{"id":"https://openalex.org/W3200287550","doi":"https://doi.org/10.1109/icassp43922.2022.9747103","title":"Fast-Slow Transformer for Visually Grounding Speech","display_name":"Fast-Slow Transformer for Visually Grounding Speech","publication_year":2022,"publication_date":"2022-04-27","ids":{"openalex":"https://openalex.org/W3200287550","doi":"https://doi.org/10.1109/icassp43922.2022.9747103","mag":"3200287550"},"language":"en","primary_location":{"id":"doi:10.1109/icassp43922.2022.9747103","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp43922.2022.9747103","pdf_url":null,"source":{"id":"https://openalex.org/S4363607702","display_name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5075735963","display_name":"Puyuan Peng","orcid":null},"institutions":[{"id":"https://openalex.org/I86519309","display_name":"The University of Texas at Austin","ror":"https://ror.org/00hj54h04","country_code":"US","type":"education","lineage":["https://openalex.org/I86519309"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Puyuan Peng","raw_affiliation_strings":["The University of Texas at Austin,Department of Computer Science,Austin,Texas,USA,78712"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The University of Texas at Austin,Department of Computer Science,Austin,Texas,USA,78712","institution_ids":["https://openalex.org/I86519309"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5004717608","display_name":"David Harwath","orcid":"https://orcid.org/0000-0003-0206-0253"},"institutions":[{"id":"https://openalex.org/I86519309","display_name":"The University of Texas at Austin","ror":"https://ror.org/00hj54h04","country_code":"US","type":"education","lineage":["https://openalex.org/I86519309"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"David Harwath","raw_affiliation_strings":["The University of Texas at Austin,Department of Computer Science,Austin,Texas,USA,78712"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The University of Texas at Austin,Department of Computer Science,Austin,Texas,USA,78712","institution_ids":["https://openalex.org/I86519309"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I86519309"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":24,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"7727","last_page":"7731"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9994000196456909,"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":0.9994000196456909,"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/T10860","display_name":"Speech and Audio Processing","score":0.9990000128746033,"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":0.9923999905586243,"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/transformer","display_name":"Transformer","score":0.7976561188697815},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7852569818496704},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.6768229007720947},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5262331366539001},{"id":"https://openalex.org/keywords/waveform","display_name":"Waveform","score":0.5145377516746521},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5141806602478027},{"id":"https://openalex.org/keywords/ground-truth","display_name":"Ground truth","score":0.4688393175601959},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.4553561210632324},{"id":"https://openalex.org/keywords/voltage","display_name":"Voltage","score":0.12765702605247498},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.12116780877113342},{"id":"https://openalex.org/keywords/electrical-engineering","display_name":"Electrical engineering","score":0.09300526976585388}],"concepts":[{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.7976561188697815},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7852569818496704},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.6768229007720947},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5262331366539001},{"id":"https://openalex.org/C197424946","wikidata":"https://www.wikidata.org/wiki/Q1165717","display_name":"Waveform","level":3,"score":0.5145377516746521},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5141806602478027},{"id":"https://openalex.org/C146849305","wikidata":"https://www.wikidata.org/wiki/Q370766","display_name":"Ground