{"id":"https://openalex.org/W4408352828","doi":"https://doi.org/10.1109/icassp49660.2025.10890587","title":"Temporally Aligned Audio for Video with Autoregression","display_name":"Temporally Aligned Audio for Video with Autoregression","publication_year":2025,"publication_date":"2025-03-12","ids":{"openalex":"https://openalex.org/W4408352828","doi":"https://doi.org/10.1109/icassp49660.2025.10890587"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49660.2025.10890587","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10890587","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2025 - 2025 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/A5114412356","display_name":"Ilpo Viertola","orcid":null},"institutions":[{"id":"https://openalex.org/I166825849","display_name":"Tampere University","ror":"https://ror.org/033003e23","country_code":"FI","type":"education","lineage":["https://openalex.org/I166825849"]}],"countries":["FI"],"is_corresponding":false,"raw_author_name":"Ilpo Viertola","raw_affiliation_strings":["Tampere University,Computing Sciences,Tampere,Finland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tampere University,Computing Sciences,Tampere,Finland","institution_ids":["https://openalex.org/I166825849"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5008909874","display_name":"Vladimir Iashin","orcid":"https://orcid.org/0000-0001-8879-587X"},"institutions":[{"id":"https://openalex.org/I40120149","display_name":"University of Oxford","ror":"https://ror.org/052gg0110","country_code":"GB","type":"education","lineage":["https://openalex.org/I40120149"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Vladimir Iashin","raw_affiliation_strings":["Tampere University Engineering Science, University of Oxford,Computing Sciences,Oxford,United Kingdom"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tampere University Engineering Science, University of Oxford,Computing Sciences,Oxford,United Kingdom","institution_ids":["https://openalex.org/I40120149"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5088180438","display_name":"Esa Rahtu","orcid":"https://orcid.org/0000-0001-8767-0864"},"institutions":[{"id":"https://openalex.org/I166825849","display_name":"Tampere University","ror":"https://ror.org/033003e23","country_code":"FI","type":"education","lineage":["https://openalex.org/I166825849"]}],"countries":["FI"],"is_corresponding":false,"raw_author_name":"Esa Rahtu","raw_affiliation_strings":["Tampere University,Computing Sciences,Tampere,Finland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tampere University,Computing Sciences,Tampere,Finland","institution_ids":["https://openalex.org/I166825849"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":11.326,"has_fulltext":false,"cited_by_count":8,"citation_normalized_percentile":{"value":0.98473087,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":97,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"5"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10688","display_name":"Image and Signal Denoising Methods","score":0.9409999847412109,"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/T10688","display_name":"Image and Signal Denoising Methods","score":0.9409999847412109,"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":0.9010000228881836,"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/computer-science","display_name":"Computer science","score":0.5945448279380798},{"id":"https://openalex.org/keywords/autoregressive-model","display_name":"Autoregressive model","score":0.4802451431751251},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.38568395376205444},{"id":"https://openalex.org/keywords/econometrics","display_name":"Econometrics","score":0.07108989357948303},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.0690234899520874}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5945448279380798},{"id":"https://openalex.org/C159877910","wikidata":"https://www.wikidata.org/wiki/Q2202883","display_name":"Autoregressive model","level":2,"score":0.4802451431751251},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.38568395376205444},{"id":"https://openalex.org/C149782125","wikidata":"https://www.wikidata.org/wiki/Q160039","display_name":"Econometrics","level":1,"score":0.07108989357948303},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0690234899520874}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/icassp49660.2025.10890587","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10890587","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},{"id":"pmh:oai:trepo.tuni.fi:10024/230956","is_oa":false,"landing_page_url":"https://trepo.tuni.fi/handle/10024/230956","pdf_url":null,"source":{"id":"https://openalex.org/S4306401860","display_name":"Tampere University Institutional Repository (Tampere University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I150589677","host_organization_name":"Tampere University of Applied Sciences","host_organization_lineage":["https://openalex.org/I150589677"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"conference"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Reduced inequalities","id":"https://metadata.un.org/sdg/10","score":0.5299999713897705}],"awards":[],"funders":[{"id":"https://openalex.org/F4320321108","display_name":"Academy of Finland","ror":"https://ror.org/05k73zm37"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":33,"referenced_works":["https://openalex.org/W2194775991","https://openalex.org/W2593116425","https://openalex.org/W2883429621","https://openalex.org/W3015371781","https://openalex.org/W3046890131","https://openalex.org/W3126721948","https://openalex.org/W3187009280","https://openalex.org/W4372348103","https://openalex.org/W4386071707","https://openalex.org/W4386071828","https://openalex.org/W4392904679","https://openalex.org/W4392910528","https://openalex.org/W4393160294","https://openalex.org/W4402671662","https://openalex.org/W4402727849","https://openalex.org/W4404002404","https://openalex.org/W4404037650","https://openalex.org/W4409364205","https://openalex.org/W4411245083","https://openalex.org/W6739901393","https://openalex.org/W6755977528","https://openalex.org/W6757817989","https://openalex.org/W6840815571","https://openalex.org/W6845298728","https://openalex.org/W6845479124","https://openalex.org/W6850625674","https://openalex.org/W6853096648","https://openalex.org/W6853515095","https://openalex.org/W6854445938","https://openalex.org/W6854866820","https://openalex.org/W6868818234","https://openalex.org/W6869358010","https://openalex.org/W6869582388"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2171218219","https://openalex.org/W1972271943","https://openalex.org/W2150410159","https://openalex.org/W2390279801","https://openalex.org/W4391913857","https://openalex.org/W2358668433","https://openalex.org/W4396701345"],"abstract_inverted_index":{"We":[0],"introduce":[1],"V-AURA,":[2],"the":[3,69,81],"first":[4],"autoregressive":[5],"model":[6],"to":[7,31],"achieve":[8],"high":[9,50],"temporal":[10,40,90],"alignment":[11,91],"and":[12,24,37,92,103],"relevance":[13,94],"in":[14,89],"video-to-audio":[15],"generation.":[16],"V-AURA":[17,84],"uses":[18],"a":[19,25,46,58],"high-framerate":[20],"visual":[21,34,82],"feature":[22,28],"extractor":[23],"cross-modal":[26],"audio-visual":[27,51],"fusion":[29],"strategy":[30],"capture":[32],"fine-grained":[33],"motion":[35],"events":[36,76],"ensure":[38],"precise":[39],"alignment.":[41],"Additionally,":[42],"we":[43,71],"propose":[44],"VisualSound,":[45],"benchmark":[47],"dataset":[48,60],"with":[49,80],"relevance.":[52],"VisualSound":[53,102],"is":[54],"based":[55],"on":[56],"VGGSound,":[57],"video":[59],"consisting":[61],"of":[62],"in-the-wild":[63],"samples":[64,73],"extracted":[65],"from":[66],"YouTube.":[67],"During":[68],"curation,":[70],"remove":[72],"where":[74],"auditory":[75],"are":[77,105],"not":[78],"aligned":[79],"ones.":[83],"outperforms":[85],"current":[86],"state-of-the-art":[87],"models":[88,104],"semantic":[93],"while":[95],"maintaining":[96],"comparable":[97],"audio":[98],"quality.":[99],"Code,":[100],"samples,":[101],"available":[106],"at":[107],"v-aura.notion.site.":[108]},"counts_by_year":[{"year":2026,"cited_by_count":4},{"year":2025,"cited_by_count":4}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}
