{"id":"https://openalex.org/W2914781455","doi":"https://doi.org/10.1109/slt.2018.8639551","title":"LSTM Language Model Adaptation with Images and Titles for Multimedia Automatic Speech Recognition","display_name":"LSTM Language Model Adaptation with Images and Titles for Multimedia Automatic Speech Recognition","publication_year":2018,"publication_date":"2018-12-01","ids":{"openalex":"https://openalex.org/W2914781455","doi":"https://doi.org/10.1109/slt.2018.8639551","mag":"2914781455"},"language":"en","primary_location":{"id":"doi:10.1109/slt.2018.8639551","is_oa":false,"landing_page_url":"https://doi.org/10.1109/slt.2018.8639551","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 IEEE Spoken Language Technology Workshop (SLT)","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/A5060841056","display_name":"Yasufumi Moriya","orcid":null},"institutions":[{"id":"https://openalex.org/I42934936","display_name":"Dublin City University","ror":"https://ror.org/04a1a1e81","country_code":"IE","type":"education","lineage":["https://openalex.org/I42934936"]}],"countries":["IE"],"is_corresponding":true,"raw_author_name":"Yasufumi Moriya","raw_affiliation_strings":["ADAPT Centre, Dublin City University, Dublin 9, Ireland"],"affiliations":[{"raw_affiliation_string":"ADAPT Centre, Dublin City University, Dublin 9, Ireland","institution_ids":["https://openalex.org/I42934936"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5018481328","display_name":"Gareth J. F. Jones","orcid":"https://orcid.org/0000-0003-2923-8365"},"institutions":[{"id":"https://openalex.org/I42934936","display_name":"Dublin City University","ror":"https://ror.org/04a1a1e81","country_code":"IE","type":"education","lineage":["https://openalex.org/I42934936"]}],"countries":["IE"],"is_corresponding":false,"raw_author_name":"Gareth J. F. Jones","raw_affiliation_strings":["ADAPT Centre, Dublin City University, Dublin 9, Ireland"],"affiliations":[{"raw_affiliation_string":"ADAPT Centre, Dublin City University, Dublin 9, Ireland","institution_ids":["https://openalex.org/I42934936"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5060841056"],"corresponding_institution_ids":["https://openalex.org/I42934936"],"apc_list":null,"apc_paid":null,"fwci":1.149,"has_fulltext":false,"cited_by_count":15,"citation_normalized_percentile":{"value":0.84211199,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":98},"biblio":{"volume":"5","issue":null,"first_page":"219","last_page":"226"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9988999962806702,"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":0.9988999962806702,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9984999895095825,"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/T11309","display_name":"Music and Audio Processing","score":0.9983999729156494,"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/perplexity","display_name":"Perplexity","score":0.9114469289779663},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8773756623268127},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.7522602081298828},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6520049571990967},{"id":"https://openalex.org/keywords/adaptation","display_name":"Adaptation (eye)","score":0.5948656797409058},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5872735977172852},{"id":"https://openalex.org/keywords/transcription","display_name":"Transcription (linguistics)","score":0.5663743615150452},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5387040376663208},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.526881754398346},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5242971777915955},{"id":"https://openalex.org/keywords/ranking","display_name":"Ranking (information retrieval)","score":0.49808835983276367},{"id":"https://openalex.org/keywords/recurrent-neural-network","display_name":"Recurrent neural network","score":0.48471498489379883},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.44430339336395264},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.4261462092399597},{"id":"https://openalex.org/keywords/rendering","display_name":"Rendering (computer graphics)","score":0.424483984708786},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.09255614876747131}],"concepts":[{"id":"https://openalex.org/C100279451","wikidata":"https://www.wikidata.org/wiki/Q372193","display_name":"Perplexity","level":3,"score":0.9114469289779663},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8773756623268127},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.7522602081298828},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6520049571990967},{"id":"https://openalex.org/C139807058","wikidata":"https://www.wikidata.org/wiki/Q352374","display_name":"Adaptation (eye)","level":2,"score":0.5948656797409058},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5872735977172852},{"id":"https://openalex.org/C179926584","wikidata":"https://www.wikidata.org/wiki/Q207714","display_name":"Transcription (linguistics)","level":2,"score":0.5663743615150452},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5387040376663208},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.526881754398346},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5242971777915955},{"id":"https://openalex.org/C189430467","wikidata":"https://www.wikidata.org/wiki/Q7293293","display_name":"Ranking (information