{"id":"https://openalex.org/W4385823457","doi":"https://doi.org/10.21437/interspeech.2023-2038","title":"Classification of Vocal Intensity Category from Speech using the Wav2vec2 and Whisper Embeddings","display_name":"Classification of Vocal Intensity Category from Speech using the Wav2vec2 and Whisper Embeddings","publication_year":2023,"publication_date":"2023-08-14","ids":{"openalex":"https://openalex.org/W4385823457","doi":"https://doi.org/10.21437/interspeech.2023-2038"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2023-2038","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2023-2038","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"INTERSPEECH 2023","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/29d59351-6c27-4df4-9422-77d00670c769","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":2.0804,"has_fulltext":false,"cited_by_count":13,"citation_normalized_percentile":{"value":0.89033201,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":98,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"4134","last_page":"4138"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9937999844551086,"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":0.9937999844551086,"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/T10863","display_name":"Voice and Speech Disorders","score":0.9386000037193298,"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"}},{"id":"https://openalex.org/T10403","display_name":"Phonetics and Phonology Research","score":0.9312999844551086,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6540432572364807},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.636877715587616},{"id":"https://openalex.org/keywords/intensity","display_name":"Intensity (physics)","score":0.46390244364738464},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.32944607734680176},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.0878034234046936}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6540432572364807},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.636877715587616},{"id":"https://openalex.org/C93038891","wikidata":"https://www.wikidata.org/wiki/Q1061524","display_name":"Intensity (physics)","level":2,"score":0.46390244364738464},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.32944607734680176},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0878034234046936},{"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.2023-2038","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2023-2038","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"INTERSPEECH 2023","raw_type":"proceedings-article"},{"id":"pmh:oai:aaltodoc.aalto.fi:123456789/124645","is_oa":true,"landing_page_url":"https://research.aalto.fi/en/publications/29d59351-6c27-4df4-9422-77d00670c769","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:123456789/124645","is_oa":true,"landing_page_url":"https://research.aalto.fi/en/publications/29d59351-6c27-4df4-9422-77d00670c769","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":[{"display_name":"Gender equality","score":0.44999998807907104,"id":"https://metadata.un.org/sdg/5"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W2358668433","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W2382290278","https://openalex.org/W2350741829","https://openalex.org/W2530322880","https://openalex.org/W1596801655","https://openalex.org/W2359140296"],"abstract_inverted_index":{"In":[0],"speech":[1,9,31,87],"communication,":[2],"talkers":[3],"regulate":[4],"vocal":[5,77],"intensity":[6,13,55,78],"resulting":[7],"in":[8,54,74,133],"signals":[10,88],"of":[11,76,100,129],"different":[12],"categories":[14],"(e.g.,":[15],"soft,":[16],"loud).":[17],"Intensity":[18],"category":[19,56,79],"carries":[20],"important":[21],"information":[22,61],"about":[23],"the":[24,45,119],"speaker's":[25],"health":[26],"and":[27,36,72,83,105],"emotions.":[28],"However,":[29],"many":[30],"databases":[32],"lack":[33],"calibration":[34,60],"information,":[35],"therefore":[37],"sound":[38],"pressure":[39],"level":[40],"cannot":[41],"be":[42,52],"measured":[43],"from":[44,86],"recorded":[46],"data.":[47],"Machine":[48],"learning,":[49],"however,":[50],"can":[51],"used":[53,111],"classification":[57,75],"even":[58],"though":[59],"is":[62,110],"not":[63],"available.":[64],"This":[65],"study":[66],"investigates":[67],"pre-trained":[68,120],"model":[69,121],"embeddings":[70,122],"(Wav2vec2":[71],"Whisper)":[73],"(soft,":[80],"normal,":[81],"loud,":[82],"very":[84],"loud)":[85],"expressed":[89],"using":[90],"arbitrary":[91],"amplitude":[92],"scales.":[93],"We":[94],"use":[95],"a":[96,113],"new":[97],"database":[98],"consisting":[99],"two":[101],"speaking":[102],"tasks":[103],"(sentence":[104],"paragraph).":[106],"Support":[107],"vector":[108],"machine":[109],"as":[112],"classifier.":[114],"Our":[115],"results":[116],"show":[117],"that":[118],"outperformed":[123],"three":[124],"baseline":[125],"features,":[126],"providing":[127],"improvements":[128],"up":[130],"to":[131],"7%(absolute)":[132],"accuracy.":[134]},"counts_by_year":[{"year":2025,"cited_by_count":7},{"year":2024,"cited_by_count":6}],"updated_date":"2026-07-02T09:51:11.867554","created_date":"2025-10-10T00:00:00"}