{"id":"https://openalex.org/W3029201431","doi":null,"title":"Earballs: Neural Transmodal Translation.","display_name":"Earballs: Neural Transmodal Translation.","publication_year":2020,"publication_date":"2020-05-27","ids":{"openalex":"https://openalex.org/W3029201431","mag":"3029201431"},"language":"en","primary_location":{"id":"mag:3029201431","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2005.13291v1","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"arXiv (Cornell University)","raw_type":null},"volume":null,"type":"preprint","is_traditional":true,"indexed_in":[],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/abs/2005.13291v1","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Andrew Port","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Andrew Port","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5089289422","display_name":"Chelhwon Kim","orcid":"https://orcid.org/0000-0002-7510-3368","observed_orcids":["https://orcid.org/0000-0002-7510-3368"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chelhwon Kim","raw_affiliation_strings":[],"raw_orcid":"https://orcid.org/0000-0002-7510-3368","affiliations":[]},{"author_position":"last","author":{"id":null,"display_name":"Mitesh Patel","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Mitesh Patel","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.6937999725341797,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.6937999725341797,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/T10860","display_name":"Speech and Audio Processing","score":0.0820000022649765,"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":0.08070000261068344,"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/generative-adversarial-networks","display_name":"generative adversarial networks","score":0.7749999761581421},{"id":"https://openalex.org/keywords/audio-classification","display_name":"audio classification","score":0.38199999928474426},{"id":"https://openalex.org/keywords/facial-images","display_name":"face images","score":0.5080000162124634},{"id":"https://openalex.org/keywords/audiovisual-communication","display_name":"audiovisual communication","score":0.44999998807907104}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7023576498031616},{"id":"https://openalex.org/C176217482","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Metric (unit)","level":2,"score":0.6641753911972046},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6119177341461182},{"id":"https://openalex.org/C83665646","wikidata":"https://www.wikidata.org/wiki/Q42139305","display_name":"Feature vector","level":2,"score":0.584671139717102},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.5354049205780029},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.4730983078479767},{"id":"https://openalex.org/C88485024","wikidata":"https://www.wikidata.org/wiki/Q1054571","display_name":"Cepstrum","level":2,"score":0.4620724320411682},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4555737376213074},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4211719036102295},{"id":"https://openalex.org/C120174047","wikidata":"https://www.wikidata.org/wiki/Q847073","display_name":"Euclidean distance","level":2,"score":0.41211721301078796},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.22458416223526},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C21547014","wikidata":"https://www.wikidata.org/wiki/Q1423657","display_name":"Operations management","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"mag:3029201431","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2005.13291v1","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"arXiv (Cornell University)","raw_type":null}],"best_oa_location":{"id":"mag:3029201431","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2005.13291v1","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"arXiv (Cornell University)","raw_type":null},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":23,"referenced_works":["https://openalex.org/W84813673","https://openalex.org/W1494198834","https://openalex.org/W1635512741","https://openalex.org/W1822494353","https://openalex.org/W2005943303","https://openalex.org/W2096733369","https://openalex.org/W2099471712","https://openalex.org/W2103869314","https://openalex.org/W2133797163","https://openalex.org/W2157558673","https://openalex.org/W2179042386","https://openalex.org/W2392029795","https://openalex.org/W2513140567","https://openalex.org/W2598581049","https://openalex.org/W2606176153","https://openalex.org/W2623767209","https://openalex.org/W2807722546","https://openalex.org/W2962793481","https://openalex.org/W2962879692","https://openalex.org/W2963207607","https://openalex.org/W2963896050","https://openalex.org/W2964019233","https://openalex.org/W3160431667"],"related_works":["https://openalex.org/W3194965282","https://openalex.org/W3115250497","https://openalex.org/W3037600971","https://openalex.org/W2515372520","https://openalex.org/W4402670354","https://openalex.org/W4319299923","https://openalex.org/W2122591539","https://openalex.org/W6891869140","https://openalex.org/W1849347704","https://openalex.org/W7064201761"],"abstract_inverted_index":{"As":[0],"is":[1,8,109],"expressed":[2],"in":[3,77,175],"the":[4,87,126,138,166],"adage":[5],"a":[10,24,29,47,65,78,99,114,131,142,170],"picture":[7],"worth":[9],"thousand":[11],"words,":[12],"when":[13],"using":[14,57],"spoken":[15],"language":[16],"to":[17,38,53,70,112,182],"communicate":[18],"visual":[19,40,72],"information,":[20],"brevity":[21],"can":[22,95],"be":[23,96],"challenge.":[25],"This":[26],"work":[27],"describes":[28],"novel":[30],"technique":[31,151],"for":[32],"leveraging":[33],"machine":[34],"learned":[35],"feature":[36,90,123],"embeddings":[37],"translate":[39],"(and":[41],"other":[42],"types":[43],"of)":[44],"information":[45,56],"into":[46,89,125,157],"perceptual":[48],"audio":[49,133,164,185],"domain,":[50],"allowing":[51],"users":[52,179],"perceive":[54],"this":[55,85,119,150],"only":[58],"their":[59],"aural":[60],"faculty.":[61],"The":[62],"system":[63],"uses":[64],"pretrained":[66],"image":[67],"embedding":[68],"network":[69,107],"extract":[71],"features":[73],"and":[74,174],"embed":[75],"them":[76],"compact":[79],"subset":[80],"of":[81,102,122,155,187],"Euclidean":[82,139],"space":[83,121,128],"--":[84],"converts":[86],"images":[88,154],"vectors":[91,124],"whose":[92],"$L^2$":[93],"distances":[94],"used":[97,111],"as":[98],"meaningful":[100],"measure":[101],"similarity.":[103],"A":[104],"generative":[105],"adversarial":[106],"(GAN)":[108],"then":[110],"find":[113],"distance":[115,146],"preserving":[116,172],"map":[117],"from":[118],"metric":[120,127,140,171],"defined":[129],"by":[130,152],"target":[132,163],"dataset":[134],"equipped":[135],"with":[136],"either":[137],"or":[141],"mel-frequency":[143],"cepstrum-based":[144],"psychoacoustic":[145],"metric.":[147],"We":[148],"demonstrate":[149],"translating":[153],"faces":[156],"human":[158,176],"speech-like":[159],"audio.":[160],"For":[161],"both":[162],"metrics,":[165],"GAN":[167],"successfully":[168],"found":[169],"mapping,":[173],"subject":[177],"tests,":[178],"were":[180],"able":[181],"accurately":[183],"classify":[184],"translations":[186],"faces.":[188]},"counts_by_year":[{"year":2020,"cited_by_count":1}],"updated_date":"2026-11-04T10:54:05.112534","created_date":"2020-06-05T00:00:00"}