{"id":"https://openalex.org/W2136033658","doi":"https://doi.org/10.1109/asru.2009.5373368","title":"Leveraging speech production knowledge for improved speech recognition","display_name":"Leveraging speech production knowledge for improved speech recognition","publication_year":2009,"publication_date":"2009-12-01","ids":{"openalex":"https://openalex.org/W2136033658","doi":"https://doi.org/10.1109/asru.2009.5373368","mag":"2136033658"},"language":"en","primary_location":{"id":"doi:10.1109/asru.2009.5373368","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asru.2009.5373368","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2009 IEEE Workshop on Automatic Speech Recognition & Understanding","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/A5111469714","display_name":"Abhijeet Sangwan","orcid":null},"institutions":[{"id":"https://openalex.org/I162577319","display_name":"The University of Texas at Dallas","ror":"https://ror.org/049emcs32","country_code":"US","type":"education","lineage":["https://openalex.org/I162577319"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Abhijeet Sangwan","raw_affiliation_strings":["Center for Robust Speech Systems (CRSS), University of Texas, Dallas, Richardson, TX, USA","Center for Robust Speech Systems (CRSS), University of Texas at Dallas (UTD), Richardson, U.S.A"],"affiliations":[{"raw_affiliation_string":"Center for Robust Speech Systems (CRSS), University of Texas, Dallas, Richardson, TX, USA","institution_ids":["https://openalex.org/I162577319"]},{"raw_affiliation_string":"Center for Robust Speech Systems (CRSS), University of Texas at Dallas (UTD), Richardson, U.S.A","institution_ids":["https://openalex.org/I162577319"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5057910370","display_name":"John H. L. Hansen","orcid":"https://orcid.org/0000-0003-1382-9929"},"institutions":[{"id":"https://openalex.org/I162577319","display_name":"The University of Texas at Dallas","ror":"https://ror.org/049emcs32","country_code":"US","type":"education","lineage":["https://openalex.org/I162577319"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"John H.L. Hansen","raw_affiliation_strings":["Center for Robust Speech Systems (CRSS), University of Texas, Dallas, Richardson, TX, USA","Center for Robust Speech Systems (CRSS), University of Texas at Dallas (UTD), Richardson, U.S.A"],"affiliations":[{"raw_affiliation_string":"Center for Robust Speech Systems (CRSS), University of Texas, Dallas, Richardson, TX, USA","institution_ids":["https://openalex.org/I162577319"]},{"raw_affiliation_string":"Center for Robust Speech Systems (CRSS), University of Texas at Dallas (UTD), Richardson, U.S.A","institution_ids":["https://openalex.org/I162577319"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5111469714"],"corresponding_institution_ids":["https://openalex.org/I162577319"],"apc_list":null,"apc_paid":null,"fwci":0.8724,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.80983503,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":"14","issue":null,"first_page":"58","last_page":"63"},"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":0.998199999332428,"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/T10403","display_name":"Phonetics and Phonology Research","score":0.9959999918937683,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/timit","display_name":"TIMIT","score":0.7700275182723999},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7324739694595337},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6979984641075134},{"id":"https://openalex.org/keywords/phonology","display_name":"Phonology","score":0.6627039313316345},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.6581684350967407},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.562070369720459},{"id":"https://openalex.org/keywords/speech-corpus","display_name":"Speech corpus","score":0.5074262022972107},{"id":"https://openalex.org/keywords/phonetics","display_name":"Phonetics","score":0.48630890250205994},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4856785535812378},{"id":"https://openalex.org/keywords/speech-production","display_name":"Speech