{"id":"https://openalex.org/W2144343335","doi":"https://doi.org/10.1109/icassp.2009.4960544","title":"Emotional speech recognition based on style estimation and adaptation with multiple-regression HMM","display_name":"Emotional speech recognition based on style estimation and adaptation with multiple-regression HMM","publication_year":2009,"publication_date":"2009-04-01","ids":{"openalex":"https://openalex.org/W2144343335","doi":"https://doi.org/10.1109/icassp.2009.4960544","mag":"2144343335"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2009.4960544","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2009.4960544","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2009 IEEE International Conference on Acoustics, Speech and Signal Processing","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/A5068604686","display_name":"Yusuke Ijima","orcid":null},"institutions":[{"id":"https://openalex.org/I114531698","display_name":"Tokyo Institute of Technology","ror":"https://ror.org/0112mx960","country_code":"JP","type":"education","lineage":["https://openalex.org/I114531698"]}],"countries":["JP"],"is_corresponding":true,"raw_author_name":"Yusuke Ijima","raw_affiliation_strings":["Interdisciplinary Graduate School of Science and Engineering, Tokyo Institute of Technology, Yokohama, Japan","Interdisciplinary Graduate School of Science and Engineering Tokyo Institute of Technology Yokohama 226-8502 Japan"],"affiliations":[{"raw_affiliation_string":"Interdisciplinary Graduate School of Science and Engineering, Tokyo Institute of Technology, Yokohama, Japan","institution_ids":["https://openalex.org/I114531698"]},{"raw_affiliation_string":"Interdisciplinary Graduate School of Science and Engineering Tokyo Institute of Technology Yokohama 226-8502 Japan","institution_ids":["https://openalex.org/I114531698"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5029705460","display_name":"Makoto Tachibana","orcid":"https://orcid.org/0000-0002-5907-5563"},"institutions":[{"id":"https://openalex.org/I114531698","display_name":"Tokyo Institute of Technology","ror":"https://ror.org/0112mx960","country_code":"JP","type":"education","lineage":["https://openalex.org/I114531698"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Makoto Tachibana","raw_affiliation_strings":["Interdisciplinary Graduate School of Science and Engineering, Tokyo Institute of Technology, Yokohama, Japan","Interdisciplinary Graduate School of Science and Engineering Tokyo Institute of Technology Yokohama 226-8502 Japan"],"affiliations":[{"raw_affiliation_string":"Interdisciplinary Graduate School of Science and Engineering, Tokyo Institute of Technology, Yokohama, Japan","institution_ids":["https://openalex.org/I114531698"]},{"raw_affiliation_string":"Interdisciplinary Graduate School of Science and Engineering Tokyo Institute of Technology Yokohama 226-8502 Japan","institution_ids":["https://openalex.org/I114531698"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103144936","display_name":"Takashi Nose","orcid":"https://orcid.org/0000-0001-5403-0019"},"institutions":[{"id":"https://openalex.org/I114531698","display_name":"Tokyo Institute of Technology","ror":"https://ror.org/0112mx960","country_code":"JP","type":"education","lineage":["https://openalex.org/I114531698"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Takashi Nose","raw_affiliation_strings":["Interdisciplinary Graduate School of Science and Engineering, Tokyo Institute of Technology, Yokohama, Japan","Interdisciplinary Graduate School of Science and Engineering Tokyo Institute of Technology Yokohama 226-8502 Japan"],"affiliations":[{"raw_affiliation_string":"Interdisciplinary Graduate School of Science and Engineering, Tokyo Institute of Technology, Yokohama, Japan","institution_ids":["https://openalex.org/I114531698"]},{"raw_affiliation_string":"Interdisciplinary Graduate School of Science and Engineering Tokyo Institute of Technology Yokohama 226-8502 Japan","institution_ids":["https://openalex.org/I114531698"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5022405100","display_name":"Takao Kobayashi","orcid":"https://orcid.org/0000-0003-0387-8030"},"institutions":[{"id":"https://openalex.org/I114531698","display_name":"Tokyo Institute of Technology","ror":"https://ror.org/0112mx960","country_code":"JP","type":"education","lineage":["https://openalex.org/I114531698"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Takao Kobayashi","raw_affiliation_strings":["Interdisciplinary Graduate School of Science and Engineering, Tokyo Institute of Technology, Yokohama, Japan","Interdisciplinary Graduate School of Science and Engineering Tokyo Institute of Technology Yokohama 226-8502 Japan"],"affiliations":[{"raw_affiliation_string":"Interdisciplinary Graduate School of Science and Engineering, Tokyo Institute of Technology, Yokohama, Japan","institution_ids":["https://openalex.org/I114531698"]},{"raw_affiliation_string":"Interdisciplinary Graduate School of Science and Engineering Tokyo Institute of Technology Yokohama 226-8502 Japan","institution_ids":["https://openalex.org/I114531698"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5068604686"],"corresponding_institution_ids":["https://openalex.org/I114531698"],"apc_list":null,"apc_paid":null,"fwci":1.7623,"has_fulltext":false,"cited_by_count":10,"citation_normalized_percentile":{"value":0.85008794,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"4157","last_page":"4160"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9994999766349792,"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":0.9994999766349792,"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":0.9991999864578247,"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/T10667","display_name":"Emotion and Mood Recognition","score":0.9909999966621399,"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/speech-recognition","display_name":"Speech