{"id":"https://openalex.org/W4408457087","doi":"https://doi.org/10.3390/computers14030102","title":"Advanced Identification of Prosodic Boundaries, Speakers, and Accents Through Multi-Task Audio Pre-Processing and Speech Language Models","display_name":"Advanced Identification of Prosodic Boundaries, Speakers, and Accents Through Multi-Task Audio Pre-Processing and Speech Language Models","publication_year":2025,"publication_date":"2025-03-14","ids":{"openalex":"https://openalex.org/W4408457087","doi":"https://doi.org/10.3390/computers14030102"},"language":"en","primary_location":{"id":"doi:10.3390/computers14030102","is_oa":true,"landing_page_url":"https://doi.org/10.3390/computers14030102","pdf_url":"https://www.mdpi.com/2073-431X/14/3/102/pdf?version=1741942935","source":{"id":"https://openalex.org/S4210228075","display_name":"Computers","issn_l":"2073-431X","issn":["2073-431X"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310310987","host_organization_name":"Multidisciplinary Digital Publishing Institute","host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Computers","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.mdpi.com/2073-431X/14/3/102/pdf?version=1741942935","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5093693074","display_name":"Francisco Javier Lima Florido","orcid":"https://orcid.org/0009-0003-2622-3843"},"institutions":[{"id":"https://openalex.org/I82767444","display_name":"Universidad de M\u00e1laga","ror":"https://ror.org/036b2ww28","country_code":"ES","type":"education","lineage":["https://openalex.org/I82767444"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"Francisco Javier Lima Florido","raw_affiliation_strings":["Instituto Universitario de Investigaci\u00f3n de Tecnolog\u00edas Ling\u00fc\u00edsticas Multiling\u00fces (IUITLM), University of Malaga, 29010 Malaga, Spain"],"affiliations":[{"raw_affiliation_string":"Instituto Universitario de Investigaci\u00f3n de Tecnolog\u00edas Ling\u00fc\u00edsticas Multiling\u00fces (IUITLM), University of Malaga, 29010 Malaga, Spain","institution_ids":["https://openalex.org/I82767444"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5079590099","display_name":"Gloria Corpas Pastor","orcid":"https://orcid.org/0000-0001-6688-1531"},"institutions":[{"id":"https://openalex.org/I82767444","display_name":"Universidad de M\u00e1laga","ror":"https://ror.org/036b2ww28","country_code":"ES","type":"education","lineage":["https://openalex.org/I82767444"]}],"countries":["ES"],"is_corresponding":true,"raw_author_name":"Gloria Corpas Pastor","raw_affiliation_strings":["Instituto Universitario de Investigaci\u00f3n de Tecnolog\u00edas Ling\u00fc\u00edsticas Multiling\u00fces (IUITLM), University of Malaga, 29010 Malaga, Spain"],"affiliations":[{"raw_affiliation_string":"Instituto Universitario de Investigaci\u00f3n de Tecnolog\u00edas Ling\u00fc\u00edsticas Multiling\u00fces (IUITLM), University of Malaga, 29010 Malaga, Spain","institution_ids":["https://openalex.org/I82767444"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5079590099"],"corresponding_institution_ids":["https://openalex.org/I82767444"],"apc_list":{"value":1600,"currency":"CHF","value_usd":1732},"apc_paid":{"value":1600,"currency":"CHF","value_usd":1732},"fwci":2.8076,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.89771628,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":"14","issue":"3","first_page":"102","last_page":"102"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9998000264167786,"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":0.9998000264167786,"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":0.9984999895095825,"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":0.9968000054359436,"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":0.6652077436447144},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5941675305366516},{"id":"https://openalex.org/keywords/identification","display_name":"Identification (biology)","score":0.5711855292320251},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5546518564224243},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.4596203863620758},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4572153091430664},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.37804484367370605},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.0642562210559845}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6652077436447144},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5941675305366516},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.5711855292320251},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5546518564224243},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.4596203863620758},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4572153091430664},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.37804484367370605},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.0642562210559845},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"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/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.3390/computers14030102","is_oa":true,"landing_page_url":"https://doi.org/10.3390/computers14030102","pdf_url":"https://www.mdpi.com/2073-431X/14/3/102/pdf?version=1741942935","source":{"id":"https://openalex.org/S4210228075","display_name":"Computers","issn_l":"2073-431X","issn":["2073-431X"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310310987","host_organization_name":"Multidisciplinary Digital Publishing Institute","host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Computers","raw_type":"journal-article"},{"id":"pmh:oai:doaj.org/article:e18f527cd8a14c9983757820e0715dcb","is_oa":true,"landing_page_url":"https://doaj.org/article/e18f527cd8a14c9983757820e0715dcb","pdf_url":null,"source":{"id":"https://openalex.org/S112646816","display_name":"SHILAP Revista de