{"id":"https://openalex.org/W4372260265","doi":"https://doi.org/10.1109/icassp49357.2023.10097160","title":"Automatic Classification of Vocal Intensity Category from Speech","display_name":"Automatic Classification of Vocal Intensity Category from Speech","publication_year":2023,"publication_date":"2023-05-05","ids":{"openalex":"https://openalex.org/W4372260265","doi":"https://doi.org/10.1109/icassp49357.2023.10097160"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49357.2023.10097160","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/icassp49357.2023.10097160","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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/9ad63f6d-95b0-4347-a66c-a81e670d6cc9","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":[{"id":"https://openalex.org/I55279860","display_name":"L-3 Communications (United States)","ror":"https://ror.org/000nwmh60","country_code":"US","type":"company","lineage":["https://openalex.org/I55279860"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Manila Kodali","raw_affiliation_strings":["Communications Engineering,Department of Information","Department of Information, Communications Engineering"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Communications Engineering,Department of Information","institution_ids":["https://openalex.org/I55279860"]},{"raw_affiliation_string":"Department of Information, Communications Engineering","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5080870546","display_name":"Sudarsana Reddy Kadiri","orcid":"https://orcid.org/0000-0001-5806-3053"},"institutions":[{"id":"https://openalex.org/I55279860","display_name":"L-3 Communications (United States)","ror":"https://ror.org/000nwmh60","country_code":"US","type":"company","lineage":["https://openalex.org/I55279860"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Sudarsana Reddy Kadiri","raw_affiliation_strings":["Communications Engineering,Department of Information","Department of Information, Communications Engineering"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Communications Engineering,Department of Information","institution_ids":["https://openalex.org/I55279860"]},{"raw_affiliation_string":"Department of Information, Communications Engineering","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5111580930","display_name":"Laura Laaksonen","orcid":null},"institutions":[{"id":"https://openalex.org/I150589677","display_name":"Tampere University of Applied Sciences","ror":"https://ror.org/00bwtjf83","country_code":"FI","type":"education","lineage":["https://openalex.org/I150589677"]}],"countries":["FI"],"is_corresponding":false,"raw_author_name":"Laura Laaksonen","raw_affiliation_strings":["Huawei Technologies Oy (Finland) Co., Ltd.,Tampere Wireless Headset Audio Lab,Tampere,Finland","Tampere Wireless Headset Audio Lab, Huawei Technologies Oy (Finland) Co., Ltd., Tampere, Finland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Huawei Technologies Oy (Finland) Co., Ltd.,Tampere Wireless Headset Audio Lab,Tampere,Finland","institution_ids":["https://openalex.org/I150589677"]},{"raw_affiliation_string":"Tampere Wireless Headset Audio Lab, Huawei Technologies Oy (Finland) Co., Ltd., Tampere, Finland","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5042186400","display_name":"Paavo Alku","orcid":"https://orcid.org/0000-0002-8173-9418"},"institutions":[{"id":"https://openalex.org/I55279860","display_name":"L-3 Communications (United States)","ror":"https://ror.org/000nwmh60","country_code":"US","type":"company","lineage":["https://openalex.org/I55279860"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Paavo Alku","raw_affiliation_strings":["Communications Engineering,Department of Information","Department of Information, Communications Engineering"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Communications Engineering,Department of Information","institution_ids":["https://openalex.org/I55279860"]},{"raw_affiliation_string":"Department of Information, Communications