{"id":"https://openalex.org/W2132505049","doi":"https://doi.org/10.1109/asru.2007.4430129","title":"Broad phonetic class recognition in a Hidden Markov model framework using extended Baum-Welch transformations","display_name":"Broad phonetic class recognition in a Hidden Markov model framework using extended Baum-Welch transformations","publication_year":2007,"publication_date":"2007-01-01","ids":{"openalex":"https://openalex.org/W2132505049","doi":"https://doi.org/10.1109/asru.2007.4430129","mag":"2132505049"},"language":"en","primary_location":{"id":"doi:10.1109/asru.2007.4430129","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asru.2007.4430129","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2007 IEEE Workshop on Automatic Speech Recognition & Understanding (ASRU)","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/A5070513394","display_name":"Tara N. Sainath","orcid":"https://orcid.org/0000-0002-4126-6556"},"institutions":[{"id":"https://openalex.org/I1341412227","display_name":"IBM (United States)","ror":"https://ror.org/05hh8d621","country_code":"US","type":"company","lineage":["https://openalex.org/I1341412227"]},{"id":"https://openalex.org/I4210114115","display_name":"IBM Research - Thomas J. Watson Research Center","ror":"https://ror.org/0265w5591","country_code":"US","type":"facility","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210114115"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Tara N. Sainath","raw_affiliation_strings":["IBM Thomas J. Watson Research Center, Yorktown, NY, USA","[IBM, Yorktown Heights]"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IBM Thomas J. Watson Research Center, Yorktown, NY, USA","institution_ids":["https://openalex.org/I4210114115"]},{"raw_affiliation_string":"[IBM, Yorktown Heights]","institution_ids":["https://openalex.org/I1341412227"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5046671967","display_name":"Dimitri Kanevsky","orcid":null},"institutions":[{"id":"https://openalex.org/I1341412227","display_name":"IBM (United States)","ror":"https://ror.org/05hh8d621","country_code":"US","type":"company","lineage":["https://openalex.org/I1341412227"]},{"id":"https://openalex.org/I4210114115","display_name":"IBM Research - Thomas J. Watson Research Center","ror":"https://ror.org/0265w5591","country_code":"US","type":"facility","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210114115"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Dimitri Kanevsky","raw_affiliation_strings":["IBM Thomas J. Watson Research Center, Yorktown, NY, USA","[IBM, Yorktown Heights]"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IBM Thomas J. Watson Research Center, Yorktown, NY, USA","institution_ids":["https://openalex.org/I4210114115"]},{"raw_affiliation_string":"[IBM, Yorktown Heights]","institution_ids":["https://openalex.org/I1341412227"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5071715737","display_name":"Bhuvana Ramabhadran","orcid":null},"institutions":[{"id":"https://openalex.org/I1341412227","display_name":"IBM (United States)","ror":"https://ror.org/05hh8d621","country_code":"US","type":"company","lineage":["https://openalex.org/I1341412227"]},{"id":"https://openalex.org/I4210114115","display_name":"IBM Research - Thomas J. Watson Research Center","ror":"https://ror.org/0265w5591","country_code":"US","type":"facility","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210114115"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Bhuvana Ramabhadran","raw_affiliation_strings":["IBM Thomas J. Watson Research Center, Yorktown, NY, USA","[IBM, Yorktown Heights]"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IBM Thomas J. Watson Research Center, Yorktown, NY, USA","institution_ids":["https://openalex.org/I4210114115"]},{"raw_affiliation_string":"[IBM, Yorktown Heights]","institution_ids":["https://openalex.org/I1341412227"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":"b","issue":null,"first_page":"306","last_page":"311"},"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":0.9994000196456909,"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":0.9994000196456909,"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/discriminative-model","display_name":"Discriminative model","score":0.8106404542922974},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.8087807893753052},{"id":"https://openalex.org/keywords/timit","display_name":"TIMIT","score":0.7246745228767395},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6664897799491882},{"id":"https://openalex.org/keywords/metric","display_name":"Metric (unit)","score":0.6630376577377319},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6136598587036133},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.5753272771835327},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.5328771471977234},{"id":"https://openalex.org/keywords/probabilistic-logic","display_name":"Probabilistic