{"id":"https://openalex.org/W1914280119","doi":"https://doi.org/10.1145/2802558.2814648","title":"Acoustic Adaptation in Cross Database Audio Visual SHMM Training for Phonetic Spoken Term Detection","display_name":"Acoustic Adaptation in Cross Database Audio Visual SHMM Training for Phonetic Spoken Term Detection","publication_year":2015,"publication_date":"2015-01-01","ids":{"openalex":"https://openalex.org/W1914280119","doi":"https://doi.org/10.1145/2802558.2814648","mag":"1914280119"},"language":"en","primary_location":{"id":"doi:10.1145/2802558.2814648","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2802558.2814648","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Third Edition Workshop on Speech, Language &amp; Audio in Multimedia - SLAM '15","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/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":true,"raw_author_name":"Shahram Kalantari","raw_affiliation_strings":["Queensland university of technoogy, Brisbane, Australia"],"affiliations":[{"raw_affiliation_string":"Queensland university of technoogy, Brisbane, Australia","institution_ids":["https://openalex.org/I160993911"]}]},{"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 technoogy, Brisbane, Australia"],"affiliations":[{"raw_affiliation_string":"Queensland university of technoogy, Brisbane, Australia","institution_ids":["https://openalex.org/I160993911"]}]},{"author_position":"middle","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 technoogy, Brisbane, Australia"],"affiliations":[{"raw_affiliation_string":"Queensland university of technoogy, Brisbane, Australia","institution_ids":["https://openalex.org/I160993911"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5012849807","display_name":"Houman Ghaemmaghami","orcid":null},"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":"Houman Ghaemmaghami","raw_affiliation_strings":["Queensland university of technoogy, Brisbane, Australia"],"affiliations":[{"raw_affiliation_string":"Queensland university of technoogy, Brisbane, Australia","institution_ids":["https://openalex.org/I160993911"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5034095159","display_name":"Clinton Fookes","orcid":"https://orcid.org/0000-0002-8515-6324"},"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":"Clinton Fookes","raw_affiliation_strings":["Queensland university of technoogy, Brisbane, Australia"],"affiliations":[{"raw_affiliation_string":"Queensland university of technoogy, Brisbane, Australia","institution_ids":["https://openalex.org/I160993911"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5072416824"],"corresponding_institution_ids":["https://openalex.org/I160993911"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.05631996,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"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":1.0,"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":1.0,"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/T11233","display_name":"Advanced Adaptive Filtering Techniques","score":0.9912999868392944,"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"}},{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9901999831199646,"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/computer-science","display_name":"Computer science","score":0.8325013518333435},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.7298340797424316},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6896919012069702},{"id":"https://openalex.org/keywords/audio-visual","display_name":"Audio visual","score":0.6234973073005676},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.5564810037612915},{"id":"https://openalex.org/keywords/audio-mining","display_name":"Audio mining","score":0.5531920194625854},{"id":"https://openalex.org/keywords/adaptation","display_name":"Adaptation (eye)","score":0.542113184928894},{"id":"https://openalex.org/keywords/modality","display_name":"Modality (human\u2013computer interaction)","score":0.5030953288078308},{"id":"https://openalex.org/keywords/phone","display_name":"Phone","score":0.49670130014419556},{"id":"https://openalex.org/keywords/term","display_name":"Term (time)","score":0.41244304180145264},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.39127010107040405},{"id":"https://openalex.org/keywords/acoustic-model","display_name":"Acoustic model","score":0.3820309042930603},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.29401224851608276},{"id":"https://openalex.org/keywords/multimedia","display_name":"Multimedia","score":0.28504106402397156}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8325013518333435},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.7298340797424316},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6896919012069702},{"id":"https://openalex.org/C3017588708","wikidata":"https://www.wikidata.org/wiki/Q758901","display_name":"Audio