recognition","score":0.7548290491104126},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.7435033321380615},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7219902276992798},{"id":"https://openalex.org/keywords/paralanguage","display_name":"Paralanguage","score":0.7089384198188782},{"id":"https://openalex.org/keywords/style","display_name":"Style (visual arts)","score":0.6220526695251465},{"id":"https://openalex.org/keywords/sentence","display_name":"Sentence","score":0.5402066707611084},{"id":"https://openalex.org/keywords/adaptation","display_name":"Adaptation (eye)","score":0.5135619640350342},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4742530882358551},{"id":"https://openalex.org/keywords/contrast","display_name":"Contrast (vision)","score":0.43351301550865173},{"id":"https://openalex.org/keywords/emotion-recognition","display_name":"Emotion recognition","score":0.4182561933994293},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.4122900366783142},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4109310209751129},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.39459025859832764},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.18801045417785645},{"id":"https://openalex.org/keywords/communication","display_name":"Communication","score":0.10149914026260376}],"concepts":[{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7548290491104126},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.7435033321380615},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7219902276992798},{"id":"https://openalex.org/C133378560","wikidata":"https://www.wikidata.org/wiki/Q1753225","display_name":"Paralanguage","level":2,"score":0.7089384198188782},{"id":"https://openalex.org/C2776445246","wikidata":"https://www.wikidata.org/wiki/Q1792644","display_name":"Style (visual arts)","level":2,"score":0.6220526695251465},{"id":"https://openalex.org/C2777530160","wikidata":"https://www.wikidata.org/wiki/Q41796","display_name":"Sentence","level":2,"score":0.5402066707611084},{"id":"https://openalex.org/C139807058","wikidata":"https://www.wikidata.org/wiki/Q352374","display_name":"Adaptation (eye)","level":2,"score":0.5135619640350342},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4742530882358551},{"id":"https://openalex.org/C2776502983","wikidata":"https://www.wikidata.org/wiki/Q690182","display_name":"Contrast (vision)","level":2,"score":0.43351301550865173},{"id":"https://openalex.org/C2777438025","wikidata":"https://www.wikidata.org/wiki/Q1339090","display_name":"Emotion recognition","level":2,"score":0.4182561933994293},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.4122900366783142},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4109310209751129},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.39459025859832764},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.18801045417785645},{"id":"https://openalex.org/C46312422","wikidata":"https://www.wikidata.org/wiki/Q11024","display_name":"Communication","level":1,"score":0.10149914026260376},{"id":"https://openalex.org/C169760540","wikidata":"https://www.wikidata.org/wiki/Q207011","display_name":"Neuroscience","level":1,"score":0.0},{"id":"https://openalex.org/C95457728","wikidata":"https://www.wikidata.org/wiki/Q309","display_name":"History","level":0,"score":0.0},{"id":"https://openalex.org/C166957645","wikidata":"https://www.wikidata.org/wiki/Q23498","display_name":"Archaeology","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp.2009.4960544","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2009.4960544","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2009 IEEE International Conference on Acoustics, Speech and Signal Processing","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.699999988079071,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":11,"referenced_works":["https://openalex.org/W22005490","https://openalex.org/W75704375","https://openalex.org/W172929083","https://openalex.org/W208375010","https://openalex.org/W1493898446","https://openalex.org/W2101967488","https://openalex.org/W2160379050","https://openalex.org/W2165108269","https://openalex.org/W2484208911","https://openalex.org/W6683927816","https://openalex.org/W7024953085"],"related_works":["https://openalex.org/W2064370490","https://openalex.org/W3166813893","https://openalex.org/W2910013580","https://openalex.org/W2391900574","https://openalex.org/W3200958703","https://openalex.org/W1990078780","https://openalex.org/W3108667266","https://openalex.org/W2376619307","https://openalex.org/W3118437876","https://openalex.org/W1527444722"],"abstract_inverted_index":{"This":[0],"paper":[1],"proposes":[2],"a":[3,48,68],"technique":[4,26,100],"for":[5],"emotional":[6,54,106],"speech":[7,23,64,85,107],"recognition":[8,86,103],"which":[9],"enables":[10],"us":[11],"to":[12],"extract":[13],"paralinguistic":[14],"information":[15,20],"as":[16,18],"well":[17],"linguistic":[19],"contained":[21],"in":[22,89],"signal.":[24],"The":[25],"is":[27,65,87],"based":[28],"on":[29,67,101],"style":[30,33,49,80],"estimation":[31],"and":[32,57,82,113,116],"adaptation":[34],"using":[35,77],"multiple-regression":[36],"HMM.":[37],"Recognition":[38],"process":[39],"consists":[40],"of":[41,59,62,97,104,120],"two":[42],"stages.":[43],"In":[44],"the":[45,53,72,78,90,95,98,102,118,121],"first":[46],"stage,":[47],"vector":[50,81],"that":[51],"represents":[52],"expression":[55],"category":[56],"intensity":[58],"its":[60],"variation":[61],"input":[63],"estimated":[66,79],"sentence-by-sentence":[69],"basis.":[70],"Then":[71],"acoustic":[73],"models":[74],"are":[75],"adapted":[76],"standard":[83],"HMM-based":[84],"performed":[88],"second":[91],"stage.":[92],"We":[93],"assess":[94],"performance":[96],"proposed":[99],"acted":[105],"uttered":[108],"by":[109],"both":[110],"professional":[111],"narrators":[112],"non-professional":[114],"speakers":[115],"show":[117],"effectiveness":[119],"technique.":[122]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2021,"cited_by_count":1},{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":1},{"year":2015,"cited_by_count":1},{"year":2012,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
