{"id":"https://openalex.org/W4387421719","doi":"https://doi.org/10.1145/3577190.3614154","title":"Video-based Respiratory Waveform Estimation in Dialogue: A Novel Task and Dataset for Human-Machine Interaction","display_name":"Video-based Respiratory Waveform Estimation in Dialogue: A Novel Task and Dataset for Human-Machine Interaction","publication_year":2023,"publication_date":"2023-10-07","ids":{"openalex":"https://openalex.org/W4387421719","doi":"https://doi.org/10.1145/3577190.3614154"},"language":"en","primary_location":{"id":"doi:10.1145/3577190.3614154","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3577190.3614154","pdf_url":null,"source":{"id":"https://openalex.org/S4363608440","display_name":"INTERNATIONAL CONFERENCE ON MULTIMODAL INTERACTION","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"INTERNATIONAL CONFERENCE ON MULTIMODAL INTERACTION","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/A5103283737","display_name":"Takao Obi","orcid":"https://orcid.org/0009-0003-4607-3379"},"institutions":[{"id":"https://openalex.org/I114531698","display_name":"Tokyo Institute of Technology","ror":"https://ror.org/0112mx960","country_code":"JP","type":"education","lineage":["https://openalex.org/I114531698"]}],"countries":["JP"],"is_corresponding":true,"raw_author_name":"Takao Obi","raw_affiliation_strings":["Tokyo Institute of Technology, Japan"],"affiliations":[{"raw_affiliation_string":"Tokyo Institute of Technology, Japan","institution_ids":["https://openalex.org/I114531698"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5069989297","display_name":"Kotaro Funakoshi","orcid":"https://orcid.org/0000-0002-4529-4634"},"institutions":[{"id":"https://openalex.org/I114531698","display_name":"Tokyo Institute of Technology","ror":"https://ror.org/0112mx960","country_code":"JP","type":"education","lineage":["https://openalex.org/I114531698"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Kotaro Funakoshi","raw_affiliation_strings":["Tokyo Institute of Technology, Japan"],"affiliations":[{"raw_affiliation_string":"Tokyo Institute of Technology, Japan","institution_ids":["https://openalex.org/I114531698"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5103283737"],"corresponding_institution_ids":["https://openalex.org/I114531698"],"apc_list":null,"apc_paid":null,"fwci":0.0959,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.42138365,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"649","last_page":"660"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9968000054359436,"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":0.9968000054359436,"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/T11309","display_name":"Music and Audio Processing","score":0.996399998664856,"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/T10863","display_name":"Voice and Speech Disorders","score":0.9937000274658203,"subfield":{"id":"https://openalex.org/subfields/2737","display_name":"Physiology"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/waveform","display_name":"Waveform","score":0.7959579229354858},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7812221050262451},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.6570507287979126},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5867319107055664},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.44710710644721985},{"id":"https://openalex.org/keywords/estimation","display_name":"Estimation","score":0.4348433017730713},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4286154508590698},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3436497151851654},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.07452535629272461}],"concepts":[{"id":"https://openalex.org/C197424946","wikidata":"https://www.wikidata.org/wiki/Q1165717","display_name":"Waveform","level":3,"score":0.7959579229354858},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7812221050262451},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.6570507287979126},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5867319107055664},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.44710710644721985},{"id":"https://openalex.org/C96250715","wikidata":"https://www.wikidata.org/wiki/Q965330","display_name":"Estimation","level":2,"score":0.4348433017730713},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4286154508590698},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3436497151851654},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.07452535629272461},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0},{"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/C554190296","wikidata":"https://www.wikidata.org/wiki/Q47528","display_name":"Radar","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3577190.3614154","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3577190.3614154","pdf_url":null,"source":{"id":"https://openalex.org/S4363608440","display_name":"INTERNATIONAL