{"id":"https://openalex.org/W30596880","doi":null,"title":"Heterogeneous acoustic measurements and multiple classifiers for speech recognition","display_name":"Heterogeneous acoustic measurements and multiple classifiers for speech recognition","publication_year":1999,"publication_date":"1999-01-01","ids":{"openalex":"https://openalex.org/W30596880","mag":"30596880"},"language":"en","primary_location":{"id":"pmh:oai:dspace.mit.edu:1721.1/79971","doi":null,"is_oa":true,"landing_page_url":"http://hdl.handle.net/1721.1/79971","pdf_url":"http://hdl.handle.net/1721.1/79971","source":{"id":"https://openalex.org/S4306400425","display_name":"DSpace@MIT (Massachusetts Institute of Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I63966007","host_organization_name":"Massachusetts Institute of Technology","host_organization_lineage":["https://openalex.org/I63966007"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Thesis"},"volume":null,"type":"dissertation","is_traditional":true,"indexed_in":[],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"http://hdl.handle.net/1721.1/79971","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5081435473","display_name":"Andrew K. Halberstadt","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Andrew K. Halberstadt","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5112758056","display_name":"James Robert Glass","orcid":"https://orcid.org/0000-0002-3097-360X","observed_orcids":["https://orcid.org/0000-0002-3097-360X"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"James Glass","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":90,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9990000128746033,"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":0.9990000128746033,"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":0.00039999998989515007,"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/T10403","display_name":"Phonetics and Phonology Research","score":0.0003000000142492354,"subfield":{"id":"https://openalex.org/subfields/3205","display_name":"Experimental and Cognitive Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/speech-recognition","display_name":"speech recognition","score":0.734000027179718},{"id":"https://openalex.org/keywords/classifier-combination","display_name":"classifier combination","score":0.6930000185966492},{"id":"https://openalex.org/keywords/phonetic-categorization","display_name":"phonetic classification","score":0.8149999976158142},{"id":"https://openalex.org/keywords/phonetic-recognition","display_name":"phonetic recognition","score":0.9490000009536743},{"id":"https://openalex.org/keywords/word-recognition","display_name":"word recognition","score":0.9210000038146973},{"id":"https://openalex.org/keywords/stop-consonants","display_name":"stop consonants","score":0.8389999866485596},{"id":"https://openalex.org/keywords/time-frequency-resolution","display_name":"time-frequency resolution","score":0.7540000081062317},{"id":"https://openalex.org/keywords/spectral-representation","display_name":"spectral representation","score":0.765999972820282},{"id":"https://openalex.org/keywords/telephone-speech","display_name":"telephone speech","score":0.4519999921321869},{"id":"https://openalex.org/keywords/timit","display_name":"TIMIT","score":0.7059999704360962},{"id":"https://openalex.org/keywords/human-machine-comparison","display_name":"human-machine comparison","score":0.7630000114440918}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7388095259666443},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7074171304702759},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5106454491615295},{"id":"https://openalex.org/C34736171","wikidata":"https://www.wikidata.org/wiki/Q918333","display_name":"Preprocessor","level":2,"score":0.4897487163543701},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.4632616639137268},{"id":"https://openalex.org/C2778724510","wikidata":"https://www.wikidata.org/wiki/Q7670405","display_name":"TIMIT","level":3,"score":0.4360194802284241},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.42560359835624695},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.4148930609226227},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3990553319454193},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:dspace.mit.edu:1721.1/79971","doi":null,"is_oa":true,"landing_page_url":"http://hdl.handle.net/1721.1/79971","pdf_url":"http://hdl.handle.net/1721.1/79971","source":{"id":"https://openalex.org/S4306400425","display_name":"DSpace@MIT (Massachusetts Institute of Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I63966007","host_organization_name":"Massachusetts Institute of Technology","host_organization_lineage":["https://openalex.org/I63966007"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Thesis"},{"id":"mag:30596880","doi":null,"is_oa":false,"landing_page_url":"https://dspace.mit.edu/handle/1721.1/79971","pdf_url":null,"source":null,"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":null}],"best_oa_location":{"id":"pmh:oai:dspace.mit.edu:1721.1/79971","doi":null,"is_oa":true,"landing_page_url":"http://hdl.handle.net/1721.1/79971","pdf_url":"http://hdl.handle.net/1721.1/79971","source":{"id":"https://openalex.org/S4306400425","display_name":"DSpace@MIT (Massachusetts Institute of Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I63966007","host_organization_name":"Massachusetts Institute of Technology","host_organization_lineage":["https://openalex.org/I63966007"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Thesis"},"sustainable_development_goals":[],"study_designs":[],"awards":[{"id":"https://openalex.org/G3460900289","display_name":"STIMULATE:  A Hierarchical Framework for Speech Recognition and Understanding","funder_award_id":"9618731","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G6562790071","display_name":null,"funder_award_id":"81772467","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G7393305094","display_name":null,"funder_award_id":"16411964600","funder_id":"https://openalex.org/F4320321885","funder_display_name":"Science and Technology Commission of Shanghai Municipality"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320306095","display_name":"American Cancer Society","ror":"https://ror.org/02e463172"},{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320321885","display_name":"Science and Technology Commission of Shanghai Municipality","ror":"https://ror.org/03kt66j61"},{"id":"https://openalex.org/F4320332180","display_name":"Defense Advanced Research Projects Agency","ror":"https://ror.org/02caytj08"},{"id":"https://openalex.org/F4320333120","display_name":"Holden Comprehensive Cancer Center, University of Iowa","ror":"https://ror.org/01jhe7086"},{"id":"https://openalex.org/F8213333748","display_name":"University of Iowa Libraries","ror":null}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W30596880.pdf","grobid_xml":"https://content.openalex.org/works/W30596880.grobid-xml"},"referenced_works_count":77,"referenced_works":["https://openalex.org/W3285877","https://openalex.org/W67341498","https://openalex.org/W110409126","https://openalex.org/W128564322","https://openalex.org/W133953651","https://openalex.org/W152459128","https://openalex.org/W162417025","https://openalex.org/W175164482","https://openalex.org/W180282077","https://openalex.org/W186915233","https://openalex.org/W567962357","https://openalex.org/W1500768201","https://openalex.org/W1512884713","https://openalex.org/W1528985505","https://openalex.org/W1536460598","https://openalex.org/W1554663460","https://openalex.org/W1566375193","https://openalex.org/W1583244341","https://openalex.org/W1610605641","https://openalex.org/W1640154593","https://openalex.org/W1647054946","https://openalex.org/W1713240683","https://openalex.org/W1871378514","https://openalex.org/W1877154798","https://openalex.org/W1902505171","https://openalex.org/W1904457459","https://openalex.org/W1932968309","https://openalex.org/W1965201650","https://openalex.org/W1970533835","https://openalex.org/W1973664945","https://openalex.org/W1974540032","https://openalex.org/W1979789261","https://openalex.org/W1987679106","https://openalex.org/W2002411303","https://openalex.org/W2012024503","https://openalex.org/W2031127240","https://openalex.org/W2042247992","https://openalex.org/W2047511547","https://openalex.org/W2049633694","https://openalex.org/W2056145427","https://openalex.org/W2062803643","https://openalex.org/W2077555370","https://openalex.org/W2077804127","https://openalex.org/W2090861223","https://openalex.org/W2092009475","https://openalex.org/W2097395002","https://openalex.org/W2097897204","https://openalex.org/W2104663520","https://openalex.org/W2105024701","https://openalex.org/W2112143507","https://openalex.org/W2120996511","https://openalex.org/W2121551440","https://openalex.org/W2121783296","https://openalex.org/W2135674597","https://openalex.org/W2140567543","https://openalex