{"id":"https://openalex.org/W2077450519","doi":"https://doi.org/10.1109/msp.2012.2210952","title":"Subword Modeling for Automatic Speech Recognition: Past, Present, and Emerging Approaches","display_name":"Subword Modeling for Automatic Speech Recognition: Past, Present, and Emerging Approaches","publication_year":2012,"publication_date":"2012-10-19","ids":{"openalex":"https://openalex.org/W2077450519","doi":"https://doi.org/10.1109/msp.2012.2210952","mag":"2077450519"},"language":"en","primary_location":{"id":"doi:10.1109/msp.2012.2210952","is_oa":false,"landing_page_url":"https://doi.org/10.1109/msp.2012.2210952","pdf_url":null,"source":{"id":"https://openalex.org/S120977877","display_name":"IEEE Signal Processing Magazine","issn_l":"1053-5888","issn":["1053-5888","1558-0792"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Signal Processing Magazine","raw_type":"journal-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/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":["EECS Department, MIT, USA","TTI-Chicago, Chicago, Illinois 60637 USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"EECS Department, MIT, USA","institution_ids":[]},{"raw_affiliation_string":"TTI-Chicago, Chicago, Illinois 60637 USA","institution_ids":["https://openalex.org/I160992636"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5056667180","display_name":"Eric Fosler\u2010Lussier","orcid":"https://orcid.org/0000-0001-8004-5169"},"institutions":[{"id":"https://openalex.org/I52357470","display_name":"The Ohio State University","ror":"https://ror.org/00rs6vg23","country_code":"US","type":"education","lineage":["https://openalex.org/I52357470"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Eric Fosler-Lussier","raw_affiliation_strings":["Department of Computer Science and Engineering, Ohio State University, USA","Dept. of Computer Science & Eng, Ohio State, Columbus, Ohio 43220 USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, Ohio State University, USA","institution_ids":["https://openalex.org/I52357470"]},{"raw_affiliation_string":"Dept. of Computer Science & Eng, Ohio State, Columbus, Ohio 43220 USA","institution_ids":["https://openalex.org/I52357470"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5085262529","display_name":"Florian Metze","orcid":"https://orcid.org/0000-0002-6663-8600"},"institutions":[{"id":"https://openalex.org/I4210093367","display_name":"Deutsche Telekom (Germany)","ror":"https://ror.org/00m8prc86","country_code":"DE","type":"company","lineage":["https://openalex.org/I4210093367"]},{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["DE","US"],"is_corresponding":false,"raw_author_name":"Florian Metze","raw_affiliation_strings":["Deutsche Telekom Laboratories in Berlin, Germany","SCS LTI, Carnegie Mellon University, Pittsburgh, Pennsylvania 15213 USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Deutsche Telekom Laboratories in Berlin, Germany","institution_ids":["https://openalex.org/I4210093367"]},{"raw_affiliation_string":"SCS LTI, Carnegie Mellon University, Pittsburgh, Pennsylvania 15213 USA","institution_ids":["https://openalex.org/I74973139"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":6.5241,"has_fulltext":false,"cited_by_count":34,"citation_normalized_percentile":{"value":0.96535042,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":"29","issue":"6","first_page":"44","last_page":"57"},"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/T10403","display_name":"Phonetics and Phonology Research","score":0.9987999796867371,"subfield":{"id":"https://openalex.org/subfields/3205","display_name":"Experimental and Cognitive Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9976999759674072,"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/computer-science","display_name":"Computer science","score":0.8584405183792114},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7437796592712402},{"id":"https://openalex.org/keywords/pronunciation","display_name":"Pronunciation","score":0.7340489625930786},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.5979213714599609},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5820314884185791},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5054562091827393},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.49313968420028687},{"id":"https://openalex.org/keywords/vocabulary","display_name":"Vocabulary","score":0.48743465542793274},{"id":"https://openalex.org/keywords/consonant","display_name":"Consonant","score":0.46367359161376953},{"id":"https://openalex.org/keywords/phone","display_name":"Phone","score":0.45214375853538513},{"id":"https://openalex.org/keywords/acoustic-model","display_name":"Acoustic