truth","level":2,"score":0.4688393175601959},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.4553561210632324},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.12765702605247498},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.12116780877113342},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.09300526976585388},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"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/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C554190296","wikidata":"https://www.wikidata.org/wiki/Q47528","display_name":"Radar","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp43922.2022.9747103","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp43922.2022.9747103","pdf_url":null,"source":{"id":"https://openalex.org/S4363607702","display_name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.6200000047683716,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":69,"referenced_works":["https://openalex.org/W68733909","https://openalex.org/W639708223","https://openalex.org/W1494198834","https://openalex.org/W1861492603","https://openalex.org/W2134670479","https://openalex.org/W2277195237","https://openalex.org/W2295158492","https://openalex.org/W2481240925","https://openalex.org/W2556930864","https://openalex.org/W2586148577","https://openalex.org/W2586850765","https://openalex.org/W2796315435","https://openalex.org/W2842511635","https://openalex.org/W2896457183","https://openalex.org/W2899663614","https://openalex.org/W2906407728","https://openalex.org/W2927673779","https://openalex.org/W2962862718","https://openalex.org/W2962866381","https://openalex.org/W2963330681","https://openalex.org/W2963341956","https://openalex.org/W2963403868","https://openalex.org/W2963525826","https://openalex.org/W2963902314","https://openalex.org/W2964001192","https://openalex.org/W2964099072","https://openalex.org/W2970231061","https://openalex.org/W2971709506","https://openalex.org/W2972892814","https://openalex.org/W2988907666","https://openalex.org/W2995680346","https://openalex.org/W3015300171","https://openalex.org/W3036601975","https://openalex.org/W3095293218","https://openalex.org/W3096372900","https://openalex.org/W3099782249","https://openalex.org/W3100813302","https://openalex.org/W3110458199","https://openalex.org/W3114436296","https://openalex.org/W3155230099","https://openalex.org/W3157861865","https://openalex.org/W3161204797","https://openalex.org/W3171668871","https://openalex.org/W3174311593","https://openalex.org/W3175947832","https://openalex.org/W3177829661","https://openalex.org/W3196698946","https://openalex.org/W3197349023","https://openalex.org/W3197467690","https://openalex.org/W3198411039","https://openalex.org/W3198815374","https://openalex.org/W4287591426","https://openalex.org/W4287757663","https://openalex.org/W4385245566","https://openalex.org/W6620707391","https://openalex.org/W6639102338","https://openalex.org/W6679792166","https://openalex.org/W6729977899","https://openalex.org/W6739901393","https://openalex.org/W6750194919","https://openalex.org/W6750570362","https://openalex.org/W6750651883","https://openalex.org/W6755207826","https://openalex.org/W6755977528","https://openalex.org/W6770596778","https://openalex.org/W6779753737","https://openalex.org/W6780218876","https://openalex.org/W6786696081","https://openalex.org/W6797832685"],"related_works":["https://openalex.org/W2378211422","https://openalex.org/W1974895211","https://openalex.org/W2745001401","https://openalex.org/W4321353415","https://openalex.org/W2176409448","https://openalex.org/W2129841057","https://openalex.org/W3040712279","https://openalex.org/W4323323165","https://openalex.org/W4386066345","https://openalex.org/W2745033168"],"abstract_inverted_index":{"We":[0],"present":[1],"Fast-Slow":[2],"Transformer":[3],"for":[4,15],"Visually":[5],"Grounding":[6],"Speech,":[7],"or":[8],"FaST-VGS.":[9],"FaST-VGS":[10,52],"is":[11],"a":[12,34],"Transformer-based":[13],"model":[14,27],"learning":[16],"the":[17,38,43,47,50,69],"associations":[18],"between":[19],"raw":[20],"speech":[21],"waveforms":[22],"and":[23,30,61,73],"visual":[24],"images.":[25],"The":[26],"unifies":[28],"dual-encoder":[29],"cross-attention":[31],"architectures":[32],"into":[33],"single":[35],"model,":[36],"reaping":[37],"superior":[39],"retrieval":[40,56],"speed":[41],"of":[42,49],"former":[44],"along":[45],"with":[46],"accuracy":[48,57],"latter.":[51],"achieves":[53],"state-of-the-art":[54],"speech-image":[55],"on":[58,68],"benchmark":[59],"datasets,":[60],"its":[62],"learned":[63],"representations":[64],"exhibit":[65],"strong":[66],"performance":[67],"ZeroSpeech":[70],"2021":[71],"phonetic":[72],"semantic":[74],"tasks.":[75]},"counts_by_year":[{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":9},{"year":2023,"cited_by_count":5},{"year":2022,"cited_by_count":6}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}