{"id":"https://openalex.org/W2965002127","doi":"https://doi.org/10.1016/j.specom.2019.07.003","title":"End-to-end audiovisual speech activity detection with bimodal recurrent neural models","display_name":"End-to-end audiovisual speech activity detection with bimodal recurrent neural models","publication_year":2019,"publication_date":"2019-08-01","ids":{"openalex":"https://openalex.org/W2965002127","doi":"https://doi.org/10.1016/j.specom.2019.07.003","mag":"2965002127"},"language":"en","primary_location":{"id":"doi:10.1016/j.specom.2019.07.003","doi":"https://doi.org/10.1016/j.specom.2019.07.003","is_oa":true,"landing_page_url":"https://doi.org/10.1016/j.specom.2019.07.003","pdf_url":null,"source":{"id":"https://openalex.org/S128025751","display_name":"Speech Communication","issn_l":"0167-6393","issn":["0167-6393","1872-7182"],"is_oa":false,"is_in_doaj":false,"is_core":true,"listed_in":["anvur-class-a","anvur-scientific","ccf-b","cwts-core","dongbi-b","erih-plus","jufo-2","ki-jl-1","norway-1","poland-140","russia-white-list-2","vabb-shw"],"host_organization":"https://openalex.org/P4310320990","host_organization_name":"Elsevier BV","host_organization_lineage":["https://openalex.org/P4310320990"],"host_organization_lineage_names":["Elsevier BV"],"type":"journal"},"license":null,"license_id":null,"version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":"Speech Communication","raw_type":"journal-article"},"volume":null,"type":"article","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"bronze","oa_url":"https://doi.org/10.1016/j.specom.2019.07.003","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5101452102","display_name":"Fei Tao","orcid":"https://orcid.org/0000-0003-4834-8949","observed_orcids":["https://orcid.org/0000-0003-4834-8949"]},"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":"Fei Tao","raw_affiliation_strings":["The University of Texas Dallas, United States"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The University of Texas Dallas, United States","institution_ids":["https://openalex.org/I162577319"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5040793194","display_name":"Carlos Busso","orcid":"https://orcid.org/0000-0002-4075-4072","observed_orcids":["https://orcid.org/0000-0002-4075-4072"]},"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":true,"raw_author_name":"Carlos Busso","raw_affiliation_strings":["The University of Texas Dallas, United States"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The University of Texas Dallas, United States","institution_ids":["https://openalex.org/I162577319"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5040793194"],"corresponding_institution_ids":["https://openalex.org/I162577319"],"apc_list":{"value":2400,"currency":"USD","value_usd":2400},"apc_paid":null,"fwci":3.9536,"has_fulltext":false,"cited_by_count":35,"citation_normalized_percentile":{"value":0.9427933,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":"113","issue":null,"first_page":"25","last_page":"35"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9911999702453613,"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":0.9911999702453613,"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":0.00800000037997961,"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/T12031","display_name":"Speech and dialogue systems","score":0.00019999999494757503,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/voice-activity-detection","display_name":"voice activity detection","score":0.9819999933242798},{"id":"https://openalex.org/keywords/end-to-end-learning","display_name":"end-to-end learning","score":0.8199999928474426},{"id":"https://openalex.org/keywords/noise-robustness","display_name":"noise robustness","score":0.7390000224113464}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8226852416992188},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.7894059419631958},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7578442096710205},{"id":"https://openalex.org/C2778263558","wikidata":"https://www.wikidata.org/wiki/Q46384","display_name":"Microphone","level":3,"score":0.6663521528244019},{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.6052598357200623},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.5361800789833069},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5140131711959839},{"id":"https://openalex.org/C2984842247","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep neural networks","level":3,"score":0.5131202340126038},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.5111554265022278},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.46074071526527405},{"id":"https://openalex.org/C155635449","wikidata":"https://www.wikidata.org/wiki/Q4674699","display_name":"Acoustic model","level":3,"score":0.45165881514549255},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.43930357694625854},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.24233412742614746},{"id":"https://openalex.org/C68115822","wikidata":"https://www.wikidata.org/wiki/Q1068172","display_name":"Sound pressure","level":2,"score":0.07638275623321533},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0684342086315155},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1016/j.specom.2019.07.003","doi":"https://doi.org/10.1016/j.specom.2019.07.003","is_oa":true,"landing_page_url":"https://doi.org/10.1016/j.specom.2019.07.003","pdf_url":null,"source":{"id":"https://openalex.org/S128025751","display_name":"Speech Communication","issn_l":"0167-6393","issn":["0167-6393","1872-7182"],"is_oa":false,"is_in_doaj":false,"is_core":true,"listed_in":["anvur-class-a","anvur-scientific","ccf-b","cwts-core","dongbi-b","erih-plus","jufo-2","ki-jl-1","norway-1","poland-140","russia-white-list-2","vabb-shw"],"host_organization":"https://openalex.org/P4310320990","host_organization_name":"Elsevier