{"id":"https://openalex.org/W4388118934","doi":"https://doi.org/10.23919/eusipco58844.2023.10289822","title":"Topic Identification for Spontaneous Speech: Enriching Audio Features with Embedded Linguistic Information","display_name":"Topic Identification for Spontaneous Speech: Enriching Audio Features with Embedded Linguistic Information","publication_year":2023,"publication_date":"2023-09-04","ids":{"openalex":"https://openalex.org/W4388118934","doi":"https://doi.org/10.23919/eusipco58844.2023.10289822"},"language":"en","primary_location":{"id":"doi:10.23919/eusipco58844.2023.10289822","is_oa":false,"landing_page_url":"https://doi.org/10.23919/eusipco58844.2023.10289822","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":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.23919/EUSIPCO58844.2023.10289822","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5052292328","display_name":"Dejan Porjazovski","orcid":"https://orcid.org/0000-0002-7219-9042"},"institutions":[{"id":"https://openalex.org/I9927081","display_name":"Aalto University","ror":"https://ror.org/020hwjq30","country_code":"FI","type":"education","lineage":["https://openalex.org/I9927081"]}],"countries":["FI"],"is_corresponding":true,"raw_author_name":"Dejan Porjazovski","raw_affiliation_strings":["Aalto University,Espoo,Finland","Aalto University, Espoo, Finland"],"affiliations":[{"raw_affiliation_string":"Aalto University,Espoo,Finland","institution_ids":["https://openalex.org/I9927081"]},{"raw_affiliation_string":"Aalto University, Espoo, Finland","institution_ids":["https://openalex.org/I9927081"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5058277119","display_name":"Tam\u00e1s Gr\u00f3sz","orcid":"https://orcid.org/0000-0001-7918-9579"},"institutions":[{"id":"https://openalex.org/I9927081","display_name":"Aalto University","ror":"https://ror.org/020hwjq30","country_code":"FI","type":"education","lineage":["https://openalex.org/I9927081"]}],"countries":["FI"],"is_corresponding":false,"raw_author_name":"Tam\u00e1s Gr\u00f3sz","raw_affiliation_strings":["Aalto University,Espoo,Finland","Aalto University, Espoo, Finland"],"affiliations":[{"raw_affiliation_string":"Aalto University,Espoo,Finland","institution_ids":["https://openalex.org/I9927081"]},{"raw_affiliation_string":"Aalto University, Espoo, Finland","institution_ids":["https://openalex.org/I9927081"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5043424064","display_name":"Mikko Kurimo","orcid":"https://orcid.org/0000-0001-5278-7974"},"institutions":[{"id":"https://openalex.org/I9927081","display_name":"Aalto University","ror":"https://ror.org/020hwjq30","country_code":"FI","type":"education","lineage":["https://openalex.org/I9927081"]}],"countries":["FI"],"is_corresponding":false,"raw_author_name":"Mikko Kurimo","raw_affiliation_strings":["Aalto University,Espoo,Finland","Aalto University, Espoo, Finland"],"affiliations":[{"raw_affiliation_string":"Aalto University,Espoo,Finland","institution_ids":["https://openalex.org/I9927081"]},{"raw_affiliation_string":"Aalto University, Espoo, Finland","institution_ids":["https://openalex.org/I9927081"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5052292328"],"corresponding_institution_ids":["https://openalex.org/I9927081"],"apc_list":null,"apc_paid":null,"fwci":0.5116,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.72308658,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"396","last_page":"400"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9994999766349792,"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/T10860","display_name":"Speech and Audio Processing","score":0.9991000294685364,"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":0.8260728716850281},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7040359377861023},{"id":"https://openalex.org/keywords/audio-mining","display_name":"Audio mining","score":0.6582008004188538},{"id":"https://openalex.org/keywords/classifier","display_name":"Classifier (UML)","score":0.5866652727127075},{"id":"https://openalex.org/keywords/acoustic-model","display_name":"Acoustic model","score":0.5592519640922546},{"id":"https://openalex.org/keywords/pipeline","display_name":"Pipeline (software)","score":0.5485868453979492},{"id":"https://openalex.org/keywords/identification","display_name":"Identification (biology)","score":0.4559384882450104},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.44032731652259827},{"id":"https://openalex.org/keywords/modal","display_name":"Modal","score":0.4113715887069702},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.37974491715431213},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.37670910358428955},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.2593846321105957}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8260728716850281},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7040359377861023},{"id":"https://openalex.org/C157968479","wikidata":"https://www.wikidata.org/wiki/Q3079876","display_name":"Audio