{"id":"https://openalex.org/W2939311817","doi":"https://doi.org/10.1109/icassp.2019.8683724","title":"Multimodal Speaker Adaptation of Acoustic Model and Language Model for Asr Using Speaker Face Embedding","display_name":"Multimodal Speaker Adaptation of Acoustic Model and Language Model for Asr Using Speaker Face Embedding","publication_year":2019,"publication_date":"2019-04-17","ids":{"openalex":"https://openalex.org/W2939311817","doi":"https://doi.org/10.1109/icassp.2019.8683724","mag":"2939311817"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2019.8683724","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2019.8683724","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2019 - 2019 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/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, Ireland"],"affiliations":[{"raw_affiliation_string":"ADAPT Centre, Dublin City University, 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, Ireland"],"affiliations":[{"raw_affiliation_string":"ADAPT Centre, Dublin City University, 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":0.4976,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.61599362,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"8643","last_page":"8647"},"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9988999962806702,"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/T11448","display_name":"Face recognition and analysis","score":0.9984999895095825,"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/computer-science","display_name":"Computer science","score":0.8319891095161438},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7949187159538269},{"id":"https://openalex.org/keywords/gesture","display_name":"Gesture","score":0.7300983667373657},{"id":"https://openalex.org/keywords/transcription","display_name":"Transcription (linguistics)","score":0.6635518670082092},{"id":"https://openalex.org/keywords/speaker-diarisation","display_name":"Speaker diarisation","score":0.642684817314148},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.6178830862045288},{"id":"https://openalex.org/keywords/adaptation","display_name":"Adaptation (eye)","score":0.5890456438064575},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.574665904045105},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.5667321681976318},{"id":"https://openalex.org/keywords/face","display_name":"Face (sociological concept)","score":0.5510721802711487},{"id":"https://openalex.org/keywords/acoustic-model","display_name":"Acoustic model","score":0.5115183591842651},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.42539775371551514},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.38518744707107544},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.34580525755882263},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.3166061043739319},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.10033807158470154}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8319891095161438},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7949187159538269},{"id":"https://openalex.org/C207347870","wikidata":"https://www.wikidata.org/wiki/Q371174","display_name":"Gesture","level":2,"score":0.7300983667373657},{"id":"https://openalex.org/C179926584","wikidata":"https://www.wikidata.org/wiki/Q207714","display_name":"Transcription (linguistics)","level":2,"score":0.6635518670082092},{"id":"https://openalex.org/C149838564","wikidata":"https://www.wikidata.org/wiki/Q7574248","display_name":"Speaker diarisation","level":3,"score":0.642684817314148},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.6178830862045288},{"id":"https://openalex.org/C139807058","wikidata":"https://www.wikidata.org/wiki/Q352374","display_name":"Adaptation (eye)","level":2,"score":0.5890456438064575},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.574665904045105},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.5667321681976318},{"id":"https://openalex.org/C2779304628","wikidata":"https://www.wikidata.org/wiki/Q3503480","display_name":"Face (sociological concept)","level":2,"score":0.5510721802711487},{"id":"https://openalex.org/C155635449","wikidata":"https://www.wikidata.org/wiki/Q4674699","display_name":"Acoustic model","level":3,"score":0.5115183591842651},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.42539775371551514},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.38518744707107544},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.34580525755882263},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.3166061043739319},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.10033807158470154},{"id":"https://openalex.org/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","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":"doi:10.1109/icassp.2019.8683724","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2019.8683724","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2019 - 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.800000011920929}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":37,"referenced_works":["https://openalex.org/W179875071","https://openalex.org/W1494198834","https://openalex.org/W1524333225","https://openalex.org/W1631260214","https://openalex.org/W2015394094","https://openalex.org/W2020755048","https://openalex.org/W2045317385","https://openalex.org/W2064675550","https://openalex.org/W2079623482","https://openalex.org/W2096391593","https://openalex.org/W2097927681","https://openalex.org/W2115252128","https://openalex.org/W2126618487","https://openalex.org/W2150769028","https://openalex.org/W2158195707","https://openalex.org/W2158387459","https://openalex.org/W2194775991","https://openalex.org/W2288371874","https://openalex.org/W2402146185","https://openalex.org/W2525932165","https://openalex.org/W2551572271","https://openalex.org/W2584561145","https://openalex.org/W2714726990","https://openalex.org/W2899274165","https://openalex.org/W2914781455","https://openalex.org/W2952746495","https://openalex.org/W2962866381","https://openalex.org/W2972972637","https://openalex.org/W4214784823","https://openalex.org/W6631362777","https://openalex.org/W6674504384","https://openalex.org/W6677618333","https://openalex.org/W6678704754","https://openalex.org/W6712930963","https://openalex.org/W6713726233","https://openalex.org/W6755559483","https://openalex.org/W6759122735"],"related_works":["https://openalex.org/W2206035908","https://openalex.org/W2149220986","https://openalex.org/W4247736853","https://openalex.org/W2162158162","https://openalex.org/W1493012537","https://openalex.org/W1999004162","https://openalex.org/W2175373321","https://openalex.org/W2125642021","https://openalex.org/W1521049138","https://openalex.org/W2023466863"],"abstract_inverted_index":{"We":[0,29,81],"present":[1,83],"an":[2],"investigation":[3,47],"into":[4,42,94],"the":[5,8,12,37,58,69,73],"adaptation":[6,67],"of":[7,25,39,60,63,68],"acoustic":[9,70],"model":[10,14,71,75],"and":[11,72,91],"language":[13,74],"for":[15,23,57,99],"automatic":[16],"speech":[17],"recognition":[18],"(ASR)":[19],"using":[20,66],"speaker":[21],"face":[22,78],"transcription":[24,59],"a":[26,49,61],"multimedia":[27],"dataset.":[28],"begin":[30],"by":[31],"overviewing":[32],"relevant":[33],"previous":[34],"work":[35],"on":[36,101],"integration":[38],"visual":[40],"signals":[41],"ASR":[43,95],"systems.":[44],"Our":[45],"experimental":[46],"shows":[48],"small":[50],"improvement":[51],"in":[52],"word":[53],"error":[54],"rate":[55],"(WER)":[56],"collection":[62],"instruction":[64],"videos":[65],"with":[76],"fixed-length":[77],"embedding":[79],"vectors.":[80],"also":[82],"potential":[84],"approaches":[85],"to":[86],"integrating":[87],"human":[88],"facial":[89],"information,":[90],"body":[92],"gestures":[93],"as":[96],"further":[97],"directions":[98],"research":[100],"this":[102],"topic.":[103]},"counts_by_year":[{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":1},{"year":2019,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}