{"id":"https://openalex.org/W3015949136","doi":"https://doi.org/10.1109/icassp40776.2020.9054332","title":"Automatic Vocal Tractlandmark Tracking in Rtmri Using Fully Convolutional Networks and Kalman Filter","display_name":"Automatic Vocal Tractlandmark Tracking in Rtmri Using Fully Convolutional Networks and Kalman Filter","publication_year":2020,"publication_date":"2020-04-09","ids":{"openalex":"https://openalex.org/W3015949136","doi":"https://doi.org/10.1109/icassp40776.2020.9054332","mag":"3015949136"},"language":"en","primary_location":{"id":"doi:10.1109/icassp40776.2020.9054332","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp40776.2020.9054332","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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/A5069030230","display_name":"Sasan Asadiabadi","orcid":"https://orcid.org/0000-0001-9774-6105"},"institutions":[{"id":"https://openalex.org/I1351752","display_name":"Ko\u00e7 University","ror":"https://ror.org/00jzwgz36","country_code":"TR","type":"education","lineage":["https://openalex.org/I1351752"]}],"countries":["TR"],"is_corresponding":true,"raw_author_name":"Sasan Asadiabadi","raw_affiliation_strings":["Multimedia, Vision and Graphics Lab, Koc\u00b8 University, Istanbul, Turkey"],"affiliations":[{"raw_affiliation_string":"Multimedia, Vision and Graphics Lab, Koc\u00b8 University, Istanbul, Turkey","institution_ids":["https://openalex.org/I1351752"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5064993025","display_name":"Engin Erzin","orcid":"https://orcid.org/0000-0002-2715-2368"},"institutions":[{"id":"https://openalex.org/I1351752","display_name":"Ko\u00e7 University","ror":"https://ror.org/00jzwgz36","country_code":"TR","type":"education","lineage":["https://openalex.org/I1351752"]}],"countries":["TR"],"is_corresponding":false,"raw_author_name":"Engin Erzin","raw_affiliation_strings":["Multimedia, Vision and Graphics Lab, Koc\u00b8 University, Istanbul, Turkey"],"affiliations":[{"raw_affiliation_string":"Multimedia, Vision and Graphics Lab, Koc\u00b8 University, Istanbul, Turkey","institution_ids":["https://openalex.org/I1351752"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5069030230"],"corresponding_institution_ids":["https://openalex.org/I1351752"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.03285056,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"abs 1412 6980","issue":null,"first_page":"7339","last_page":"7343"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9998000264167786,"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":0.9998000264167786,"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/T11447","display_name":"Blind Source Separation Techniques","score":0.9962999820709229,"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/T11448","display_name":"Face recognition and analysis","score":0.9955000281333923,"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/vocal-tract","display_name":"Vocal tract","score":0.8130381107330322},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7347165942192078},{"id":"https://openalex.org/keywords/kalman-filter","display_name":"Kalman filter","score":0.7241395115852356},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.585415244102478},{"id":"https://openalex.org/keywords/principal-component-analysis","display_name":"Principal component analysis","score":0.5641371607780457},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.5558385848999023},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5479644536972046},{"id":"https://openalex.org/keywords/speech-production","display_name":"Speech production","score":0.45691901445388794},{"id":"https://openalex.org/keywords/landmark","display_name":"Landmark","score":0.45163825154304504},{"id":"https://openalex.org/keywords/tracking","display_name":"Tracking (education)","score":0.44148018956184387},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.32717204093933105}],"concepts":[{"id":"https://openalex.org/C47401133","wikidata":"https://www.wikidata.org/wiki/Q748953","display_name":"Vocal tract","level":2,"score":0.8130381107330322},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7347165942192078},{"id":"https://openalex.org/C157286648","wikidata":"https://www.wikidata.org/wiki/Q846780","display_name":"Kalman filter","level":2,"score":0.7241395115852356},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.585415244102478},{"id":"https://openalex.org/C27438332","wikidata":"https://www.wikidata.org/wiki/Q2873","display_name":"Principal component