logic","score":0.45085564255714417},{"id":"https://openalex.org/keywords/mixture-model","display_name":"Mixture model","score":0.4467323124408722},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.43295592069625854},{"id":"https://openalex.org/keywords/statistical-model","display_name":"Statistical model","score":0.4109008014202118}],"concepts":[{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.8106404542922974},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.8087807893753052},{"id":"https://openalex.org/C2778724510","wikidata":"https://www.wikidata.org/wiki/Q7670405","display_name":"TIMIT","level":3,"score":0.7246745228767395},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6664897799491882},{"id":"https://openalex.org/C176217482","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Metric (unit)","level":2,"score":0.6630376577377319},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6136598587036133},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.5753272771835327},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.5328771471977234},{"id":"https://openalex.org/C49937458","wikidata":"https://www.wikidata.org/wiki/Q2599292","display_name":"Probabilistic logic","level":2,"score":0.45085564255714417},{"id":"https://openalex.org/C61224824","wikidata":"https://www.wikidata.org/wiki/Q2260434","display_name":"Mixture model","level":2,"score":0.4467323124408722},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.43295592069625854},{"id":"https://openalex.org/C114289077","wikidata":"https://www.wikidata.org/wiki/Q3284399","display_name":"Statistical model","level":2,"score":0.4109008014202118},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","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/C21547014","wikidata":"https://www.wikidata.org/wiki/Q1423657","display_name":"Operations management","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/asru.2007.4430129","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asru.2007.4430129","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2007 IEEE Workshop on Automatic Speech Recognition & Understanding (ASRU)","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.154.6299","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.154.6299","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/2007/ASRU_Sainath.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/10","score":0.7799999713897705,"display_name":"Reduced inequalities"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":14,"referenced_works":["https://openalex.org/W129305155","https://openalex.org/W155522212","https://openalex.org/W1567923445","https://openalex.org/W1943381225","https://openalex.org/W1974387177","https://openalex.org/W2100474170","https://openalex.org/W2102898380","https://openalex.org/W2125838338","https://openalex.org/W2149317649","https://openalex.org/W2154887136","https://openalex.org/W2162436288","https://openalex.org/W6605277767","https://openalex.org/W6640591054","https://openalex.org/W7009721181"],"related_works":["https://openalex.org/W2167155152","https://openalex.org/W4324119469","https://openalex.org/W2164868312","https://openalex.org/W2146591867","https://openalex.org/W2155033763","https://openalex.org/W3134920593","https://openalex.org/W1990589093","https://openalex.org/W2160650576","https://openalex.org/W4285282705","https://openalex.org/W2501000458"],"abstract_inverted_index":{"In":[0,72],"many":[1],"pattern":[2],"recognition":[3,92],"tasks,":[4],"given":[5],"some":[6],"input":[7],"data":[8],"and":[9,97,102,129],"a":[10,12,37,54,99],"model,":[11],"probabilistic":[13],"likelihood":[14,127],"score":[15],"is":[16,121],"often":[17],"computed":[18],"to":[19,52,58,65,123],"measure":[20],"how":[21],"well":[22],"the":[23,26,60,63,67,70,78,84,105,112,125],"model":[24,64],"describes":[25],"data.":[27,71],"Extended":[28],"Baum-Welch":[29],"(EBW)":[30],"transformations":[31],"are":[32],"most":[33],"commonly":[34],"used":[35,51],"as":[36],"discriminative":[38],"technique":[39],"for":[40,91],"estimating":[41],"parameters":[42],"of":[43,62,69,86,93,107],"Gaussian":[44],"mixtures,":[45],"though":[46],"recently":[47],"they":[48],"have":[49],"been":[50],"derive":[53],"gradient":[55,80,109,119],"steepness":[56,81],"measurement":[57],"evaluate":[59],"quality":[61],"match":[66],"distribution":[68],"this":[73,108],"paper,":[74],"we":[75],"explore":[76],"applying":[77],"EBW":[79],"metric":[82,110,120],"in":[83,132],"context":[85],"Hidden":[87],"Markov":[88],"Models":[89],"(HMMs)":[90],"broad":[94],"phonetic":[95],"classes":[96],"present":[98],"detailed":[100],"analysis":[101],"results":[103],"on":[104,111],"use":[106],"TIMIT":[113],"corpus.":[114],"We":[115],"find":[116],"that":[117],"our":[118],"able":[122],"outperform":[124],"baseline":[126],"method,":[128],"offers":[130],"improvements":[131],"noisy":[133],"conditions.":[134]},"counts_by_year":[{"year":2016,"cited_by_count":2}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}