lepidopterolog\u00eda","issn_l":"0300-5267","issn":["0300-5267","2340-4078"],"is_oa":true,"is_in_doaj":true,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Computers, Vol 14, Iss 3, p 102 (2025)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.3390/computers14030102","is_oa":true,"landing_page_url":"https://doi.org/10.3390/computers14030102","pdf_url":"https://www.mdpi.com/2073-431X/14/3/102/pdf?version=1741942935","source":{"id":"https://openalex.org/S4210228075","display_name":"Computers","issn_l":"2073-431X","issn":["2073-431X"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310310987","host_organization_name":"Multidisciplinary Digital Publishing Institute","host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Computers","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":false},"content_urls":{"pdf":"https://content.openalex.org/works/W4408457087.pdf"},"referenced_works_count":65,"referenced_works":["https://openalex.org/W106555234","https://openalex.org/W107354767","https://openalex.org/W179380408","https://openalex.org/W1570629387","https://openalex.org/W1586532344","https://openalex.org/W1965819578","https://openalex.org/W2025617415","https://openalex.org/W2071764087","https://openalex.org/W2102003408","https://openalex.org/W2115551835","https://openalex.org/W2143612262","https://openalex.org/W2160564400","https://openalex.org/W2160815625","https://openalex.org/W2171850596","https://openalex.org/W2501398076","https://openalex.org/W2673722796","https://openalex.org/W2831625831","https://openalex.org/W2890964092","https://openalex.org/W2937501454","https://openalex.org/W2938358845","https://openalex.org/W2946200149","https://openalex.org/W2962788625","https://openalex.org/W2973094925","https://openalex.org/W2973157397","https://openalex.org/W2991213871","https://openalex.org/W3008357631","https://openalex.org/W3009344039","https://openalex.org/W3015213852","https://openalex.org/W3015678936","https://openalex.org/W3015780472","https://openalex.org/W3036601975","https://openalex.org/W3085139254","https://openalex.org/W3097378616","https://openalex.org/W3162508345","https://openalex.org/W3170201991","https://openalex.org/W3197530164","https://openalex.org/W4206472724","https://openalex.org/W4214556932","https://openalex.org/W4220953074","https://openalex.org/W4224927243","https://openalex.org/W4252272339","https://openalex.org/W4252331534","https://openalex.org/W4256161595","https://openalex.org/W4295936633","https://openalex.org/W4297841447","https://openalex.org/W4297841566","https://openalex.org/W4309475413","https://openalex.org/W4311000453","https://openalex.org/W4366829200","https://openalex.org/W4372344102","https://openalex.org/W4379193822","https://openalex.org/W4385573729","https://openalex.org/W4389521026","https://openalex.org/W4399188511","https://openalex.org/W4399740272","https://openalex.org/W4401236403","https://openalex.org/W4401822528","https://openalex.org/W4402683820","https://openalex.org/W4403975771","https://openalex.org/W4405365437","https://openalex.org/W4406859174","https://openalex.org/W6739901393","https://openalex.org/W6780218876","https://openalex.org/W6785362200","https://openalex.org/W6809832847"],"related_works":["https://openalex.org/W2981428355","https://openalex.org/W1834994814","https://openalex.org/W2041273198","https://openalex.org/W1599055764","https://openalex.org/W2131711534","https://openalex.org/W2149163000","https://openalex.org/W2962858469","https://openalex.org/W2289873871","https://openalex.org/W2559040841","https://openalex.org/W114661351"],"abstract_inverted_index":{"In":[0,101,140],"recent":[1],"years,":[2],"the":[3,133,168,180,183],"advances":[4],"in":[5,25,52,57,76,137],"deep":[6],"neural":[7],"networks":[8],"(DNNs)":[9],"and":[10,20,46,60,89,111,116,127,155,194],"large":[11,96],"language":[12],"models":[13,42,71],"(LLMs)":[14],"have":[15,72,82],"led":[16],"to":[17,33,108,172,187],"major":[18],"breakthroughs":[19],"new":[21,39,41,175],"levels":[22],"of":[23,98,104,132,160,182],"performance":[24,51,181],"Natural":[26],"Language":[27],"Processing":[28],"(NLP),":[29],"including":[30],"tasks":[31,88,135],"related":[32],"speech":[34,53,62,78,114],"processing.":[35],"Based":[36],"on":[37],"these":[38,70,138],"trends,":[40],"such":[43],"as":[44],"Whisper":[45],"Wav2Vec":[47,148],"2.0":[48,149],"achieve":[49],"robust":[50],"processing":[54],"tasks,":[55],"even":[56],"speech-to-text":[58],"translation":[59],"end-to-end":[61],"translation,":[63],"far":[64],"exceeding":[65],"all":[66],"previous":[67],"results.":[68],"Although":[69],"shown":[73],"excellent":[74],"results":[75],"real-time":[77],"processing,":[79],"they":[80],"still":[81],"some":[83,87,131],"accuracy":[84],"issues":[85],"for":[86,113,152,167,191],"high":[90],"latency":[91],"problems":[92],"when":[93],"working":[94],"with":[95,185],"amounts":[97],"audio":[99,107,156,192],"data.":[100],"addition,":[102],"many":[103],"them":[105],"need":[106],"be":[109,165],"segmented":[110],"labelled":[112],"synthesis":[115],"annotation":[117],"tasks.":[118],"Speaker":[119],"diarisation,":[120],"background":[121],"noise":[122],"detection,":[123],"prosodic":[124,188],"boundary":[125],"detection":[126,190],"accent":[128,196],"classification":[129,154],"are":[130],"pre-processing":[134],"required":[136],"cases.":[139],"this":[141,174],"study,":[142],"we":[143],"will":[144,164],"fine-tune":[145],"a":[146],"small":[147],"base":[150],"model":[151,184],"multi-task":[153],"segmentation.":[157],"A":[158],"corpus":[159],"spoken":[161],"American":[162],"English":[163],"used":[166],"experiments.":[169],"We":[170],"intend":[171],"explore":[173],"approach":[176],"and,":[177],"more":[178],"specifically,":[179],"regard":[186],"boundaries":[189],"segmentation,":[193],"advanced":[195],"identification.":[197]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-02-27T16:54:17.756197","created_date":"2025-10-10T00:00:00"}