CONFERENCE ON MULTIMODAL INTERACTION","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"INTERNATIONAL CONFERENCE ON MULTIMODAL INTERACTION","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.6100000143051147}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":45,"referenced_works":["https://openalex.org/W175385064","https://openalex.org/W1964951887","https://openalex.org/W1987573031","https://openalex.org/W1992245461","https://openalex.org/W1993055580","https://openalex.org/W2001565257","https://openalex.org/W2024765177","https://openalex.org/W2036882286","https://openalex.org/W2036966696","https://openalex.org/W2046790216","https://openalex.org/W2055580635","https://openalex.org/W2069470928","https://openalex.org/W2077302143","https://openalex.org/W2079382073","https://openalex.org/W2092244451","https://openalex.org/W2111294435","https://openalex.org/W2139070213","https://openalex.org/W2147154374","https://openalex.org/W2162464803","https://openalex.org/W2167355791","https://openalex.org/W2191779130","https://openalex.org/W2209977956","https://openalex.org/W2309023520","https://openalex.org/W2317015831","https://openalex.org/W2327960307","https://openalex.org/W2399858921","https://openalex.org/W2425118219","https://openalex.org/W2486828091","https://openalex.org/W2532937210","https://openalex.org/W2603276336","https://openalex.org/W2614550605","https://openalex.org/W2745346281","https://openalex.org/W2765312147","https://openalex.org/W2980014438","https://openalex.org/W2980823180","https://openalex.org/W3009203799","https://openalex.org/W3015484904","https://openalex.org/W3092697035","https://openalex.org/W3104042626","https://openalex.org/W3176601509","https://openalex.org/W3196984997","https://openalex.org/W4220725617","https://openalex.org/W4234994791","https://openalex.org/W4249803144","https://openalex.org/W4251603968"],"related_works":["https://openalex.org/W1974895211","https://openalex.org/W2129841057","https://openalex.org/W3040712279","https://openalex.org/W2176409448","https://openalex.org/W2364769705","https://openalex.org/W2056136368","https://openalex.org/W2374664672","https://openalex.org/W4367555392","https://openalex.org/W2538520412","https://openalex.org/W2883092465"],"abstract_inverted_index":{"Respiration":[0],"is":[1,9,23,110],"closely":[2],"related":[3],"to":[4,29,94],"speech,":[5],"so":[6],"respiratory":[7,64],"information":[8],"useful":[10],"for":[11,25,66,71,112],"improving":[12,113],"human-machine":[13,114],"multimodal":[14,26,115],"spoken":[15],"interaction":[16,39],"from":[17],"various":[18],"perspectives.":[19],"A":[20,60],"machine-learning":[21],"task":[22,48],"presented":[24],"interactive":[27],"systems":[28,35],"improve":[30],"the":[31,34,85],"compatibility":[32],"of":[33,50,63],"and":[36,56,74],"promote":[37],"smooth":[38],"with":[40],"them.":[41],"This":[42],"\u201cvideo-based":[43],"respiration":[44],"waveform":[45,53,57],"estimation":[46,55],"(VRWE)\u201d":[47],"consists":[49],"two":[51],"subtasks:":[52],"amplitude":[54],"gradient":[58,90],"estimation.":[59],"dataset":[61],"consisting":[62],"data":[65],"30":[67],"participants":[68],"was":[69,82,92],"created":[70],"this":[72],"task,":[73],"a":[75],"strong":[76],"baseline":[77],"method":[78],"based":[79],"on":[80,84],"3DCNN-ConvLSTM":[81],"evaluated":[83],"dataset.":[86],"Finally,":[87],"VRWE,":[88],"especially":[89],"estimation,":[91],"shown":[93],"be":[95],"effective":[96,111],"in":[97],"predicting":[98],"user":[99],"voice":[100],"activity":[101],"after":[102],"200":[103],"ms.":[104],"These":[105],"results":[106],"suggest":[107],"that":[108],"VRWE":[109],"interaction.":[116]},"counts_by_year":[{"year":2024,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}