{"id":"https://openalex.org/W2972363853","doi":"https://doi.org/10.21437/interspeech.2019-2295","title":"Acoustic and Articulatory Feature Based Speech Rate Estimation Using a Convolutional Dense Neural Network","display_name":"Acoustic and Articulatory Feature Based Speech Rate Estimation Using a Convolutional Dense Neural Network","publication_year":2019,"publication_date":"2019-09-13","ids":{"openalex":"https://openalex.org/W2972363853","doi":"https://doi.org/10.21437/interspeech.2019-2295","mag":"2972363853"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2019-2295","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2019-2295","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2019","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/A5072700492","display_name":"Renuka Mannem","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Renuka Mannem","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5008931819","display_name":"Jhansi Mallela","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jhansi Mallela","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5023231479","display_name":"Aravind Illa","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Aravind Illa","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5046000500","display_name":"Prasanta Ghosh","orcid":"https://orcid.org/0000-0002-2925-1802"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Prasanta Kumar Ghosh","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.6676,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.69066894,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"929","last_page":"933"},"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":0.9987000226974487,"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":0.9843000173568726,"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/computer-science","display_name":"Computer science","score":0.818516731262207},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.748846709728241},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7393498420715332},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.572942852973938},{"id":"https://openalex.org/keywords/estimation","display_name":"Estimation","score":0.5151142477989197},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4671786427497864},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.4610987901687622},{"id":"https://openalex.org/keywords/acoustic-model","display_name":"Acoustic model","score":0.441037654876709},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.38287463784217834},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.3564814329147339},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.05743160843849182}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.818516731262207},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.748846709728241},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7393498420715332},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.572942852973938},{"id":"https://openalex.org/C96250715","wikidata":"https://www.wikidata.org/wiki/Q965330","display_name":"Estimation","level":2,"score":0.5151142477989197},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4671786427497864},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.4610987901687622},{"id":"https://openalex.org/C155635449","wikidata":"https://www.wikidata.org/wiki/Q4674699","display_name":"Acoustic model","level":3,"score":0.441037654876709},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.38287463784217834},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.3564814329147339},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.05743160843849182},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"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}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.21437/interspeech.2019-2295","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2019-2295","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2019","raw_type":"proceedings-article"},{"id":"pmh:oai::78254","is_oa":false,"landing_page_url":null,"pdf_url":null,"source":{"id":"https://openalex.org/S4306401429","display_name":"ePrints@IISc (Indian Institute of Science)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I59270414","host_organization_name":"Indian Institute of Science Bangalore","host_organization_lineage":["https://openalex.org/I59270414"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":"","raw_type":"Conference Paper"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":17,"referenced_works":["https://openalex.org/W222076935","https://openalex.org/W1598253959","https://openalex.org/W1761922146","https://openalex.org/W1976698896","https://openalex.org/W1988687075","https://openalex.org/W1998628338","https://openalex.org/W2009254313","https://openalex.org/W2018882848","https://openalex.org/W2049515993","https://openalex.org/W2054889609","https://openalex.org/W2066381494","https://openalex.org/W2096774922","https://openalex.org/W2098396290","https://openalex.org/W2146562971","https://openalex.org/W2171907819","https://openalex.org/W2938626520","https://openalex.org/W2991007063"],"related_works":["https://openalex.org/W4293226380","https://openalex.org/W2921005841","https://openalex.org/W2992378684","https://openalex.org/W2964829415","https://openalex.org/W642007152","https://openalex.org/W2122233706","https://openalex.org/W2105439218","https://openalex.org/W3143423642","https://openalex.org/W2131711534","https://openalex.org/W2341426843"],"abstract_inverted_index":{"In":[0],"this":[1],"paper,":[2],"we":[3,93],"propose":[4],"a":[5,11,60,72,100,172],"speech":[6,28,90,160],"rate":[7,29,161],"estimation":[8],"approach":[9,20,117,170],"using":[10,99,118,141],"convolutional":[12],"dense":[13],"neural":[14],"network":[15,104],"(CDNN).":[16],"The":[17,31,55,113,151],"CDNN":[18,115,168],"based":[19,116,169,184],"uses":[21],"the":[22,43,68,79,107,111,159,167,177],"acoustic":[23,40,87,124,134],"and":[24,42,125,179,189,194],"articulatory":[25,53,120,126],"features":[26,41,81,88,109,121,127],"for":[27],"estimation.":[30,162],"Mel":[32],"Frequency":[33],"Cepstral":[34],"Coefficients":[35],"(MFCCs)":[36],"are":[37,50,82,139],"used":[38,51,156],"as":[39,52],"articulograms":[44],"representing":[45],"time-varying":[46],"vocal":[47],"tract":[48],"profile":[49],"features.":[54],"articulogram":[56,80,108],"is":[57,155,164],"computed":[58],"from":[59,89,110,144],"real-time":[61],"magnetic":[62],"resonance":[63],"imaging":[64],"(rtMRI)":[65],"video":[66],"in":[67,77,192],"midsagittal":[69],"plane":[70],"of":[71],"subject":[73,196],"while":[74],"speaking.":[75],"However,":[76],"practice,":[78],"not":[83],"directly":[84],"available,":[85],"unlike":[86],"recording.":[91],"Thus,":[92],"use":[94],"an":[95],"Acoustic-to-Articulatory":[96],"Inversion":[97],"method":[98],"bidirectional":[101],"long-short-term":[102],"memory":[103],"which":[105],"estimates":[106],"acoustics.":[112],"proposed":[114],"estimated":[119],"requires":[122,132],"both":[123],"during":[128,136],"training":[129],"but":[130],"it":[131],"only":[133],"data":[135],"testing.":[137],"Experiments":[138],"conducted":[140],"rtMRI":[142],"videos":[143],"four":[145],"subjects":[146],"each":[147],"speaking":[148],"460":[149],"sentences.":[150],"Pearson":[152],"correlation":[153,174,182],"coefficient":[154,175],"to":[157],"evaluate":[158],"It":[163],"found":[165],"that":[166],"gives":[171],"better":[173],"than":[176],"temporal":[178],"selected":[180],"sub-band":[181],"(TCSSBC)":[183],"baseline":[185],"scheme":[186],"by":[187],"81.58":[188],"73.68":[190],"(relative)":[191],"seen":[193],"unseen":[195],"conditions":[197],"respectively.":[198]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":3}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}