Engineering","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.1753,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.36742303,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":94},"biblio":{"volume":"123","issue":null,"first_page":"1","last_page":"5"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9995999932289124,"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":0.9995999932289124,"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":0.9994999766349792,"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":0.9991999864578247,"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/spectrogram","display_name":"Spectrogram","score":0.8835092782974243},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7310126423835754},{"id":"https://openalex.org/keywords/phonation","display_name":"Phonation","score":0.6547589302062988},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6526825428009033},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.5170865058898926},{"id":"https://openalex.org/keywords/formant","display_name":"Formant","score":0.5159366726875305},{"id":"https://openalex.org/keywords/signal","display_name":"SIGNAL (programming language)","score":0.5046254396438599},{"id":"https://openalex.org/keywords/linear-predictive-coding","display_name":"Linear predictive coding","score":0.47066935896873474},{"id":"https://openalex.org/keywords/cepstrum","display_name":"Cepstrum","score":0.45645400881767273},{"id":"https://openalex.org/keywords/mel-frequency-cepstrum","display_name":"Mel-frequency cepstrum","score":0.4503905475139618},{"id":"https://openalex.org/keywords/classifier","display_name":"Classifier (UML)","score":0.4427562654018402},{"id":"https://openalex.org/keywords/support-vector-machine","display_name":"Support vector machine","score":0.43985801935195923},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.39447110891342163},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.3102484941482544},{"id":"https://openalex.org/keywords/vowel","display_name":"Vowel","score":0.30739253759384155}],"concepts":[{"id":"https://openalex.org/C45273575","wikidata":"https://www.wikidata.org/wiki/Q578970","display_name":"Spectrogram","level":2,"score":0.8835092782974243},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7310126423835754},{"id":"https://openalex.org/C173988693","wikidata":"https://www.wikidata.org/wiki/Q678132","display_name":"Phonation","level":2,"score":0.6547589302062988},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6526825428009033},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.5170865058898926},{"id":"https://openalex.org/C158215666","wikidata":"https://www.wikidata.org/wiki/Q1414685","display_name":"Formant","level":3,"score":0.5159366726875305},{"id":"https://openalex.org/C2779843651","wikidata":"https://www.wikidata.org/wiki/Q7390335","display_name":"SIGNAL (programming language)","level":2,"score":0.5046254396438599},{"id":"https://openalex.org/C59883199","wikidata":"https://www.wikidata.org/wiki/Q1826438","display_name":"Linear predictive coding","level":3,"score":0.47066935896873474},{"id":"https://openalex.org/C88485024","wikidata":"https://www.wikidata.org/wiki/Q1054571","display_name":"Cepstrum","level":2,"score":0.45645400881767273},{"id":"https://openalex.org/C151989614","wikidata":"https://www.wikidata.org/wiki/Q440370","display_name":"Mel-frequency cepstrum","level":3,"score":0.4503905475139618},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.4427562654018402},{"id":"https://openalex.org/C12267149","wikidata":"https://www.wikidata.org/wiki/Q282453","display_name":"Support vector machine","level":2,"score":0.43985801935195923},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.39447110891342163},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.3102484941482544},{"id":"https://openalex.org/C2779581591","wikidata":"https://www.wikidata.org/wiki/Q36244","display_name":"Vowel","level":2,"score":0.30739253759384155},{"id":"https://openalex.org/C71924100","wikidata":"https://www.wikidata.org/wiki/Q11190","display_name":"Medicine","level":0,"score":0.0},{"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/C548259974","wikidata":"https://www.wikidata.org/wiki/Q569965","display_name":"Audiology","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/icassp49357.2023.10097160","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/icassp49357.2023.10097160","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},{"id":"pmh:oai:aaltodoc.aalto.fi:123456789/111795","is_oa":false,"landing_page_url":"https://aaltodoc.aalto.fi/handle/123456789/111795","pdf_url":null,"source":{"id":"https://openalex.org/S4306401662","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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"G2 Pro gradu, diplomity\u00f6"},{"id":"pmh:oai:aaltodoc.aalto.fi:123456789/125848","is_oa":true,"landing_page_url":"https://research.aalto.fi/en/publications/9ad63f6d-95b0-4347-a66c-a81e670d6cc9","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:123456789/125848","is_oa":true,"landing_page_url":"https://research.aalto.fi/en/publications/9ad63f6d-95b0-4347-a66c-a81e670d6cc9","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":[{"id":"https://metadata.un.org/sdg/5","score":0.5,"display_name":"Gender