{"id":"https://openalex.org/W2128841238","doi":"https://doi.org/10.1109/icassp.2002.5743787","title":"Acoustic-phonetic speech parameters for speaker-independent speech recognition","display_name":"Acoustic-phonetic speech parameters for speaker-independent speech recognition","publication_year":2002,"publication_date":"2002-05-01","ids":{"openalex":"https://openalex.org/W2128841238","doi":"https://doi.org/10.1109/icassp.2002.5743787","mag":"2128841238"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2002.5743787","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2002.5743787","pdf_url":null,"source":{"id":"https://openalex.org/S4363607879","display_name":"IEEE International Conference on Acoustics Speech and Signal Processing","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":"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/A5091331877","display_name":"Om Deshmukh","orcid":null},"institutions":[{"id":"https://openalex.org/I66946132","display_name":"University of Maryland, College Park","ror":"https://ror.org/047s2c258","country_code":"US","type":"education","lineage":["https://openalex.org/I66946132"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Om Deshmukh","raw_affiliation_strings":["Department of Electrical & Computer Engineering, University of Maryland, College Park, MD, USA","University of Maryland, Department of Electrical & Computer Engineering, A. V. Williams Bldg., College Park, 20752, USA"],"affiliations":[{"raw_affiliation_string":"Department of Electrical & Computer Engineering, University of Maryland, College Park, MD, USA","institution_ids":["https://openalex.org/I66946132"]},{"raw_affiliation_string":"University of Maryland, Department of Electrical & Computer Engineering, A. V. Williams Bldg., College Park, 20752, USA","institution_ids":["https://openalex.org/I66946132"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5078241735","display_name":"Carol Espy-Wilson","orcid":"https://orcid.org/0000-0002-1012-183X"},"institutions":[{"id":"https://openalex.org/I66946132","display_name":"University of Maryland, College Park","ror":"https://ror.org/047s2c258","country_code":"US","type":"education","lineage":["https://openalex.org/I66946132"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Carol Y. Espy-Wilson","raw_affiliation_strings":["Department of Electrical & Computer Engineering, University of Maryland, College Park, MD, USA","University of Maryland, Department of Electrical & Computer Engineering, A. V. Williams Bldg., College Park, 20752, USA"],"affiliations":[{"raw_affiliation_string":"Department of Electrical & Computer Engineering, University of Maryland, College Park, MD, USA","institution_ids":["https://openalex.org/I66946132"]},{"raw_affiliation_string":"University of Maryland, Department of Electrical & Computer Engineering, A. V. Williams Bldg., College Park, 20752, USA","institution_ids":["https://openalex.org/I66946132"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5109070201","display_name":"Amit Juneja","orcid":null},"institutions":[{"id":"https://openalex.org/I66946132","display_name":"University of Maryland, College Park","ror":"https://ror.org/047s2c258","country_code":"US","type":"education","lineage":["https://openalex.org/I66946132"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Amit Juneja","raw_affiliation_strings":["Department of Electrical & Computer Engineering, University of Maryland, College Park, MD, USA","University of Maryland, Department of Electrical & Computer Engineering, A. V. Williams Bldg., College Park, 20752, USA"],"affiliations":[{"raw_affiliation_string":"Department of Electrical & Computer Engineering, University of Maryland, College Park, MD, USA","institution_ids":["https://openalex.org/I66946132"]},{"raw_affiliation_string":"University of Maryland, Department of Electrical & Computer Engineering, A. V. Williams Bldg., College Park, 20752, USA","institution_ids":["https://openalex.org/I66946132"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5091331877"],"corresponding_institution_ids":["https://openalex.org/I66946132"],"apc_list":null,"apc_paid":null,"fwci":3.5803,"has_fulltext":false,"cited_by_count":21,"citation_normalized_percentile":{"value":0.95,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":96},"biblio":{"volume":"3","issue":null,"first_page":"I","last_page":"593"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9990000128746033,"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":0.9990000128746033,"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":0.9933000206947327,"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":0.9783999919891357,"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/speech-recognition","display_name":"Speech