{"id":"https://openalex.org/W110409126","doi":"https://doi.org/10.21437/eurospeech.1997-552","title":"Speaker normalization and speaker adaptation - a combination for conversational speech recognition","display_name":"Speaker normalization and speaker adaptation - a combination for conversational speech recognition","publication_year":1997,"publication_date":"1997-09-22","ids":{"openalex":"https://openalex.org/W110409126","doi":"https://doi.org/10.21437/eurospeech.1997-552","mag":"110409126"},"language":"en","primary_location":{"id":"doi:10.21437/eurospeech.1997-552","is_oa":false,"landing_page_url":"https://doi.org/10.21437/eurospeech.1997-552","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"5th European Conference on Speech Communication and Technology (Eurospeech 1997)","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/A5109588257","display_name":"Puming Zhan","orcid":null},"institutions":[{"id":"https://openalex.org/I102335020","display_name":"Karlsruhe Institute of Technology","ror":"https://ror.org/04t3en479","country_code":"DE","type":"education","lineage":["https://openalex.org/I102335020","https://openalex.org/I1305996414"]}],"countries":["DE"],"is_corresponding":true,"raw_author_name":"Puming Zhan","raw_affiliation_strings":["Interactive Systems Laboratories Carnegie Mellon University University of Karlsruhe, Germany"],"affiliations":[{"raw_affiliation_string":"Interactive Systems Laboratories Carnegie Mellon University University of Karlsruhe, Germany","institution_ids":["https://openalex.org/I102335020"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5108383045","display_name":"Martin Westphal","orcid":null},"institutions":[{"id":"https://openalex.org/I102335020","display_name":"Karlsruhe Institute of Technology","ror":"https://ror.org/04t3en479","country_code":"DE","type":"education","lineage":["https://openalex.org/I102335020","https://openalex.org/I1305996414"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Martin Westphal","raw_affiliation_strings":["Interactive Systems Laboratories Carnegie Mellon University University of Karlsruhe, Germany"],"affiliations":[{"raw_affiliation_string":"Interactive Systems Laboratories Carnegie Mellon University University of Karlsruhe, Germany","institution_ids":["https://openalex.org/I102335020"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103138098","display_name":"Michael Finke","orcid":"https://orcid.org/0000-0003-2355-7779"},"institutions":[{"id":"https://openalex.org/I102335020","display_name":"Karlsruhe Institute of Technology","ror":"https://ror.org/04t3en479","country_code":"DE","type":"education","lineage":["https://openalex.org/I102335020","https://openalex.org/I1305996414"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Michael Finke","raw_affiliation_strings":["Interactive Systems Laboratories Carnegie Mellon University University of Karlsruhe, Germany"],"affiliations":[{"raw_affiliation_string":"Interactive Systems Laboratories Carnegie Mellon University University of Karlsruhe, Germany","institution_ids":["https://openalex.org/I102335020"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5110453805","display_name":"Alex Waibel","orcid":null},"institutions":[{"id":"https://openalex.org/I102335020","display_name":"Karlsruhe Institute of Technology","ror":"https://ror.org/04t3en479","country_code":"DE","type":"education","lineage":["https://openalex.org/I102335020","https://openalex.org/I1305996414"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Alex Waibel","raw_affiliation_strings":["Interactive Systems Laboratories Carnegie Mellon University University of Karlsruhe, Germany"],"affiliations":[{"raw_affiliation_string":"Interactive Systems Laboratories Carnegie Mellon University University of Karlsruhe, Germany","institution_ids":["https://openalex.org/I102335020"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5109588257"],"corresponding_institution_ids":["https://openalex.org/I102335020"],"apc_list":null,"apc_paid":null,"fwci":1.2076,"has_fulltext":false,"cited_by_count":15,"citation_normalized_percentile":{"value":0.81155706,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"2087","last_page":"2090"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9988999962806702,"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":0.9988999962806702,"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":0.9965999722480774,"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":0.9908000230789185,"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/normalization","display_name":"Normalization (sociology)","score":0.8332654237747192},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7987855076789856},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7564429640769958},{"id":"https://openalex.org/keywords/vocal-tract","display_name":"Vocal tract","score":0.6557216644287109},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.5375691652297974},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.5086544156074524},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.46585613489151},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3829194903373718}],"concepts":[{"id":"https://openalex.org/C136886441","wikidata":"https://www.wikidata.org/wiki/Q926129","display_name":"Normalization (sociology)","level":2,"score":0.8332654237747192},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7987855076789856},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7564429640769958},{"id":"https://openalex.org/C47401133","wikidata":"https://www.wikidata.org/wiki/Q748953","display_name":"Vocal tract","level":2,"score":0.6557216644287109},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.5375691652297974},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.5086544156074524},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.46585613489151},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3829194903373718},{"id":"https://openalex.org/C19165224","wikidata":"https://www.wikidata.org/wiki/Q23404","display_name":"Anthropology","level":1,"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":4,"locations":[{"id":"doi:10.21437/eurospeech.1997-552","is_oa":false,"landing_page_url":"https://doi.org/10.21437/eurospeech.1997-552","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"5th European Conference on Speech Communication and Technology (Eurospeech 1997)","raw_type":"proceedings-article"},{"id":"pmh:oai:EVASTAR-Karlsruhe.de:308497","is_oa":false,"landing_page_url":"https://publikationen.bibliothek.kit.edu/308497","pdf_url":null,"source":{"id":"https://openalex.org/S4306401992","display_name":"Repository KITopen (Karlsruhe Institute of Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I102335020","host_organization_name":"Karlsruhe Institute of Technology","host_organization_lineage":["https://openalex.org/I102335020"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"doc-type:bookPart"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.153.3658","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.153.3658","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.ri.cmu.edu/pub_files/pub1/zhan_puming_1997_1/zhan_puming_1997_1.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.45.9787","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.45.9787","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.ri.cmu.edu/pub_files/pub1/zhan_puming_1997_1/zhan_puming_1997_1.ps.gz","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.550000011920929,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320306078","display_name":"U.S. Department of Defense","ror":"https://ror.org/0447fe631"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":8,"referenced_works":["https://openalex.org/W186411692","https://openalex.org/W1992468098","https://openalex.org/W2090861223","https://openalex.org/W2104663520","https://openalex.org/W2121981798","https://openalex.org/W2140567543","https://openalex.org/W2165871906","https://openalex.org/W4300336696"],"related_works":["https://openalex.org/W1911592522","https://openalex.org/W2087669554","https://openalex.org/W3044757496","https://openalex.org/W153239700","https://openalex.org/W2067459736","https://openalex.org/W2105635394","https://openalex.org/W203970584","https://openalex.org/W4297807400","https://openalex.org/W2499802997","https://openalex.org/W2112059504"],"abstract_inverted_index":{"Speaker":[0],"normalization":[1,21,27],"and":[2,15,69,81,112,125],"speaker":[3,26],"adaptation":[4],"are":[5,127],"two":[6],"strategies":[7],"to":[8,29,105,117,150],"tackle":[9],"the":[10,32,62,65,76,88,97,108,131,136,151],"variations":[11,33,152],"from":[12],"speaker,":[13],"channel,":[14],"environment.":[16],"The":[17,38,83],"vocal":[18,35],"tract":[19,36],"length":[20],"(VTLN)":[22],"is":[23,43,92],"an":[24,71],"effective":[25,94,129],"approach":[28],"compensate":[30],"for":[31,48,74,130,135],"of":[34,64,79,110,153],"shapes.":[37],"Maximum":[39],"Likelihood":[40],"Linear":[41],"Regression(MLLR)":[42],"a":[44,55],"recent":[45],"proposed":[46],"method":[47,91],"speaker-adaptation.":[49],"In":[50],"this":[51],"paper,":[52],"we":[53],"propose":[54],"speaker-specific":[56],"Bark":[57],"scale":[58],"VTLN":[59,66,80,90,111,124],"method,":[60],"investigate":[61],"combination":[63,109],"with":[67,95],"MLLR,":[68],"present":[70],"iterative":[72],"procedure":[73],"decoding":[75],"combined":[77],"system":[78],"MLLR.":[82],"results":[84],"show":[85],"that:":[86],"(1)":[87],"new":[89],"very":[93],"which":[96],"word":[98,119],"error":[99,120],"rate":[100],"can":[101,114],"be":[102],"reduced":[103],"up":[104,116],"11%;":[106],"(2)":[107],"MLLR":[113,126],"provide":[115],"15%":[118],"reduction;":[121],"(3)":[122],"both":[123],"more":[128],"push-to-talk":[132],"data":[133],"than":[134],"cross-talk":[137],"data.":[138],"1":[139],"INTRODUCTION":[140],"Almost":[141],"all":[142],"speech":[143],"recognizers":[144],"are,":[145],"in":[146],"some":[147],"extent,":[148],"sensitive":[149],"speakers":[154],"and/or":[155],"env...":[156]},"counts_by_year":[{"year":2021,"cited_by_count":1}],"updated_date":"2026-04-05T17:49:38.594831","created_date":"2025-10-10T00:00:00"}
