{"id":"https://openalex.org/W2570575067","doi":"https://doi.org/10.1007/s10844-016-0438-z","title":"An audio-visual corpus for multimodal automatic speech recognition","display_name":"An audio-visual corpus for multimodal automatic speech recognition","publication_year":2017,"publication_date":"2017-01-07","ids":{"openalex":"https://openalex.org/W2570575067","doi":"https://doi.org/10.1007/s10844-016-0438-z","mag":"2570575067"},"language":"en","primary_location":{"id":"doi:10.1007/s10844-016-0438-z","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s10844-016-0438-z","pdf_url":"https://link.springer.com/content/pdf/10.1007%2Fs10844-016-0438-z.pdf","source":{"id":"https://openalex.org/S36033921","display_name":"Journal of Intelligent Information Systems","issn_l":"0925-9902","issn":["0925-9902","1573-7675"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Intelligent Information Systems","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://link.springer.com/content/pdf/10.1007%2Fs10844-016-0438-z.pdf","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5079397804","display_name":"Andrzej Czy\u017cewski","orcid":"https://orcid.org/0000-0001-9159-8658"},"institutions":[{"id":"https://openalex.org/I169333911","display_name":"Gda\u0144sk University of Technology","ror":"https://ror.org/006x4sc24","country_code":"PL","type":"education","lineage":["https://openalex.org/I169333911"]}],"countries":["PL"],"is_corresponding":false,"raw_author_name":"Andrzej Czyzewski","raw_affiliation_strings":["Faculty of Electronics, Telecommunications and Informatics, Multimedia Systems Department, Gdansk University of Technology, Gdansk, Poland","Faculty of Electronics, Telecommunications and Informatics, Multimedia Systems Department, Gdansk University of Technology, ul. Narutowicza 11/12, 80-233, Gdansk, Poland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Faculty of Electronics, Telecommunications and Informatics, Multimedia Systems Department, Gdansk University of Technology, Gdansk, Poland","institution_ids":["https://openalex.org/I169333911"]},{"raw_affiliation_string":"Faculty of Electronics, Telecommunications and Informatics, Multimedia Systems Department, Gdansk University of Technology, ul. Narutowicza 11/12, 80-233, Gdansk, Poland","institution_ids":["https://openalex.org/I169333911"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5033154448","display_name":"Bo\u017cena Kostek","orcid":"https://orcid.org/0000-0001-6288-2908"},"institutions":[{"id":"https://openalex.org/I169333911","display_name":"Gda\u0144sk University of Technology","ror":"https://ror.org/006x4sc24","country_code":"PL","type":"education","lineage":["https://openalex.org/I169333911"]}],"countries":["PL"],"is_corresponding":false,"raw_author_name":"Bozena Kostek","raw_affiliation_strings":["Faculty of Electronics, Telecommunications and Informatics, Audio Acoustics Laboratory, Gdansk University of Technology, Gdansk, Poland","Faculty of Electronics, Telecommunications and Informatics, Audio Acoustics Laboratory, Gdansk University of Technology, ul. Narutowicza 11/12, 80-233, Gdansk, Poland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Faculty of Electronics, Telecommunications and Informatics, Audio Acoustics Laboratory, Gdansk University of Technology, Gdansk, Poland","institution_ids":["https://openalex.org/I169333911"]},{"raw_affiliation_string":"Faculty of Electronics, Telecommunications and Informatics, Audio Acoustics Laboratory, Gdansk University of Technology, ul. Narutowicza 11/12, 80-233, Gdansk, Poland","institution_ids":["https://openalex.org/I169333911"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5064015953","display_name":"Piotr Bratoszewski","orcid":null},"institutions":[{"id":"https://openalex.org/I169333911","display_name":"Gda\u0144sk University of Technology","ror":"https://ror.org/006x4sc24","country_code":"PL","type":"education","lineage":["https://openalex.org/I169333911"]}],"countries":["PL"],"is_corresponding":false,"raw_author_name":"Piotr Bratoszewski","raw_affiliation_strings":["Faculty of Electronics, Telecommunications and Informatics, Multimedia Systems Department, Gdansk University of Technology, Gdansk, Poland","Faculty of Electronics, Telecommunications and