production","score":0.41972947120666504},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.38151001930236816},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.2565818428993225},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.1798337697982788}],"concepts":[{"id":"https://openalex.org/C2778724510","wikidata":"https://www.wikidata.org/wiki/Q7670405","display_name":"TIMIT","level":3,"score":0.7700275182723999},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7324739694595337},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6979984641075134},{"id":"https://openalex.org/C148934300","wikidata":"https://www.wikidata.org/wiki/Q40998","display_name":"Phonology","level":2,"score":0.6627039313316345},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.6581684350967407},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.562070369720459},{"id":"https://openalex.org/C91863865","wikidata":"https://www.wikidata.org/wiki/Q4349497","display_name":"Speech corpus","level":3,"score":0.5074262022972107},{"id":"https://openalex.org/C137584468","wikidata":"https://www.wikidata.org/wiki/Q35395","display_name":"Phonetics","level":2,"score":0.48630890250205994},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4856785535812378},{"id":"https://openalex.org/C43617652","wikidata":"https://www.wikidata.org/wiki/Q7575399","display_name":"Speech production","level":2,"score":0.41972947120666504},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.38151001930236816},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.2565818428993225},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.1798337697982788},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/asru.2009.5373368","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asru.2009.5373368","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2009 IEEE Workshop on Automatic Speech Recognition & Understanding","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.5299999713897705,"display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":12,"referenced_works":["https://openalex.org/W109694413","https://openalex.org/W1571735237","https://openalex.org/W1773803948","https://openalex.org/W2052382192","https://openalex.org/W2104212264","https://openalex.org/W2106404689","https://openalex.org/W2125838338","https://openalex.org/W2130392381","https://openalex.org/W2151311453","https://openalex.org/W2161967414","https://openalex.org/W4285719527","https://openalex.org/W6637852806"],"related_works":["https://openalex.org/W2994894110","https://openalex.org/W4377862891","https://openalex.org/W2005708641","https://openalex.org/W3127686677","https://openalex.org/W2050397613","https://openalex.org/W2080458333","https://openalex.org/W1995562189","https://openalex.org/W172689163","https://openalex.org/W80423236","https://openalex.org/W2808291730"],"abstract_inverted_index":{"This":[0],"study":[1],"presents":[2],"a":[3,56,85],"novel":[4],"phonological":[5,12],"methodology":[6],"for":[7,131,150],"speech":[8,20,34,94],"recognition":[9,121],"based":[10],"on":[11],"features":[13],"(PFs)":[14],"which":[15,91],"leverages":[16],"the":[17,26,30,43,49,65,72,81,93,110,135],"relationship":[18,73,98],"between":[19,74,99],"phonology":[21,35,100],"and":[22,76,96,101,127,134,142,152],"phonetics.":[23],"In":[24,40],"particular,":[25],"proposed":[27,104],"scheme":[28,44],"estimates":[29],"likelihood":[31],"of":[32,47,58,112,124],"observing":[33],"given":[36],"an":[37,117],"associative":[38],"lexicon.":[39],"this":[41],"manner,":[42],"is":[45,107],"capable":[46],"choosing":[48],"most":[50],"likely":[51],"hypothesis":[52],"(word":[53,120],"candidate)":[54],"among":[55],"group":[57],"competing":[59],"alternative":[60],"hypotheses.":[61],"The":[62,103],"framework":[63],"employs":[64],"maximum":[66],"entropy":[67],"(ME)":[68],"model":[69,83,106],"to":[70,84,109],"learn":[71],"phonetics":[75],"phonology.":[77],"Subsequently,":[78],"we":[79],"extend":[80],"ME":[82],"ME-HMM":[86,105],"(maximum":[87],"entropy-hidden":[88],"Markov":[89],"model)":[90],"captures":[92],"production":[95],"linguistic":[97],"words.":[102],"applied":[108],"task":[111],"re-processing":[113],"N-best":[114],"lists":[115],"where":[116],"absolute":[118],"WRA":[119],"rate)":[122],"increase":[123],"1.7%,":[125],"1.9%":[126],"1%":[128],"are":[129],"reported":[130],"TIMIT,":[132],"NTIMIT,":[133],"SPINE":[136],"(speech":[137],"in":[138,146],"noise)":[139],"corpora":[140],"(15.5%":[141],"22.5%":[143],"relative":[144],"reduction":[145],"word":[147],"error":[148],"rate":[149],"TIMIT":[151],"NTIMIT).":[153]},"counts_by_year":[{"year":2014,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}