{"id":"https://openalex.org/W4375868821","doi":"https://doi.org/10.1109/icassp49357.2023.10096121","title":"An End-to-End Neural Network for Image-to-Audio Transformation","display_name":"An End-to-End Neural Network for Image-to-Audio Transformation","publication_year":2023,"publication_date":"2023-05-05","ids":{"openalex":"https://openalex.org/W4375868821","doi":"https://doi.org/10.1109/icassp49357.2023.10096121"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49357.2023.10096121","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49357.2023.10096121","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2023 - 2023 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/A5100322202","display_name":"Chen Liu","orcid":"https://orcid.org/0000-0003-2000-8133"},"institutions":[{"id":"https://openalex.org/I1343180700","display_name":"Intel (United States)","ror":"https://ror.org/01ek73717","country_code":"US","type":"company","lineage":["https://openalex.org/I1343180700"]},{"id":"https://openalex.org/I165690674","display_name":"Oregon Health & Science University","ror":"https://ror.org/009avj582","country_code":"US","type":"education","lineage":["https://openalex.org/I165690674"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Liu Chen","raw_affiliation_strings":["Oregon Health and Science University,Oregon,USA","Intel Corporation, Hillsboro, Oregon, USA","Oregon Health and Science University, Oregon, USA"],"affiliations":[{"raw_affiliation_string":"Oregon Health and Science University,Oregon,USA","institution_ids":["https://openalex.org/I165690674"]},{"raw_affiliation_string":"Intel Corporation, Hillsboro, Oregon, USA","institution_ids":["https://openalex.org/I1343180700"]},{"raw_affiliation_string":"Oregon Health and Science University, Oregon, USA","institution_ids":["https://openalex.org/I165690674"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5064741703","display_name":"Michael Deisher","orcid":null},"institutions":[{"id":"https://openalex.org/I1343180700","display_name":"Intel (United States)","ror":"https://ror.org/01ek73717","country_code":"US","type":"company","lineage":["https://openalex.org/I1343180700"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Michael Deisher","raw_affiliation_strings":["Intel Corporation,Hillsboro,Oregon,USA","Intel Corporation, Hillsboro, Oregon, USA"],"affiliations":[{"raw_affiliation_string":"Intel Corporation,Hillsboro,Oregon,USA","institution_ids":["https://openalex.org/I1343180700"]},{"raw_affiliation_string":"Intel Corporation, Hillsboro, Oregon, USA","institution_ids":["https://openalex.org/I1343180700"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5040558849","display_name":"Munir Georges","orcid":"https://orcid.org/0000-0002-5542-149X"},"institutions":[{"id":"https://openalex.org/I4210106192","display_name":"Technische Hochschule Ingolstadt","ror":"https://ror.org/02bxzcy64","country_code":"DE","type":"education","lineage":["https://openalex.org/I4210106192"]},{"id":"https://openalex.org/I4210094487","display_name":"Intel (Germany)","ror":"https://ror.org/00m2x0g47","country_code":"DE","type":"company","lineage":["https://openalex.org/I1343180700","https://openalex.org/I4210094487"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Munir Georges","raw_affiliation_strings":["Intel Labs,Munich,Germany","Intel Labs, Munich, Germany","Technische Hochschule Ingolstadt"],"affiliations":[{"raw_affiliation_string":"Intel Labs,Munich,Germany","institution_ids":["https://openalex.org/I4210094487"]},{"raw_affiliation_string":"Intel Labs, Munich, Germany","institution_ids":["https://openalex.org/I4210094487"]},{"raw_affiliation_string":"Technische Hochschule Ingolstadt","institution_ids":["https://openalex.org/I4210106192"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5100322202"],"corresponding_institution_ids":["https://openalex.org/I1343180700","https://openalex.org/I165690674"],"apc_list":null,"apc_paid":null,"fwci":0.246,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.49695797,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":99},"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/T10036","display_name":"Advanced Neural Network Applications","score":0.9970999956130981,"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/T10036","display_name":"Advanced Neural Network Applications","score":0.9970999956130981,"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/T10601","display_name":"Handwritten Text Recognition Techniques","score":0.9965999722480774,"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/T10914","display_name":"Tactile and Sensory Interactions","score":0.9940999746322632,"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/computer-science","display_name":"Computer science","score":0.8267147541046143},{"id":"https://openalex.org/keywords/rendering","display_name":"Rendering (computer graphics)","score":0.7862502336502075},{"id":"https://openalex.org/keywords/end-to-end-principle","display_name":"End-to-end