{"id":"https://openalex.org/W4416799750","doi":"https://doi.org/10.1109/apsipaasc65261.2025.11249169","title":"Investigating Polyglot Speech Foundation Models for Learning Collective Emotion from Crowds","display_name":"Investigating Polyglot Speech Foundation Models for Learning Collective Emotion from Crowds","publication_year":2025,"publication_date":"2025-10-22","ids":{"openalex":"https://openalex.org/W4416799750","doi":"https://doi.org/10.1109/apsipaasc65261.2025.11249169"},"language":null,"primary_location":{"id":"doi:10.1109/apsipaasc65261.2025.11249169","is_oa":false,"landing_page_url":"https://doi.org/10.1109/apsipaasc65261.2025.11249169","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 Asia Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)","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/A5076790933","display_name":"Orchid Chetia Phukan","orcid":"https://orcid.org/0000-0002-2542-8084"},"institutions":[{"id":"https://openalex.org/I119939252","display_name":"Indraprastha Institute of Information Technology Delhi","ror":"https://ror.org/03vfp4g33","country_code":"IN","type":"education","lineage":["https://openalex.org/I119939252"]},{"id":"https://openalex.org/I68891433","display_name":"Indian Institute of Technology Delhi","ror":"https://ror.org/049tgcd06","country_code":"IN","type":"education","lineage":["https://openalex.org/I68891433"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Orchid Chetia Phukan","raw_affiliation_strings":["IIIT-Delhi,India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IIIT-Delhi,India","institution_ids":["https://openalex.org/I119939252","https://openalex.org/I68891433"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5099056916","display_name":"Girish","orcid":null},"institutions":[{"id":"https://openalex.org/I119939252","display_name":"Indraprastha Institute of Information Technology Delhi","ror":"https://ror.org/03vfp4g33","country_code":"IN","type":"education","lineage":["https://openalex.org/I119939252"]},{"id":"https://openalex.org/I68891433","display_name":"Indian Institute of Technology Delhi","ror":"https://ror.org/049tgcd06","country_code":"IN","type":"education","lineage":["https://openalex.org/I68891433"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Girish","raw_affiliation_strings":["IIIT-Delhi,India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IIIT-Delhi,India","institution_ids":["https://openalex.org/I119939252","https://openalex.org/I68891433"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5113394151","display_name":"Mohd Mujtaba Akhtar","orcid":"https://orcid.org/0009-0000-1982-7110"},"institutions":[{"id":"https://openalex.org/I119939252","display_name":"Indraprastha Institute of Information Technology Delhi","ror":"https://ror.org/03vfp4g33","country_code":"IN","type":"education","lineage":["https://openalex.org/I119939252"]},{"id":"https://openalex.org/I68891433","display_name":"Indian Institute of Technology Delhi","ror":"https://ror.org/049tgcd06","country_code":"IN","type":"education","lineage":["https://openalex.org/I68891433"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Mohd Mujtaba Akhtar","raw_affiliation_strings":["IIIT-Delhi,India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IIIT-Delhi,India","institution_ids":["https://openalex.org/I119939252","https://openalex.org/I68891433"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5120491738","display_name":"Panchal Nayak","orcid":"https://orcid.org/0000-0002-4332-3518"},"institutions":[{"id":"https://openalex.org/I4210097295","display_name":"Vital Research","ror":"https://ror.org/00svqj211","country_code":"US","type":"facility","lineage":["https://openalex.org/I4210097295"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Panchal Nayak","raw_affiliation_strings":["VIT,India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"VIT,India","institution_ids":["https://openalex.org/I4210097295"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5111310826","display_name":"Priyabrata Mallick","orcid":null},"institutions":[{"id":"https://openalex.org/I142253595","display_name":"University B.D.T College of Engineering","ror":"https://ror.org/033dx8j94","country_code":"IN","type":"education","lineage":["https://openalex.org/I142253595"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Priyabrata Mallick","raw_affiliation_strings":["L.B.R College of Engineering,India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"L.B.R College of Engineering,India","institution_ids":["https://openalex.org/I142253595"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5120570689","display_name":"Swarup Ranjan Beherall","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Swarup Ranjan Beherall","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5078351978","display_name":"Parabattina Bhagath","orcid":null},"institutions":[{"id":"https://openalex.org/I142253595","display_name":"University