model","score":0.4112177789211273},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.38629579544067383},{"id":"https://openalex.org/keywords/vowel","display_name":"Vowel","score":0.30507323145866394},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.1516994833946228}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8584405183792114},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7437796592712402},{"id":"https://openalex.org/C2780844864","wikidata":"https://www.wikidata.org/wiki/Q184377","display_name":"Pronunciation","level":2,"score":0.7340489625930786},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.5979213714599609},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5820314884185791},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5054562091827393},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.49313968420028687},{"id":"https://openalex.org/C2777601683","wikidata":"https://www.wikidata.org/wiki/Q6499736","display_name":"Vocabulary","level":2,"score":0.48743465542793274},{"id":"https://openalex.org/C2778203577","wikidata":"https://www.wikidata.org/wiki/Q38035","display_name":"Consonant","level":3,"score":0.46367359161376953},{"id":"https://openalex.org/C2778707766","wikidata":"https://www.wikidata.org/wiki/Q202064","display_name":"Phone","level":2,"score":0.45214375853538513},{"id":"https://openalex.org/C155635449","wikidata":"https://www.wikidata.org/wiki/Q4674699","display_name":"Acoustic model","level":3,"score":0.4112177789211273},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.38629579544067383},{"id":"https://openalex.org/C2779581591","wikidata":"https://www.wikidata.org/wiki/Q36244","display_name":"Vowel","level":2,"score":0.30507323145866394},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.1516994833946228},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/msp.2012.2210952","is_oa":false,"landing_page_url":"https://doi.org/10.1109/msp.2012.2210952","pdf_url":null,"source":{"id":"https://openalex.org/S120977877","display_name":"IEEE Signal Processing Magazine","issn_l":"1053-5888","issn":["1053-5888","1558-0792"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Signal Processing Magazine","raw_type":"journal-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.412.255","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.412.255","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/~klivescu/papers/livescu_etal_SPM2012.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.7599999904632568,"display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":97,"referenced_works":["https://openalex.org/W14023614","https://openalex.org/W63916190","https://openalex.org/W82292940","https://openalex.org/W104457985","https://openalex.org/W114725541","https://openalex.org/W134006180","https://openalex.org/W160832508","https://openalex.org/W196692374","https://openalex.org/W206405314","https://openalex.org/W1236994949","https://openalex.org/W1493946344","https://openalex.org/W1509905243","https://openalex.org/W1511986666","https://openalex.org/W1529942162","https://openalex.org/W1583757088","https://openalex.org/W1606491534","https://openalex.org/W1608231129","https://openalex.org/W1763005514","https://openalex.org/W1900410644","https://openalex.org/W1939950554","https://openalex.org/W1964917299","https://openalex.org/W1976117112","https://openalex.org/W1986174057","https://openalex.org/W1986317063","https://openalex.org/W1993628836","https://openalex.org/W1998653683","https://openalex.org/W2003890417","https://openalex.org/W2015073768","https://openalex.org/W2015720298","https://openalex.org/W2018913061","https://openalex.org/W2034031956","https://openalex.org/W2044359724","https://openalex.org/W2049633694","https://openalex.org/W2052382192","https://openalex.org/W2053280194","https://openalex.org/W2068447135","https://openalex.org/W2080723515","https://openalex.org/W2100768664","https://openalex.org/W2100966557","https://openalex.org/W2101859041","https://openalex.org/W2104981903","https://openalex.org/W2105842272","https://openalex.org/W2110842560","https://openalex.org/W2115900267","https