visual","level":2,"score":0.6234973073005676},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.5564810037612915},{"id":"https://openalex.org/C157968479","wikidata":"https://www.wikidata.org/wiki/Q3079876","display_name":"Audio mining","level":4,"score":0.5531920194625854},{"id":"https://openalex.org/C139807058","wikidata":"https://www.wikidata.org/wiki/Q352374","display_name":"Adaptation (eye)","level":2,"score":0.542113184928894},{"id":"https://openalex.org/C2780226545","wikidata":"https://www.wikidata.org/wiki/Q6888030","display_name":"Modality (human\u2013computer interaction)","level":2,"score":0.5030953288078308},{"id":"https://openalex.org/C2778707766","wikidata":"https://www.wikidata.org/wiki/Q202064","display_name":"Phone","level":2,"score":0.49670130014419556},{"id":"https://openalex.org/C61797465","wikidata":"https://www.wikidata.org/wiki/Q1188986","display_name":"Term (time)","level":2,"score":0.41244304180145264},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.39127010107040405},{"id":"https://openalex.org/C155635449","wikidata":"https://www.wikidata.org/wiki/Q4674699","display_name":"Acoustic model","level":3,"score":0.3820309042930603},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.29401224851608276},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.28504106402397156},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"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/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","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/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1145/2802558.2814648","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2802558.2814648","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Third Edition Workshop on Speech, Language &amp; Audio in Multimedia - SLAM '15","raw_type":"proceedings-article"},{"id":"pmh:oai:eprints.qut.edu.au:86033","is_oa":false,"landing_page_url":null,"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 Third Edition Workshop on Speech, Language and Audio in Multimedia","raw_type":"Chapter in Book, Report or Conference volume"},{"id":"mag:1914280119","is_oa":false,"landing_page_url":"https://eprints.qut.edu.au/86033/","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":[{"display_name":"Quality Education","score":0.6600000262260437,"id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":15,"referenced_works":["https://openalex.org/W51714401","https://openalex.org/W69656834","https://openalex.org/W1072292725","https://openalex.org/W1506438021","https://openalex.org/W2014621385","https://openalex.org/W2033961931","https://openalex.org/W2034480015","https://openalex.org/W2096391593","https://openalex.org/W2103743127","https://openalex.org/W2145565887","https://openalex.org/W2149998531","https://openalex.org/W2151096985","https://openalex.org/W2402407026","https://openalex.org/W2402543639","https://openalex.org/W2612891210"],"related_works":["https://openalex.org/W2000954587","https://openalex.org/W2746692812","https://openalex.org/W2402543639","https://openalex.org/W2402407026","https://openalex.org/W2293750915","https://openalex.org/W2148659689","https://openalex.org/W2981544649","https://openalex.org/W2109443308","https://openalex.org/W3081788987","https://openalex.org/W2888436980","https://openalex.org/W2163215038","https://openalex.org/W2799046698","https://openalex.org/W2792308360","https://openalex.org/W3011234510","https://openalex.org/W2137044559","https://openalex.org/W3023895054","https://openalex.org/W1915785597","https://openalex.org/W3171357516","https://openalex.org/W2185662035","https://openalex.org/W2394679591"],"abstract_inverted_index":{"Visual":[0],"information":[1],"in":[2,50,108,113],"the":[3,9,16,53,63,88,102],"form":[4],"of":[5,8,18,33,42,87,115],"lip":[6],"movements":[7],"speaker":[10],"has":[11],"been":[12],"shown":[13],"to":[14,39,52,82,96],"improve":[15],"performance":[17],"speech":[19],"recognition":[20,117],"and":[21,45,110],"search":[22],"applications.":[23],"In":[24,60],"our":[25],"previous":[26],"work,":[27,62],"we":[28],"proposed":[29,99],"cross":[30,64,104],"database":[31,65,105],"training":[32,66,106],"synchronous":[34],"hidden":[35],"Markov":[36],"models":[37,91],"(SHMMs)":[38],"make":[40],"use":[41],"external":[43,89],"large":[44],"publicly":[46],"available":[47],"audio":[48,57,74,79,85,90],"databases":[49],"addition":[51],"relatively":[54],"small":[55],"given":[56],"visual":[58,80,94],"database.":[59],"this":[61],"approach":[67,100,107],"is":[68],"improved":[69],"by":[70],"performing":[71],"an":[72],"additional":[73],"adaptation":[75],"step,":[76],"which":[77],"enables":[78],"SHMMs":[81],"benefit":[83],"from":[84],"observations":[86],"before":[92],"adding":[93],"modality":[95],"them.":[97],"The":[98],"outperforms":[101],"baseline":[103],"clean":[109],"noisy":[111],"environments":[112],"terms":[114],"phone":[116],"accuracy":[118],"as":[119,121],"well":[120],"spoken":[122],"term":[123],"detection":[124],"(STD)":[125],"accuracy.":[126]},"counts_by_year":[],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
