{"id":"https://openalex.org/W2097187469","doi":"https://doi.org/10.1109/icassp.2003.1200023","title":"Audio-based context awareness - acoustic modeling and perceptual evaluation","display_name":"Audio-based context awareness - acoustic modeling and perceptual evaluation","publication_year":2004,"publication_date":"2004-01-23","ids":{"openalex":"https://openalex.org/W2097187469","doi":"https://doi.org/10.1109/icassp.2003.1200023","mag":"2097187469"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2003.1200023","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2003.1200023","pdf_url":null,"source":{"id":"https://openalex.org/S4363608982","display_name":"2003 IEEE International Conference on Acoustics, Speech, and Signal Processing, 2003. Proceedings. (ICASSP '03).","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2003 IEEE International Conference on Acoustics, Speech, and Signal Processing, 2003. Proceedings. (ICASSP '03).","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/A5076376566","display_name":"Antti Eronen","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"]},{"id":"https://openalex.org/I4210133110","display_name":"Tampere University","ror":null,"country_code":"FI","type":null,"lineage":["https://openalex.org/I4210133110"]}],"countries":["FI"],"is_corresponding":true,"raw_author_name":"A. Eronen","raw_affiliation_strings":["Institute of Signal Processing, Tampere University of Technology, Tampere, Finland","[Inst. of Signal Process., Tampere Univ. of Technol., Finland]"],"affiliations":[{"raw_affiliation_string":"Institute of Signal Processing, Tampere University of Technology, Tampere, Finland","institution_ids":["https://openalex.org/I4210133110"]},{"raw_affiliation_string":"[Inst. of Signal Process., Tampere Univ. of Technol., Finland]","institution_ids":["https://openalex.org/I150589677"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5111774883","display_name":"J. Tuomi","orcid":null},"institutions":[{"id":"https://openalex.org/I4210133110","display_name":"Tampere University","ror":null,"country_code":"FI","type":null,"lineage":["https://openalex.org/I4210133110"]},{"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":"J. Tuomi","raw_affiliation_strings":["Institute of Signal Processing, Tampere University of Technology, Tampere, Finland","[Inst. of Signal Process., Tampere Univ. of Technol., Finland]"],"affiliations":[{"raw_affiliation_string":"Institute of Signal Processing, Tampere University of Technology, Tampere, Finland","institution_ids":["https://openalex.org/I4210133110"]},{"raw_affiliation_string":"[Inst. of Signal Process., Tampere Univ. of Technol., Finland]","institution_ids":["https://openalex.org/I150589677"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5035987859","display_name":"Anssi Klapuri","orcid":null},"institutions":[{"id":"https://openalex.org/I4210133110","display_name":"Tampere University","ror":null,"country_code":"FI","type":null,"lineage":["https://openalex.org/I4210133110"]},{"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":"A. Klapuri","raw_affiliation_strings":["Institute of Signal Processing, Tampere University of Technology, Tampere, Finland","[Inst. of Signal Process., Tampere Univ. of Technol., Finland]"],"affiliations":[{"raw_affiliation_string":"Institute of Signal Processing, Tampere University of Technology, Tampere, Finland","institution_ids":["https://openalex.org/I4210133110"]},{"raw_affiliation_string":"[Inst. of Signal Process., Tampere Univ. of Technol., Finland]","institution_ids":["https://openalex.org/I150589677"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5028771070","display_name":"Seppo Fagerlund","orcid":null},"institutions":[{"id":"https://openalex.org/I2738502077","display_name":"Nokia (Finland)","ror":"https://ror.org/04pkc8m17","country_code":"FI","type":"company","lineage":["https://openalex.org/I2738502077"]}],"countries":["FI"],"is_corresponding":false,"raw_author_name":"S. Fagerlund","raw_affiliation_strings":["Nokia Research Center Speech, Nokia Group, Finland","[Nokia Research Center Speech, Nokia Group, Finland]"],"affiliations":[{"raw_affiliation_string":"Nokia Research Center Speech, Nokia Group, Finland","institution_ids":["https://openalex.org/I2738502077"]},{"raw_affiliation_string":"[Nokia Research Center Speech, Nokia