{"id":"https://openalex.org/W7074736534","doi":null,"title":"The Role of Speech in Multimodal Human-Computer Interaction (Towards Reliable Rejection of Non-Keyword Input)","display_name":"The Role of Speech in Multimodal Human-Computer Interaction (Towards Reliable Rejection of Non-Keyword Input)","publication_year":2005,"publication_date":"2005-01-01","ids":{"openalex":"https://openalex.org/W7074736534"},"language":"en","primary_location":{"id":"pmh:oai:infoscience.tind.io:83198","doi":null,"is_oa":true,"landing_page_url":"https://infoscience.epfl.ch/handle/20.500.14299/228649","pdf_url":"http://infoscience.epfl.ch/record/83198","source":{"id":"https://openalex.org/S4306400487","display_name":"Infoscience (Ecole Polytechnique F\u00e9d\u00e9rale de Lausanne)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I5124864","host_organization_name":"\u00c9cole Polytechnique F\u00e9d\u00e9rale de Lausanne","host_organization_lineage":["https://openalex.org/I5124864"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"report"},"volume":null,"type":"report","is_traditional":false,"indexed_in":[],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"http://infoscience.epfl.ch/record/83198","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5042260050","display_name":"Hynek He\u0159mansk\u00fd","orcid":"https://orcid.org/0000-0001-8032-4811","observed_orcids":["https://orcid.org/0000-0001-8032-4811"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hynek Hermansky","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5006171209","display_name":"Petr Fousek","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Petr Fousek","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5021341532","display_name":"Mikko Lehtonen","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Mikko Lehtonen","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":null,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":true,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.5785999894142151,"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"}},"topics":[{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.5785999894142151,"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":0.18330000340938568,"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/T10860","display_name":"Speech and Audio Processing","score":0.1680999994277954,"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/multimodal-human-computer-interaction","display_name":"multimodal human-computer interaction","score":0.949999988079071},{"id":"https://openalex.org/keywords/keyword-spotting","display_name":"keyword spotting","score":0.7739999890327454},{"id":"https://openalex.org/keywords/audio-classification","display_name":"audio classification","score":0.593999981880188},{"id":"https://openalex.org/keywords/gesture-recognition","display_name":"gesture recognition","score":0.8220000267028809}],"concepts":[{"id":"https://openalex.org/C207347870","wikidata":"https://www.wikidata.org/wiki/Q371174","display_name":"Gesture","level":2,"score":0.6812000274658203},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6330000162124634},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5861999988555908},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.5659999847412109},{"id":"https://openalex.org/C2776608160","wikidata":"https://www.wikidata.org/wiki/Q4785462","display_name":"Natural (archaeology)","level":2,"score":0.527999997138977},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.48649999499320984},{"id":"https://openalex.org/C113843644","wikidata":"https://www.wikidata.org/wiki/Q901882","display_name":"Interface (matter)","level":4,"score":0.4226999878883362},{"id":"https://openalex.org/C3018392663","wikidata":"https://www.wikidata.org/wiki/Q202064","display_name":"Speech sound","level":2,"score":0.38359999656677246},{"id":"https://openalex.org/C2780646970","wikidata":"https://www.wikidata.org/wiki/Q6980787","display_name":"Natural sounds","level":2,"score":0.37560001015663147},{"id":"https://openalex.org/C203718221","wikidata":"https://www.wikidata.org/wiki/Q491713","display_name":"Sound (geography)","level":2,"score":0.37459999322891235},{"id":"https://openalex.org/C135641252","wikidata":"https://www.wikidata.org/wiki/Q738567","display_name":"Multimodal interaction","level":2,"score":0.35339999198913574},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3395000100135803},{"id":"https://openalex.org/C2992428333","wikidata":"https://www.wikidata.org/wiki/Q11461","display_name":"Sound production","level":2,"score":0.3221000134944916},{"id":"https://openalex.org/C89505385","wikidata":"https://www.wikidata.org/wiki/Q47146","display_name":"User interface","level":2,"score":0.3172999918460846},{"id":"https://openalex.org/C46312422","wikidata":"https://www.wikidata.org/wiki/Q11024","display_name":"Communication","level":1,"score":0.3084999918937683},{"id":"https://openalex.org/C165024716","wikidata":"https://www.wikidata.org/wiki/Q47146","display_name":"Human\u2013machine