mining","level":4,"score":0.6582008004188538},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.5866652727127075},{"id":"https://openalex.org/C155635449","wikidata":"https://www.wikidata.org/wiki/Q4674699","display_name":"Acoustic model","level":3,"score":0.5592519640922546},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.5485868453979492},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.4559384882450104},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.44032731652259827},{"id":"https://openalex.org/C71139939","wikidata":"https://www.wikidata.org/wiki/Q910194","display_name":"Modal","level":2,"score":0.4113715887069702},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.37974491715431213},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.37670910358428955},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.2593846321105957},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","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/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C59822182","wikidata":"https://www.wikidata.org/wiki/Q441","display_name":"Botany","level":1,"score":0.0},{"id":"https://openalex.org/C188027245","wikidata":"https://www.wikidata.org/wiki/Q750446","display_name":"Polymer chemistry","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.23919/eusipco58844.2023.10289822","is_oa":false,"landing_page_url":"https://doi.org/10.23919/eusipco58844.2023.10289822","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"},{"id":"pmh:oai:zenodo.org:10158851","is_oa":true,"landing_page_url":"https://doi.org/10.23919/EUSIPCO58844.2023.10289822","pdf_url":null,"source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"2023 31st European Signal Processing Conference (EUSIPCO), (2023-08)","raw_type":"info:eu-repo/semantics/other"}],"best_oa_location":{"id":"pmh:oai:zenodo.org:10158851","is_oa":true,"landing_page_url":"https://doi.org/10.23919/EUSIPCO58844.2023.10289822","pdf_url":null,"source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"2023 31st European Signal Processing Conference (EUSIPCO), (2023-08)","raw_type":"info:eu-repo/semantics/other"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G7234502784","display_name":null,"funder_award_id":"337073,345790","funder_id":"https://openalex.org/F4320321108","funder_display_name":"Academy of Finland"}],"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":21,"referenced_works":["https://openalex.org/W2127141656","https://openalex.org/W2130180273","https://openalex.org/W2168363555","https://openalex.org/W2187089797","https://openalex.org/W2237275956","https://openalex.org/W2624871570","https://openalex.org/W2719865699","https://openalex.org/W2766219058","https://openalex.org/W2916113431","https://openalex.org/W2963230678","https://openalex.org/W2963250244","https://openalex.org/W3008083857","https://openalex.org/W3015797571","https://openalex.org/W3036601975","https://openalex.org/W3198771897","https://openalex.org/W4287993739","https://openalex.org/W4292457883","https://openalex.org/W6739365718","https://openalex.org/W6760790549","https://openalex.org/W6771823989","https://openalex.org/W6780218876"],"related_works":["https://openalex.org/W2121652828","https://openalex.org/W2157598242","https://openalex.org/W2620660273","https://openalex.org/W2619911963","https://openalex.org/W2014474048","https://openalex.org/W2762879233","https://openalex.org/W1969715806","https://openalex.org/W22517275","https://openalex.org/W1554343988","https://openalex.org/W2129389759"],"abstract_inverted_index":{"Traditional":[0],"topic":[1],"identification":[2],"solutions":[3,86,111,126],"from":[4],"audio":[5,98],"rely":[6],"on":[7,103],"an":[8],"automatic":[9],"speech":[10,64,106],"recognition":[11],"system":[12],"(ASR)":[13],"to":[14,20,36,57,82],"produce":[15],"transcripts":[16],"used":[17],"as":[18],"input":[19],"a":[21,58,113],"text-based":[22,60],"model.":[23,75],"These":[24],"approaches":[25],"work":[26],"well":[27],"in":[28,44],"high-resource":[29],"scenarios,":[30],"where":[31],"there":[32],"are":[33,112,119],"sufficient":[34],"data":[35],"train":[37],"both":[38],"components":[39,118],"of":[40,72,93],"the":[41,47,70,73,83,123,128],"pipeline.":[42],"However,":[43],"low-resource":[45],"situations,":[46],"ASR":[48,74,117],"system,":[49],"even":[50],"if":[51],"available,":[52,121],"produces":[53],"low-quality":[54],"transcripts,":[55],"leading":[56],"bad":[59],"classifier.":[61],"Moreover,":[62],"spontaneous":[63,104],"containing":[65],"hesitations":[66],"can":[67],"further":[68],"degrade":[69],"performance":[71],"In":[76],"this":[77],"paper,":[78],"we":[79],"investigate":[80],"alternatives":[81],"standard":[84],"text-only":[85],"by":[87],"comparing":[88],"audio-only":[89],"and":[90,97],"hybrid":[91,124],"techniques":[92],"jointly":[94],"utilising":[95],"text":[96],"features.":[99],"The":[100],"models":[101],"evaluated":[102],"Finnish":[105],"demonstrate":[107],"that":[108],"purely":[109],"audio-based":[110],"viable":[114],"option":[115],"when":[116],"not":[120],"while":[122],"multi-modal":[125],"achieve":[127],"best":[129],"results.":[130]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1}],"updated_date":"2026-04-23T09:07:50.710637","created_date":"2023-11-02T00:00:00"}