{"id":"https://openalex.org/W27162768","doi":"https://doi.org/10.21437/eurospeech.1997-503","title":"Acoustic clustering and adaptation for robust speech recognition","display_name":"Acoustic clustering and adaptation for robust speech recognition","publication_year":1997,"publication_date":"1997-09-22","ids":{"openalex":"https://openalex.org/W27162768","doi":"https://doi.org/10.21437/eurospeech.1997-503","mag":"27162768"},"language":"en","primary_location":{"id":"doi:10.21437/eurospeech.1997-503","is_oa":false,"landing_page_url":"https://doi.org/10.21437/eurospeech.1997-503","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/A5003679010","display_name":"Larry Heck","orcid":"https://orcid.org/0000-0003-3358-6362"},"institutions":[{"id":"https://openalex.org/I1298353152","display_name":"SRI International","ror":"https://ror.org/05s570m15","country_code":"US","type":"nonprofit","lineage":["https://openalex.org/I1298353152"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Larry Heck","raw_affiliation_strings":["SRI, International;"],"affiliations":[{"raw_affiliation_string":"SRI, International;","institution_ids":["https://openalex.org/I1298353152"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5104349809","display_name":"Ananth Sankar","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ananth Sankar","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5003679010"],"corresponding_institution_ids":["https://openalex.org/I1298353152"],"apc_list":null,"apc_paid":null,"fwci":0.6038,"has_fulltext":false,"cited_by_count":15,"citation_normalized_percentile":{"value":0.72706892,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"1867","last_page":"1870"},"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/T11309","display_name":"Music and Audio Processing","score":0.9997000098228455,"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/T10860","display_name":"Speech and Audio Processing","score":0.9995999932289124,"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/cluster-analysis","display_name":"Cluster analysis","score":0.78865647315979},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7618474960327148},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.735407292842865},{"id":"https://openalex.org/keywords/hierarchical-clustering","display_name":"Hierarchical clustering","score":0.598897397518158},{"id":"https://openalex.org/keywords/adaptation","display_name":"Adaptation (eye)","score":0.5514748692512512},{"id":"https://openalex.org/keywords/test-data","display_name":"Test data","score":0.5395928621292114},{"id":"https://openalex.org/keywords/acoustic-model","display_name":"Acoustic model","score":0.5166726112365723},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.5119284391403198},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.49096158146858215},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.4603763222694397},{"id":"https://openalex.org/keywords/test-set","display_name":"Test set","score":0.4199222922325134},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4119390845298767},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.3742777705192566}],"concepts":[{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.78865647315979},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7618474960327148},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.735407292842865},{"id":"https://openalex.org/C92835128","wikidata":"https://www.wikidata.org/wiki/Q1277447","display_name":"Hierarchical clustering","level":3,"score":0.598897397518158},{"id":"https://openalex.org/C139807058","wikidata":"https://www.wikidata.org/wiki/Q352374","display_name":"Adaptation (eye)","level":2,"score":0.5514748692512512},{"id":"https://openalex.org/C16910744","wikidata":"https://www.wikidata.org/wiki/Q7705759","display_name":"Test data","level":2,"score":0.5395928621292114},{"id":"https://openalex.org/C155635449","wikidata":"https://www.wikidata.org/wiki/Q4674699","display_name":"Acoustic model","level":3,"score":0.5166726112365723},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.5119284391403198},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.49096158146858215},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.4603763222694397},{"id":"https://openalex.org/C169903167","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Test set","level":2,"score":0.4199222922325134},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4119390845298767},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.3742777705192566},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","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}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.21437/eurospeech.1997-503","is_oa":false,"landing_page_url":"https://doi.org/10.21437/eurospeech.1997-503","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:10.1.1.50.5922","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.50.5922","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"ftp://ftp.speech.sri.com/pub/papers/eurospeech.97.heck.ps","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":7,"referenced_works":["https://openalex.org/W127709214","https://openalex.org/W136723611","https://openalex.org/W2037740282","https://openalex.org/W2082474452","https://openalex.org/W2098773974","https://openalex.org/W2100969003","https://openalex.org/W2139884663"],"related_works":["https://openalex.org/W2914064142","https://openalex.org/W173802198","https://openalex.org/W2028462208","https://openalex.org/W4285337533","https://openalex.org/W2982831492","https://openalex.org/W1955848339","https://openalex.org/W3138055416","https://openalex.org/W2187490799","https://openalex.org/W1574942924","https://openalex.org/W3094735304"],"abstract_inverted_index":{"We":[0,39],"describe":[1],"an":[2,63,136],"algorithm":[3,108],"based":[4],"on":[5,125],"acoustic":[6,9,53,65],"clustering":[7,66],"and":[8,31,55],"adaptation":[10],"to":[11,28,51,71,89,100],"significantly":[12],"improve":[13],"speech":[14,23,82],"recognition":[15,83],"performance.":[16],"The":[17,68,81],"method":[18],"is":[19,27,36,46,70],"particularly":[20],"useful":[21],"when":[22],"from":[24,104],"multiple":[25],"speakers":[26,35],"be":[29],"recognized":[30],"the":[32,52,102,115,126],"boundary":[33],"between":[34],"not":[37],"known.":[38],"assume":[40],"that":[41,77,105,135],"each":[42,90],"test":[43,75,91],"data":[44,92,103,130],"segment":[45],"relatively":[47],"homogeneous":[48],"with":[49],"respect":[50],"background":[54],"speaker.":[56],"These":[57],"segments":[58,76],"are":[59,78,85,98,123],"then":[60,86],"grouped":[61],"using":[62,143],"agglomerative":[64],"algorithm.":[67,145],"idea":[69],"group":[72],"together":[73],"all":[74],"acoustically":[79],"similar.":[80],"models":[84,97],"adapted":[87,96],"separately":[88],"cluster.":[93,106],"Finally":[94],"these":[95],"used":[99,110],"recognize":[101],"This":[107],"was":[109,133,140],"in":[111],"SRI's":[112],"system":[113],"for":[114],"1996":[116,127],"DARPA":[117],"Hub4":[118],"partitioned":[119],"evaluation.":[120],"Experimental":[121],"results":[122],"presented":[124],"H4":[128],"development":[129],"set.":[131],"It":[132],"found":[134],"improvement":[137],"of":[138],"9.5%":[139],"achieved":[141],"by":[142],"this":[144],"1.":[146],"INTRODUCTION":[147],"Recently":[148],"there":[149],"has":[150],"been":[151],"mu...":[152]},"counts_by_year":[{"year":2017,"cited_by_count":1},{"year":2015,"cited_by_count":1},{"year":2012,"cited_by_count":1}],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}