Informatics, Multimedia Systems Department, Gdansk University of Technology, ul. Narutowicza 11/12, 80-233, Gdansk, Poland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Faculty of Electronics, Telecommunications and Informatics, Multimedia Systems Department, Gdansk University of Technology, Gdansk, Poland","institution_ids":["https://openalex.org/I169333911"]},{"raw_affiliation_string":"Faculty of Electronics, Telecommunications and Informatics, Multimedia Systems Department, Gdansk University of Technology, ul. Narutowicza 11/12, 80-233, Gdansk, Poland","institution_ids":["https://openalex.org/I169333911"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5013437469","display_name":"J\u00f3zef Kotus","orcid":"https://orcid.org/0000-0001-8087-3095"},"institutions":[{"id":"https://openalex.org/I169333911","display_name":"Gda\u0144sk University of Technology","ror":"https://ror.org/006x4sc24","country_code":"PL","type":"education","lineage":["https://openalex.org/I169333911"]}],"countries":["PL"],"is_corresponding":false,"raw_author_name":"Jozef Kotus","raw_affiliation_strings":["Faculty of Electronics, Telecommunications and Informatics, Multimedia Systems Department, Gdansk University of Technology, Gdansk, Poland","Faculty of Electronics, Telecommunications and Informatics, Multimedia Systems Department, Gdansk University of Technology, ul. Narutowicza 11/12, 80-233, Gdansk, Poland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Faculty of Electronics, Telecommunications and Informatics, Multimedia Systems Department, Gdansk University of Technology, Gdansk, Poland","institution_ids":["https://openalex.org/I169333911"]},{"raw_affiliation_string":"Faculty of Electronics, Telecommunications and Informatics, Multimedia Systems Department, Gdansk University of Technology, ul. Narutowicza 11/12, 80-233, Gdansk, Poland","institution_ids":["https://openalex.org/I169333911"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5071538898","display_name":"Marcin Szykulski","orcid":"https://orcid.org/0000-0001-7907-822X"},"institutions":[{"id":"https://openalex.org/I169333911","display_name":"Gda\u0144sk University of Technology","ror":"https://ror.org/006x4sc24","country_code":"PL","type":"education","lineage":["https://openalex.org/I169333911"]}],"countries":["PL"],"is_corresponding":true,"raw_author_name":"Marcin Szykulski","raw_affiliation_strings":["Faculty of Electronics, Telecommunications and Informatics, Multimedia Systems Department, Gdansk University of Technology, Gdansk, Poland","Faculty of Electronics, Telecommunications and Informatics, Multimedia Systems Department, Gdansk University of Technology, ul. Narutowicza 11/12, 80-233, Gdansk, Poland"],"raw_orcid":"https://orcid.org/0000-0001-7907-822X","affiliations":[{"raw_affiliation_string":"Faculty of Electronics, Telecommunications and Informatics, Multimedia Systems Department, Gdansk University of Technology, Gdansk, Poland","institution_ids":["https://openalex.org/I169333911"]},{"raw_affiliation_string":"Faculty of Electronics, Telecommunications and Informatics, Multimedia Systems Department, Gdansk University of Technology, ul. Narutowicza 11/12, 80-233, Gdansk, Poland","institution_ids":["https://openalex.org/I169333911"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5071538898"],"corresponding_institution_ids":["https://openalex.org/I169333911"],"apc_list":{"value":3090,"currency":"USD","value_usd":3090},"apc_paid":{"value":3090,"currency":"USD","value_usd":3090},"fwci":7.8032,"has_fulltext":true,"cited_by_count":89,"citation_normalized_percentile":{"value":0.9801552,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":100},"biblio":{"volume":"49","issue":"2","first_page":"167","last_page":"192"},"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/T11309","display_name":"Music and Audio Processing","score":0.9995999932289124,"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":0.9990000128746033,"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/computer-science","display_name":"Computer science","score":0.8809014558792114},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6776763200759888},{"id":"https://openalex.org/keywords/audio-mining","display_name":"Audio