{"id":"https://openalex.org/W1998628338","doi":"https://doi.org/10.1109/taslp.2015.2434213","title":"Convex Weighting Criteria for Speaking Rate Estimation","display_name":"Convex Weighting Criteria for Speaking Rate Estimation","publication_year":2015,"publication_date":"2015-05-15","ids":{"openalex":"https://openalex.org/W1998628338","doi":"https://doi.org/10.1109/taslp.2015.2434213","mag":"1998628338","pmid":"https://pubmed.ncbi.nlm.nih.gov/26167516"},"language":"en","primary_location":{"id":"doi:10.1109/taslp.2015.2434213","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taslp.2015.2434213","pdf_url":null,"source":{"id":"https://openalex.org/S4210169297","display_name":"IEEE/ACM Transactions on Audio Speech and Language Processing","issn_l":"2329-9290","issn":["2329-9290","2329-9304"],"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/ACM Transactions on Audio, Speech, and Language Processing","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","pubmed"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/4497798","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5109394386","display_name":"Yishan Jiao","orcid":null},"institutions":[{"id":"https://openalex.org/I55732556","display_name":"Arizona State University","ror":"https://ror.org/03efmqc40","country_code":"US","type":"education","lineage":["https://openalex.org/I55732556"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Yishan Jiao","raw_affiliation_strings":["Department of Speech and Hearing Science, Arizona State University","Arizona State University, Tempe AZ"],"affiliations":[{"raw_affiliation_string":"Department of Speech and Hearing Science, Arizona State University","institution_ids":["https://openalex.org/I55732556"]},{"raw_affiliation_string":"Arizona State University, Tempe AZ","institution_ids":["https://openalex.org/I55732556"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5021646973","display_name":"Visar Berisha","orcid":"https://orcid.org/0000-0001-8804-8874"},"institutions":[{"id":"https://openalex.org/I55732556","display_name":"Arizona State University","ror":"https://ror.org/03efmqc40","country_code":"US","type":"education","lineage":["https://openalex.org/I55732556"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Visar Berisha","raw_affiliation_strings":["Department of Speech and Hearing Science, Arizona State University","Arizona State University, Tempe AZ"],"affiliations":[{"raw_affiliation_string":"Department of Speech and Hearing Science, Arizona State University","institution_ids":["https://openalex.org/I55732556"]},{"raw_affiliation_string":"Arizona State University, Tempe AZ","institution_ids":["https://openalex.org/I55732556"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102334100","display_name":"Ming Tu","orcid":null},"institutions":[{"id":"https://openalex.org/I55732556","display_name":"Arizona State University","ror":"https://ror.org/03efmqc40","country_code":"US","type":"education","lineage":["https://openalex.org/I55732556"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ming Tu","raw_affiliation_strings":["Department of Speech and Hearing Science, Arizona State University","Arizona State University, Tempe AZ"],"affiliations":[{"raw_affiliation_string":"Department of Speech and Hearing Science, Arizona State University","institution_ids":["https://openalex.org/I55732556"]},{"raw_affiliation_string":"Arizona State University, Tempe AZ","institution_ids":["https://openalex.org/I55732556"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5056934840","display_name":"Julie Liss","orcid":"https://orcid.org/0000-0001-8782-2901"},"institutions":[{"id":"https://openalex.org/I55732556","display_name":"Arizona State University","ror":"https://ror.org/03efmqc40","country_code":"US","type":"education","lineage":["https://openalex.org/I55732556"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Julie Liss","raw_affiliation_strings":["Department of Speech and Hearing Science, Arizona State University","Arizona State University, Tempe AZ"],"affiliations":[{"raw_affiliation_string":"Department of Speech and Hearing Science, Arizona State University","institution_ids":["https://openalex.org/I55732556"]},{"raw_affiliation_string":"Arizona State University, Tempe AZ","institution_ids":["https://openalex.org/I55732556"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5109394386"],"corresponding_institution_ids":["https://openalex.org/I55732556"],"apc_list":null,"apc_paid":null,"fwci":4.0533,"has_fulltext":false,"cited_by_count":25,"citation_normalized_percentile":{"value":0.94466131,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":98},"biblio":{"volume":"23","issue":"9","first_page":"1421","last_page":"1430"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9997000098228455,"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":0.9997000098228455,"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":0.9987999796867371,"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/T11447","display_name":"Blind