recognition","score":0.847652018070221},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7747460603713989},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.7251607775688171},{"id":"https://openalex.org/keywords/vocal-tract","display_name":"Vocal tract","score":0.6887921094894409},{"id":"https://openalex.org/keywords/mel-frequency-cepstrum","display_name":"Mel-frequency cepstrum","score":0.6800858974456787},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.5803183317184448},{"id":"https://openalex.org/keywords/speaker-diarisation","display_name":"Speaker diarisation","score":0.4437348246574402},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.4302581548690796},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.39625638723373413},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.3094859719276428}],"concepts":[{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.847652018070221},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7747460603713989},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.7251607775688171},{"id":"https://openalex.org/C47401133","wikidata":"https://www.wikidata.org/wiki/Q748953","display_name":"Vocal tract","level":2,"score":0.6887921094894409},{"id":"https://openalex.org/C151989614","wikidata":"https://www.wikidata.org/wiki/Q440370","display_name":"Mel-frequency cepstrum","level":3,"score":0.6800858974456787},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.5803183317184448},{"id":"https://openalex.org/C149838564","wikidata":"https://www.wikidata.org/wiki/Q7574248","display_name":"Speaker diarisation","level":3,"score":0.4437348246574402},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.4302581548690796},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.39625638723373413},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.3094859719276428}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/icassp.2002.5743787","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2002.5743787","pdf_url":null,"source":{"id":"https://openalex.org/S4363607879","display_name":"IEEE International Conference on Acoustics Speech and Signal Processing","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":"IEEE International Conference on Acoustics Speech and Signal Processing","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.12.8930","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.12.8930","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.enee.umd.edu/~juneja/icassp_digits.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Gender equality","score":0.550000011920929,"id":"https://metadata.un.org/sdg/5"},{"display_name":"Quality Education","score":0.44999998807907104,"id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":11,"referenced_works":["https://openalex.org/W150988814","https://openalex.org/W1616590059","https://openalex.org/W2036483592","https://openalex.org/W2099838536","https://openalex.org/W2160017196","https://openalex.org/W2165871906","https://openalex.org/W3080540467","https://openalex.org/W4297941543","https://openalex.org/W6606114000","https://openalex.org/W6636362120","https://openalex.org/W6684567468"],"related_works":["https://openalex.org/W2189089965","https://openalex.org/W2416972381","https://openalex.org/W2480869102","https://openalex.org/W134286696","https://openalex.org/W2402949781","https://openalex.org/W181359039","https://openalex.org/W132353998","https://openalex.org/W2163541010","https://openalex.org/W4327774276","https://openalex.org/W2128841238"],"abstract_inverted_index":{"Coping":[0],"with":[1],"inter-speaker":[2],"variability":[3],"(i.e.,":[4],"differences":[5,32],"in":[6,33,73],"the":[7,52,61,74,79,86],"vocal":[8],"tract":[9],"characteristics":[10],"of":[11,78],"speakers)":[12],"is":[13,49,70],"still":[14],"a":[15,27,54,71],"major":[16],"challenge":[17],"for":[18,31],"Automatic":[19],"Speech":[20],"Recognizers.":[21],"In":[22,36],"this":[23],"paper,":[24],"we":[25,38],"discuss":[26],"method":[28],"that":[29,40],"compensates":[30],"speaker":[34],"characteristics.":[35],"particular,":[37],"demonstrate":[39],"when":[41,68],"continuous":[42],"density":[43],"hidden":[44],"Markov":[45],"model":[46],"based":[47],"system":[48],"used":[50,81],"as":[51],"back-end,":[53],"Knowledge-Based":[55],"Front":[56],"End":[57],"(KBFE)":[58],"can":[59],"outperform":[60],"traditional":[62],"Mel-Frequency":[63],"Cepstral":[64],"Coefficients":[65],"(MFCCs),":[66],"particularly":[67],"there":[69],"mismatch":[72],"gender":[75],"and":[76,84,97],"ages":[77],"subjects":[80],"to":[82],"train":[83],"test":[85],"recognizer.":[87],"This":[88],"work":[89],"was":[90],"supported":[91],"by":[92],"NSF":[93],"grant":[94,99],"#":[95,100],"SBR-9729688":[96],"NIH":[98],"IK02DCOOI49.":[101]},"counts_by_year":[{"year":2017,"cited_by_count":1},{"year":2012,"cited_by_count":2}],"updated_date":"2026-04-05T17:49:38.594831","created_date":"2025-10-10T00:00:00"}