equality"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320321108","display_name":"Academy of Finland","ror":"https://ror.org/05k73zm37"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":36,"referenced_works":["https://openalex.org/W177407077","https://openalex.org/W1964469912","https://openalex.org/W1968637674","https://openalex.org/W1971243715","https://openalex.org/W1976725440","https://openalex.org/W1991705300","https://openalex.org/W2010841217","https://openalex.org/W2018837547","https://openalex.org/W2022895291","https://openalex.org/W2025386793","https://openalex.org/W2034079859","https://openalex.org/W2038936610","https://openalex.org/W2041649634","https://openalex.org/W2047341518","https://openalex.org/W2072346640","https://openalex.org/W2080278484","https://openalex.org/W2101234009","https://openalex.org/W2125514156","https://openalex.org/W2131406347","https://openalex.org/W2155517073","https://openalex.org/W2398932003","https://openalex.org/W2400137844","https://openalex.org/W2401969501","https://openalex.org/W2471136870","https://openalex.org/W2482235060","https://openalex.org/W2615879453","https://openalex.org/W2885005742","https://openalex.org/W2889254982","https://openalex.org/W2953384591","https://openalex.org/W2995930930","https://openalex.org/W3006688804","https://openalex.org/W3007267003","https://openalex.org/W3127686677","https://openalex.org/W4254718357","https://openalex.org/W6633574636","https://openalex.org/W6713134421"],"related_works":["https://openalex.org/W2025848302","https://openalex.org/W1975454382","https://openalex.org/W2799441357","https://openalex.org/W5449343","https://openalex.org/W2409530148","https://openalex.org/W2053642297","https://openalex.org/W4250508028","https://openalex.org/W4403337003","https://openalex.org/W2070513494","https://openalex.org/W2049648127"],"abstract_inverted_index":{"Regulation":[0],"of":[1,39,46,85,100,120,139,159,212],"vocal":[2,121,140,164],"intensity":[3,12,78,141,165],"is":[4,102,107,147,217],"a":[5,28,86],"fundamental":[6],"phenomenon":[7],"in":[8,136,162],"speech":[9,33,42,51,62,88,101,114,146,160],"communication.":[10],"Vocal":[11],"can":[13,22,90],"be":[14,23,91],"quantified":[15],"using":[16,68,149,192,204],"sound":[17],"pressure":[18],"level":[19,98],"(SPL),":[20],"which":[21],"measured":[24],"easily":[25],"by":[26,35],"recording":[27],"standard":[29],"calibration":[30,48,59],"signal":[31,43,89,106,115],"with":[32,44],"and":[34,61,131,170,179,195],"comparing":[36],"the":[37,40,47,57,74,77,96,105,113,124,144,205,208],"energy":[38],"recorded":[41],"that":[45],"tone.":[49],"Unfortunately,":[50],"recordings":[52],"are":[53,64],"mostly":[54],"conducted":[55],"without":[56],"SPL":[58,75],"signal,":[60],"signals":[63],"saved":[65,87],"to":[66,187],"databases":[67],"arbitrary":[69,110,151],"amplitude":[70,111,152],"scales.":[71],"Therefore,":[72],"neither":[73],"nor":[76],"category":[79,142],"(e.g.":[80],"soft":[81],"or":[82],"loud":[83],"phonation)":[84],"determined":[92],"afterwards.":[93],"Even":[94],"though":[95],"original":[97],"information":[99],"lost":[103],"when":[104,143],"presented":[108],"on":[109],"scales,":[112],"contains":[116],"other":[117],"acoustic":[118],"cues":[119],"intensity.":[122],"In":[123],"current":[125],"study,":[126],"we":[127],"study":[128],"machine":[129,178],"learning":[130,133],"deep":[132,180],"-based":[134],"methods":[135],"automatic":[137,189],"classification":[138,190,210],"input":[145],"expressed":[148],"an":[150],"scale.":[153],"A":[154],"new":[155],"gender-balanced":[156],"database":[157,216],"consisting":[158],"produced":[161],"four":[163],"categories":[166],"(soft,":[167],"normal,":[168],"loud,":[169],"very":[171],"loud)":[172],"was":[173],"first":[174],"recorded.":[175],"Support":[176],"vector":[177],"neural":[181],"network":[182],"(DNN)":[183],"models":[184],"were":[185],"used":[186],"develop":[188],"systems":[191],"spectrograms,":[193],"mel-spectrograms,":[194],"mel-frequency":[196],"cepstral":[197],"coefficients":[198],"as":[199],"features.":[200],"The":[201,215],"DNN":[202],"classifier":[203],"mel-spectrogram":[206],"showed":[207],"best":[209],"accuracy":[211],"about":[213],"90%.":[214],"made":[218],"publicly":[219],"available":[220],"at":[221],"https://bit.ly/3tLPGRx.":[222]},"counts_by_year":[{"year":2024,"cited_by_count":1}],"updated_date":"2026-07-02T09:51:11.867554","created_date":"2025-10-10T00:00:00"}