retrieval)","level":2,"score":0.49808835983276367},{"id":"https://openalex.org/C147168706","wikidata":"https://www.wikidata.org/wiki/Q1457734","display_name":"Recurrent neural network","level":3,"score":0.48471498489379883},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.44430339336395264},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.4261462092399597},{"id":"https://openalex.org/C205711294","wikidata":"https://www.wikidata.org/wiki/Q176953","display_name":"Rendering (computer graphics)","level":2,"score":0.424483984708786},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.09255614876747131},{"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},{"id":"https://openalex.org/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","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/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/slt.2018.8639551","is_oa":false,"landing_page_url":"https://doi.org/10.1109/slt.2018.8639551","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 IEEE Spoken Language Technology Workshop (SLT)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.8100000023841858,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320320847","display_name":"Science Foundation Ireland","ror":"https://ror.org/0271asj38"},{"id":"https://openalex.org/F4320320865","display_name":"Dublin City University","ror":"https://ror.org/04a1a1e81"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":45,"referenced_works":["https://openalex.org/W14941018","https://openalex.org/W179875071","https://openalex.org/W1494198834","https://openalex.org/W1514535095","https://openalex.org/W1521626219","https://openalex.org/W1524333225","https://openalex.org/W1631260214","https://openalex.org/W1686810756","https://openalex.org/W1895577753","https://openalex.org/W1984076147","https://openalex.org/W2033256038","https://openalex.org/W2064675550","https://openalex.org/W2097927681","https://openalex.org/W2108598243","https://openalex.org/W2134670479","https://openalex.org/W2153579005","https://openalex.org/W2158195707","https://openalex.org/W2163605009","https://openalex.org/W2288371874","https://openalex.org/W2401969231","https://openalex.org/W2402146185","https://openalex.org/W2493916176","https://openalex.org/W2575842049","https://openalex.org/W2586850765","https://openalex.org/W2714726990","https://openalex.org/W2752172973","https://openalex.org/W2899771611","https://openalex.org/W2962835968","https://openalex.org/W2962866381","https://openalex.org/W2963499246","https://openalex.org/W4246962055","https://openalex.org/W4294170691","https://openalex.org/W4295803813","https://openalex.org/W6630875275","https://openalex.org/W6631362777","https://openalex.org/W6636811518","https://openalex.org/W6637373629","https://openalex.org/W6674504384","https://openalex.org/W6679792166","https://openalex.org/W6682691769","https://openalex.org/W6684191040","https://openalex.org/W6684953378","https://openalex.org/W6712930963","https://openalex.org/W6743384090","https://openalex.org/W6756040250"],"related_works":["https://openalex.org/W2610308580","https://openalex.org/W2169518243","https://openalex.org/W2252095989","https://openalex.org/W4322096525","https://openalex.org/W2551914602","https://openalex.org/W4281893144","https://openalex.org/W2105076537","https://openalex.org/W2050138804","https://openalex.org/W2151348424","https://openalex.org/W1494910745"],"abstract_inverted_index":{"Transcription":[0],"of":[1,16,73,77,86,140,162],"multimedia":[2],"data":[3,31],"sources":[4],"is":[5,69,95,104,126,144],"often":[6],"a":[7,24,52,60,82],"challenging":[8],"automatic":[9],"speech":[10],"recognition":[11],"(ASR)":[12],"task.":[13],"The":[14],"incorporation":[15],"visual":[17],"features":[18],"as":[19,23],"additional":[20],"contextual":[21],"information":[22],"means":[25],"to":[26,50],"improve":[27],"ASR":[28,42,117],"for":[29,115],"this":[30],"has":[32],"recently":[33],"drawn":[34],"attention":[35],"from":[36],"researchers.":[37],"Our":[38,66],"investigation":[39],"extends":[40],"existing":[41,75],"methods":[43],"by":[44,93,128],"using":[45],"images":[46],"and":[47,80,110,150],"video":[48,111,151],"titles":[49],"adapt":[51],"recurrent":[53],"neural":[54],"network":[55],"(RNN)":[56],"language":[57,67],"model":[58,68,103,156],"with":[59,106],"long-short":[61],"term":[62],"memory":[63],"(LSTM)":[64],"network.":[65],"tested":[70],"on":[71,81,97,131],"transcription":[72],"an":[74],"corpus":[76,84],"instruction":[78],"videos":[79],"new":[83],"consisting":[85],"lecture":[87],"videos.":[88],"Consistent":[89],"reduction":[90],"in":[91,159],"perplexity":[92],"5-10":[94],"observed":[96],"both":[98,132,147],"datasets.":[99,133],"When":[100],"the":[101,107,121,136,141,155,160],"non-adapted":[102],"combined":[105],"image":[108,148],"adaptation":[109,113,149,153],"title":[112,152],"models":[114],"n-best":[116],"hypotheses":[118],"re-ranking,":[119],"additionally":[120],"word":[122,138],"error":[123],"rate":[124],"(WER)":[125],"decreased":[127],"around":[129],"0.5%":[130],"By":[134],"analysing":[135],"output":[137],"probabilities":[139],"model,":[142],"it":[143],"found":[145],"that":[146],"give":[154],"more":[157],"confidence":[158],"choice":[161],"contextually":[163],"correct":[164],"informative":[165],"words.":[166]},"counts_by_year":[{"year":2024,"cited_by_count":2},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":5},{"year":2019,"cited_by_count":3},{"year":2018,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}