{"id":"https://openalex.org/W4388117487","doi":"https://doi.org/10.23919/eusipco58844.2023.10290005","title":"Attentions for Short Duration Speech Classification","display_name":"Attentions for Short Duration Speech Classification","publication_year":2023,"publication_date":"2023-09-04","ids":{"openalex":"https://openalex.org/W4388117487","doi":"https://doi.org/10.23919/eusipco58844.2023.10290005"},"language":"en","primary_location":{"id":"doi:10.23919/eusipco58844.2023.10290005","is_oa":false,"landing_page_url":"http://dx.doi.org/10.23919/eusipco58844.2023.10290005","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 31st European Signal Processing Conference (EUSIPCO)","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/A5108874321","display_name":"Hastin Modi","orcid":null},"institutions":[{"id":"https://openalex.org/I98389781","display_name":"Dhirubhai Ambani University","ror":"https://ror.org/02d5b7g69","country_code":"IN","type":"education","lineage":["https://openalex.org/I98389781"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Hastin Modi","raw_affiliation_strings":["Dhirubhai Ambani Institute of Information and Communication Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Dhirubhai Ambani Institute of Information and Communication Technology","institution_ids":["https://openalex.org/I98389781"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5018555559","display_name":"Maitreya Patel","orcid":null},"institutions":[{"id":"https://openalex.org/I98389781","display_name":"Dhirubhai Ambani University","ror":"https://ror.org/02d5b7g69","country_code":"IN","type":"education","lineage":["https://openalex.org/I98389781"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Maitreya Patel","raw_affiliation_strings":["Dhirubhai Ambani Institute of Information and Communication Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Dhirubhai Ambani Institute of Information and Communication Technology","institution_ids":["https://openalex.org/I98389781"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5043002276","display_name":"Hemant A. Patil","orcid":"https://orcid.org/0000-0002-4068-2005"},"institutions":[{"id":"https://openalex.org/I98389781","display_name":"Dhirubhai Ambani University","ror":"https://ror.org/02d5b7g69","country_code":"IN","type":"education","lineage":["https://openalex.org/I98389781"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Hemant A. Patil","raw_affiliation_strings":["Dhirubhai Ambani Institute of Information and Communication Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Dhirubhai Ambani Institute of Information and Communication Technology","institution_ids":["https://openalex.org/I98389781"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I98389781"],"apc_list":null,"apc_paid":null,"fwci":0.4356,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.60642854,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"1340","last_page":"1344"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9991999864578247,"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"}},"topics":[{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9991999864578247,"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/T13289","display_name":"Infant Health and Development","score":0.9991000294685364,"subfield":{"id":"https://openalex.org/subfields/3611","display_name":"Pharmacy"},"field":{"id":"https://openalex.org/fields/36","display_name":"Health Professions"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}},{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9969000220298767,"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":0.7549517154693604},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.6452731490135193},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5586313009262085},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.5284165143966675},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5115740895271301},{"id":"https://openalex.org/keywords/popularity","display_name":"Popularity","score":0.502493143081665},{"id":"https://openalex.org/keywords/leverage","display_name":"Leverage (statistics)","score":0.4973349869251251},{"id":"https://openalex.org/keywords/recall","display_name":"Recall","score":0.4645293653011322},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4588002562522888},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.4479852318763733},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.10129192471504211}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7549517154693604},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.6452731490135193},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5586313009262085},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.5284165143966675},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5115740895271301},{"id":"https://openalex.org/C2780586970","wikidata":"https://www.wikidata.org/wiki/Q1357284","display_name":"Popularity","level":2,"score":0.502493143081665},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.4973349869251251},{"id":"https://openalex.org/C100660578","wikidata":"https://www.wikidata.org/wiki/Q18733","display_name":"Recall","level":2,"score":0.4645293653011322},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4588002562522888},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.4479852318763733},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.10129192471504211},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C77805123","wikidata":"https://www.wikidata.org/wiki/Q161272","display_name":"Social