gladstone Alexander Butler","orcid":null},"institutions":[{"id":"https://openalex.org/I4210114444","display_name":"Meta (United States)","ror":"https://ror.org/01zbnvs85","country_code":"US","type":"company","lineage":["https://openalex.org/I4210114444"]},{"id":"https://openalex.org/I2252078561","display_name":"Meta (Israel)","ror":"https://ror.org/02388em19","country_code":"IL","type":"company","lineage":["https://openalex.org/I2252078561","https://openalex.org/I4210114444"]}],"countries":["IL","US"],"is_corresponding":false,"raw_author_name":"Gladstone A. Butler","raw_affiliation_strings":["Facebook Reality Labs Research,Pittsburgh,PA,USA","Facebook Reality Labs Research, Pittsburgh, PA, USA"],"affiliations":[{"raw_affiliation_string":"Facebook Reality Labs Research,Pittsburgh,PA,USA","institution_ids":["https://openalex.org/I2252078561"]},{"raw_affiliation_string":"Facebook Reality Labs Research, Pittsburgh, PA, USA","institution_ids":["https://openalex.org/I4210114444"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5003508045","display_name":"Fernando De la Torre","orcid":"https://orcid.org/0000-0002-5143-3709"},"institutions":[{"id":"https://openalex.org/I4210114444","display_name":"Meta (United States)","ror":"https://ror.org/01zbnvs85","country_code":"US","type":"company","lineage":["https://openalex.org/I4210114444"]},{"id":"https://openalex.org/I2252078561","display_name":"Meta (Israel)","ror":"https://ror.org/02388em19","country_code":"IL","type":"company","lineage":["https://openalex.org/I2252078561","https://openalex.org/I4210114444"]}],"countries":["IL","US"],"is_corresponding":false,"raw_author_name":"Fernando De la Torre","raw_affiliation_strings":["Facebook Reality Labs Research,Pittsburgh,PA,USA","Facebook Reality Labs Research, Pittsburgh, PA, USA"],"affiliations":[{"raw_affiliation_string":"Facebook Reality Labs Research,Pittsburgh,PA,USA","institution_ids":["https://openalex.org/I2252078561"]},{"raw_affiliation_string":"Facebook Reality Labs Research, Pittsburgh, PA, USA","institution_ids":["https://openalex.org/I4210114444"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5060280374","display_name":"Yaser Sheikh","orcid":"https://orcid.org/0000-0001-6512-9348"},"institutions":[{"id":"https://openalex.org/I4210114444","display_name":"Meta (United States)","ror":"https://ror.org/01zbnvs85","country_code":"US","type":"company","lineage":["https://openalex.org/I4210114444"]},{"id":"https://openalex.org/I2252078561","display_name":"Meta (Israel)","ror":"https://ror.org/02388em19","country_code":"IL","type":"company","lineage":["https://openalex.org/I2252078561","https://openalex.org/I4210114444"]}],"countries":["IL","US"],"is_corresponding":false,"raw_author_name":"Yaser Sheikh","raw_affiliation_strings":["Facebook Reality Labs Research,Pittsburgh,PA,USA","Facebook Reality Labs Research, Pittsburgh, PA, USA"],"affiliations":[{"raw_affiliation_string":"Facebook Reality Labs Research,Pittsburgh,PA,USA","institution_ids":["https://openalex.org/I2252078561"]},{"raw_affiliation_string":"Facebook Reality Labs Research, Pittsburgh, PA, USA","institution_ids":["https://openalex.org/I4210114444"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5072548521"],"corresponding_institution_ids":["https://openalex.org/I2252078561","https://openalex.org/I4210114444"],"apc_list":null,"apc_paid":null,"fwci":2.8949,"has_fulltext":false,"cited_by_count":26,"citation_normalized_percentile":{"value":0.91521298,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":93,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"3385","last_page":"3389"},"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/T10283","display_name":"Hearing Loss and Rehabilitation","score":0.9997000098228455,"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"}},{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9993000030517578,"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/binaural-recording","display_name":"Binaural recording","score":0.9090489149093628},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7778835296630859},{"id":"https://openalex.org/keywords/anechoic-chamber","display_name":"Anechoic chamber","score":0.7231015563011169},{"id":"https://openalex.org/keywords/head-related-transfer-function","display_name":"Head-related transfer function","score":0.5997083783149719},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.5689264535903931},{"id":"https://openalex.org/keywords/transfer-function","display_name":"Transfer function","score":0.5384535193443298},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5250927209854126},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.44259509444236755},{"id":"https://openalex.org/keywords/audio-signal-processing","display_name":"Audio signal processing","score":0.42162927985191345},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3630618453025818},{"id":"https://openalex.org/keywords/audio-signal","display_name":"Audio signal","score":0.20263803005218506},{"id":"https://openalex.org/keywords/speech-coding","display_name":"Speech coding","score":0.10846158862113953},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.08644121885299683}],"concepts":[{"id":"https://openalex.org/C201247586","wikidata":"https://www.wikidata.org/wiki/Q5612967","display_name":"Binaural