{"id":"https://openalex.org/W2403708103","doi":"https://doi.org/10.21437/interspeech.2014-307","title":"A comparison of training approaches for discriminative segmental models","display_name":"A comparison of training approaches for discriminative segmental models","publication_year":2014,"publication_date":"2014-09-14","ids":{"openalex":"https://openalex.org/W2403708103","doi":"https://doi.org/10.21437/interspeech.2014-307","mag":"2403708103"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2014-307","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2014-307","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2014","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/A5100662187","display_name":"Hao Tang","orcid":"https://orcid.org/0000-0002-2445-2605"},"institutions":[{"id":"https://openalex.org/I160992636","display_name":"Toyota Technological Institute at Chicago","ror":"https://ror.org/02sn5gb64","country_code":"US","type":"education","lineage":["https://openalex.org/I160992636"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Hao Tang","raw_affiliation_strings":["Toyota Technological Institute at Chicago,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Toyota Technological Institute at Chicago,","institution_ids":["https://openalex.org/I160992636"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5081022650","display_name":"Kevin Gimpel","orcid":null},"institutions":[{"id":"https://openalex.org/I160992636","display_name":"Toyota Technological Institute at Chicago","ror":"https://ror.org/02sn5gb64","country_code":"US","type":"education","lineage":["https://openalex.org/I160992636"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Kevin Gimpel","raw_affiliation_strings":["Toyota Technological Institute at Chicago,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Toyota Technological Institute at Chicago,","institution_ids":["https://openalex.org/I160992636"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5015602781","display_name":"Karen Livescu","orcid":"https://orcid.org/0000-0003-4962-946X"},"institutions":[{"id":"https://openalex.org/I160992636","display_name":"Toyota Technological Institute at Chicago","ror":"https://ror.org/02sn5gb64","country_code":"US","type":"education","lineage":["https://openalex.org/I160992636"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Karen Livescu","raw_affiliation_strings":["Toyota Technological Institute at Chicago,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Toyota Technological Institute at Chicago,","institution_ids":["https://openalex.org/I160992636"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I160992636"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":13,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1219","last_page":"1223"},"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9991000294685364,"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/T10028","display_name":"Topic Modeling","score":0.9988999962806702,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/discriminative-model","display_name":"Discriminative model","score":0.8950225710868835},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8204864263534546},{"id":"https://openalex.org/keywords/conditional-random-field","display_name":"Conditional random field","score":0.6058191061019897},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5913280248641968},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.5588675737380981},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.521289587020874},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4858657717704773},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.46294817328453064},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3376203775405884},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.32901981472969055}],"concepts":[{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.8950225710868835},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8204864263534546},{"id":"https://openalex.org/C152565575","wikidata":"https://www.wikidata.org/wiki/Q1124538","display_name":"Conditional random field","level":2,"score":0.6058191061019897},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5913280248641968},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.5588675737380981},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.521289587020874},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4858657717704773},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.46294817328453064},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3376203775405884},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.32901981472969055},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"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:10.21437/interspeech.2014-307","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2014-307","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2014","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.702.7272","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.702.7272","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://ttic.uchicago.edu/%7Eklivescu/papers/tang_interspeech2014.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Reduced inequalities","score":0.7400000095367432,"id":"https://metadata.un.org/sdg/10"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":36,"referenced_works":["https://openalex.org/W14913773","https://openalex.org/W178496478","https://openalex.org/W232191560","https://openalex.org/W398859631","https://openalex.org/W853436745","https://openalex.org/W1877570817","https://openalex.org/W1969048569","https://openalex.org/W2001679125","https://openalex.org/W2022768064","https://openalex.org/W2053567709","https://openalex.org/W2093028810","https://openalex.org/W2096199223","https://openalex.org/W2097207027","https://openalex.org/W2097826433","https://openalex.org/W2105842272","https://openalex.org/W2111479622","https://openalex.org/W2111535841","https://openalex.org/W2111732304","https://openalex.org/W2125234026","https://openalex.org/W2126336864","https://openalex.org/W2130647295","https://openalex.org/W2131033001","https://openalex.org/W2131148434","https://openalex.org/W2137368806","https://openalex.org/W2143612262","https://openalex.org/W2143908786","https://openalex.org/W2146502635","https://openalex.org/W2147880316","https://openalex.org/W2150142469","https://openalex.org/W2150907703","https://openalex.org/W2151660570","https://openalex.org/W2158188757","https://openalex.org/W2158460069","https://openalex.org/W2158575505","https://openalex.org/W2162734244","https://openalex.org/W2584852661"],"related_works":["https://openalex.org/W2163278254","https://openalex.org/W155708904","https://openalex.org/W1574213390","https://openalex.org/W2162582511","https://openalex.org/W2309273277","https://openalex.org/W1769849273","https://openalex.org/W2061937230","https://openalex.org/W1574295218","https://openalex.org/W2547793174","https://openalex.org/W2070212102"],"abstract_inverted_index":{"Segmental":[0],"models":[1,43],"such":[2,36,42],"as":[3,37,77],"segmental":[4,99,126],"conditional":[5,50,127],"random":[6],"fields":[7],"have":[8,44],"had":[9],"some":[10],"recent":[11],"success":[12],"in":[13],"lattice":[14,103],"rescoring":[15,104],"for":[16,24,59,79,97,106],"speech":[17,64,124],"recognition.":[18,65],"They":[19],"provide":[20],"a":[21,26,93],"flexible":[22],"framework":[23],"incorpo-rating":[25],"wide":[27],"range":[28],"of":[29,34,63,114],"features":[30],"across":[31],"different":[32],"levels":[33],"units,":[35],"phones":[38],"and":[39,91,109],"words.":[40],"However,":[41],"mainly":[45],"been":[46,70],"trained":[47],"by":[48],"maximizing":[49],"likelihood,":[51],"which":[52],"may":[53],"not":[54],"be":[55],"the":[56,60,80,112],"best":[57],"proxy":[58],"task":[61],"loss":[62],"In":[66,84],"addition,":[67],"there":[68],"has":[69],"little":[71],"work":[72],"on":[73],"designing":[74],"cost":[75,95],"func-tions":[76],"surrogates":[78],"word":[81],"error":[82],"rate.":[83],"this":[85],"paper,":[86],"we":[87],"investigate":[88],"various":[89],"losses":[90],"introduce":[92],"new":[94],"function":[96],"training":[98,134],"models.":[100],"We":[101],"compare":[102],"results":[105],"multiple":[107],"tasks":[108],"also":[110],"study":[111],"impact":[113],"several":[115],"choices":[116],"required":[117],"when":[118],"optimizing":[119],"these":[120],"losses.":[121],"Index":[122],"Terms:":[123],"recognition,":[125],"ran-dom":[128],"fields,":[129],"empirical":[130],"Bayes":[131],"risk,":[132],"large-margin":[133]},"counts_by_year":[{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":1},{"year":2017,"cited_by_count":2},{"year":2016,"cited_by_count":5},{"year":2015,"cited_by_count":4}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}