Group, Finland]","institution_ids":["https://openalex.org/I2738502077"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5054055354","display_name":"T. Sorsa","orcid":null},"institutions":[{"id":"https://openalex.org/I2738502077","display_name":"Nokia (Finland)","ror":"https://ror.org/04pkc8m17","country_code":"FI","type":"company","lineage":["https://openalex.org/I2738502077"]}],"countries":["FI"],"is_corresponding":false,"raw_author_name":"T. Sorsa","raw_affiliation_strings":["Nokia Research Center Speech, Nokia Group, Finland","[Nokia Research Center Speech, Nokia Group, Finland]"],"affiliations":[{"raw_affiliation_string":"Nokia Research Center Speech, Nokia Group, Finland","institution_ids":["https://openalex.org/I2738502077"]},{"raw_affiliation_string":"[Nokia Research Center Speech, Nokia Group, Finland]","institution_ids":["https://openalex.org/I2738502077"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5033513116","display_name":"Ga\u00ebtan Lorho","orcid":null},"institutions":[{"id":"https://openalex.org/I2738502077","display_name":"Nokia (Finland)","ror":"https://ror.org/04pkc8m17","country_code":"FI","type":"company","lineage":["https://openalex.org/I2738502077"]}],"countries":["FI"],"is_corresponding":false,"raw_author_name":"G. Lorho","raw_affiliation_strings":["Nokia Research Center Speech, Nokia Group, Finland","[Nokia Research Center Speech, Nokia Group, Finland]"],"affiliations":[{"raw_affiliation_string":"Nokia Research Center Speech, Nokia Group, Finland","institution_ids":["https://openalex.org/I2738502077"]},{"raw_affiliation_string":"[Nokia Research Center Speech, Nokia Group, Finland]","institution_ids":["https://openalex.org/I2738502077"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5057652089","display_name":"Jyri Huopaniemi","orcid":null},"institutions":[{"id":"https://openalex.org/I2738502077","display_name":"Nokia (Finland)","ror":"https://ror.org/04pkc8m17","country_code":"FI","type":"company","lineage":["https://openalex.org/I2738502077"]}],"countries":["FI"],"is_corresponding":false,"raw_author_name":"J. Huopaniemi","raw_affiliation_strings":["Nokia Research Center Speech, Nokia Group, Finland","[Nokia Research Center Speech, Nokia Group, Finland]"],"affiliations":[{"raw_affiliation_string":"Nokia Research Center Speech, Nokia Group, Finland","institution_ids":["https://openalex.org/I2738502077"]},{"raw_affiliation_string":"[Nokia Research Center Speech, Nokia Group, Finland]","institution_ids":["https://openalex.org/I2738502077"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5076376566"],"corresponding_institution_ids":["https://openalex.org/I150589677","https://openalex.org/I4210133110"],"apc_list":null,"apc_paid":null,"fwci":2.1478,"has_fulltext":false,"cited_by_count":33,"citation_normalized_percentile":{"value":0.87939698,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":"5","issue":null,"first_page":"V","last_page":"529"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9993000030517578,"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":0.9993000030517578,"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/T11309","display_name":"Music and Audio Processing","score":0.9993000030517578,"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":0.995199978351593,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.8718118667602539},{"id":"https://openalex.org/keywords/discriminative-model","display_name":"Discriminative model","score":0.859683096408844},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7124603986740112},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7085122466087341},{"id":"https://openalex.org/keywords/mel-frequency-cepstrum","display_name":"Mel-frequency cepstrum","score":0.6684743762016296},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.5440614819526672},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.5260486602783203},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5029727816581726},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.45869535207748413},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.39855846762657166},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3707007169723511},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.34402239322662354},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.11282625794410706}],"concepts":[{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.8718118667602539},{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.859683096408844},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7124603986740112},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7085122466087341},{"id":"https://openalex.org/C151989614","wikidata":"https://www.wikidata.org/wiki/Q440370","display_name":"Mel-frequency