{"id":"https://openalex.org/W2107338293","doi":"https://doi.org/10.1109/asru.2007.4430177","title":"Phonological feature based variable frame rate scheme for improved speech recognition","display_name":"Phonological feature based variable frame rate scheme for improved speech recognition","publication_year":2007,"publication_date":"2007-01-01","ids":{"openalex":"https://openalex.org/W2107338293","doi":"https://doi.org/10.1109/asru.2007.4430177","mag":"2107338293"},"language":"en","primary_location":{"id":"doi:10.1109/asru.2007.4430177","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asru.2007.4430177","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2007 IEEE Workshop on Automatic Speech Recognition & Understanding (ASRU)","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":false,"raw_author_name":"Abhijeet Sangwan","raw_affiliation_strings":["Center for Robust Speech Systems (CRSS), Department of Electrical Engineering, University of Texas, Dallas, Richardson, TX, USA","Univ. of Texas at Dallas, Richardson"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Center for Robust Speech Systems (CRSS), Department of Electrical Engineering, University of Texas, Dallas, Richardson, TX, USA","institution_ids":["https://openalex.org/I162577319"]},{"raw_affiliation_string":"Univ. of Texas at Dallas, Richardson","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), Department of Electrical Engineering, University of Texas, Dallas, Richardson, TX, USA","Univ. of Texas at Dallas, Richardson"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Center for Robust Speech Systems (CRSS), Department of Electrical Engineering, University of Texas, Dallas, Richardson, TX, USA","institution_ids":["https://openalex.org/I162577319"]},{"raw_affiliation_string":"Univ. of Texas at Dallas, Richardson","institution_ids":["https://openalex.org/I162577319"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.14446086,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"582","last_page":"586"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9998999834060669,"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"}},"topics":[{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9998999834060669,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9998000264167786,"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/T10901","display_name":"Advanced Data Compression Techniques","score":0.9968000054359436,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/timit","display_name":"TIMIT","score":0.7963563203811646},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7802549600601196},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7481927275657654},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.5480265617370605},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.46249982714653015},{"id":"https://openalex.org/keywords/linear-predictive-coding","display_name":"Linear predictive coding","score":0.4586915671825409},{"id":"https://openalex.org/keywords/voice-activity-detection","display_name":"Voice activity detection","score":0.4368622899055481},{"id":"https://openalex.org/keywords/frame","display_name":"Frame (networking)","score":0.41526445746421814},{"id":"https://openalex.org/keywords/speech-coding","display_name":"Speech coding","score":0.4144548773765564},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.36848294734954834},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.35298049449920654},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.3356587290763855}],"concepts":[{"id":"https://openalex.org/C2778724510","wikidata":"https://www.wikidata.org/wiki/Q7670405","display_name":"TIMIT","level":3,"score":0.7963563203811646},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7802549600601196},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7481927275657654},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.5480265617370605},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.46249982714653015},{"id":"https://openalex.org/C59883199","wikidata":"https://www.wikidata.org/wiki/Q1826438","display_name":"Linear predictive coding","level":3,"score":0.4586915671825409},{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.4368622899055481},{"id":"https://openalex.org/C126042441","wikidata":"https://www.wikidata.org/wiki/Q1324888","display_name":"Frame (networking)","level":2,"score":0.41526445746421814},{"id":"https://openalex.org/C13895895","wikidata":"https://www.wikidata.org/wiki/Q3270773","display_name":"Speech coding","level":2,"score":0.4144548773765564},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.36848294734954834},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.35298049449920654},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.3356587290763855},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/asru.2007.4430177","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asru.2007.4430177","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2007 IEEE Workshop on Automatic Speech Recognition & Understanding (ASRU)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","score":0.44999998807907104,"display_name":"Peace, Justice and strong institutions"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":14,"referenced_works":["https://openalex.org/W14023614","https://openalex.org/W15731617","https://openalex.org/W1550527692","https://openalex.org/W1585535777","https://openalex.org/W2111880697","https://openalex.org/W2124243855","https://openalex.org/W2126948708","https://openalex.org/W2127846433","https://openalex.org/W2151311453","https://openalex.org/W2156561020","https://openalex.org/W2170389424","https://openalex.org/W2396408141","https://openalex.org/W6600577253","https://openalex.org/W6600635708"],"related_works":["https://openalex.org/W2070982348","https://openalex.org/W1976952689","https://openalex.org/W1984921740","https://openalex.org/W2496295964","https://openalex.org/W1572861854","https://openalex.org/W2069501481","https://openalex.org/W2253161769","https://openalex.org/W2020464095","https://openalex.org/W2336887028","https://openalex.org/W823775484"],"abstract_inverted_index":{"In":[0,82],"this":[1,83],"paper,":[2],"we":[3],"propose":[4],"a":[5,112,136],"new":[6,117],"scheme":[7,48,87,119],"for":[8,158],"variable":[9,113],"frame":[10],"rate":[11],"(VFR)":[12],"feature":[13],"processing":[14,29],"based":[15],"on":[16],"high":[17],"level":[18],"segmentation":[19],"(HLS)":[20],"of":[21,33,38,53,90,94,108,126,149],"speech":[22,55,95,109,124],"into":[23],"broad":[24],"phone":[25,65,69],"classes.":[26],"Traditional":[27],"fixed-rate":[28],"is":[30,88,120,133],"not":[31],"capable":[32,89],"accurately":[34],"reflecting":[35],"the":[36,42,45,50,54,59,63,85,92,98,104],"dynamics":[37],"continuous":[39],"speech.":[40],"On":[41],"other":[43],"hand,":[44],"proposed":[46,86],"VFR":[47,118],"adapts":[49],"temporal":[51],"representation":[52],"signal":[56],"by":[57,75,110],"tying":[58],"framing":[60,114],"strategy":[61],"with":[62,146],"detected":[64,72],"class":[66],"sequence.":[67],"The":[68,116],"classes":[70],"are":[71],"and":[73,102,128,151,160],"segmented":[74],"using":[76,111],"appropriately":[77],"trained":[78],"phonological":[79],"features":[80],"(PFs).":[81],"manner,":[84],"tracking":[91],"evolution":[93],"due":[96],"to":[97,122,135],"underlying":[99],"phonetic":[100],"content,":[101],"exploiting":[103],"non-uniform":[105],"information":[106],"flow-rate":[107],"strategy.":[115],"applied":[121],"automatic":[123],"recognition":[125],"TIMIT":[127,159],"NTIMIT":[129,161],"corpora,":[130],"where":[131],"it":[132],"compared":[134],"traditional":[137],"fixed":[138],"window-size/frame-rate":[139],"scheme.":[140],"Our":[141],"experiments":[142],"yield":[143],"encouraging":[144],"results":[145],"relative":[147],"reductions":[148],"24%":[150],"8%":[152],"in":[153],"WER":[154],"(word":[155],"error":[156],"rate)":[157],"tasks,":[162],"respectively.":[163]},"counts_by_year":[{"year":2012,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}