Source Separation Techniques","score":0.9908999800682068,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/timit","display_name":"TIMIT","score":0.7573668360710144},{"id":"https://openalex.org/keywords/weighting","display_name":"Weighting","score":0.6967854499816895},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6735956072807312},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6351408958435059},{"id":"https://openalex.org/keywords/thresholding","display_name":"Thresholding","score":0.49124234914779663},{"id":"https://openalex.org/keywords/heuristics","display_name":"Heuristics","score":0.47965601086616516},{"id":"https://openalex.org/keywords/signal","display_name":"SIGNAL (programming language)","score":0.432101309299469},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.42111122608184814},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.34977737069129944},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3312993049621582},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.21435251832008362},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.08216878771781921}],"concepts":[{"id":"https://openalex.org/C2778724510","wikidata":"https://www.wikidata.org/wiki/Q7670405","display_name":"TIMIT","level":3,"score":0.7573668360710144},{"id":"https://openalex.org/C183115368","wikidata":"https://www.wikidata.org/wiki/Q856577","display_name":"Weighting","level":2,"score":0.6967854499816895},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6735956072807312},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6351408958435059},{"id":"https://openalex.org/C191178318","wikidata":"https://www.wikidata.org/wiki/Q2256906","display_name":"Thresholding","level":3,"score":0.49124234914779663},{"id":"https://openalex.org/C127705205","wikidata":"https://www.wikidata.org/wiki/Q5748245","display_name":"Heuristics","level":2,"score":0.47965601086616516},{"id":"https://openalex.org/C2779843651","wikidata":"https://www.wikidata.org/wiki/Q7390335","display_name":"SIGNAL (programming language)","level":2,"score":0.432101309299469},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.42111122608184814},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.34977737069129944},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3312993049621582},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.21435251832008362},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.08216878771781921},{"id":"https://openalex.org/C71924100","wikidata":"https://www.wikidata.org/wiki/Q11190","display_name":"Medicine","level":0,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C126838900","wikidata":"https://www.wikidata.org/wiki/Q77604","display_name":"Radiology","level":1,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/taslp.2015.2434213","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taslp.2015.2434213","pdf_url":null,"source":{"id":"https://openalex.org/S4210169297","display_name":"IEEE/ACM Transactions on Audio Speech and Language Processing","issn_l":"2329-9290","issn":["2329-9290","2329-9304"],"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/ACM Transactions on Audio, Speech, and Language Processing","raw_type":"journal-article"},{"id":"pmid:26167516","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/26167516","pdf_url":null,"source":{"id":"https://openalex.org/S4306525036","display_name":"PubMed","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE/ACM transactions on audio, speech, and language processing","raw_type":null},{"id":"pmh:oai:pubmedcentral.nih.gov:4497798","is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/4497798","pdf_url":null,"source":{"id":"https://openalex.org/S2764455111","display_name":"PubMed Central","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"IEEE/ACM Trans Audio Speech Lang Process","raw_type":"Text"}],"best_oa_location":{"id":"pmh:oai:pubmedcentral.nih.gov:4497798","is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/4497798","pdf_url":null,"source":{"id":"https://openalex.org/S2764455111","display_name":"PubMed Central","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"IEEE/ACM Trans Audio Speech Lang Process","raw_type":"Text"},"sustainable_development_goals":[{"score":0.41999998688697815,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[{"id":"https://openalex.org/G2727897912","display_name":null,"funder_award_id":"2R01DC006859","funder_id":"https://openalex.org/F4320332161","funder_display_name":"National Institutes of Health"},{"id":"https://openalex.org/G649842886","display_name":null,"funder_award_id":"N000141410722","funder_id":"https://openalex.org/F4320337345","funder_display_name":"Office of Naval