{"id":"https://openalex.org/W2100474170","doi":"https://doi.org/10.1109/icassp.2007.366912","title":"Comparison of Large Margin Training to Other Discriminative Methods for Phonetic Recognition by Hidden Markov Models","display_name":"Comparison of Large Margin Training to Other Discriminative Methods for Phonetic Recognition by Hidden Markov Models","publication_year":2007,"publication_date":"2007-04-01","ids":{"openalex":"https://openalex.org/W2100474170","doi":"https://doi.org/10.1109/icassp.2007.366912","mag":"2100474170"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2007.366912","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2007.366912","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2007 IEEE International Conference on Acoustics, Speech and Signal Processing - ICASSP '07","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/A5101544732","display_name":"Fei Sha","orcid":"https://orcid.org/0000-0002-9382-0010"},"institutions":[{"id":"https://openalex.org/I95457486","display_name":"University of California, Berkeley","ror":"https://ror.org/01an7q238","country_code":"US","type":"education","lineage":["https://openalex.org/I95457486"]},{"id":"https://openalex.org/I36788626","display_name":"California University of Pennsylvania","ror":"https://ror.org/01spssf70","country_code":"US","type":"education","lineage":["https://openalex.org/I36788626"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Fei Sha","raw_affiliation_strings":["Computer Science Division, University of California, Berkeley, CA, USA","University of Pennsylvania, USA"],"affiliations":[{"raw_affiliation_string":"Computer Science Division, University of California, Berkeley, CA, USA","institution_ids":["https://openalex.org/I95457486"]},{"raw_affiliation_string":"University of Pennsylvania, USA","institution_ids":["https://openalex.org/I36788626"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5103354854","display_name":"Lawrence K. Saul","orcid":null},"institutions":[{"id":"https://openalex.org/I36258959","display_name":"University of California, San Diego","ror":"https://ror.org/0168r3w48","country_code":"US","type":"education","lineage":["https://openalex.org/I36258959"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Lawrence K. Saul","raw_affiliation_strings":["Department of Computer Science and Engineering, University of California, San Diego, La Jolla, CA, USA"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, University of California, San Diego, La Jolla, CA, USA","institution_ids":["https://openalex.org/I36258959"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5101544732"],"corresponding_institution_ids":["https://openalex.org/I36788626","https://openalex.org/I95457486"],"apc_list":null,"apc_paid":null,"fwci":20.2845,"has_fulltext":false,"cited_by_count":75,"citation_normalized_percentile":{"value":0.99364352,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"IV","last_page":"313"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":1.0,"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":1.0,"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":0.9997000098228455,"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/T11309","display_name":"Music and Audio Processing","score":0.9961000084877014,"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/hidden-markov-model","display_name":"Hidden Markov model","score":0.8918125629425049},{"id":"https://openalex.org/keywords/discriminative-model","display_name":"Discriminative model","score":0.8312174081802368},{"id":"https://openalex.org/keywords/margin","display_name":"Margin (machine learning)","score":0.7446674108505249},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7158658504486084},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6283508539199829},{"id":"https://openalex.org/keywords/maxima-and-minima","display_name":"Maxima and minima","score":0.5919312834739685},{"id":"https://openalex.org/keywords/timit","display_name":"TIMIT","score":0.5581637620925903},{"id":"https://openalex.org/keywords/spurious-relationship","display_name":"Spurious relationship","score":0.5483303070068359},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.5367708206176758},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4945389926433563},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.28678154945373535},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.22257155179977417}],"concepts":[{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.8918125629425049},{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.8312174081802368},{"id":"https://openalex.org/C774472","wikidata":"https://www.wikidata.org/wiki/Q6760393","display_name":"Margin (machine learning)","level":2,"score":0.7446674108505249},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7158658504486084},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6283508539199829},{"id":"https://openalex.org/C186633575","wikidata":"https://www.wikidata.org/wiki/Q845060","display_name":"Maxima