B.D.T College of Engineering","ror":"https://ror.org/033dx8j94","country_code":"IN","type":"education","lineage":["https://openalex.org/I142253595"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Parabattina Bhagath","raw_affiliation_strings":["L.B.R College of Engineering,India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"L.B.R College of Engineering,India","institution_ids":["https://openalex.org/I142253595"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5025920434","display_name":"Pailla Balakrishna Reddy","orcid":null},"institutions":[{"id":"https://openalex.org/I228011842","display_name":"Reliance Industries (United States)","ror":"https://ror.org/00jfs8131","country_code":"US","type":"company","lineage":["https://openalex.org/I228011842","https://openalex.org/I4210136064"]},{"id":"https://openalex.org/I4210136064","display_name":"Reliance Industries (India)","ror":"https://ror.org/04j6cfb03","country_code":"IN","type":"company","lineage":["https://openalex.org/I4210136064"]}],"countries":["IN","US"],"is_corresponding":false,"raw_author_name":"Pailla Balakrishna Reddy","raw_affiliation_strings":["Reliance AI,India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Reliance AI,India","institution_ids":["https://openalex.org/I4210136064","https://openalex.org/I228011842"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5014100784","display_name":"Arun Balaji Buduru","orcid":"https://orcid.org/0000-0002-6267-8138"},"institutions":[{"id":"https://openalex.org/I119939252","display_name":"Indraprastha Institute of Information Technology Delhi","ror":"https://ror.org/03vfp4g33","country_code":"IN","type":"education","lineage":["https://openalex.org/I119939252"]},{"id":"https://openalex.org/I68891433","display_name":"Indian Institute of Technology Delhi","ror":"https://ror.org/049tgcd06","country_code":"IN","type":"education","lineage":["https://openalex.org/I68891433"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Arun Balaji Buduru","raw_affiliation_strings":["IIIT-Delhi,India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IIIT-Delhi,India","institution_ids":["https://openalex.org/I119939252","https://openalex.org/I68891433"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":9,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.34721698,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1016","last_page":"1021"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10667","display_name":"Emotion and Mood Recognition","score":0.9487000107765198,"subfield":{"id":"https://openalex.org/subfields/3205","display_name":"Experimental and Cognitive Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},"topics":[{"id":"https://openalex.org/T10667","display_name":"Emotion and Mood Recognition","score":0.9487000107765198,"subfield":{"id":"https://openalex.org/subfields/3205","display_name":"Experimental and Cognitive Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.007799999788403511,"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/T11309","display_name":"Music and Audio Processing","score":0.007199999876320362,"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/polyglot","display_name":"Polyglot","score":0.9700999855995178},{"id":"https://openalex.org/keywords/crowds","display_name":"Crowds","score":0.6779999732971191},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.5530999898910522},{"id":"https://openalex.org/keywords/foundation","display_name":"Foundation (evidence)","score":0.5315999984741211},{"id":"https://openalex.org/keywords/crowd-sourcing","display_name":"Crowd sourcing","score":0.39660000801086426},{"id":"https://openalex.org/keywords/adaptation","display_name":"Adaptation (eye)","score":0.38769999146461487},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.3192000091075897},{"id":"https://openalex.org/keywords/overfitting","display_name":"Overfitting","score":0.3142000138759613},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.311599999666214}],"concepts":[{"id":"https://openalex.org/C2780239667","wikidata":"https://www.wikidata.org/wiki/Q2102850","display_name":"Polyglot","level":2,"score":0.9700999855995178},{"id":"https://openalex.org/C2777852691","wikidata":"https://www.wikidata.org/wiki/Q13430821","display_name":"Crowds","level":2,"score":0.6779999732971191},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6513000130653381},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5910000205039978},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.5530999898910522},{"id":"https://openalex.org/C2780966255","wikidata":"https://www.wikidata.org/wiki/Q5474306","display_name":"Foundation (evidence)","level":2,"score":0.5315999984741211},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5224999785423279},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.42320001125335693},{"id":"https://openalex.org/C3018396927","wikidata":"https://www.wikidata.org/wiki/Q275969","display_name":"Crowd