{"id":"https://openalex.org/W2161329381","doi":"https://doi.org/10.1109/icassp.2012.6288979","title":"Discriminative training for speech recognition is compensating for statistical dependence in the HMM framework","display_name":"Discriminative training for speech recognition is compensating for statistical dependence in the HMM framework","publication_year":2012,"publication_date":"2012-03-01","ids":{"openalex":"https://openalex.org/W2161329381","doi":"https://doi.org/10.1109/icassp.2012.6288979","mag":"2161329381"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2012.6288979","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2012.6288979","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2012 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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/A5110207594","display_name":"Dan Gillick","orcid":null},"institutions":[{"id":"https://openalex.org/I1297971548","display_name":"International Computer Science Institute","ror":"https://ror.org/01ewh7m12","country_code":"US","type":"nonprofit","lineage":["https://openalex.org/I1297971548"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Dan Gillick","raw_affiliation_strings":["International Computer Science Institute, Berkeley, CA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"International Computer Science Institute, Berkeley, CA, USA","institution_ids":["https://openalex.org/I1297971548"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5025957537","display_name":"Steven Wegmann","orcid":null},"institutions":[{"id":"https://openalex.org/I1297971548","display_name":"International Computer Science Institute","ror":"https://ror.org/01ewh7m12","country_code":"US","type":"nonprofit","lineage":["https://openalex.org/I1297971548"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Steven Wegmann","raw_affiliation_strings":["International Computer Science Institute, Berkeley, CA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"International Computer Science Institute, Berkeley, CA, USA","institution_ids":["https://openalex.org/I1297971548"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5058277853","display_name":"Larry Gillick","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Larry Gillick","raw_affiliation_strings":["EnglishCentral, Inc., Arlington, MA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"EnglishCentral, Inc., Arlington, MA, USA","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.3269,"has_fulltext":false,"cited_by_count":17,"citation_normalized_percentile":{"value":0.8472191,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"4745","last_page":"4748"},"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/T10860","display_name":"Speech and Audio Processing","score":0.9983999729156494,"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":0.9908999800682068,"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":0.9295617341995239},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.8708729147911072},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7609730958938599},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7158119678497314},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.5570611357688904},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.5372704267501831},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.526641845703125},{"id":"https://openalex.org/keywords/resampling","display_name":"Resampling","score":0.4799111783504486},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.36116427183151245}],"concepts":[{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.9295617341995239},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.8708729147911072},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7609730958938599},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7158119678497314},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.5570611357688904},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.5372704267501831},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.526641845703125},{"id":"https://openalex.org/C150921843","wikidata":"https://www.wikidata.org/wiki/Q1170431","display_name":"Resampling","level":2,"score":0.4799111783504486},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.36116427183151245}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/icassp.2012.6288979","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2012.6288979","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2012 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.799.8008","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.799.8008","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.icsi.berkeley.edu/pubs/speech/gillickwegmannicassp12.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Reduced inequalities","score":0.7699999809265137,"id":"https://metadata.un.org/sdg/10"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":10,"referenced_works":["https://openalex.org/W943204654","https://openalex.org/W1877570817","https://openalex.org/W1975953721","https://openalex.org/W1978741356","https://openalex.org/W2003123121","https://openalex.org/W2060895888","https://openalex.org/W2150907703","https://openalex.org/W2977305403","https://openalex.org/W3149335959","https://openalex.org/W6645148572"],"related_works":["https://openalex.org/W2167155152","https://openalex.org/W2136763963","https://openalex.org/W2109705048","https://openalex.org/W2940588515","https://openalex.org/W1909151225","https://openalex.org/W1987783679","https://openalex.org/W2160030256","https://openalex.org/W1521297879","https://openalex.org/W4253235840","https://openalex.org/W3151937861"],"abstract_inverted_index":{"The":[0],"parameters":[1],"of":[2,68,88],"the":[3,61,89],"standard":[4],"Hidden":[5],"Markov":[6],"Model":[7],"framework":[8],"for":[9,59,83],"speech":[10,91],"recognition":[11,20],"are":[12,45,63,93],"typically":[13],"trained":[14],"via":[15],"Maximum":[16,29],"Likelihood.":[17],"However,":[18],"better":[19,46],"performance":[21],"is":[22,38,54],"achievable":[23],"with":[24],"discriminative":[25,43,74],"training":[26,75],"criteria":[27,44],"like":[28],"Mutual":[30],"Information":[31],"or":[32],"Minimum":[33],"Phone":[34],"Error.":[35],"While":[36],"it":[37],"generally":[39],"accepted":[40],"that":[41,73],"these":[42],"suited":[47],"to":[48,80],"minimizing":[49],"Word":[50],"Error":[51],"Rate,":[52],"there":[53],"very":[55],"little":[56],"qualitative":[57],"intuition":[58],"how":[60],"improvements":[62],"achieved.":[64],"Through":[65],"a":[66,84],"series":[67],"\u201cresampling\u201d":[69],"experiments,":[70],"we":[71],"show":[72],"(MPE":[76],"in":[77],"particular)":[78],"appears":[79],"be":[81],"compensating":[82],"specific":[85],"incorrect":[86],"assumption":[87],"HMM-that":[90],"frames":[92],"conditionally":[94],"independent.":[95]},"counts_by_year":[{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":4},{"year":2018,"cited_by_count":3},{"year":2017,"cited_by_count":2},{"year":2015,"cited_by_count":1},{"year":2014,"cited_by_count":2}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}