{"id":"https://openalex.org/W4406461559","doi":"https://doi.org/10.1109/slt61566.2024.10832309","title":"Classification Of Spontaneous And Scripted Speech For Multilingual Audio","display_name":"Classification Of Spontaneous And Scripted Speech For Multilingual Audio","publication_year":2024,"publication_date":"2024-12-02","ids":{"openalex":"https://openalex.org/W4406461559","doi":"https://doi.org/10.1109/slt61566.2024.10832309"},"language":"en","primary_location":{"id":"doi:10.1109/slt61566.2024.10832309","is_oa":false,"landing_page_url":"https://doi.org/10.1109/slt61566.2024.10832309","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE Spoken Language Technology Workshop (SLT)","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/A5114655179","display_name":"Shahar Elisha","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Shahar Elisha","raw_affiliation_strings":["Spotify Ltd"],"affiliations":[{"raw_affiliation_string":"Spotify Ltd","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101328572","display_name":"Andrew McDowell","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Andrew McDowell","raw_affiliation_strings":["Spotify Ltd"],"affiliations":[{"raw_affiliation_string":"Spotify Ltd","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5014735979","display_name":"Mariano Beguerisse-D\u00edaz","orcid":"https://orcid.org/0000-0002-8750-8346"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Mariano Beguerisse-D\u00edaz","raw_affiliation_strings":["Spotify Ltd"],"affiliations":[{"raw_affiliation_string":"Spotify Ltd","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5084672392","display_name":"Emmanouil Benetos","orcid":null},"institutions":[{"id":"https://openalex.org/I166337079","display_name":"Queen Mary University of London","ror":"https://ror.org/026zzn846","country_code":"GB","type":"education","lineage":["https://openalex.org/I124357947","https://openalex.org/I166337079"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Emmanouil Benetos","raw_affiliation_strings":["Queen Mary University of London,Centre for Digital Music"],"affiliations":[{"raw_affiliation_string":"Queen Mary University of London,Centre for Digital Music","institution_ids":["https://openalex.org/I166337079"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5114655179"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.29319484,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"489","last_page":"495"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9998000264167786,"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/T10860","display_name":"Speech and Audio Processing","score":0.9998000264167786,"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/T11309","display_name":"Music 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"}},{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9990000128746033,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7196222543716431},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6733248829841614},{"id":"https://openalex.org/keywords/audio-mining","display_name":"Audio mining","score":0.4791228771209717},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.31748539209365845},{"id":"https://openalex.org/keywords/acoustic-model","display_name":"Acoustic model","score":0.22370216250419617}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7196222543716431},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6733248829841614},{"id":"https://openalex.org/C157968479","wikidata":"https://www.wikidata.org/wiki/Q3079876","display_name":"Audio mining","level":4,"score":0.4791228771209717},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.31748539209365845},{"id":"https://openalex.org/C155635449","wikidata":"https://www.wikidata.org/wiki/Q4674699","display_name":"Acoustic model","level":3,"score":0.22370216250419617}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/slt61566.2024.10832309","is_oa":false,"landing_page_url":"https://doi.org/10.1109/slt61566.2024.10832309","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE Spoken Language Technology Workshop (SLT)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.49000000953674316,"display_name":"Gender equality","id":"https://metadata.un.org/sdg/5"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":43,"referenced_works":["https://openalex.org/W199119985","https://openalex.org/W1558115493","https://openalex.org/W1576161893","https://openalex.org/W1969218003","https://openalex.org/W1977686269","https://openalex.org/W1997124557","https://openalex.org/W2031812806","https://openalex.org/W2078442260","https://openalex.org/W2084543186","https://openalex.org/W2085662862","https://openalex.org/W2239141610","https://openalex.org/W2338447355","https://openalex.org/W2417759506","https://openalex.org/W2513230217","https://openalex.org/W2803098682","https://openalex.org/W2972921407","https://openalex.org/W3026689121","https://openalex.org/W3036601975","https://openalex.org/W3037312903","https://openalex.org/W3091129453","https://openalex.org/W3097109903","https://openalex.org/W3199964822","https://openalex.org/W3205148967","https://openalex.org/W4248034423","https://openalex.org/W4281491776","https://openalex.org/W4296069303","https://openalex.org/W4297775537","https://openalex.org/W4308796119","https://openalex.org/W4312677692","https://openalex.org/W4372259780","https://openalex.org/W4385822353","https://openalex.org/W4385822356","https://openalex.org/W4385823150","https://openalex.org/W4385823457","https://openalex.org/W4388345785","https://openalex.org/W4388585769","https://openalex.org/W4392931772","https://openalex.org/W4402715009","https://openalex.org/W6737664043","https://openalex.org/W6780218876","https://openalex.org/W6847363464","https://openalex.org/W6859004195","https://openalex.org/W6890389421"],"related_works":["https://openalex.org/W2539919382","https://openalex.org/W22517275","https://openalex.org/W2042419400","https://openalex.org/W2122924390","https://openalex.org/W2064347532","https://openalex.org/W2589081144","https://openalex.org/W2171620991","https://openalex.org/W189256204","https://openalex.org/W2981428355","https://openalex.org/W2131711534"],"abstract_inverted_index":{"Distinguishing":[0],"scripted":[1,132],"from":[2,61],"spontaneous":[3,134],"speech":[4,13,16,37,135],"is":[5],"an":[6],"essential":[7],"tool":[8],"for":[9,28,79],"better":[10,32],"understanding":[11],"how":[12],"styles":[14],"influence":[15],"processing":[17],"research.":[18],"It":[19],"can":[20],"also":[21],"improve":[22],"recommendation":[23],"systems":[24],"and":[25,54,65,81,133],"discovery":[26],"experiences":[27],"media":[29],"users":[30],"through":[31],"segmentation":[33],"of":[34,44,88],"large":[35],"recorded":[36],"catalogues.":[38],"This":[39],"paper":[40],"addresses":[41],"the":[42,86,109],"challenge":[43],"building":[45],"a":[46,73],"classifier":[47],"that":[48,118],"generalises":[49],"well":[50],"across":[51,91,136],"different":[52],"formats":[53],"languages.":[55,138],"We":[56,83],"systematically":[57],"evaluate":[58,96],"models":[59,120],"ranging":[60],"traditional,":[62],"handcrafted":[63],"acoustic":[64],"prosodic":[66],"features":[67],"to":[68,95,103,107,112],"advanced":[69],"audio":[70],"transformers,":[71],"utilising":[72],"large,":[74],"multilingual":[75],"proprietary":[76],"podcast":[77],"dataset":[78],"training":[80],"validation.":[82],"break":[84],"down":[85],"performance":[87,128],"each":[89],"model":[90],"11":[92],"language":[93],"groups":[94],"cross-lingual":[97],"biases.":[98],"Our":[99,115],"experimental":[100],"analysis":[101],"extends":[102],"publicly":[104],"available":[105],"datasets":[106],"assess":[108],"models\u2019":[110],"generalisability":[111],"non-podcast":[113],"domains.":[114],"results":[116],"indicate":[117],"transformer-based":[119],"consistently":[121],"outperform":[122],"traditional":[123],"feature-based":[124],"techniques,":[125],"achieving":[126],"state-of-the-art":[127],"in":[129],"distinguishing":[130],"between":[131],"various":[137]},"counts_by_year":[],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}