interface","level":3,"score":0.2953999936580658},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.2842000126838684},{"id":"https://openalex.org/C126042441","wikidata":"https://www.wikidata.org/wiki/Q1324888","display_name":"Frame (networking)","level":2,"score":0.27790001034736633},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.2775000035762787},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.27399998903274536},{"id":"https://openalex.org/C137584468","wikidata":"https://www.wikidata.org/wiki/Q35395","display_name":"Phonetics","level":2,"score":0.26330000162124634},{"id":"https://openalex.org/C187482481","wikidata":"https://www.wikidata.org/wiki/Q1851756","display_name":"Natural user interface","level":4,"score":0.25519999861717224}],"mesh":[],"locations_count":4,"locations":[{"id":"pmh:oai:infoscience.tind.io:83198","doi":null,"is_oa":true,"landing_page_url":"https://infoscience.epfl.ch/handle/20.500.14299/228649","pdf_url":"http://infoscience.epfl.ch/record/83198","source":{"id":"https://openalex.org/S4306400487","display_name":"Infoscience (Ecole Polytechnique F\u00e9d\u00e9rale de Lausanne)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I5124864","host_organization_name":"\u00c9cole Polytechnique F\u00e9d\u00e9rale de Lausanne","host_organization_lineage":["https://openalex.org/I5124864"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"report"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.87.4340","doi":null,"is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.87.4340","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.im.ethz.ch/people/mlehtonen/tsd05.pdf","raw_type":"text"},{"id":"pmh:oai:infoscience.epfl.ch:83198","doi":null,"is_oa":true,"landing_page_url":"http://infoscience.epfl.ch/record/83198","pdf_url":null,"source":{"id":"https://openalex.org/S4306400487","display_name":"Infoscience (Ecole Polytechnique F\u00e9d\u00e9rale de Lausanne)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I5124864","host_organization_name":"\u00c9cole Polytechnique F\u00e9d\u00e9rale de Lausanne","host_organization_lineage":["https://openalex.org/I5124864"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Text"},{"id":"pmh:oai:infoscience.epfl.ch:83200","doi":null,"is_oa":true,"landing_page_url":"http://infoscience.epfl.ch/record/83200","pdf_url":null,"source":{"id":"https://openalex.org/S4306400487","display_name":"Infoscience (Ecole Polytechnique F\u00e9d\u00e9rale de Lausanne)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I5124864","host_organization_name":"\u00c9cole Polytechnique F\u00e9d\u00e9rale de Lausanne","host_organization_lineage":["https://openalex.org/I5124864"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Text"}],"best_oa_location":{"id":"pmh:oai:infoscience.tind.io:83198","doi":null,"is_oa":true,"landing_page_url":"https://infoscience.epfl.ch/handle/20.500.14299/228649","pdf_url":"http://infoscience.epfl.ch/record/83198","source":{"id":"https://openalex.org/S4306400487","display_name":"Infoscience (Ecole Polytechnique F\u00e9d\u00e9rale de Lausanne)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I5124864","host_organization_name":"\u00c9cole Polytechnique F\u00e9d\u00e9rale de Lausanne","host_organization_lineage":["https://openalex.org/I5124864"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"report"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7074736534.pdf","grobid_xml":"https://content.openalex.org/works/W7074736534.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W7096179182","https://openalex.org/W1513301185","https://openalex.org/W2327919033","https://openalex.org/W1527904782","https://openalex.org/W2526711902","https://openalex.org/W7074158839","https://openalex.org/W1808112631","https://openalex.org/W2248801282","https://openalex.org/W2108891849","https://openalex.org/W2327109811"],"abstract_inverted_index":{"Abstract.":[0],"Natural":[1],"audio-visual":[2,13],"interface":[3],"between":[4],"human":[5],"user":[6],"and":[7,22,63,74],"machine":[8,39],"requires":[9],"understanding":[10],"of":[11,42,70],"user\u2019s":[12],"commands.":[14],"This":[15],"does":[16,26],"not":[17],"necessarily":[18],"require":[19],"full":[20],"speech":[21],"image":[23],"recognition.":[24],"It":[25],"require,":[27],"just":[28],"as":[29],"the":[30,38,52,71],"interaction":[31],"with":[32],"any":[33],"working":[34,59],"animal":[35],"does,":[36],"that":[37,66],"is":[40],"capable":[41],"reacting":[43],"to":[44,77],"certain":[45],"particular":[46,79],"sounds":[47],"and/or":[48],"gestures":[49],"while":[50],"ignoring":[51],"rest.":[53],"Towards":[54],"this":[55],"end,":[56],"we":[57],"are":[58],"on":[60],"sound":[61,80],"identification":[62],"classification":[64],"approaches":[65],"would":[67],"ignore":[68],"most":[69],"acoustic":[72],"input":[73],"react":[75],"only":[76],"a":[78],"(keyword).":[81],"1":[82]},"counts_by_year":[],"updated_date":"2026-11-06T12:05:46.655746","created_date":"2025-10-10T00:00:00"}