Research"},{"id":"https://openalex.org/G865891436","display_name":null,"funder_award_id":"1R21DC012558","funder_id":"https://openalex.org/F4320332161","funder_display_name":"National Institutes of Health"}],"funders":[{"id":"https://openalex.org/F4320332161","display_name":"National Institutes of Health","ror":"https://ror.org/01cwqze88"},{"id":"https://openalex.org/F4320337345","display_name":"Office of Naval Research","ror":"https://ror.org/00rk2pe57"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":45,"referenced_works":["https://openalex.org/W113313807","https://openalex.org/W137732731","https://openalex.org/W173400130","https://openalex.org/W1965635292","https://openalex.org/W1965992883","https://openalex.org/W1967073510","https://openalex.org/W1969176743","https://openalex.org/W2009254313","https://openalex.org/W2018882848","https://openalex.org/W2026942286","https://openalex.org/W2049515993","https://openalex.org/W2052384514","https://openalex.org/W2056500762","https://openalex.org/W2066730619","https://openalex.org/W2067380555","https://openalex.org/W2073885837","https://openalex.org/W2081318766","https://openalex.org/W2084027991","https://openalex.org/W2091578674","https://openalex.org/W2096774922","https://openalex.org/W2098396290","https://openalex.org/W2113642685","https://openalex.org/W2115501357","https://openalex.org/W2117903328","https://openalex.org/W2129244720","https://openalex.org/W2144950156","https://openalex.org/W2145983039","https://openalex.org/W2148603752","https://openalex.org/W2149298154","https://openalex.org/W2166637769","https://openalex.org/W2167393648","https://openalex.org/W2168961642","https://openalex.org/W2171907819","https://openalex.org/W2402942190","https://openalex.org/W2426479676","https://openalex.org/W2466106549","https://openalex.org/W2561557072","https://openalex.org/W3127686677","https://openalex.org/W4233392025","https://openalex.org/W4246961297","https://openalex.org/W4254721730","https://openalex.org/W6668861157","https://openalex.org/W6681368121","https://openalex.org/W6712664310","https://openalex.org/W7071374342"],"related_works":["https://openalex.org/W80423236","https://openalex.org/W2180954594","https://openalex.org/W2052835778","https://openalex.org/W1542224353","https://openalex.org/W2049003611","https://openalex.org/W2127804977","https://openalex.org/W2015876361","https://openalex.org/W2131486661","https://openalex.org/W3086174161","https://openalex.org/W1959176866"],"abstract_inverted_index":{"Speaking":[0],"rate":[1,23,43,180,192],"estimation":[2,24],"directly":[3,97],"from":[4],"the":[5,21,41,55,64,74,79,84,120,129,143,153,162,182,189],"speech":[6,13,65,104,149,157,179],"waveform":[7],"is":[8],"a":[9,30,37,103,108,132,147,185],"long-standing":[10],"problem":[11,25],"in":[12,102],"signal":[14,66,105],"processing.":[15],"In":[16,47,175],"this":[17],"paper,":[18],"we":[19,53,68],"pose":[20],"speaking":[22,42,191],"as":[26,72],"that":[27,45,94,161],"of":[28,59,81],"estimating":[29],"temporal":[31,75,109],"density":[32,110],"function":[33,93],"whose":[34],"integral":[35],"over":[36],"given":[38],"interval":[39],"yields":[40],"within":[44,63],"interval.":[46],"contrast":[48],"to":[49,77,88,99,106,127,131],"many":[50],"existing":[51],"methods,":[52],"avoid":[54,69],"more":[56],"difficult":[57],"task":[58],"detecting":[60],"individual":[61],"phonemes":[62],"and":[67,123,151,172,193],"heuristics":[70],"such":[71],"thresholding":[73],"envelope":[76],"estimate":[78],"number":[80],"vowels.":[82],"Rather,":[83],"proposed":[85,163],"method":[86],"aims":[87],"learn":[89],"an":[90,124],"optimal":[91],"weighting":[92,121],"can":[95],"be":[96],"applied":[98],"time-frequency":[100],"features":[101],"yield":[107],"function.":[111],"We":[112],"propose":[113],"two":[114],"convex":[115],"cost":[116],"functions":[117,122],"for":[118,177],"learning":[119],"adaptation":[125],"strategy":[126],"customize":[128],"approach":[130],"particular":[133],"speaker":[134],"using":[135],"minimal":[136],"training.":[137],"The":[138],"algorithms":[139],"are":[140],"evaluated":[141],"on":[142,146,152,169],"TIMIT":[144],"corpus,":[145,150],"dysarthric":[148,173],"ICSI":[154],"Switchboard":[155],"spontaneous":[156,178],"corpus.":[158],"Results":[159],"show":[160,184],"methods":[164,168],"outperform":[165],"three":[166],"competing":[167],"both":[170],"healthy":[171],"speech.":[174],"addition,":[176],"estimation,":[181],"result":[183],"high":[186],"correlation":[187],"between":[188],"estimated":[190],"ground":[194],"truth":[195],"values.":[196]},"counts_by_year":[{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":4},{"year":2020,"cited_by_count":2},{"year":2019,"cited_by_count":3},{"year":2018,"cited_by_count":4},{"year":2017,"cited_by_count":5},{"year":2016,"cited_by_count":4},{"year":2015,"cited_by_count":1}],"updated_date":"2026-04-21T08:09:41.155169","created_date":"2025-10-10T00:00:00"}