analysis","level":2,"score":0.5641371607780457},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.5558385848999023},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5479644536972046},{"id":"https://openalex.org/C43617652","wikidata":"https://www.wikidata.org/wiki/Q7575399","display_name":"Speech production","level":2,"score":0.45691901445388794},{"id":"https://openalex.org/C2780297707","wikidata":"https://www.wikidata.org/wiki/Q4895393","display_name":"Landmark","level":2,"score":0.45163825154304504},{"id":"https://openalex.org/C2775936607","wikidata":"https://www.wikidata.org/wiki/Q466845","display_name":"Tracking (education)","level":2,"score":0.44148018956184387},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.32717204093933105},{"id":"https://openalex.org/C19417346","wikidata":"https://www.wikidata.org/wiki/Q7922","display_name":"Pedagogy","level":1,"score":0.0},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/icassp40776.2020.9054332","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp40776.2020.9054332","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},{"id":"pmh:oai:cdm21054.contentdm.oclc.org:IR/9418","is_oa":false,"landing_page_url":"http://cdm21054.contentdm.oclc.org/cdm/ref/collection/IR/id/9418","pdf_url":null,"source":{"id":"https://openalex.org/S4306401341","display_name":"Digital Collections portal (Ko\u00e7 University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1351752","host_organization_name":"Ko\u00e7 University","host_organization_lineage":["https://openalex.org/I1351752"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"2020 IEEE International Conference On Acoustics, Speech And Signal Processing (ICASSP)","raw_type":"Conference proceeding"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","score":0.4399999976158142,"display_name":"Peace, Justice and strong institutions"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":29,"referenced_works":["https://openalex.org/W123135133","https://openalex.org/W1522301498","https://openalex.org/W2022869622","https://openalex.org/W2066381494","https://openalex.org/W2087681821","https://openalex.org/W2101234009","https://openalex.org/W2104095591","https://openalex.org/W2105934661","https://openalex.org/W2115252128","https://openalex.org/W2137037226","https://openalex.org/W2158203944","https://openalex.org/W2182927573","https://openalex.org/W2395611524","https://openalex.org/W2402144811","https://openalex.org/W2746515373","https://openalex.org/W2747580863","https://openalex.org/W2793830723","https://openalex.org/W2888804310","https://openalex.org/W2936504074","https://openalex.org/W2938626520","https://openalex.org/W2953384591","https://openalex.org/W2964121744","https://openalex.org/W2972635256","https://openalex.org/W6631190155","https://openalex.org/W6675354045","https://openalex.org/W6677618333","https://openalex.org/W6685993629","https://openalex.org/W6713134421","https://openalex.org/W7063629575"],"related_works":["https://openalex.org/W2082000062","https://openalex.org/W4234201046","https://openalex.org/W2058733683","https://openalex.org/W2150243332","https://openalex.org/W2804836678","https://openalex.org/W953964455","https://openalex.org/W2010642486","https://openalex.org/W1445695360","https://openalex.org/W2120882262","https://openalex.org/W2621968591"],"abstract_inverted_index":{"Vocal":[0],"tract":[1,39],"(VT)":[2],"contour":[3],"detection":[4,33,86],"in":[5,40,78,103],"real":[6],"time":[7],"MRI":[8],"is":[9],"a":[10,49,57,63],"pre-stage":[11],"to":[12,74],"many":[13],"speech":[14],"production":[15],"related":[16],"applications":[17],"such":[18],"as":[19,54],"articulatory":[20],"analysis":[21],"and":[22,70,80,92,107],"synthesis.":[23],"In":[24],"this":[25],"work,":[26],"we":[27],"present":[28],"an":[29],"algorithm":[30,87],"for":[31],"robust":[32],"of":[34,65,99,105],"keypoints":[35],"on":[36,62],"the":[37,97,100],"vocal":[38],"rtMRI":[41],"sequences":[42],"using":[43],"fully":[44],"convolutional":[45],"networks":[46],"(FCN)":[47],"via":[48],"heatmap":[50],"regression":[51],"approach.":[52],"We":[53],"well":[55,89],"introduce":[56],"spatio-temporal":[58],"stabilization":[59],"scheme":[60],"based":[61],"combination":[64],"Principal":[66],"Component":[67],"Analysis":[68],"(PCA)":[69],"Kalman":[71],"filter":[72],"(KF)":[73],"extract":[75],"stable":[76],"landmarks":[77],"space":[79],"time.":[81],"The":[82],"proposed":[83],"VT":[84],"landmark":[85],"generalizes":[88],"across":[90],"subjects":[91],"demonstrates":[93],"significant":[94],"improvement":[95],"over":[96],"state":[98],"art":[101],"baselines,":[102],"terms":[104],"spatial":[106],"temporal":[108],"errors.":[109]},"counts_by_year":[],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2020-04-17T00:00:00"}
