{"id":"https://openalex.org/W1098746774","doi":"https://doi.org/10.21437/interspeech.2015-203","title":"Incorporating visual information for spoken term detection","display_name":"Incorporating visual information for spoken term detection","publication_year":2015,"publication_date":"2015-09-06","ids":{"openalex":"https://openalex.org/W1098746774","doi":"https://doi.org/10.21437/interspeech.2015-203","mag":"1098746774"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2015-203","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2015-203","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2015","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/A5072416824","display_name":"Shahram Kalantari","orcid":null},"institutions":[{"id":"https://openalex.org/I165143802","display_name":"University of Queensland","ror":"https://ror.org/00rqy9422","country_code":"AU","type":"education","lineage":["https://openalex.org/I165143802"]}],"countries":["AU"],"is_corresponding":true,"raw_author_name":"Shahram Kalantari","raw_affiliation_strings":["University of Queensland, Brisbane, Australia"],"affiliations":[{"raw_affiliation_string":"University of Queensland, Brisbane, Australia","institution_ids":["https://openalex.org/I165143802"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5000014182","display_name":"David Dean","orcid":"https://orcid.org/0000-0003-1274-9775"},"institutions":[{"id":"https://openalex.org/I160993911","display_name":"Queensland University of Technology","ror":"https://ror.org/03pnv4752","country_code":"AU","type":"education","lineage":["https://openalex.org/I160993911"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"David Dean","raw_affiliation_strings":["Queensland University of Technology, Brisbane, Australia"],"affiliations":[{"raw_affiliation_string":"Queensland University of Technology, Brisbane, Australia","institution_ids":["https://openalex.org/I160993911"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5055128383","display_name":"Sridha Sridharan","orcid":"https://orcid.org/0000-0003-4316-9001"},"institutions":[{"id":"https://openalex.org/I160993911","display_name":"Queensland University of Technology","ror":"https://ror.org/03pnv4752","country_code":"AU","type":"education","lineage":["https://openalex.org/I160993911"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Sridha Sridharan","raw_affiliation_strings":["Queensland University of Technology, Brisbane, Australia"],"affiliations":[{"raw_affiliation_string":"Queensland University of Technology, Brisbane, Australia","institution_ids":["https://openalex.org/I160993911"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5072416824"],"corresponding_institution_ids":["https://openalex.org/I165143802"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.01112367,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"558","last_page":"562"},"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/T10901","display_name":"Advanced Data Compression Techniques","score":0.9940999746322632,"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"}},{"id":"https://openalex.org/T11233","display_name":"Advanced Adaptive Filtering Techniques","score":0.9916999936103821,"subfield":{"id":"https://openalex.org/subfields/2206","display_name":"Computational Mechanics"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8301044702529907},{"id":"https://openalex.org/keywords/search-engine-indexing","display_name":"Search engine indexing","score":0.7941370010375977},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.77472323179245},{"id":"https://openalex.org/keywords/matching","display_name":"Matching (statistics)","score":0.5798967480659485},{"id":"https://openalex.org/keywords/phone","display_name":"Phone","score":0.5690953135490417},{"id":"https://openalex.org/keywords/term","display_name":"Term (time)","score":0.5550028085708618},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5123027563095093},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.45093098282814026},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.448068231344223},{"id":"https://openalex.org/keywords/visual-search","display_name":"Visual search","score":0.42074763774871826},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.33980557322502136},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.06921634078025818},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.06768694519996643}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8301044702529907},{"id":"https://openalex.org/C75165309","wikidata":"https://www.wikidata.org/wiki/Q2258979","display_name":"Search engine