{"id":"https://openalex.org/W1525353239","doi":"https://doi.org/10.21437/icslp.2002-407","title":"ASR dependent techniques for speaker identification","display_name":"ASR dependent techniques for speaker identification","publication_year":2002,"publication_date":"2002-09-16","ids":{"openalex":"https://openalex.org/W1525353239","doi":"https://doi.org/10.21437/icslp.2002-407","mag":"1525353239"},"language":"en","primary_location":{"id":"doi:10.21437/icslp.2002-407","is_oa":false,"landing_page_url":"https://doi.org/10.21437/icslp.2002-407","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"7th International Conference on Spoken Language Processing (ICSLP 2002)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5111429885","display_name":"Alex Park","orcid":null},"institutions":[{"id":"https://openalex.org/I63966007","display_name":"Massachusetts Institute of Technology","ror":"https://ror.org/042nb2s44","country_code":"US","type":"education","lineage":["https://openalex.org/I63966007"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Alex Park","raw_affiliation_strings":["Massachusetts Institute of Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Massachusetts Institute of Technology","institution_ids":["https://openalex.org/I63966007"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5114018312","display_name":"Timothy J. Hazen","orcid":"https://orcid.org/0009-0006-1413-9590"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Timothy J. Hazen","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":62,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1337","last_page":"1340"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9919999837875366,"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":0.989300012588501,"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":0.8109372854232788},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7949832677841187},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.7156813740730286},{"id":"https://openalex.org/keywords/utterance","display_name":"Utterance","score":0.6644611954689026},{"id":"https://openalex.org/keywords/speaker-diarisation","display_name":"Speaker diarisation","score":0.6634270548820496},{"id":"https://openalex.org/keywords/speaker-identification","display_name":"Speaker identification","score":0.6629164218902588},{"id":"https://openalex.org/keywords/mixture-model","display_name":"Mixture model","score":0.6145641207695007},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5356075167655945},{"id":"https://openalex.org/keywords/identification","display_name":"Identification (biology)","score":0.5203613638877869},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.5137587785720825},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4791654646396637},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3568355143070221}],"concepts":[{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.8109372854232788},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7949832677841187},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.7156813740730286},{"id":"https://openalex.org/C2775852435","wikidata":"https://www.wikidata.org/wiki/Q258403","display_name":"Utterance","level":2,"score":0.6644611954689026},{"id":"https://openalex.org/C149838564","wikidata":"https://www.wikidata.org/wiki/Q7574248","display_name":"Speaker diarisation","level":3,"score":0.6634270548820496},{"id":"https://openalex.org/C2986627078","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker identification","level":3,"score":0.6629164218902588},{"id":"https://openalex.org/C61224824","wikidata":"https://www.wikidata.org/wiki/Q2260434","display_name":"Mixture model","level":2,"score":0.6145641207695007},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5356075167655945},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.5203613638877869},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.5137587785720825},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4791654646396637},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3568355143070221},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C59822182","wikidata":"https://www.wikidata.org/wiki/Q441","display_name":"Botany","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.21437/icslp.2002-407","is_oa":false,"landing_page_url":"https://doi.org/10.21437/icslp.2002-407","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"7th International Conference on Spoken Language Processing (ICSLP 2002)","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.330.5822","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.330.5822","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://people.csail.mit.edu/malex/research_files/park_icslp.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.6200000047683716,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":12,"referenced_works":["https://openalex.org/W48148591","https://openalex.org/W141909156","https://openalex.org/W1752971345","https://openalex.org/W1877154798","https://openalex.org/W1982122133","https://openalex.org/W1988846520","https://openalex.org/W2049680645","https://openalex.org/W2069883713","https://openalex.org/W2100969003","https://openalex.org/W2146320039","https://openalex.org/W2156517809","https://openalex.org/W2407803946"],"related_works":["https://openalex.org/W2206035908","https://openalex.org/W2545131480","https://openalex.org/W4401661962","https://openalex.org/W1521049138","https://openalex.org/W2129090883","https://openalex.org/W4247736853","https://openalex.org/W2997340161","https://openalex.org/W2972577568","https://openalex.org/W1964028329","https://openalex.org/W2136038945"],"abstract_inverted_index":{"Traditional":[0],"text":[1],"independent":[2,107],"speaker":[3,31,66,114,118,125],"recognition":[4,39],"systems":[5],"are":[6],"based":[7],"on":[8,52,64,90],"Gaussian":[9],"Mixture":[10],"Models":[11],"(GMMs)":[12],"trained":[13],"globally":[14],"over":[15,132],"all":[16],"speech":[17,38,74],"from":[18,142],"a":[19,43,70,81,133,143],"given":[20],"speaker.":[21,144],"In":[22],"this":[23],"paper,":[24],"we":[25,76,112,120],"describe":[26],"alternative":[27],"methods":[28],"for":[29,117],"performing":[30],"identification":[32,87,126],"that":[33],"utilize":[34],"domain":[35],"dependent":[36,99],"automatic":[37],"(ASR)":[40],"to":[41,79,85,123],"provide":[42],"phonetic":[44],"segmentation":[45],"of":[46,55,83],"the":[47,65,97,105],"test":[48,92,140],"utterance.":[49],"When":[50],"evaluated":[51],"YOHO,":[53],"several":[54],"these":[56],"approaches":[57,100],"were":[58,77,121],"able":[59,78,122],"outperform":[60],"previously":[61],"published":[62],"results":[63],"ID":[67],"task.":[68],"On":[69],"more":[71],"difficult":[72],"conversational":[73],"task,":[75],"use":[80],"combination":[82],"classifiers":[84],"reduce":[86,124],"error":[88,127],"rates":[89,128],"single":[91],"utterances.":[93],"Over":[94],"multiple":[95],"utterances,":[96],"ASR":[98,106],"performed":[101],"significantly":[102],"better":[103],"than":[104],"methods.":[108],"Using":[109],"an":[110],"approach":[111,136],"call":[113],"adaptive":[115],"modelling":[116],"identification,":[119],"by":[129],"39":[130],"%":[131],"baseline":[134],"GMM":[135],"when":[137],"observing":[138],"five":[139],"utterances":[141],"1.":[145]},"counts_by_year":[{"year":2019,"cited_by_count":1},{"year":2017,"cited_by_count":3},{"year":2016,"cited_by_count":3},{"year":2015,"cited_by_count":1},{"year":2014,"cited_by_count":1},{"year":2013,"cited_by_count":2},{"year":2012,"cited_by_count":4}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}
