{"id":"https://openalex.org/W2123596612","doi":"https://doi.org/10.1109/icassp.2011.5947564","title":"Discriminatively estimated discrete, parametric and smoothed-discrete duration models for speech recognition","display_name":"Discriminatively estimated discrete, parametric and smoothed-discrete duration models for speech recognition","publication_year":2011,"publication_date":"2011-05-01","ids":{"openalex":"https://openalex.org/W2123596612","doi":"https://doi.org/10.1109/icassp.2011.5947564","mag":"2123596612"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2011.5947564","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2011.5947564","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2011 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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/A5007425606","display_name":"Maider Lehr","orcid":null},"institutions":[{"id":"https://openalex.org/I165690674","display_name":"Oregon Health & Science University","ror":"https://ror.org/009avj582","country_code":"US","type":"education","lineage":["https://openalex.org/I165690674"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Maider Lehr","raw_affiliation_strings":["Center of Spoken Language Understanding, Oregon Health and Sciences University, Portland, OR, USA","The Center for Spoken Language Understanding, The Oregon Health & Science University, Portland, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Center of Spoken Language Understanding, Oregon Health and Sciences University, Portland, OR, USA","institution_ids":["https://openalex.org/I165690674"]},{"raw_affiliation_string":"The Center for Spoken Language Understanding, The Oregon Health & Science University, Portland, USA","institution_ids":["https://openalex.org/I165690674"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5025419994","display_name":"Izhak Shafran","orcid":null},"institutions":[{"id":"https://openalex.org/I165690674","display_name":"Oregon Health & Science University","ror":"https://ror.org/009avj582","country_code":"US","type":"education","lineage":["https://openalex.org/I165690674"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Izhak Shafran","raw_affiliation_strings":["Center of Spoken Language Understanding, Oregon Health and Sciences University, Portland, OR, USA","The Center for Spoken Language Understanding, The Oregon Health & Science University, Portland, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Center of Spoken Language Understanding, Oregon Health and Sciences University, Portland, OR, USA","institution_ids":["https://openalex.org/I165690674"]},{"raw_affiliation_string":"The Center for Spoken Language Understanding, The Oregon Health & Science University, Portland, USA","institution_ids":["https://openalex.org/I165690674"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I165690674"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.19158301,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"5340","last_page":"5343"},"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":0.9994999766349792,"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":0.996999979019165,"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/duration","display_name":"Duration (music)","score":0.686607301235199},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6812233328819275},{"id":"https://openalex.org/keywords/bigram","display_name":"Bigram","score":0.5929769277572632},{"id":"https://openalex.org/keywords/metric","display_name":"Metric (unit)","score":0.5849201083183289},{"id":"https://openalex.org/keywords/parametric-statistics","display_name":"Parametric statistics","score":0.5418903827667236},{"id":"https://openalex.org/keywords/parametric-model","display_name":"Parametric model","score":0.5341523885726929},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.47228366136550903},{"id":"https://openalex.org/keywords/vocabulary","display_name":"Vocabulary","score":0.4593276381492615},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4504375159740448},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3669286370277405},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.21446141600608826},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.16816651821136475}],"concepts":[{"id":"https://openalex.org/C112758219","wikidata":"https://www.wikidata.org/wiki/Q16038819","display_name":"Duration (music)","level":2,"score":0.686607301235199},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6812233328819275},{"id":"https://openalex.org/C108757681","wikidata":"https://www.wikidata.org/wiki/Q2773912","display_name":"Bigram","level":3,"score":0.5929769277572632},{"id":"https://openalex.org/C176217482","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Metric (unit)","level":2,"score":0.5849201083183289},{"id":"https://openalex.org/C117251300","wikidata":"https://www.wikidata.org/wiki/Q1849855","display_name":"Parametric statistics","level":2,"score":0.5418903827667236},{"id":"https://openalex.org/C24574437","wikidata":"https://www.wikidata.org/wiki/Q7135228","display_name":"Parametric model","level":3,"score":0.5341523885726929},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.47228366136550903},{"id":"https://openalex.org/C2777601683","wikidata":"https://www.wikidata.org/wiki/Q6499736","display_name":"Vocabulary","level":2,"score":0.4593276381492615},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4504375159740448},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3669286370277405},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.21446141600608826},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.16816651821136475},{"id":"https://openalex.org/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"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/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C124952713","wikidata":"https://www.wikidata.org/wiki/Q8242","display_name":"Literature","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},{"id":"https://openalex.org/C137546455","wikidata":"https://www.wikidata.org/wiki/Q3213474","display_name":"Trigram","level":2,"score":0.0},{"id":"https://openalex.org/C21547014","wikidata":"https://www.wikidata.org/wiki/Q1423657","display_name":"Operations management","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/icassp.2011.5947564","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2011.5947564","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2011 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.386.5117","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.386.5117","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.cslu.ogi.edu/~zak/icassp11-dur.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/10","display_name":"Reduced inequalities","score":0.7300000190734863}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":8,"referenced_works":["https://openalex.org/W2013466429","https://openalex.org/W2033204316","https://openalex.org/W2064218608","https://openalex.org/W2131964822","https://openalex.org/W2136727248","https://openalex.org/W2144165558","https://openalex.org/W2158025800","https://openalex.org/W2170510631"],"related_works":["https://openalex.org/W3020951519","https://openalex.org/W3173084154","https://openalex.org/W2334448532","https://openalex.org/W2982021180","https://openalex.org/W2131563376","https://openalex.org/W2251497876","https://openalex.org/W2241081188","https://openalex.org/W2128567707","https://openalex.org/W4327499987","https://openalex.org/W2011383762"],"abstract_inverted_index":{"Duration":[0],"of":[1,89,116],"phonemic":[2],"segments":[3],"provide":[4],"important":[5],"cues":[6],"for":[7,27,43,85],"distinguishing":[8],"words":[9],"in":[10],"languages":[11],"such":[12],"as":[13],"Arabic.":[14],"Recently,":[15],"we":[16,35,75,103],"proposed":[17],"a":[18,90,94,98],"discriminatively":[19,79],"estimated":[20],"joint":[21],"acoustic,":[22],"duration":[23,73,122],"and":[24,64,80,109,128],"language":[25],"model":[26],"large":[28,99],"vocabulary":[29,100],"speech":[30],"recognition.":[31],"In":[32],"that":[33],"work,":[34],"found":[36],"simple":[37],"discrete":[38],"models":[39,62,123,132],"to":[40],"be":[41],"effective":[42],"modeling":[44],"duration,":[45],"albeit":[46],"they":[47],"were":[48],"neither":[49],"smoothed":[50],"nor":[51],"parsimonious.":[52],"These":[53],"limitations":[54],"are":[55,124],"ad":[56],"dressed":[57],"here":[58],"with":[59,120],"two":[60],"alternative":[61],"parametric":[63],"smoothed-discrete":[65,121],"models.":[66,111],"Unlike":[67],"previous":[68],"work":[69],"on":[70],"para":[71],"metric":[72],"model,":[74],"estimate":[76],"their":[77],"parameters":[78,88],"derive":[81],"an":[82],"analytical":[83],"expression":[84],"estimating":[86],"the":[87],"log-normal":[91],"distribution":[92],"using":[93],"recent":[95],"approach.":[96],"On":[97],"Arabic":[101],"task,":[102],"empirically":[104],"evaluated":[105],"different":[106],"segmental":[107],"units":[108],"durations":[110],"Our":[112],"results":[113],"show":[114],"bigrams":[115],"clustered":[117],"states":[118],"modeled":[119],"relatively":[125],"more":[126],"accurate":[127],"efficient":[129],"than":[130],"other":[131],"considered.":[133]},"counts_by_year":[],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}