{"id":"https://openalex.org/W3046495372","doi":"https://doi.org/10.21437/interspeech.2020-2870","title":"Evaluating Automatically Generated Phoneme Captions for Images","display_name":"Evaluating Automatically Generated Phoneme Captions for Images","publication_year":2020,"publication_date":"2020-10-25","ids":{"openalex":"https://openalex.org/W3046495372","doi":"https://doi.org/10.21437/interspeech.2020-2870","mag":"3046495372"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2020-2870","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2020-2870","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2020","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2007.15916","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5024937302","display_name":"Justin van der Hout","orcid":null},"institutions":[{"id":"https://openalex.org/I98358874","display_name":"Delft University of Technology","ror":"https://ror.org/02e2c7k09","country_code":"NL","type":"education","lineage":["https://openalex.org/I98358874"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Justin van der Hout","raw_affiliation_strings":["(Delft University of Technology)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"(Delft University of Technology)","institution_ids":["https://openalex.org/I98358874"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5082683394","display_name":"Zolt\u00e1n D\u2019Haese","orcid":null},"institutions":[{"id":"https://openalex.org/I99464096","display_name":"KU Leuven","ror":"https://ror.org/05f950310","country_code":"BE","type":"education","lineage":["https://openalex.org/I99464096"]}],"countries":["BE"],"is_corresponding":false,"raw_author_name":"Zolt\u00e1n D\u2019Haese","raw_affiliation_strings":["Katholieke Universiteit Leuven"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Katholieke Universiteit Leuven","institution_ids":["https://openalex.org/I99464096"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5004778663","display_name":"Mark Hasegawa\u2010Johnson","orcid":"https://orcid.org/0000-0002-5631-2893"},"institutions":[{"id":"https://openalex.org/I157725225","display_name":"University of Illinois Urbana-Champaign","ror":"https://ror.org/047426m28","country_code":"US","type":"education","lineage":["https://openalex.org/I157725225"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Mark Hasegawa-Johnson","raw_affiliation_strings":["***University of Illinois at Urbana-Champaign"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"***University of Illinois at Urbana-Champaign","institution_ids":["https://openalex.org/I157725225"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5048860892","display_name":"Odette Scharenborg","orcid":"https://orcid.org/0000-0003-0693-8852"},"institutions":[{"id":"https://openalex.org/I98358874","display_name":"Delft University of Technology","ror":"https://ror.org/02e2c7k09","country_code":"NL","type":"education","lineage":["https://openalex.org/I98358874"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Odette Scharenborg","raw_affiliation_strings":["(Delft University of Technology)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"(Delft University of Technology)","institution_ids":["https://openalex.org/I98358874"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"2317","last_page":"2321"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":1.0,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":1.0,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9965999722480774,"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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9959999918937683,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/metric","display_name":"Metric (unit)","score":0.8117929100990295},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.7897732257843018},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7392314672470093},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.6035975813865662},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5985682010650635},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.582007884979248},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5381966233253479},{"id":"https://openalex.org/keywords/correlation","display_name":"Correlation","score":0.468608021736145},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4222673177719116},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.15595480799674988}],"concepts":[{"id":"https://openalex.org/C176217482","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Metric (unit)","level":2,"score":0.8117929100990295},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.7897732257843018},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7392314672470093},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.6035975813865662},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5985682010650635},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.582007884979248},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5381966233253479},{"id":"https://openalex.org/C117220453","wikidata":"https://www.wikidata.org/wiki/Q5172842","display_name":"Correlation","level":2,"score":0.468608021736145},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4222673177719116},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.15595480799674988},{"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/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"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}],"mesh":[],"locations_count":5,"locations":[{"id":"doi:10.21437/interspeech.2020-2870","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2020-2870","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2020","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2007.15916","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2007.15916","pdf_url":"https://arxiv.org/pdf/2007.15916","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"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":"","raw_type":null},{"id":"pmh:tud:oai:tudelft.nl:uuid:d1373fda-1ee3-42c0-96d2-a2f44d668d82","is_oa":true,"landing_page_url":"http://resolver.tudelft.nl/uuid:d1373fda-1ee3-42c0-96d2-a2f44d668d82","pdf_url":"http://resolver.tudelft.nl/uuid:d1373fda-1ee3-42c0-96d2-a2f44d668d82","source":{"id":"https://openalex.org/S4306401843","display_name":"Data Archiving and Networked Services (DANS)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1322597698","host_organization_name":"Royal Netherlands Academy of Arts and Sciences","host_organization_lineage":["https://openalex.org/I1322597698"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Proceedings of Interspeech 2020","raw_type":"info:eu-repo/semantics/conferencepaper"},{"id":"mag:3046495372","is_oa":true,"landing_page_url":"http://arxiv.org/pdf/2007.15916.pdf","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"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},{"id":"doi:10.48550/arxiv.2007.15916","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2007.15916","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"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":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2007.15916","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2007.15916","pdf_url":"https://arxiv.org/pdf/2007.15916","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"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":"","raw_type":null},"sustainable_development_goals":[{"score":0.6800000071525574,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":14,"referenced_works":["https://openalex.org/W1482114536","https://openalex.org/W2038721957","https://openalex.org/W2101105183","https://openalex.org/W2119775030","https://openalex.org/W2123301721","https://openalex.org/W2154652894","https://openalex.org/W2168322495","https://openalex.org/W2347145335","https://openalex.org/W2729046720","https://openalex.org/W2962835968","https://openalex.org/W2962862718","https://openalex.org/W2963260927","https://openalex.org/W2964115348","https://openalex.org/W3204007566"],"related_works":["https://openalex.org/W3096249149","https://openalex.org/W2736876693","https://openalex.org/W1550647568","https://openalex.org/W2857898790","https://openalex.org/W2051884718","https://openalex.org/W2155072375","https://openalex.org/W7082836","https://openalex.org/W1601571016","https://openalex.org/W2993145789","https://openalex.org/W3038482060","https://openalex.org/W2811672742","https://openalex.org/W2257902562","https://openalex.org/W2009734203","https://openalex.org/W2965127334","https://openalex.org/W2134591869","https://openalex.org/W1989284072","https://openalex.org/W3146136731","https://openalex.org/W2800078807","https://openalex.org/W2014979411","https://openalex.org/W2952712483"],"abstract_inverted_index":{"Image2Speech":[0,29,46,117,140],"is":[1,109],"the":[2,20,44,49,74,82,101,105,110,116,124,139],"relatively":[3],"new":[4],"task":[5,141],"of":[6,11,22,38,60,72,81,149],"generating":[7],"a":[8],"spoken":[9],"description":[10],"an":[12,17,28],"image.":[13,75],"This":[14,41],"paper":[15],"presents":[16],"investigation":[18],"into":[19,58],"evaluation":[21],"this":[23],"task.":[24,118],"For":[25],"this,":[26],"first":[27],"system":[30,42,47],"was":[31],"implemented":[32],"which":[33],"generates":[34],"image":[35],"captions":[36,55,63],"consisting":[37],"phoneme":[39,54],"sequences.":[40],"outperformed":[43],"original":[45],"on":[48],"Flickr8k":[50],"corpus.":[51],"Subsequently,":[52],"these":[53,87],"were":[56,64,84],"converted":[57],"sentences":[59],"words.":[61,133],"The":[62],"rated":[65],"by":[66,123],"human":[67,88,97],"evaluators":[68],"for":[69,115,138],"their":[70,129],"goodness":[71],"describing":[73],"Finally,":[76],"several":[77],"objective":[78],"metric":[79,114,137],"scores":[80],"results":[83],"correlated":[85],"with":[86,96],"ratings.":[89],"Although":[90],"BLEU4":[91],"does":[92],"not":[93],"perfectly":[94],"correlate":[95],"ratings,":[98],"it":[99],"obtained":[100],"highest":[102],"correlation":[103],"among":[104],"investigated":[106],"metrics,":[107],"and":[108],"best":[111],"currently":[112],"existing":[113],"Current":[119],"metrics":[120],"are":[121],"limited":[122],"fact":[125],"that":[126],"they":[127],"assume":[128,143],"input":[130,145],"to":[131,146],"be":[132,147],"A":[134],"more":[135],"appropriate":[136],"should":[142],"its":[144],"parts":[148],"words,":[150],"i.e.":[151],"phonemes,":[152],"instead.":[153]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}