recording","level":2,"score":0.9090489149093628},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7778835296630859},{"id":"https://openalex.org/C149712133","wikidata":"https://www.wikidata.org/wiki/Q332774","display_name":"Anechoic chamber","level":2,"score":0.7231015563011169},{"id":"https://openalex.org/C151382886","wikidata":"https://www.wikidata.org/wiki/Q1432854","display_name":"Head-related transfer function","level":3,"score":0.5997083783149719},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.5689264535903931},{"id":"https://openalex.org/C81299745","wikidata":"https://www.wikidata.org/wiki/Q334269","display_name":"Transfer function","level":2,"score":0.5384535193443298},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5250927209854126},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.44259509444236755},{"id":"https://openalex.org/C127220857","wikidata":"https://www.wikidata.org/wiki/Q2719318","display_name":"Audio signal processing","level":4,"score":0.42162927985191345},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3630618453025818},{"id":"https://openalex.org/C64922751","wikidata":"https://www.wikidata.org/wiki/Q4650799","display_name":"Audio signal","level":3,"score":0.20263803005218506},{"id":"https://openalex.org/C13895895","wikidata":"https://www.wikidata.org/wiki/Q3270773","display_name":"Speech coding","level":2,"score":0.10846158862113953},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.08644121885299683},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp39728.2021.9414750","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp39728.2021.9414750","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":40,"referenced_works":["https://openalex.org/W124275677","https://openalex.org/W1487212816","https://openalex.org/W1492808278","https://openalex.org/W1552314771","https://openalex.org/W1557172698","https://openalex.org/W1804765934","https://openalex.org/W1968549621","https://openalex.org/W2028673460","https://openalex.org/W2045356643","https://openalex.org/W2048909388","https://openalex.org/W2068325601","https://openalex.org/W2108668360","https://openalex.org/W2114402068","https://openalex.org/W2141998673","https://openalex.org/W2143600425","https://openalex.org/W2169132460","https://openalex.org/W2519091744","https://openalex.org/W2550143307","https://openalex.org/W2890855852","https://openalex.org/W2949382160","https://openalex.org/W2950388022","https://openalex.org/W2952218014","https://openalex.org/W2970906079","https://openalex.org/W2978559234","https://openalex.org/W2982624843","https://openalex.org/W3004940340","https://openalex.org/W3015338123","https://openalex.org/W3034742263","https://openalex.org/W3044194010","https://openalex.org/W3064752666","https://openalex.org/W3096780661","https://openalex.org/W3099330747","https://openalex.org/W3128620267","https://openalex.org/W4285719527","https://openalex.org/W6629150500","https://openalex.org/W6633389739","https://openalex.org/W6754782314","https://openalex.org/W6769767169","https://openalex.org/W6791001089","https://openalex.org/W6864424756"],"related_works":["https://openalex.org/W4294828282","https://openalex.org/W4221151737","https://openalex.org/W2163344649","https://openalex.org/W4366826909","https://openalex.org/W4327497366","https://openalex.org/W2622611424","https://openalex.org/W2145981655","https://openalex.org/W4221151007","https://openalex.org/W2089571040","https://openalex.org/W1482498986"],"abstract_inverted_index":{"Estimation":[0],"of":[1,33,37,64,104],"accurate":[2],"head-related":[3],"transfer":[4],"functions":[5],"(HRTFs)":[6],"is":[7,118],"crucial":[8],"to":[9,26,53,69],"achieve":[10],"realistic":[11],"binaural":[12,116],"acoustic":[13],"experiences.":[14],"HRTFs":[15,34,55],"depend":[16],"on":[17,74,120],"source/listener":[18],"locations":[19],"and":[20,24,91,128,139],"are":[21,142],"therefore":[22],"expensive":[23],"cumbersome":[25],"measure;":[27],"traditional":[28,70,123],"approaches":[29,71,125],"require":[30],"listener-dependent":[31],"measurements":[32],"at":[35],"thousands":[36],"distinct":[38],"spatial":[39],"directions":[40],"in":[41,84,109],"an":[42],"anechoic":[43],"chamber.":[44],"In":[45],"this":[46],"work,":[47],"we":[48],"present":[49],"a":[50,58,75,110],"data-driven":[51],"approach":[52,101],"learn":[54],"implicitly":[56],"with":[57,122],"neural":[59],"network":[60],"that":[61,80,89,113,130],"achieves":[62],"state":[63],"the":[65,114],"art":[66],"results":[67],"compared":[68],"but":[72],"relies":[73],"much":[76],"simpler":[77,90],"data":[78,95],"capture":[79],"can":[81],"be":[82],"performed":[83],"arbitrary,":[85],"non-anechoic":[86],"rooms.":[87],"Despite":[88],"less":[92],"acoustically":[93],"ideal":[94],"capture,":[96],"our":[97],"deep":[98],"learning":[99],"based":[100],"learns":[102],"HRTF":[103],"high":[105],"quality.":[106],"We":[107],"show":[108],"perceptual":[111],"study":[112],"produced":[115],"audio":[117],"ranked":[119],"par":[121],"DSP":[124],"by":[126],"humans":[127],"illustrate":[129],"interaural":[131,135],"time":[132],"differences":[133,137],"(ITDs),":[134],"level":[136],"(ILDs)":[138],"spectral":[140],"clues":[141],"accurately":[143],"estimated.":[144]},"counts_by_year":[{"year":2025,"cited_by_count":7},{"year":2024,"cited_by_count":5},{"year":2023,"cited_by_count":5},{"year":2022,"cited_by_count":7},{"year":2021,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