principle","score":0.7720756530761719},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.6604547500610352},{"id":"https://openalex.org/keywords/phone","display_name":"Phone","score":0.4680922329425812},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.44594091176986694},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.44564688205718994},{"id":"https://openalex.org/keywords/autoregressive-model","display_name":"Autoregressive model","score":0.4394858777523041},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.3629729449748993}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8267147541046143},{"id":"https://openalex.org/C205711294","wikidata":"https://www.wikidata.org/wiki/Q176953","display_name":"Rendering (computer graphics)","level":2,"score":0.7862502336502075},{"id":"https://openalex.org/C74296488","wikidata":"https://www.wikidata.org/wiki/Q2527392","display_name":"End-to-end principle","level":2,"score":0.7720756530761719},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.6604547500610352},{"id":"https://openalex.org/C2778707766","wikidata":"https://www.wikidata.org/wiki/Q202064","display_name":"Phone","level":2,"score":0.4680922329425812},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.44594091176986694},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.44564688205718994},{"id":"https://openalex.org/C159877910","wikidata":"https://www.wikidata.org/wiki/Q2202883","display_name":"Autoregressive model","level":2,"score":0.4394858777523041},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.3629729449748993},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"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/C149782125","wikidata":"https://www.wikidata.org/wiki/Q160039","display_name":"Econometrics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49357.2023.10096121","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49357.2023.10096121","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2023 - 2023 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":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":30,"referenced_works":["https://openalex.org/W1491389626","https://openalex.org/W1922126009","https://openalex.org/W2127141656","https://openalex.org/W2343052201","https://openalex.org/W2519091744","https://openalex.org/W2946200149","https://openalex.org/W2963517393","https://openalex.org/W2979371747","https://openalex.org/W2989373050","https://openalex.org/W3026874504","https://openalex.org/W3033411150","https://openalex.org/W3038172701","https://openalex.org/W3092028330","https://openalex.org/W3143013427","https://openalex.org/W3161296985","https://openalex.org/W3196001064","https://openalex.org/W3197294703","https://openalex.org/W4286950013","https://openalex.org/W4287761884","https://openalex.org/W6629590909","https://openalex.org/W6760749843","https://openalex.org/W6763832098","https://openalex.org/W6777694618","https://openalex.org/W6778823374","https://openalex.org/W6779337556","https://openalex.org/W6779871621","https://openalex.org/W6783867762","https://openalex.org/W6792707330","https://openalex.org/W6802142237","https://openalex.org/W6917585676"],"related_works":["https://openalex.org/W3179968364","https://openalex.org/W2171218219","https://openalex.org/W1972271943","https://openalex.org/W2150410159","https://openalex.org/W4327525404","https://openalex.org/W4287185323","https://openalex.org/W3150905897","https://openalex.org/W1999612375","https://openalex.org/W1520183331","https://openalex.org/W2061937230"],"abstract_inverted_index":{"This":[0],"paper":[1],"describes":[2],"an":[3],"end-to-end":[4],"(E2E)":[5],"neural":[6,77],"architecture":[7],"for":[8,33],"the":[9,29,39,92,95],"audio":[10],"rendering":[11],"of":[12,15,31],"small":[13],"portions":[14],"display":[16],"content":[17],"on":[18],"low":[19],"resource":[20],"personal":[21],"computing":[22],"devices.":[23],"It":[24],"is":[25,55,65,80,99,120],"intended":[26],"to":[27,57,71,117],"address":[28,118],"problem":[30],"accessibility":[32],"vision-impaired":[34],"or":[35],"vision-distracted":[36],"users":[37],"at":[38],"hardware":[40],"level.":[41],"Neural":[42],"image-to-text":[43],"(ITT)":[44],"and":[45,51,68,82,102],"text-to-speech":[46],"(TTS)":[47],"approaches":[48],"are":[49,86],"reviewed":[50],"a":[52,62,72,108],"new":[53],"technique":[54],"introduced":[56],"efficiently":[58],"integrate":[59],"them":[60],"in":[61,111],"way":[63],"that":[64,79],"both":[66],"efficient":[67,81],"back-propagate-able,":[69],"leading":[70],"non-autoregressive":[73],"E2E":[74,97],"image-to-speech":[75],"(ITS)":[76],"network":[78],"trainable.":[83],"Experimental":[84],"results":[85],"presented":[87],"showing":[88],"that,":[89],"compared":[90],"with":[91,107],"non-E2E":[93],"approach,":[94],"proposed":[96],"system":[98],"29%":[100],"faster":[101],"uses":[103],"19%":[104],"fewer":[105],"parameters":[106],"2%":[109],"reduction":[110],"phone":[112],"accuracy.":[113],"A":[114],"future":[115],"direction":[116],"accuracy":[119],"presented.":[121]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1}],"updated_date":"2026-02-25T08:12:03.925757","created_date":"2025-10-10T00:00:00"}