{"id":"https://openalex.org/W2963688273","doi":"https://doi.org/10.1109/asru.2015.7404845","title":"Discriminative segmental cascades for feature-rich phone recognition","display_name":"Discriminative segmental cascades for feature-rich phone recognition","publication_year":2015,"publication_date":"2015-12-01","ids":{"openalex":"https://openalex.org/W2963688273","doi":"https://doi.org/10.1109/asru.2015.7404845","mag":"2963688273"},"language":"en","primary_location":{"id":"doi:10.1109/asru.2015.7404845","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asru.2015.7404845","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2015 IEEE Workshop on Automatic Speech Recognition and 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/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, Chicago"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Toyota Technological Institute, Chicago","institution_ids":["https://openalex.org/I160992636"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101432591","display_name":"Weiran Wang","orcid":"https://orcid.org/0009-0000-0843-707X"},"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":"Weiran Wang","raw_affiliation_strings":["Toyota Technological Institute, Chicago"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Toyota Technological Institute, 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, Chicago"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Toyota Technological Institute, 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, Chicago"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Toyota Technological Institute, 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":12,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":"93","issue":null,"first_page":"561","last_page":"568"},"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/T11309","display_name":"Music and Audio Processing","score":0.9987999796867371,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9977999925613403,"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":0.8641774654388428},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7640169858932495},{"id":"https://openalex.org/keywords/decoding-methods","display_name":"Decoding methods","score":0.7167321443557739},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6488812565803528},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5556812882423401},{"id":"https://openalex.org/keywords/conditional-random-field","display_name":"Conditional random field","score":0.5544113516807556},{"id":"https://openalex.org/keywords/hinge-loss","display_name":"Hinge loss","score":0.5355536937713623},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.524304986000061},{"id":"https://openalex.org/keywords/phone","display_name":"Phone","score":0.5213578939437866},{"id":"https://openalex.org/keywords/pruning","display_name":"Pruning","score":0.477678120136261},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.4771827459335327},{"id":"https://openalex.org/keywords/cascade","display_name":"Cascade","score":0.45194438099861145},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.4515579640865326},{"id":"https://openalex.org/keywords/support-vector-machine","display_name":"Support vector machine","score":0.4049651622772217},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.17259472608566284}],"concepts":[{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.8641774654388428},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7640169858932495},{"id":"https://openalex.org/C57273362","wikidata":"https://www.wikidata.org/wiki/Q576722","display_name":"Decoding methods","level":2,"score":0.7167321443557739},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6488812565803528},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5556812882423401},{"id":"https://openalex.org/C152565575","wikidata":"https://www.wikidata.org/wiki/Q1124538","display_name":"Conditional random field","level":2,"score":0.5544113516807556},{"id":"https://openalex.org/C39891107","wikidata":"https://www.wikidata.org/wiki/Q5767098","display_name":"Hinge loss","level":3,"score":0.5355536937713623},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.524304986000061},{"id":"https://openalex.org/C2778707766","wikidata":"https://www.wikidata.org/wiki/Q202064","display_name":"Phone","level":2,"score":0.5213578939437866},{"id":"https://openalex.org/C108010975","wikidata":"https://www.wikidata.org/wiki/Q500094","display_name":"Pruning","level":2,"score":0.477678120136261},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.4771827459335327},{"id":"https://openalex.org/C34146451","wikidata":"https://www.wikidata.org/wiki/Q5048094","display_name":"Cascade","level":2,"score":0.45194438099861145},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.4515579640865326},{"id":"https://openalex.org/C12267149","wikidata":"https://www.wikidata.org/wiki/Q282453","display_name":"Support