.org/W2140661214","https://openalex.org/W2143137842","https://openalex.org/W2148154194","https://openalex.org/W2152131029","https://openalex.org/W2153723410","https://openalex.org/W2158286329","https://openalex.org/W2163680580","https://openalex.org/W2164931619","https://openalex.org/W2164952084","https://openalex.org/W2165490943","https://openalex.org/W2165871906","https://openalex.org/W2169513726","https://openalex.org/W2169951677","https://openalex.org/W2222708513","https://openalex.org/W2229459702","https://openalex.org/W2232411433","https://openalex.org/W2278747065","https://openalex.org/W2728109360","https://openalex.org/W2903126092","https://openalex.org/W2990525441","https://openalex.org/W2991416376","https://openalex.org/W3017143921"],"related_works":["https://openalex.org/W7097305829","https://openalex.org/W1562289873","https://openalex.org/W7048956944","https://openalex.org/W55249335","https://openalex.org/W4244947139","https://openalex.org/W2400345866","https://openalex.org/W4205144734","https://openalex.org/W4233289729","https://openalex.org/W4230723169","https://openalex.org/W1802969839"],"abstract_inverted_index":{"The":[0],"acoustic-phonetic":[1,72],"modeling":[2],"component":[3],"of":[4,14,71,92,99,102,138,141,189],"most":[5],"current":[6,142],"speech":[7,77,104],"recognition":[8,29,177,214,241],"systems":[9,112,185],"calculates":[10],"a":[11,19,36,243],"small":[12],"set":[13],"homogeneous":[15],"frame-based":[16],"measurements":[17,66,79,164],"at":[18],"single,":[20],"fixed":[21],"time-frequency":[22,85],"resolution.This":[23],"thesis":[24],"presents":[25],"evidence":[26],"indicating":[27],"that":[28,206,235],"performance":[30],"can":[31],"be":[32],"significantly":[33],"improved":[34],"through":[35,123,149],"contrasting":[37],"approach":[38],"using":[39,162,216],"more":[40,43],"detailed":[41],"and":[42,96,125,160,165,175,191,197],"diverse":[44],"acoustic":[45,65,118,245],"measurements,":[46],"which":[47,155],"we":[48,207],"refer":[49],"to":[50,62,67,109,135,239],"as":[51],"heterogeneous":[52,64,117,163],"measurements.This":[53],"investigation":[54],"has":[55],"three":[56],"principal":[57],"goals.The":[58],"first":[59],"goal":[60,107,133],"is":[61,108,121,134,147],"develop":[63,110],"increase":[68,136],"the":[69,76,84,87,90,100,103,139,179,204,217,221],"amount":[70],"information":[73,225],"extracted":[74],"from":[75],"signal.Diverse":[78],"are":[80,203],"obtained":[81],"by":[82],"varying":[83],"resolution,":[86],"spectral":[88],"representation,":[89],"choice":[91],"temporal":[93],"basis":[94],"vectors,":[95],"other":[97],"aspects":[98],"preprocessing":[101],"waveform.The":[105],"second":[106],"classifier":[111],"for":[113,128,193],"successfully":[114],"utilizing":[115],"high-dimensional":[116],"measurement":[119],"spaces.This":[120],"accomplished":[122,148],"hierarchical":[124],"committee-based":[126],"techniques":[127,237],"combining":[129],"multiple":[130,166],"classifiers.The":[131],"third":[132],"understanding":[137],"weaknesses":[140],"automatic":[143],"phonetic":[144,171,173,195,199],"classification":[145,196],"systems.This":[146],"perceptual":[150],"experiments":[151,215],"on":[152,211],"stop":[153],"consonants":[154],"facilitate":[156],"comparisons":[157],"between":[158],"humans":[159],"machines.Systems":[161],"classifiers":[167],"were":[168],"evaluated":[169],"in":[170,242],"classification,":[172],"recognition,":[174,200],"word":[176,229,240],"tasks.On":[178],"TIMIT":[180],"core":[181],"test":[182],"set,":[183],"these":[184,212,236],"achieved":[186],"error":[187,230],"rates":[188],"18.3%":[190],"24.4%":[192],"context-independent":[194],"context-dependent":[198],"respectively.These":[201],"results":[202],"best":[205],"have":[208],"seen":[209],"reported":[210],"tasks.Word":[213],"corpus":[218],"associated":[219],"with":[220],"JUPITER":[222],"telephone-based":[223],"weather":[224],"system":[226],"showed":[227],"10-16%":[228],"rate":[231],"reduction,":[232],"thus":[233],"demonstrating":[234],"generalize":[238],"telephone-bandwidth":[244],"environment.":[246]},"counts_by_year":[{"year":2021,"cited_by_count":3},{"year":2020,"cited_by_count":2},{"year":2019,"cited_by_count":2},{"year":2018,"cited_by_count":3},{"year":2017,"cited_by_count":3},{"year":2016,"cited_by_count":2},{"year":2015,"cited_by_count":9},{"year":2014,"cited_by_count":4},{"year":2013,"cited_by_count":4},{"year":2012,"cited_by_count":9}],"updated_date":"2026-11-08T12:12:28.789561","created_date":"2016-06-24T00:00:00"}