{"id":"https://openalex.org/W1577059319","doi":"https://doi.org/10.21437/interspeech.2004-546","title":"A comparison of normalization and training approaches for ASR-dependent speaker identification","display_name":"A comparison of normalization and training approaches for ASR-dependent speaker identification","publication_year":2004,"publication_date":"2004-10-04","ids":{"openalex":"https://openalex.org/W1577059319","doi":"https://doi.org/10.21437/interspeech.2004-546","mag":"1577059319"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2004-546","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2004-546","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2004","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":[],"countries":[],"is_corresponding":false,"raw_author_name":"Alex Park","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5114018312","display_name":"Timothy J. Hazen","orcid":"https://orcid.org/0009-0006-1413-9590"},"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":"Timothy J. Hazen","raw_affiliation_strings":["Massachusetts Institute of Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Massachusetts Institute of Technology","institution_ids":["https://openalex.org/I63966007"]}]}],"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":4,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"2601","last_page":"2604"},"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":0.9972000122070312,"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/T12031","display_name":"Speech and dialogue systems","score":0.9948999881744385,"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/normalization","display_name":"Normalization (sociology)","score":0.913081169128418},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8204984068870544},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7846493721008301},{"id":"https://openalex.org/keywords/speaker-identification","display_name":"Speaker identification","score":0.7527376413345337},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.665228545665741},{"id":"https://openalex.org/keywords/speaker-diarisation","display_name":"Speaker diarisation","score":0.6082250475883484},{"id":"https://openalex.org/keywords/phone","display_name":"Phone","score":0.5849249362945557},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.535374104976654},{"id":"https://openalex.org/keywords/mixture-model","display_name":"Mixture model","score":0.441369891166687},{"id":"https://openalex.org/keywords/gaussian","display_name":"Gaussian","score":0.42125675082206726},{"id":"https://openalex.org/keywords/identification","display_name":"Identification (biology)","score":0.41089433431625366},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3468863070011139},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.32210439443588257},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.0588056743144989}],"concepts":[{"id":"https://openalex.org/C136886441","wikidata":"https://www.wikidata.org/wiki/Q926129","display_name":"Normalization (sociology)","level":2,"score":0.913081169128418},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8204984068870544},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7846493721008301},{"id":"https://openalex.org/C2986627078","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker identification","level":3,"score":0.7527376413345337},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.665228545665741},{"id":"https://openalex.org/C149838564","wikidata":"https://www.wikidata.org/wiki/Q7574248","display_name":"Speaker diarisation","level":3,"score":0.6082250475883484},{"id":"https://openalex.org/C2778707766","wikidata":"https://www.wikidata.org/wiki/Q202064","display_name":"Phone","level":2,"score":0.5849249362945557},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.535374104976654},{"id":"https://openalex.org/C61224824","wikidata":"https://www.wikidata.org/wiki/Q2260434","display_name":"Mixture model","level":2,"score":0.441369891166687},{"id":"https://openalex.org/C163716315","wikidata":"https://www.wikidata.org/wiki/Q901177","display_name":"Gaussian","level":2,"score":0.42125675082206726},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.41089433431625366},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3468863070011139},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.32210439443588257},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0588056743144989},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C19165224","wikidata":"https://www.wikidata.org/wiki/Q23404","display_name":"Anthropology","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","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/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.21437/interspeech.2004-546","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2004-546","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2004","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.154.7126","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.154.7126","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.sls.csail.mit.edu/sls/publications/2004/ICSLP04_Park.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.202.6317","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.202.6317","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/people/malex/research_files/draft_icslp04.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.7699999809265137}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":8,"referenced_works":["https://openalex.org/W1486557376","https://openalex.org/W1486680178","https://openalex.org/W1504478957","https://openalex.org/W1525353239","https://openalex.org/W1988846520","https://openalex.org/W2069883713","https://openalex.org/W2097225004","https://openalex.org/W2111732304"],"related_works":["https://openalex.org/W36105149","https://openalex.org/W2545131480","https://openalex.org/W4401661962","https://openalex.org/W4247736853","https://openalex.org/W1521049138","https://openalex.org/W2129090883","https://openalex.org/W2997340161","https://openalex.org/W1589374915","https://openalex.org/W2972577568","https://openalex.org/W2136038945"],"abstract_inverted_index":{"In":[0],"this":[1],"paper":[2,71],"we":[3],"discuss":[4],"a":[5,52],"speaker":[6,11,32,66,85,90],"identification":[7],"approach,":[8,56],"called":[9,57],"ASR-dependent":[10],"identification,":[12,33],"that":[13,40,89],"incorporates":[14],"phonetic":[15,44],"knowledge":[16],"into":[17],"the":[18,43,47,74,81,98],"models":[19,91,102],"for":[20,29],"each":[21],"speaker.":[22],"This":[23,70],"approach":[24],"differs":[25],"from":[26],"traditional":[27],"methods":[28],"performing":[30],"textindependent":[31],"such":[34],"as":[35,101],"global":[36],"Gaussian":[37],"mixture":[38],"modeling,":[39],"typically":[41],"ignore":[42],"content":[45],"of":[46,76,83],"speech":[48],"signal.":[49],"We":[50],"introduce":[51],"new":[53],"score":[54],"normalization":[55,68],"phone":[58],"adaptive":[59,67],"normalization,":[60],"which":[61],"improves":[62],"upon":[63],"our":[64,84],"previous":[65],"technique.":[69],"also":[72],"examines":[73],"use":[75],"automatically":[77,94],"generated":[78,95,106],"transcriptions":[79,96],"during":[80],"training":[82],"models.":[86],"Experiments":[87],"show":[88],"trained":[92,103],"using":[93,104],"achieve":[97],"same":[99],"performance":[100],"manually":[105],"transcriptions.":[107],"1.":[108]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}