mining","score":0.6024739146232605},{"id":"https://openalex.org/keywords/microphone","display_name":"Microphone","score":0.5973321795463562},{"id":"https://openalex.org/keywords/speech-corpus","display_name":"Speech corpus","score":0.5525722503662109},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.4644145369529724},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.4404236674308777},{"id":"https://openalex.org/keywords/acoustic-model","display_name":"Acoustic model","score":0.4262278378009796},{"id":"https://openalex.org/keywords/speech-technology","display_name":"Speech technology","score":0.4102794826030731},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.40447598695755005},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.2463911473751068}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8809014558792114},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6776763200759888},{"id":"https://openalex.org/C157968479","wikidata":"https://www.wikidata.org/wiki/Q3079876","display_name":"Audio mining","level":4,"score":0.6024739146232605},{"id":"https://openalex.org/C2778263558","wikidata":"https://www.wikidata.org/wiki/Q46384","display_name":"Microphone","level":3,"score":0.5973321795463562},{"id":"https://openalex.org/C91863865","wikidata":"https://www.wikidata.org/wiki/Q4349497","display_name":"Speech corpus","level":3,"score":0.5525722503662109},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.4644145369529724},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.4404236674308777},{"id":"https://openalex.org/C155635449","wikidata":"https://www.wikidata.org/wiki/Q4674699","display_name":"Acoustic model","level":3,"score":0.4262278378009796},{"id":"https://openalex.org/C504749915","wikidata":"https://www.wikidata.org/wiki/Q9010971","display_name":"Speech technology","level":3,"score":0.4102794826030731},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.40447598695755005},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.2463911473751068},{"id":"https://openalex.org/C68115822","wikidata":"https://www.wikidata.org/wiki/Q1068172","display_name":"Sound pressure","level":2,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1007/s10844-016-0438-z","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s10844-016-0438-z","pdf_url":"https://link.springer.com/content/pdf/10.1007%2Fs10844-016-0438-z.pdf","source":{"id":"https://openalex.org/S36033921","display_name":"Journal of Intelligent Information Systems","issn_l":"0925-9902","issn":["0925-9902","1573-7675"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Intelligent Information Systems","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1007/s10844-016-0438-z","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s10844-016-0438-z","pdf_url":"https://link.springer.com/content/pdf/10.1007%2Fs10844-016-0438-z.pdf","source":{"id":"https://openalex.org/S36033921","display_name":"Journal of Intelligent Information Systems","issn_l":"0925-9902","issn":["0925-9902","1573-7675"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Intelligent Information Systems","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G7739175826","display_name":null,"funder_award_id":"2015/17/B/ST6/01874","funder_id":"https://openalex.org/F4320322511","funder_display_name":"Narodowe Centrum Nauki"}],"funders":[{"id":"https://openalex.org/F4320322511","display_name":"Narodowe Centrum Nauki","ror":"https://ror.org/03ha2q922"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2570575067.pdf","grobid_xml":"https://content.openalex.org/works/W2570575067.grobid-xml"},"referenced_works_count":53,"referenced_works":["https://openalex.org/W25302482","https://openalex.org/W31621703","https://openalex.org/W142945732","https://openalex.org/W428668422","https://openalex.org/W1273351261","https://openalex.org/W1482998036","https://openalex.org/W1503933356","https://openalex.org/W1520228114","https://openalex.org/W1525176859","https://openalex.org/W1527240141","https://openalex.org/W1540804449","https://openalex.org/W1554169525","https://openalex.org/W1579055241","https://openalex.org/W1596452184","https://openalex.org/W1600492480","https://openalex.org/W1633840029","https://openalex.org/W1635512741","https://openalex.org/W1863613949","https://openalex.org/W1963564449","https://