psychology","level":1,"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/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","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/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.0},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","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/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.23919/eusipco58844.2023.10290005","is_oa":false,"landing_page_url":"http://dx.doi.org/10.23919/eusipco58844.2023.10290005","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 31st European Signal Processing Conference (EUSIPCO)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.41999998688697815,"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":36,"referenced_works":["https://openalex.org/W1522301498","https://openalex.org/W1902237438","https://openalex.org/W2030931454","https://openalex.org/W2133564696","https://openalex.org/W2267186426","https://openalex.org/W2595840341","https://openalex.org/W2806051338","https://openalex.org/W2892009249","https://openalex.org/W2896457183","https://openalex.org/W2963495494","https://openalex.org/W2972451902","https://openalex.org/W2972459675","https://openalex.org/W2972498864","https://openalex.org/W2972986317","https://openalex.org/W2978329087","https://openalex.org/W2987496713","https://openalex.org/W2995124259","https://openalex.org/W2995394700","https://openalex.org/W3012437242","https://openalex.org/W3015465870","https://openalex.org/W3016719260","https://openalex.org/W3081753361","https://openalex.org/W3082218567","https://openalex.org/W3090558582","https://openalex.org/W3114227432","https://openalex.org/W3117807895","https://openalex.org/W3130967494","https://openalex.org/W3159598768","https://openalex.org/W3208624098","https://openalex.org/W4385245566","https://openalex.org/W6623517193","https://openalex.org/W6631190155","https://openalex.org/W6679434410","https://openalex.org/W6684821475","https://openalex.org/W6752083267","https://openalex.org/W6755207826"],"related_works":["https://openalex.org/W2368605798","https://openalex.org/W2518037665","https://openalex.org/W2348524959","https://openalex.org/W2477036161","https://openalex.org/W2368049389","https://openalex.org/W2384861574","https://openalex.org/W2170801710","https://openalex.org/W2952704802","https://openalex.org/W4294565801","https://openalex.org/W4390723067"],"abstract_inverted_index":{"Neural":[0],"attention":[1,14,56],"mechanisms":[2,15],"have":[3,41,62],"gained":[4],"significant":[5],"popularity":[6],"and":[7,24,35,46,87,108,138,153],"widespread":[8],"adoption":[9],"in":[10,144],"various":[11,77],"applications.":[12],"These":[13],"can":[16],"be":[17],"applied":[18],"to":[19,53,132],"different":[20,99],"models,":[21],"including":[22],"sequential":[23,45],"spatial":[25,47],"models.":[26],"Recently,":[27],"the":[28,36,95,105,115,133,141],"Transformer":[29,116,137],"model,":[30,38],"based":[31],"on":[32,83,98],"multi-head":[33],"self-attention,":[34],"ResNeSt":[37,127,139],"utilizing":[39],"split-attention,":[40],"been":[42,63],"developed":[43],"for":[44,58,123],"tasks,":[48],"respectively.":[49,155],"However,":[50,122],"many":[51],"attempts":[52],"leverage":[54],"state-of-the-art":[55,143],"methodologies":[57],"speech-related":[59],"classification":[60,86],"problems":[61],"made":[64],"without":[65],"thorough":[66],"analysis.":[67],"In":[68],"this":[69],"paper,":[70],"we":[71,93],"conduct":[72],"an":[73],"extensive":[74],"analysis":[75],"of":[76,101,151],"attention-based":[78],"methods":[79],"by":[80],"performing":[81],"experiments":[82],"infant":[84,145],"cry":[85,146],"speech":[88],"emotion":[89],"recognition":[90],"tasks.":[91],"Additionally,":[92],"evaluate":[94],"proposed":[96],"models":[97],"durations":[100],"audio":[102,125],"clips":[103],"from":[104],"Baby":[106],"Chillanto":[107],"CREMA-D":[109],"databases.":[110],"Our":[111],"results":[112],"demonstrate":[113],"that":[114],"(encoder-only)":[117],"model":[118],"significantly":[119],"outperforms":[120],"ResNeSt.":[121],"longer":[124],"clips,":[126],"exhibits":[128],"greater":[129],"robustness":[130],"compared":[131],"Transformer.":[134],"Furthermore,":[135],"both":[136],"surpass":[140],"previous":[142],"classification,":[147],"achieving":[148],"recall":[149],"improvements":[150],"10.9%":[152],"4.3%,":[154]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}