{"id":"https://openalex.org/W4402112313","doi":"https://doi.org/10.21437/interspeech.2024-2237","title":"Fine-tuning of Pre-trained Models for Classification of Vocal Intensity Category from Speech Signals","display_name":"Fine-tuning of Pre-trained Models for Classification of Vocal Intensity Category from Speech Signals","publication_year":2024,"publication_date":"2024-09-01","ids":{"openalex":"https://openalex.org/W4402112313","doi":"https://doi.org/10.21437/interspeech.2024-2237"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2024-2237","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2024-2237","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2024","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://research.aalto.fi/en/publications/7ef2ef86-a5c3-4e39-a9e2-70fc4969d0f5","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5042157833","display_name":"Manila Kodali","orcid":"https://orcid.org/0000-0003-4594-4921"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Manila Kodali","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5080870546","display_name":"Sudarsana Reddy Kadiri","orcid":"https://orcid.org/0000-0001-5806-3053"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Sudarsana Reddy Kadiri","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5042186400","display_name":"Paavo Alku","orcid":"https://orcid.org/0000-0002-8173-9418"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Paavo Alku","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.1302,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.81423715,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":95,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"482","last_page":"486"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9897000193595886,"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":0.9897000193595886,"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/T10860","display_name":"Speech and Audio Processing","score":0.9624000191688538,"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/T10863","display_name":"Voice and Speech Disorders","score":0.9143000245094299,"subfield":{"id":"https://openalex.org/subfields/2737","display_name":"Physiology"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6941783428192139},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6850067377090454},{"id":"https://openalex.org/keywords/intensity","display_name":"Intensity (physics)","score":0.4564592242240906},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.44390904903411865},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.05414572358131409}],"concepts":[{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6941783428192139},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6850067377090454},{"id":"https://openalex.org/C93038891","wikidata":"https://www.wikidata.org/wiki/Q1061524","display_name":"Intensity (physics)","level":2,"score":0.4564592242240906},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.44390904903411865},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.05414572358131409},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.21437/interspeech.2024-2237","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2024-2237","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2024","raw_type":"proceedings-article"},{"id":"pmh:oai:aaltodoc.aalto.fi:123456789/132408","is_oa":true,"landing_page_url":"https://research.aalto.fi/en/publications/7ef2ef86-a5c3-4e39-a9e2-70fc4969d0f5","pdf_url":null,"source":{"id":"https://openalex.org/S4306401663","display_name":"Aaltodoc (Aalto University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I9927081","host_organization_name":"Aalto University","host_organization_lineage":["https://openalex.org/I9927081"],"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":null,"raw_type":"info:eu-repo/semantics/article"}],"best_oa_location":{"id":"pmh:oai:aaltodoc.aalto.fi:123456789/132408","is_oa":true,"landing_page_url":"https://research.aalto.fi/en/publications/7ef2ef86-a5c3-4e39-a9e2-70fc4969d0f5","pdf_url":null,"source":{"id":"https://openalex.org/S4306401663","display_name":"Aaltodoc (Aalto University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I9927081","host_organization_name":"Aalto University","host_organization_lineage":["https://openalex.org/I9927081"],"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":null,"raw_type":"info:eu-repo/semantics/article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W4396696052","https://openalex.org/W2382290278","https://openalex.org/W4395014643"],"abstract_inverted_index":{"Speakers":[0],"regulate":[1,23],"vocal":[2,19,24,42,53],"intensity":[3,25,43,54,93,128,134],"on":[4,70,104],"many":[5],"occasions":[6],"for":[7,125],"example":[8],"to":[9,17,123],"be":[10,38],"heard":[11],"over":[12,26],"a":[13,27],"long":[14],"distance":[15],"or":[16],"express":[18],"emotions.":[20],"Humans":[21],"can":[22,37],"wide":[28],"sound":[29],"pressure":[30],"level":[31],"(SPL)":[32],"range":[33],"and":[34,66,118,131],"therefore":[35],"speech":[36,57,83,90,101],"categorized":[39],"into":[40,91],"different":[41],"categories.":[44],"Recent":[45],"machine":[46],"learning":[47],"experiments":[48],"have":[49,60],"studied":[50],"classification":[51,88],"of":[52,89,116],"category":[55,129,135],"from":[56],"signals":[58],"which":[59,67],"been":[61],"recorded":[62],"without":[63],"SPL":[64],"information":[65],"are":[68],"represented":[69],"arbitrary":[71,106],"amplitude":[72,107],"scales.":[73],"By":[74],"fine-tuning":[75],"four":[76,92],"pre-trained":[77],"models":[78],"(wav2vec2-BASE,":[79],"wav2vec2-LARGE,":[80],"HuBERT,":[81],"audio":[82],"transformers),":[84],"this":[85],"paper":[86],"studies":[87],"categories":[94],"(soft,":[95],"normal,":[96],"loud,":[97],"very":[98],"loud),":[99],"when":[100],"is":[102],"presented":[103],"such":[105],"scale.":[108],"The":[109],"fine-tuned":[110],"model":[111],"embeddings":[112],"showed":[113],"absolute":[114],"improvements":[115],"5%":[117],"10-12%":[119],"in":[120],"accuracy":[121],"compared":[122],"baselines":[124],"the":[126,132],"target":[127],"label":[130],"SPL-based":[133],"label,":[136],"respectively.":[137]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":2}],"updated_date":"2026-07-02T09:51:11.867554","created_date":"2025-10-10T00:00:00"}