://openalex.org/W2117172387","https://openalex.org/W2126061911","https://openalex.org/W2127217706","https://openalex.org/W2127611282","https://openalex.org/W2128022332","https://openalex.org/W2128780426","https://openalex.org/W2129653310","https://openalex.org/W2131646590","https://openalex.org/W2131968858","https://openalex.org/W2133924365","https://openalex.org/W2137368806","https://openalex.org/W2139406248","https://openalex.org/W2143742295","https://openalex.org/W2147284655","https://openalex.org/W2147880316","https://openalex.org/W2148226542","https://openalex.org/W2150750246","https://openalex.org/W2153189098","https://openalex.org/W2153474519","https://openalex.org/W2154092232","https://openalex.org/W2156615793","https://openalex.org/W2158575505","https://openalex.org/W2158840414","https://openalex.org/W2159501365","https://openalex.org/W2167200294","https://openalex.org/W2167655920","https://openalex.org/W2295531324","https://openalex.org/W2468248883","https://openalex.org/W3020737195","https://openalex.org/W3129711340","https://openalex.org/W4205130185","https://openalex.org/W4240043473","https://openalex.org/W4388323202","https://openalex.org/W6600577253","https://openalex.org/W6603233642","https://openalex.org/W6604211769","https://openalex.org/W6604577772","https://openalex.org/W6605496812","https://openalex.org/W6606579444","https://openalex.org/W6607928866","https://openalex.org/W6608353406","https://openalex.org/W6628027437","https://openalex.org/W6639657620","https://openalex.org/W6640797530","https://openalex.org/W6674963043","https://openalex.org/W6675022971","https://openalex.org/W6675783020","https://openalex.org/W6678820558","https://openalex.org/W6678822581","https://openalex.org/W6680293506","https://openalex.org/W6682082992","https://openalex.org/W6683422774","https://openalex.org/W6697090054"],"related_works":["https://openalex.org/W2951327905","https://openalex.org/W2754624720","https://openalex.org/W2121509853","https://openalex.org/W3080136773","https://openalex.org/W2474331230","https://openalex.org/W2759980945","https://openalex.org/W2479091890","https://openalex.org/W2110022257","https://openalex.org/W2121755096","https://openalex.org/W2077450519"],"abstract_inverted_index":{"Modern":[0],"automatic":[1],"speech":[2,45,130],"recognition":[3],"systems":[4],"handle":[5],"large":[6],"vocabularies":[7],"of":[8,17,33,66,75,85,99,101,107,156],"words,":[9],"making":[10],"it":[11],"infeasible":[12],"to":[13,20,140],"collect":[14],"enough":[15],"repetitions":[16],"each":[18,29],"word":[19,23,30,55],"train":[21],"individual":[22],"models.":[24,158],"Instead,":[25],"large-vocabulary":[26],"recognizers":[27],"represent":[28],"in":[31,69,91,97,116],"terms":[32,98],"subword":[34,38,76,86,108,111,141],"units.":[35],"Typically":[36],"the":[37,41,89,93,105,150,153],"unit":[39],"is":[40,56,104],"phone,":[42],"a":[43,49,60,70],"basic":[44],"sound":[46],"such":[47,119],"as":[48,59,81,120],"single":[50],"consonant":[51],"or":[52,62,128],"vowel.":[53],"Each":[54],"then":[57],"represented":[58],"sequence,":[61],"several":[63],"alternative":[64],"sequences,":[65],"phones":[67],"specified":[68],"pronunciation":[71],"dictionary.":[72],"Other":[73],"choices":[74],"units":[77],"have":[78],"been":[79],"studied":[80],"well.":[82],"The":[83],"choice":[84],"units,":[87,103],"and":[88,137],"way":[90],"which":[92],"recognizer":[94],"represents":[95],"words":[96],"combinations":[100],"those":[102],"problem":[106],"modeling.":[109,142],"Different":[110],"models":[112],"may":[113],"be":[114],"preferable":[115],"different":[117],"settings,":[118,127],"high-variability":[121],"conversational":[122],"speech,":[123],"high-noise":[124],"conditions,":[125],"low-resource":[126],"multilingual":[129],"recognition.":[131],"This":[132],"article":[133],"reviews":[134],"past,":[135],"present,":[136],"emerging":[138],"approaches":[139],"To":[143],"make":[144],"clean":[145],"comparisons":[146],"between":[147],"many":[148],"approaches,":[149],"review":[151],"uses":[152],"unifying":[154],"language":[155],"graphical":[157]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":5},{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":2},{"year":2017,"cited_by_count":3},{"year":2016,"cited_by_count":4},{"year":2015,"cited_by_count":7},{"year":2014,"cited_by_count":4},{"year":2013,"cited_by_count":4}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}