{"id":"https://openalex.org/W4206047378","doi":"https://doi.org/10.23919/eusipco54536.2021.9616340","title":"WaveTransformer: An Architecture for Audio Captioning Based on Learning Temporal and Time-Frequency Information","display_name":"WaveTransformer: An Architecture for Audio Captioning Based on Learning Temporal and Time-Frequency Information","publication_year":2021,"publication_date":"2021-08-23","ids":{"openalex":"https://openalex.org/W4206047378","doi":"https://doi.org/10.23919/eusipco54536.2021.9616340"},"language":"en","primary_location":{"id":"doi:10.23919/eusipco54536.2021.9616340","is_oa":false,"landing_page_url":"https://doi.org/10.23919/eusipco54536.2021.9616340","pdf_url":null,"source":{"id":"https://openalex.org/S4363607854","display_name":"2021 29th European Signal Processing Conference (EUSIPCO)","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":"2021 29th European Signal Processing Conference (EUSIPCO)","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/A5044245107","display_name":"An Cong Tran","orcid":"https://orcid.org/0000-0001-6184-909X"},"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":true,"raw_author_name":"An Tran","raw_affiliation_strings":["Audio Research Group Tampere University, Tampere, Finland"],"affiliations":[{"raw_affiliation_string":"Audio Research Group Tampere University, Tampere, Finland","institution_ids":["https://openalex.org/I166825849"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5108358814","display_name":"Konstantinos Drossos","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":"Konstantinos Drossos","raw_affiliation_strings":["Audio Research Group Tampere University, Tampere, Finland"],"affiliations":[{"raw_affiliation_string":"Audio Research Group Tampere University, Tampere, Finland","institution_ids":["https://openalex.org/I166825849"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5049691461","display_name":"Tuomas Virtanen","orcid":"https://orcid.org/0000-0002-4604-9729"},"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":"Tuomas Virtanen","raw_affiliation_strings":["Audio Research Group Tampere University, Tampere, Finland"],"affiliations":[{"raw_affiliation_string":"Audio Research Group Tampere University, Tampere, Finland","institution_ids":["https://openalex.org/I166825849"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5044245107"],"corresponding_institution_ids":["https://openalex.org/I166825849"],"apc_list":null,"apc_paid":null,"fwci":1.8924,"has_fulltext":false,"cited_by_count":11,"citation_normalized_percentile":{"value":0.92142377,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"576","last_page":"580"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9997000098228455,"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/T11309","display_name":"Music and Audio Processing","score":0.9997000098228455,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9987999796867371,"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/T11439","display_name":"Video Analysis and Summarization","score":0.9979000091552734,"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/closed-captioning","display_name":"Closed captioning","score":0.9419233798980713},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8440108299255371},{"id":"https://openalex.org/keywords/merge","display_name":"Merge (version control)","score":0.594816267490387},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.561124861240387},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.5490992665290833},{"id":"https://openalex.org/keywords/architecture","display_name":"Architecture","score":0.4785650074481964},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4543567895889282},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.17590177059173584},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.13380756974220276}],"concepts":[{"id":"https://openalex.org/C157657479","wikidata":"https://www.wikidata.org/wiki/Q2367247","display_name":"Closed captioning","level":3,"score":0.9419233798980713},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8440108299255371},{"id":"https://openalex.org/C197129107","wikidata":"https://www.wikidata.org/wiki/Q1921621","display_name":"Merge (version