BV","host_organization_lineage":["https://openalex.org/P4310320990"],"host_organization_lineage_names":["Elsevier BV"],"type":"journal"},"license":null,"license_id":null,"version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":"Speech Communication","raw_type":"journal-article"},{"id":"pmh:oai:arXiv.org:1809.04553","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/1809.04553","pdf_url":"https://arxiv.org/pdf/1809.04553","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.1809.04553","doi":"https://doi.org/10.48550/arxiv.1809.04553","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.1809.04553","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"article-journal"}],"best_oa_location":{"id":"doi:10.1016/j.specom.2019.07.003","doi":"https://doi.org/10.1016/j.specom.2019.07.003","is_oa":true,"landing_page_url":"https://doi.org/10.1016/j.specom.2019.07.003","pdf_url":null,"source":{"id":"https://openalex.org/S128025751","display_name":"Speech Communication","issn_l":"0167-6393","issn":["0167-6393","1872-7182"],"is_oa":false,"is_in_doaj":false,"is_core":true,"listed_in":["anvur-class-a","anvur-scientific","ccf-b","cwts-core","dongbi-b","erih-plus","jufo-2","ki-jl-1","norway-1","poland-140","russia-white-list-2","vabb-shw"],"host_organization":"https://openalex.org/P4310320990","host_organization_name":"Elsevier BV","host_organization_lineage":["https://openalex.org/P4310320990"],"host_organization_lineage_names":["Elsevier BV"],"type":"journal"},"license":null,"license_id":null,"version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":"Speech Communication","raw_type":"journal-article"},"sustainable_development_goals":[],"sustainable_development_goals_aurora":[{"id":"https://metadata.un.org/sdg/16","display_name":"Peace, justice, and strong institutions","score":0.7699999809265137}],"study_designs":[],"awards":[{"id":"https://openalex.org/G276546230","display_name":"RI: Small: Integrative, Semantic-Aware, Speech-Driven Models for Believable Conversational Agents with Meaningful Behaviors","funder_award_id":"1718944","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G380673404","display_name":"CAREER: Advanced Knowledge Extraction of Affective Behaviors During Natural Human Interaction","funder_award_id":"1453781","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G6671297155","display_name":null,"funder_award_id":"CAREER","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":75,"referenced_works":["https://openalex.org/W179875071","https://openalex.org/W1514579074","https://openalex.org/W1522301498","https://openalex.org/W1538131130","https://openalex.org/W1665214252","https://openalex.org/W1922655562","https://openalex.org/W1973067693","https://openalex.org/W1976187917","https://openalex.org/W1986769338","https://openalex.org/W2016589492","https://openalex.org/W2023100145","https://openalex.org/W2023582935","https://openalex.org/W2028706510","https://openalex.org/W2033571983","https://openalex.org/W2041470347","https://openalex.org/W2041741035","https://openalex.org/W2071301891","https://openalex.org/W2072128103","https://openalex.org/W2078639319","https://openalex.org/W2084237818","https://openalex.org/W2088725063","https://openalex.org/W2097831178","https://openalex.org/W2099471712","https://openalex.org/W2108891849","https://openalex.org/W2109788549","https://openalex.org/W2109886035","https://openalex.org/W2116529913","https://openalex.org/W2127141656","https://openalex.org/W2136922672","https://openalex.org/W2143612262","https://openalex.org/W2157285372","https://openalex.org/W2160815625","https://openalex.org/W2163605009","https://openalex.org/W2164637175","https://openalex.org/W2167734090","https://openalex.org/W2169896329","https://openalex.org/W2184188583","https://openalex.org/W2193413348","https://openalex.org/W2198724430","https://openalex.org/W2341824394","https://openalex.org/W2397098974","https://openalex.org/W2400392957","https://openalex.org/W2400967734","https://openalex.org/W2404704342","https://openalex.org/W2405180117","https://openalex.org/W2406262283","https://openalex.org/W2512215050","https://openalex.org/W2517955251","https://openalex.org/W2530876040","https://openalex.org/W2551572271","https://openalex.org/W2556171197","https://openalex.org/W2560281793","https://openalex.org/W2560431730","https://openalex.org/W2580471497","https://openalex.org/W2593163713","https://openalex.org/W2604769302","https://openalex.org/W2612754342","https://openalex.org/W2734695582","https://openalex.org/W2747172199","https://openalex.org/W2749094483","https://openalex.org/W2749694333","https://openalex.org/W2769321409","https://openalex.org/W2790326622","https://openalex.org/W2889522887","https://openalex.org/W2897067191","https://openalex.org/W2952746495","https://openalex.org/W2963192365","https://openalex.org/W2964018249","https://openalex.org/W2964121744","https://openalex.org/W3099202502","https://openalex.org/W4231109964","https://openalex.org/W4298870604","https://openalex.org/W6687566353","https://openalex.org/W6743044911","https://openalex.org/W7027429494"],"related_works":["https://openalex.org/W2749694333","https://openalex.org/W2734695582","https://openalex.org/W2917987043","https://openalex.org/W2885130944","https://openalex.org/W6907928225","https://openalex.org/W2115066753","https://openalex.org/W3119269912","https://openalex.org/W2557135105","https://openalex.org/W1985158632","https://openalex.org/W2787944098"],"abstract_inverted_index":null,"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":7},{"year":2021,"cited_by_count":8},{"year":2020,"cited_by_count":9},{"year":2019,"cited_by_count":1}],"updated_date":"2026-10-16T09:59:22.235173","created_date":"2019-08-13T00:00:00"}