and minima","level":2,"score":0.5919312834739685},{"id":"https://openalex.org/C2778724510","wikidata":"https://www.wikidata.org/wiki/Q7670405","display_name":"TIMIT","level":3,"score":0.5581637620925903},{"id":"https://openalex.org/C97256817","wikidata":"https://www.wikidata.org/wiki/Q1462316","display_name":"Spurious relationship","level":2,"score":0.5483303070068359},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.5367708206176758},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4945389926433563},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.28678154945373535},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.22257155179977417},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/icassp.2007.366912","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2007.366912","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2007 IEEE International Conference on Acoustics, Speech and Signal Processing - ICASSP '07","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.136.1060","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.136.1060","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.cs.berkeley.edu/~feisha/pubs/icassp2007.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.219.130","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.219.130","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.cs.ucsd.edu/~saul/papers/icassp07_margin.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Reduced inequalities","id":"https://metadata.un.org/sdg/10","score":0.7099999785423279}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":17,"referenced_works":["https://openalex.org/W1802969839","https://openalex.org/W1877570817","https://openalex.org/W1975953721","https://openalex.org/W2003123121","https://openalex.org/W2033565080","https://openalex.org/W2063541597","https://openalex.org/W2077804127","https://openalex.org/W2104997912","https://openalex.org/W2105644991","https://openalex.org/W2115439799","https://openalex.org/W2148177126","https://openalex.org/W2150142469","https://openalex.org/W2158808283","https://openalex.org/W6675604347","https://openalex.org/W6675760969","https://openalex.org/W6682143068","https://openalex.org/W6682334925"],"related_works":["https://openalex.org/W1565453839","https://openalex.org/W2008638795","https://openalex.org/W2134999511","https://openalex.org/W1507239162","https://openalex.org/W2140027889","https://openalex.org/W2160356362","https://openalex.org/W2096528733","https://openalex.org/W2160277484","https://openalex.org/W2100474170","https://openalex.org/W2118923628"],"abstract_inverted_index":{"In":[0],"this":[1],"paper":[2],"we":[3,17,135],"compare":[4,18],"three":[5,94],"frameworks":[6,95],"for":[7,140],"discriminative":[8],"training":[9,50,143],"of":[10,47,62,77,83,126],"continuous-density":[11],"hidden":[12,64,116],"Markov":[13],"models":[14],"(CD-HMMs).":[15],"Specifically,":[16],"two":[19],"popular":[20],"frameworks,":[21],"based":[22,37],"on":[23,38,100],"conditional":[24],"maximum":[25],"likelihood":[26],"(CML)":[27],"and":[28,43,115,131,152],"minimum":[29],"classification":[30],"error":[31,147],"(MCE),":[32],"to":[33,59,69,96,122],"a":[34,70],"new":[35],"framework":[36,139],"margin":[39,49,142],"maximization.":[40],"Unlike":[41],"CML":[42,151],"MCE,":[44],"our":[45,138],"formulation":[46],"large":[48,141],"explicitly":[51],"penalizes":[52],"incorrect":[53],"decodings":[54],"by":[55],"an":[56],"amount":[57],"proportional":[58],"the":[60,74,81,101,110,124],"number":[61],"mislabeled":[63],"states.":[65],"It":[66],"also":[67],"leads":[68],"convex":[71],"optimization":[72],"over":[73],"parameter":[75],"space":[76],"CD-HMMs,":[78],"thus":[79,119],"avoiding":[80],"problem":[82],"spurious":[84],"local":[85],"minima.":[86],"We":[87],"used":[88],"discriminatively":[89],"trained":[90],"CD-HMMs":[91],"from":[92],"all":[93],"build":[97],"phonetic":[98],"recognizers":[99,107],"TIMIT":[102],"speech":[103],"corpus.":[104],"The":[105],"different":[106,127],"employed":[108],"exactly":[109],"same":[111],"acoustic":[112],"front":[113],"end":[114],"state":[117],"space,":[118],"enabling":[120],"us":[121],"isolate":[123],"effect":[125],"cost":[128],"functions,":[129],"parameterizations,":[130],"numerical":[132],"optimizations.":[133],"Experimentally,":[134],"find":[136],"that":[137],"yields":[144],"significantly":[145],"lower":[146],"rates":[148],"than":[149],"both":[150],"MCE":[153],"training.":[154]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2019,"cited_by_count":1},{"year":2017,"cited_by_count":2},{"year":2016,"cited_by_count":1},{"year":2015,"cited_by_count":1},{"year":2014,"cited_by_count":3},{"year":2013,"cited_by_count":6},{"year":2012,"cited_by_count":7}],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}