openalex.org/W1964178275","https://openalex.org/W1979882273","https://openalex.org/W2004826498","https://openalex.org/W2015143272","https://openalex.org/W2015394094","https://openalex.org/W2035777533","https://openalex.org/W2043853084","https://openalex.org/W2046058153","https://openalex.org/W2058542017","https://openalex.org/W2070115136","https://openalex.org/W2076462394","https://openalex.org/W2089974679","https://openalex.org/W2092776130","https://openalex.org/W2098923380","https://openalex.org/W2114174754","https://openalex.org/W2122702209","https://openalex.org/W2130602224","https://openalex.org/W2132999255","https://openalex.org/W2142248209","https://openalex.org/W2142518644","https://openalex.org/W2146824864","https://openalex.org/W2148154194","https://openalex.org/W2148332551","https://openalex.org/W2203871458","https://openalex.org/W2243107572","https://openalex.org/W2365880764","https://openalex.org/W2398406965","https://openalex.org/W2615059019","https://openalex.org/W2708562533","https://openalex.org/W2952746495","https://openalex.org/W4234826015","https://openalex.org/W6624852173","https://openalex.org/W6631618440","https://openalex.org/W6765296696"],"related_works":["https://openalex.org/W4388404911","https://openalex.org/W2184127972","https://openalex.org/W1987021544","https://openalex.org/W4312668661","https://openalex.org/W3151376046","https://openalex.org/W2964829415","https://openalex.org/W3089379469","https://openalex.org/W2105439218","https://openalex.org/W4238262908","https://openalex.org/W642007152"],"abstract_inverted_index":{"A":[0],"review":[1],"of":[2,10,15,27,81,106,122,129,135,193],"available":[3,199],"audio-visual":[4,34,156],"speech":[5,17,35,123,158],"corpora":[6],"and":[7,70,143,163,174],"a":[8,11,67,71,75,182],"description":[9],"new":[12,22],"multimodal":[13],"corpus":[14,23,45,100,114,171,195],"English":[16],"recordings":[18,28,107],"is":[19,146,197],"provided.":[20],"The":[21,40,133],"containing":[24],"31":[25],"hours":[26],"was":[29,90],"created":[30],"specifically":[31],"to":[32,43,84,98,103,188],"assist":[33],"recognition":[36,124,159],"systems":[37,86,125],"(AVSR)":[38],"development.":[39],"database":[41],"related":[42,83],"the":[44,79,99,104,112,127,137,140,149,154,166,170,190,194,201],"includes":[46],"high-resolution,":[47],"high-framerate":[48],"stereoscopic":[49],"video":[50],"streams":[51],"from":[52],"RGB":[53],"cameras,":[54],"depth":[55],"imaging":[56],"stream":[57],"utilizing":[58],"Time-of-Flight":[59],"camera":[60],"accompanied":[61],"by":[62],"audio":[63],"recorded":[64],"using":[65],"both:":[66],"microphone":[68,72],"array":[69],"built":[73],"in":[74,94,109,126,148,169],"mobile":[76],"computer.":[77],"For":[78],"purpose":[80],"applications":[82],"AVSR":[85],"training,":[87],"every":[88],"utterance":[89],"manually":[91],"labeled,":[92],"resulting":[93],"label":[95],"files":[96],"added":[97],"repository.":[101],"Owing":[102],"inclusion":[105],"made":[108,198],"noisy":[110],"conditions":[111],"elaborated":[113],"can":[115],"also":[116],"be":[117],"used":[118],"for":[119,200],"testing":[120],"robustness":[121],"presence":[128],"acoustic":[130],"background":[131],"noise.":[132],"process":[134],"building":[136],"corpus,":[138],"including":[139],"recording,":[141],"labeling":[142],"post-processing":[144],"phases":[145],"described":[147],"paper.":[150],"Results":[151],"achieved":[152],"with":[153,165,177],"developed":[155],"automatic":[157],"(ASR)":[160],"engine":[161],"trained":[162],"tested":[164],"material":[167],"contained":[168],"are":[172],"presented":[173],"discussed":[175],"together":[176],"comparative":[178],"test":[179],"results":[180],"employing":[181],"state-of-the-art/commercial":[183],"ASR":[184],"engine.":[185],"In":[186],"order":[187],"demonstrate":[189],"practical":[191],"use":[192],"it":[196],"public":[202],"use.":[203]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":7},{"year":2024,"cited_by_count":8},{"year":2023,"cited_by_count":10},{"year":2022,"cited_by_count":10},{"year":2021,"cited_by_count":12},{"year":2020,"cited_by_count":13},{"year":2019,"cited_by_count":14},{"year":2018,"cited_by_count":11},{"year":2017,"cited_by_count":3}],"updated_date":"2026-07-29T09:40:50.615796","created_date":"2025-10-10T00:00:00"}