vector machine","level":2,"score":0.4049651622772217},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.17259472608566284},{"id":"https://openalex.org/C43617362","wikidata":"https://www.wikidata.org/wiki/Q170050","display_name":"Chromatography","level":1,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C6557445","wikidata":"https://www.wikidata.org/wiki/Q173113","display_name":"Agronomy","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/asru.2015.7404845","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asru.2015.7404845","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2015 IEEE Workshop on Automatic Speech Recognition and Understanding (ASRU)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.75,"id":"https://metadata.un.org/sdg/10","display_name":"Reduced inequalities"}],"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":39,"referenced_works":["https://openalex.org/W30596880","https://openalex.org/W162171320","https://openalex.org/W178496478","https://openalex.org/W1524333225","https://openalex.org/W1635512741","https://openalex.org/W1686810756","https://openalex.org/W1990387894","https://openalex.org/W2034961825","https://openalex.org/W2035424729","https://openalex.org/W2058641082","https://openalex.org/W2083393647","https://openalex.org/W2093231248","https://openalex.org/W2111535841","https://openalex.org/W2111732304","https://openalex.org/W2131033001","https://openalex.org/W2131870124","https://openalex.org/W2132714218","https://openalex.org/W2134797427","https://openalex.org/W2151660570","https://openalex.org/W2157059077","https://openalex.org/W2158188757","https://openalex.org/W2164714022","https://openalex.org/W2395342389","https://openalex.org/W2402040300","https://openalex.org/W2403708103","https://openalex.org/W2406482790","https://openalex.org/W2952472064","https://openalex.org/W6601201855","https://openalex.org/W6606507723","https://openalex.org/W6607261905","https://openalex.org/W6631362777","https://openalex.org/W6637373629","https://openalex.org/W6679579573","https://openalex.org/W6679909955","https://openalex.org/W6682469464","https://openalex.org/W6683226453","https://openalex.org/W6712847557","https://openalex.org/W6713457929","https://openalex.org/W6713948334"],"related_works":["https://openalex.org/W4389116644","https://openalex.org/W2153315159","https://openalex.org/W2356597680","https://openalex.org/W3103844505","https://openalex.org/W2942806827","https://openalex.org/W259157601","https://openalex.org/W2163278254","https://openalex.org/W155708904","https://openalex.org/W1574213390","https://openalex.org/W2382987388"],"abstract_inverted_index":{"Discriminative":[0],"segmental":[1,5,11,88,96],"models,":[2],"such":[3,31,44],"as":[4,45],"conditional":[6],"random":[7],"fields":[8],"(SCRFs)":[9],"and":[10,27,164],"structured":[12,97,134],"support":[13],"vector":[14],"machines":[15],"(SSVMs),":[16],"have":[17],"had":[18],"success":[19],"in":[20,65,111],"speech":[21],"recognition":[22,149],"via":[23],"both":[24],"lattice":[25,76],"rescoring":[26,109],"first-pass":[28],"decoding.":[29],"However,":[30],"models":[32,89,110],"suffer":[33],"from":[34],"slow":[35],"decoding,":[36,60],"hampering":[37],"the":[38,122],"use":[39,58,138],"of":[40],"computationally":[41],"expensive":[42,153],"features,":[43],"segment":[46,157],"neural":[47,158],"networks":[48],"or":[49,69],"other":[50],"high-order":[51],"features.":[52,168],"A":[53],"typical":[54],"solution":[55],"is":[56,104,124],"to":[57,73,141],"approximate":[59,118],"either":[61],"by":[62,70,78,133],"beam":[63,71,102],"pruning":[64,72,140],"a":[66,75,79,92,146,156,160],"single":[67],"pass":[68],"generate":[74,142],"followed":[77],"second":[80],"pass.":[81],"In":[82],"this":[83,112],"work,":[84],"we":[85,128],"study":[86],"discriminative":[87],"trained":[90],"with":[91,151],"hinge":[93],"loss":[94],"(i.e.,":[95],"SVMs).":[98],"We":[99,144],"show":[100],"that":[101],"search":[103],"not":[105],"suitable":[106],"for":[107],"learning":[108],"approach,":[113],"though":[114],"it":[115],"gives":[116],"good":[117],"decoding":[119],"performance":[120],"when":[121],"model":[123],"already":[125],"well-trained.":[126],"Instead,":[127],"consider":[129],"an":[130],"approach":[131],"inspired":[132],"prediction":[135],"cascades,":[136],"which":[137],"max-marginal":[139],"lattices.":[143],"obtain":[145],"high-accuracy":[147],"phonetic":[148],"system":[150],"several":[152],"feature":[154],"types:":[155],"network,":[159],"second-order":[161,165],"language":[162],"model,":[163],"phone":[166],"boundary":[167]},"counts_by_year":[{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":2},{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":1},{"year":2017,"cited_by_count":2},{"year":2016,"cited_by_count":5}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}