cepstrum","level":3,"score":0.6684743762016296},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.5440614819526672},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.5260486602783203},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5029727816581726},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.45869535207748413},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.39855846762657166},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3707007169723511},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.34402239322662354},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.11282625794410706},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/icassp.2003.1200023","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2003.1200023","pdf_url":null,"source":{"id":"https://openalex.org/S4363608982","display_name":"2003 IEEE International Conference on Acoustics, Speech, and Signal Processing, 2003. Proceedings. (ICASSP '03).","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2003 IEEE International Conference on Acoustics, Speech, and Signal Processing, 2003. Proceedings. (ICASSP '03).","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.5.7874","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.5.7874","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.cs.tut.fi/sgn/arg/music/eronen_icassp03.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/10","display_name":"Reduced inequalities","score":0.7599999904632568}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":6,"referenced_works":["https://openalex.org/W1560013842","https://openalex.org/W1570317704","https://openalex.org/W2012745928","https://openalex.org/W2058189943","https://openalex.org/W3146177989","https://openalex.org/W6665314674"],"related_works":["https://openalex.org/W2990982991","https://openalex.org/W4317383455","https://openalex.org/W2548511587","https://openalex.org/W2422472940","https://openalex.org/W2019475500","https://openalex.org/W2548162870","https://openalex.org/W2162582511","https://openalex.org/W4245698648","https://openalex.org/W2405257913","https://openalex.org/W3133710586"],"abstract_inverted_index":{"The":[0],"paper":[1],"concerns":[2],"the":[3,9,77,81,89,92,95,104,114],"development":[4],"of":[5,11,91,94,116],"a":[6,12,60,86],"system":[7,23,105],"for":[8,51,88],"recognition":[10,115],"context":[13],"or":[14],"an":[15],"environment":[16],"based":[17],"on":[18],"acoustic":[19,41],"information":[20],"only.":[21],"Our":[22],"uses":[24],"Mel-frequency":[25],"cepstral":[26],"coefficients":[27],"and":[28,33,48,53,83,120],"their":[29],"derivatives":[30],"as":[31,40],"features,":[32],"continuous":[34],"density":[35],"hidden":[36],"Markov":[37],"models":[38],"(HMM)":[39],"models.":[42],"We":[43],"evaluate":[44],"different":[45],"model":[46],"topologies":[47],"training":[49,57],"methods":[50],"HMMs":[52],"show":[54],"that":[55,103],"discriminative":[56],"can":[58],"yield":[59],"10%":[61],"reduction":[62],"in":[63,80,113,123],"error":[64],"rate":[65],"compared":[66],"to":[67,75,84,99],"maximum-likelihood":[68],"training.":[69],"A":[70],"listening":[71],"test":[72],"is":[73],"made":[74],"study":[76],"human":[78,100,110],"accuracy":[79],"task":[82],"obtain":[85],"baseline":[87],"assessment":[90],"performance":[93,101],"system.":[96],"Direct":[97],"comparison":[98],"indicates":[102],"performs":[106],"somewhat":[107],"worse":[108],"than":[109],"subjects":[111],"do":[112],"18":[117],"everyday":[118],"contexts":[119],"almost":[121],"comparably":[122],"recognizing":[124],"six":[125],"higher":[126],"level":[127],"categories.":[128]},"counts_by_year":[{"year":2024,"cited_by_count":3},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":3},{"year":2017,"cited_by_count":3},{"year":2016,"cited_by_count":2},{"year":2015,"cited_by_count":1},{"year":2014,"cited_by_count":2},{"year":2012,"cited_by_count":1}],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}