sourcing","level":2,"score":0.39660000801086426},{"id":"https://openalex.org/C139807058","wikidata":"https://www.wikidata.org/wiki/Q352374","display_name":"Adaptation (eye)","level":2,"score":0.38769999146461487},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.34540000557899475},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.3192000091075897},{"id":"https://openalex.org/C22019652","wikidata":"https://www.wikidata.org/wiki/Q331309","display_name":"Overfitting","level":3,"score":0.3142000138759613},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.311599999666214},{"id":"https://openalex.org/C136389625","wikidata":"https://www.wikidata.org/wiki/Q334384","display_name":"Supervised learning","level":3,"score":0.298799991607666},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.29600000381469727},{"id":"https://openalex.org/C145912823","wikidata":"https://www.wikidata.org/wiki/Q113558","display_name":"Dynamics (music)","level":2,"score":0.28999999165534973},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.2849999964237213},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.2824999988079071},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.2824000120162964},{"id":"https://openalex.org/C95851461","wikidata":"https://www.wikidata.org/wiki/Q468809","display_name":"Reverberation","level":2,"score":0.26930001378059387},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.2655999958515167},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.2653000056743622},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.2653000056743622},{"id":"https://openalex.org/C157138929","wikidata":"https://www.wikidata.org/wiki/Q570","display_name":"Loudspeaker","level":2,"score":0.26409998536109924},{"id":"https://openalex.org/C2779426996","wikidata":"https://www.wikidata.org/wiki/Q18389128","display_name":"Echo (communications protocol)","level":2,"score":0.258899986743927},{"id":"https://openalex.org/C74672266","wikidata":"https://www.wikidata.org/wiki/Q815859","display_name":"Language acquisition","level":2,"score":0.2542000114917755}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/apsipaasc65261.2025.11249169","is_oa":false,"landing_page_url":"https://doi.org/10.1109/apsipaasc65261.2025.11249169","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 Asia Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":22,"referenced_works":["https://openalex.org/W2104351951","https://openalex.org/W2890964092","https://openalex.org/W3049149679","https://openalex.org/W3167258964","https://openalex.org/W3205324166","https://openalex.org/W3206252155","https://openalex.org/W3209059054","https://openalex.org/W3209984917","https://openalex.org/W3213029956","https://openalex.org/W4285410091","https://openalex.org/W4295308405","https://openalex.org/W4297841583","https://openalex.org/W4311161179","https://openalex.org/W4312951904","https://openalex.org/W4375869379","https://openalex.org/W4385822342","https://openalex.org/W4385822494","https://openalex.org/W4385823241","https://openalex.org/W4388821108","https://openalex.org/W4402112099","https://openalex.org/W4403442400","https://openalex.org/W4408254227"],"related_works":[],"abstract_inverted_index":{"This":[0],"paper":[1],"investigates":[2],"the":[3,33,88,110],"polyglot":[4,18,91],"(multilingual)":[5],"speech":[6,26],"foundation":[7],"models":[8],"(SFMs)":[9],"for":[10,48,112,121],"Crowd":[11],"Emotion":[12],"Recognition":[13],"(CER).":[14],"We":[15],"hypothesize":[16],"that":[17],"SFMs,":[19,92],"pre-trained":[20],"on":[21,68],"diverse":[22],"languages,":[23],"accents,":[24],"and":[25,35,61,81,100],"patterns,":[27],"are":[28],"particularly":[29],"adept":[30],"at":[31],"navigating":[32],"noisy":[34],"complex":[36],"acoustic":[37],"environments":[38],"characteristic":[39],"of":[40,90,114],"crowd":[41],"settings,":[42],"thereby":[43],"offering":[44],"a":[45,55,69],"significant":[46],"advantage":[47],"CER.":[49,122],"To":[50],"substantiate":[51],"this,":[52],"we":[53],"perform":[54],"comprehensive":[56],"analysis,":[57],"comparing":[58],"polyglot,":[59],"monolingual,":[60],"speaker":[62],"recognition":[63],"SFMs":[64,115],"through":[65],"extensive":[66],"experiments":[67],"benchmark":[70],"CER":[71],"dataset":[72],"across":[73,96],"varying":[74],"audio":[75,98],"durations":[76],"(1":[77],"sec,":[78],"500":[79],"ms,":[80],"250":[82],"ms).":[83],"The":[84],"results":[85],"consistently":[86],"demonstrate":[87],"superiority":[89],"outperforming":[93],"their":[94],"counterparts":[95],"all":[97],"lengths":[99],"excelling":[101],"even":[102],"with":[103],"extremely":[104],"short-duration":[105],"inputs.":[106],"These":[107],"findings":[108],"pave":[109],"way":[111],"adaptation":[113],"in":[116],"setting":[117],"up":[118],"new":[119],"benchmarks":[120]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-11-28T00:00:00"}