{"id":"https://openalex.org/W37491457","doi":"https://doi.org/10.21437/icslp.2000-466","title":"Perceptual interfaces for information interaction: joint processing of audio and visual information for human-computer interaction","display_name":"Perceptual interfaces for information interaction: joint processing of audio and visual information for human-computer interaction","publication_year":2000,"publication_date":"2000-10-16","ids":{"openalex":"https://openalex.org/W37491457","doi":"https://doi.org/10.21437/icslp.2000-466","mag":"37491457"},"language":"en","primary_location":{"id":"doi:10.21437/icslp.2000-466","doi":"https://doi.org/10.21437/icslp.2000-466","is_oa":false,"landing_page_url":"https://doi.org/10.21437/icslp.2000-466","pdf_url":null,"source":{"id":"https://openalex.org/S4363607739","display_name":"International Conference on Spoken Language Processing (ICSLP)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":"6th International Conference on Spoken Language Processing (ICSLP 2000)","raw_type":"proceedings-article"},"volume":null,"type":"conference-paper","is_traditional":true,"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/A5112716175","display_name":"Chalapathi Neti","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chalapathi Neti","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5022650481","display_name":"Giridharan Iyengar","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Giridharan Iyengar","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5024184433","display_name":"Gerasimos Potamianos","orcid":"https://orcid.org/0000-0002-9833-7124","observed_orcids":["https://orcid.org/0000-0002-9833-7124"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Gerasimos Potamianos","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5079708487","display_name":"Andrew Senior","orcid":"https://orcid.org/0000-0002-2401-5691","observed_orcids":["https://orcid.org/0000-0002-2401-5691"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"A. Senior","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5016131266","display_name":"Benoit Maison","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Benoit Maison","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":5.2856,"has_fulltext":false,"cited_by_count":23,"citation_normalized_percentile":{"value":0.95080321,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":88,"max":93},"biblio":{"volume":null,"issue":null,"first_page":"vol. 3, 11","last_page":"14"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9092000126838684,"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":0.9092000126838684,"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":0.06599999964237213,"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":0.008700000122189522,"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/audiovisual-integration","display_name":"audiovisual integration","score":0.746999979019165},{"id":"https://openalex.org/keywords/sensory-integration","display_name":"sensory integration","score":0.8180000185966492},{"id":"https://openalex.org/keywords/human-computer-interaction","display_name":"human-computer interaction","score":0.8320000171661377},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"speech recognition","score":0.8880000114440918},{"id":"https://openalex.org/keywords/speech-event-detection","display_name":"speech event detection","score":0.9340000152587891},{"id":"https://openalex.org/keywords/speaker-change-detection","display_name":"speaker change detection","score":0.9810000061988831},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"speaker recognition","score":0.8090000152587891},{"id":"https://openalex.org/keywords/intent-recognition","display_name":"intent classification","score":0.652999997138977},{"id":"https://openalex.org/keywords/noise-robustness","display_name":"noise robustness","score":0.7400000095367432},{"id":"https://openalex.org/keywords/acoustic-degradation","display_name":"acoustic degradation","score":0.5659999847412109},{"id":"https://openalex.org/keywords/multisensory-perception","display_name":"multisensory perception","score":0.6050000190734863}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7922216653823853},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6910943984985352},{"id":"https://openalex.org/C18555067","wikidata":"https://www.wikidata.org/wiki/Q8375051","display_name":"Joint (building)","level":2,"score":0.6239858865737915},{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.6148882508277893},{"id":"https://openalex.org/C136197465","wikidata":"https://www.wikidata.org/wiki/Q1729295","display_name":"Variety (cybernetics)","level":2,"score":0.5015764236450195},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.49846529960632324},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.4835633933544159},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.4378751516342163},{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.4337015450000763},{"id":"https://openalex.org/C113843644","wikidata":"https://www.wikidata.org/wiki/Q901882","display_name":"Interface (matter)","level":4,"score":0.4212421178817749},{"id":"https://openalex.org/C94487597","wikidata":"https://www.wikidata.org/wiki/Q11101","display_name":"Sensory system","level":2,"score":0.41042786836624146},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2743557393550873},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.11416062712669373},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.10591766238212585},{"id":"https://openalex.org/C180747234","wikidata":"https://www.wikidata.org/wiki/Q23373","display_name":"Cognitive psychology","level":1,"score":0.09325695037841797},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.08275672793388367},{"id":"https://openalex.org/C157915830","wikidata":"https://www.wikidata.org/wiki/Q2928001","display_name":"Bubble","level":2,"score":0.0},{"id":"https://openalex.org/C170154142","wikidata":"https://www.wikidata.org/wiki/Q150737","display_name":"Architectural engineering","level":1,"score":0.0},{"id":"https://openalex.org/C169760540","wikidata":"https://www.wikidata.org/wiki/Q207011","display_name":"Neuroscience","level":1,"score":0.0},{"id":"https://openalex.org/C129307140","wikidata":"https://www.wikidata.org/wiki/Q6795880","display_name":"Maximum bubble pressure method","level":3,"score":0.0},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.21437/icslp.2000-466","doi":"https://doi.org/10.21437/icslp.2000-466","is_oa":false,"landing_page_url":"https://doi.org/10.21437/icslp.2000-466","pdf_url":null,"source":{"id":"https://openalex.org/S4363607739","display_name":"International Conference on Spoken Language Processing (ICSLP)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":"6th International Conference on Spoken Language Processing (ICSLP 2000)","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.25.5505","doi":null,"is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.25.5505","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.research.ibm.com/AVSTG/ICSLP00_PERCEPTUAL.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":11,"referenced_works":["https://openalex.org/W170371357","https://openalex.org/W1520736967","https://openalex.org/W1599408644","https://openalex.org/W2015394094","https://openalex.org/W2039562357","https://openalex.org/W2051091181","https://openalex.org/W2102863932","https://openalex.org/W2108891849","https://openalex.org/W2111135419","https://openalex.org/W2146555731","https://openalex.org/W2170308399"],"related_works":["https://openalex.org/W180027692","https://openalex.org/W185043196","https://openalex.org/W75825362","https://openalex.org/W2917462003","https://openalex.org/W1516357917","https://openalex.org/W2146614494","https://openalex.org/W1520114230","https://openalex.org/W1797158261","https://openalex.org/W31621703","https://openalex.org/W2581624321"],"abstract_inverted_index":{"We":[0],"are":[1],"exploiting":[2],"the":[3,20,44,68],"human":[4,23,38],"perceptual":[5],"principle":[6],"of":[7,13,22,46,64,70],"sensory":[8],"integration":[9],"(the":[10],"joint":[11,71],"use":[12],"audio":[14],"and":[15,30,37,52],"visual":[16],"information)":[17],"to":[18,35,50],"improve":[19],"recognition":[21],"activity":[24],"(speech":[25],"recognition,":[26],"speech":[27],"event":[28],"detection":[29],"speaker":[31],"change),":[32],"intent":[33],"(intent":[34],"speak)":[36],"identity":[39],"(speaker":[40],"recognition),":[41],"particularly":[42],"in":[43,61],"presence":[45],"acoustic":[47],"degradation":[48],"due":[49],"noise":[51],"channel.":[53],"In":[54],"this":[55],"paper,":[56],"we":[57],"present":[58],"experimental":[59],"results":[60],"a":[62],"variety":[63],"contexts":[65],"that":[66],"demonstrate":[67],"benefit":[69],"audio-visual":[72],"processing.":[73]},"counts_by_year":[{"year":2020,"cited_by_count":1},{"year":2016,"cited_by_count":1},{"year":2014,"cited_by_count":1},{"year":2012,"cited_by_count":1}],"updated_date":"2026-11-04T10:54:05.112534","created_date":"2016-06-24T00:00:00"}