control)","level":2,"score":0.594816267490387},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.561124861240387},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.5490992665290833},{"id":"https://openalex.org/C123657996","wikidata":"https://www.wikidata.org/wiki/Q12271","display_name":"Architecture","level":2,"score":0.4785650074481964},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4543567895889282},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.17590177059173584},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.13380756974220276},{"id":"https://openalex.org/C153349607","wikidata":"https://www.wikidata.org/wiki/Q36649","display_name":"Visual arts","level":1,"score":0.0},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"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/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.23919/eusipco54536.2021.9616340","is_oa":false,"landing_page_url":"https://doi.org/10.23919/eusipco54536.2021.9616340","pdf_url":null,"source":{"id":"https://openalex.org/S4363607854","display_name":"2021 29th European Signal Processing Conference (EUSIPCO)","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":"2021 29th European Signal Processing Conference (EUSIPCO)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.7200000286102295,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[{"id":"https://openalex.org/G1816425981","display_name":null,"funder_award_id":"957337","funder_id":"https://openalex.org/F4320332999","funder_display_name":"Horizon 2020 Framework Programme"}],"funders":[{"id":"https://openalex.org/F4320332999","display_name":"Horizon 2020 Framework Programme","ror":"https://ror.org/00k4n6c32"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":27,"referenced_works":["https://openalex.org/W1522301498","https://openalex.org/W1956340063","https://openalex.org/W2133512280","https://openalex.org/W2154652894","https://openalex.org/W2506483933","https://openalex.org/W2519091744","https://openalex.org/W2591013610","https://openalex.org/W2783831488","https://openalex.org/W2916103538","https://openalex.org/W2949376505","https://openalex.org/W2964213897","https://openalex.org/W2982554818","https://openalex.org/W3015591594","https://openalex.org/W3042165234","https://openalex.org/W3088092535","https://openalex.org/W3091490309","https://openalex.org/W3097791920","https://openalex.org/W3103022576","https://openalex.org/W4287727142","https://openalex.org/W4385245566","https://openalex.org/W6631190155","https://openalex.org/W6682631176","https://openalex.org/W6739901393","https://openalex.org/W6747747266","https://openalex.org/W6779820445","https://openalex.org/W6783591283","https://openalex.org/W6898505805"],"related_works":["https://openalex.org/W4210416330","https://openalex.org/W3088136942","https://openalex.org/W2949362007","https://openalex.org/W4310447809","https://openalex.org/W4200243030","https://openalex.org/W2800782462","https://openalex.org/W4323777661","https://openalex.org/W3209117276","https://openalex.org/W4388184981","https://openalex.org/W2363497019"],"abstract_inverted_index":{"Automated":[0],"audio":[1,16,69],"captioning":[2,36],"(AAC)":[3],"is":[4,126],"a":[5,9,20,24,46],"novel":[6,47],"task,":[7],"where":[8],"method":[10,104],"takes":[11],"as":[12],"an":[13,15],"input":[14],"sample":[17],"and":[18,58,76,79],"outputs":[19],"textual":[21],"description":[22],"(i.e.":[23],"caption)":[25],"of":[26,55,85,110],"its":[27],"contents.":[28],"Most":[29],"AAC":[30,48],"methods":[31],"are":[32],"adapted":[33],"from":[34,123],"image":[35],"or":[37],"machine":[38],"translation":[39],"fields.":[40],"In":[41],"this":[42],"work,":[43],"we":[44,94],"present":[45],"method,":[49],"explicitly":[50],"focused":[51],"on":[52],"the":[53,56,74,83,86,92,96,106,111],"exploitation":[54],"temporal":[57,75],"time-frequency":[59,77],"patterns":[60],"in":[61],"audio.":[62],"We":[63,101],"employ":[64,95],"three":[65],"learnable":[66],"processes":[67],"for":[68,72],"encoding,":[70],"two":[71,88],"extracting":[73],"information,":[78],"one":[80],"to":[81,121],"merge":[82],"output":[84],"previous":[87],"processes.":[89],"To":[90],"generate":[91],"caption,":[93],"widely":[97],"used":[98],"Transformer":[99],"decoder.":[100],"assess":[102],"our":[103],"utilizing":[105],"freely":[107],"available":[108],"splits":[109],"Clotho":[112],"dataset.":[113],"Our":[114],"results":[115],"increase":[116],"previously":[117],"reported":[118],"highest":[119],"SPIDEr":[120],"17.3,":[122],"16.2":[124],"(higher":[125],"better).":[127]},"counts_by_year":[{"year":2024,"cited_by_count":4},{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":3},{"year":2021,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}