indexing","level":2,"score":0.7941370010375977},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.77472323179245},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.5798967480659485},{"id":"https://openalex.org/C2778707766","wikidata":"https://www.wikidata.org/wiki/Q202064","display_name":"Phone","level":2,"score":0.5690953135490417},{"id":"https://openalex.org/C61797465","wikidata":"https://www.wikidata.org/wiki/Q1188986","display_name":"Term (time)","level":2,"score":0.5550028085708618},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5123027563095093},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.45093098282814026},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.448068231344223},{"id":"https://openalex.org/C158495155","wikidata":"https://www.wikidata.org/wiki/Q2369151","display_name":"Visual search","level":2,"score":0.42074763774871826},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.33980557322502136},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.06921634078025818},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.06768694519996643},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.21437/interspeech.2015-203","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2015-203","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2015","raw_type":"proceedings-article"},{"id":"pmh:oai:eprints.qut.edu.au:86034","is_oa":false,"landing_page_url":"http://www.isca-speech.org/archive/interspeech_2015/i15_0558.html","pdf_url":null,"source":{"id":"https://openalex.org/S4306402607","display_name":"QUT ePrints (Queensland University of Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I160993911","host_organization_name":"Queensland University of Technology","host_organization_lineage":["https://openalex.org/I160993911"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Proceedings of the 16th Annual Conference of the International Speech Communication Association, Interspeech 2015","raw_type":"Chapter in Book, Report or Conference volume"},{"id":"mag:1098746774","is_oa":false,"landing_page_url":"https://eprints.qut.edu.au/86034/","pdf_url":null,"source":{"id":"https://openalex.org/S2764552960","display_name":"Science & Engineering Faculty","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":"Science & Engineering Faculty","raw_type":null}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.4099999964237213,"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W2402407026","https://openalex.org/W2293750915","https://openalex.org/W2584889690","https://openalex.org/W1914280119","https://openalex.org/W946500394","https://openalex.org/W2000954587","https://openalex.org/W2163215038","https://openalex.org/W2137044559","https://openalex.org/W2888436980","https://openalex.org/W2799046698","https://openalex.org/W2402543639","https://openalex.org/W2466965474","https://openalex.org/W2018107982","https://openalex.org/W2150347857","https://openalex.org/W1915785597","https://openalex.org/W2981544649","https://openalex.org/W3171357516","https://openalex.org/W3115365386","https://openalex.org/W124776053","https://openalex.org/W3015399080"],"abstract_inverted_index":{"Spoken":[0],"term":[1,12],"detection":[2],"(STD)":[3],"is":[4],"the":[5,54,59,101,107,133,142,157],"task":[6],"of":[7,17,62,97,103,106,159],"looking":[8],"up":[9],"a":[10,14,148],"spoken":[11],"in":[13,73,87,100,109,126,141,166],"large":[15],"volume":[16],"speech":[18,26,36,45,64],"segments.":[19],"In":[20,90],"order":[21],"to":[22,57,75,81,137],"provide":[23,40,138],"fast":[24],"search,":[25],"segments":[27],"are":[28,50],"first":[29],"indexed":[30],"into":[31],"an":[32],"intermediate":[33],"representation":[34],"using":[35,70,160],"recognition":[37,65,84,128],"engines":[38,66],"which":[39],"multiple":[41],"hypotheses":[42],"for":[43],"each":[44],"segment.":[46],"Approximate":[47],"matching":[48,135],"techniques":[49],"usually":[51],"applied":[52],"at":[53],"search":[55],"stage":[56,111,136],"compensate":[58],"poor":[60],"performance":[61,165],"automatic":[63],"during":[67],"indexing.":[68],"Recently,":[69],"visual":[71,98,161],"information":[72,77,99,162],"addition":[74],"audio":[76,150],"has":[78],"been":[79],"shown":[80],"improve":[82],"phone":[83,127],"performance,":[85],"particularly":[86],"noisy":[88],"environments.":[89,169],"this":[91],"paper,":[92],"we":[93,121],"will":[94,113,122,130,154],"make":[95],"use":[96],"form":[102],"lip":[104],"movements":[105],"speaker":[108],"indexing":[110],"and":[112],"investigate":[114,123,156],"its":[115],"effect":[116,158],"on":[117,163],"STD":[118,145,164],"performance.":[119],"Particularly,":[120],"if":[124],"gains":[125,140],"accuracy":[129],"carry":[131],"through":[132],"approximate":[134],"similar":[139],"final":[143],"audio-visual":[144],"system":[146],"over":[147],"traditional":[149],"only":[151],"approach.":[152],"We":[153],"also":[155],"different":[167],"noise":[168]},"counts_by_year":[],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
