{"id":"https://openalex.org/W118865840","doi":"https://doi.org/10.21437/eurospeech.1997-542","title":"A comparison of novel techniques for instantaneous speaker adaptation","display_name":"A comparison of novel techniques for instantaneous speaker adaptation","publication_year":1997,"publication_date":"1997-09-22","ids":{"openalex":"https://openalex.org/W118865840","doi":"https://doi.org/10.21437/eurospeech.1997-542","mag":"118865840"},"language":"en","primary_location":{"id":"doi:10.21437/eurospeech.1997-542","is_oa":false,"landing_page_url":"https://doi.org/10.21437/eurospeech.1997-542","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/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":true,"raw_author_name":"Timothy J. Hazen","raw_affiliation_strings":["Spoken Language Systems Group Laboratory for Computer Science Massachusetts Institute of Technology Cambridge, Massachusetts 02139 USA"],"affiliations":[{"raw_affiliation_string":"Spoken Language Systems Group Laboratory for Computer Science Massachusetts Institute of Technology Cambridge, Massachusetts 02139 USA","institution_ids":["https://openalex.org/I63966007"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5112758056","display_name":"James Glass","orcid":"https://orcid.org/0000-0002-3097-360X"},"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":"James R. Glass","raw_affiliation_strings":["Spoken Language Systems Group Laboratory for Computer Science Massachusetts Institute of Technology Cambridge, Massachusetts 02139 USA"],"affiliations":[{"raw_affiliation_string":"Spoken Language Systems Group Laboratory for Computer Science Massachusetts Institute of Technology Cambridge, Massachusetts 02139 USA","institution_ids":["https://openalex.org/I63966007"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5114018312"],"corresponding_institution_ids":["https://openalex.org/I63966007"],"apc_list":null,"apc_paid":null,"fwci":4.8301,"has_fulltext":false,"cited_by_count":39,"citation_normalized_percentile":{"value":0.94715603,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"2047","last_page":"2050"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9998000264167786,"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":0.9998000264167786,"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":0.9973999857902527,"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":0.9882000088691711,"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/computer-science","display_name":"Computer science","score":0.7033931016921997},{"id":"https://openalex.org/keywords/adaptation","display_name":"Adaptation (eye)","score":0.6263453960418701},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5846827626228333},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.06707721948623657}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7033931016921997},{"id":"https://openalex.org/C139807058","wikidata":"https://www.wikidata.org/wiki/Q352374","display_name":"Adaptation (eye)","level":2,"score":0.6263453960418701},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5846827626228333},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.06707721948623657},{"id":"https://openalex.org/C169760540","wikidata":"https://www.wikidata.org/wiki/Q207011","display_name":"Neuroscience","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.21437/eurospeech.1997-542","is_oa":false,"landing_page_url":"https://doi.org/10.21437/eurospeech.1997-542","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:CiteSeerX.psu:10.1.1.377.9481","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.377.9481","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/hazen/publications/Eurospeech97.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.48.5848","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.48.5848","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.sls.lcs.mit.edu/hazen/publications/Eurospeech97.ps.gz","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":5,"referenced_works":["https://openalex.org/W158338006","https://openalex.org/W1643320849","https://openalex.org/W2100969003","https://openalex.org/W2119802228","https://openalex.org/W4299513203"],"related_works":["https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W2358668433","https://openalex.org/W2376932109","https://openalex.org/W2997567050","https://openalex.org/W2382290278","https://openalex.org/W2350741829","https://openalex.org/W2130043461","https://openalex.org/W2530322880"],"abstract_inverted_index":{"This":[0],"paper":[1],"introduces":[2],"two":[3],"novel":[4],"techniques":[5],"for":[6,56,79],"instantaneous":[7,90],"speaker":[8,11,20],"adaptation,":[9],"reference":[10],"weighting":[12],"and":[13,24],"consistency":[14],"modeling.":[15],"An":[16],"approach":[17],"to":[18,38,68],"hierarchical":[19],"clustering":[21,29],"using":[22,93,111],"gender":[23],"speaking":[25],"rate":[26,104],"as":[27],"the":[28,40,48,70,86,94],"criteria":[30],"is":[31],"also":[32],"presented.":[33],"All":[34],"three":[35],"methods":[36],"attempt":[37],"utilize":[39],"underlying":[41],"within-speaker":[42],"correlations":[43,58],"that":[44],"are":[45],"present":[46],"between":[47],"acoustic":[49,75],"realizations":[50],"of":[51,62,72,105,114],"different":[52],"phones.":[53],"By":[54],"accounting":[55],"these":[57,115],"a":[59,99,112],"limited":[60],"amount":[61],"adaptation":[63,87,91],"data":[64],"can":[65],"be":[66],"used":[67],"adapt":[69],"models":[71],"every":[73],"phonetic":[74],"model":[76],"including":[77],"those":[78],"phones":[80],"which":[81],"havenot":[82],"been":[83,109],"observed":[84],"in":[85,101],"data.":[88],"In":[89],"experiments":[92],"DARPA":[95],"Resource":[96],"Management":[97],"corpus,":[98],"reduction":[100],"word":[102],"error":[103],"20":[106],"%":[107],"has":[108],"achieved":[110],"combination":[113],"new":[116],"techniques.":[117]},"counts_by_year":[{"year":2021,"cited_by_count":1},{"year":2018,"cited_by_count":1},{"year":2017,"cited_by_count":1},{"year":2016,"cited_by_count":1},{"year":2015,"cited_by_count":1},{"year":2014,"cited_by_count":5},{"year":2013,"cited_by_count":3},{"year":2012,"cited_by_count":2}],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}