{"id":"https://openalex.org/W1106956463","doi":"https://doi.org/10.21437/interspeech.2015-202","title":"Cross database training of audio-visual hidden Markov models for phone recognition","display_name":"Cross database training of audio-visual hidden Markov models for phone recognition","publication_year":2015,"publication_date":"2015-09-06","ids":{"openalex":"https://openalex.org/W1106956463","doi":"https://doi.org/10.21437/interspeech.2015-202","mag":"1106956463"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2015-202","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2015-202","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":true,"oa_status":"green","oa_url":"https://eprints.qut.edu.au/86035/33/cross%2Bdatabase%2Btraining.pdf","any_repository_has_fulltext":true},"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":"middle","author":{"id":"https://openalex.org/A5012849807","display_name":"Houman Ghaemmaghami","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":false,"raw_author_name":"Houman Ghaemmaghami","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/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"]}]},{"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 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":5,"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":0.01131129,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"553","last_page":"557"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9998999834060669,"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":0.9998999834060669,"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/T11309","display_name":"Music and Audio Processing","score":0.9904000163078308,"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/T10326","display_name":"Indoor and Outdoor Localization Technologies","score":0.9811000227928162,"subfield":{"id":"https://openalex.org/subfields/2208","display_name":"Electrical and Electronic Engineering"},"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":0.8163948059082031},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.7768690586090088},{"id":"https://openalex.org/keywords/audio-visual","display_name":"Audio visual","score":0.7335047721862793},{"id":"https://openalex.org/keywords/audio-mining","display_name":"Audio mining","score":0.6702015399932861},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6408042311668396},{"id":"https://openalex.org/keywords/phone","display_name":"Phone","score":0.5763266086578369},{"id":"https://openalex.org/keywords/modality","display_name":"Modality (human\u2013computer interaction)","score":0.46588224172592163},{"id":"https://openalex.org/keywords/audio-signal","display_name":"Audio signal","score":0.4451363682746887},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.42531290650367737},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.42229312658309937},{"id":"https://openalex.org/keywords/markov-model","display_name":"Markov model","score":0.4126986563205719},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3444473147392273},{"id":"https://openalex.org/keywords/speech-coding","display_name":"Speech coding","score":0.30350276827812195},{"id":"https://openalex.org/keywords/markov-chain","display_name":"Markov chain","score":0.298870325088501},{"id":"https://openalex.org/keywords/acoustic-model","display_name":"Acoustic model","score":0.2915322780609131},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.2851044237613678},{"id":"https://openalex.org/keywords/multimedia","display_name":"Multimedia","score":0.24035418033599854},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.22655710577964783},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.15591731667518616}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8163948059082031},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.7768690586090088},{"id":"https://openalex.org/C3017588708","wikidata":"https://www.wikidata.org/wiki/Q758901","display_name":"Audio visual","level":2,"score":0.7335047721862793},{"id":"https://openalex.org/C157968479","wikidata":"https://www.wikidata.org/wiki/Q3079876","display_name":"Audio mining","level":4,"score":0.6702015399932861},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6408042311668396},{"id":"https://openalex.org/C2778707766","wikidata":"https://www.wikidata.org/wiki/Q202064","display_name":"Phone","level":2,"score":0.5763266086578369},{"id":"https://openalex.org/C2780226545","wikidata":"https://www.wikidata.org/wiki/Q6888030","display_name":"Modality (human\u2013computer interaction)","level":2,"score":0.46588224172592163},{"id":"https://openalex.org/C64922751","wikidata":"https://www.wikidata.org/wiki/Q4650799","display_name":"Audio signal","level":3,"score":0.4451363682746887},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.42531290650367737},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.42229312658309937},{"id":"https://openalex.org/C163836022","wikidata":"https://www.wikidata.org/wiki/Q6771326","display_name":"Markov model","level":3,"score":0.4126986563205719},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3444473147392273},{"id":"https://openalex.org/C13895895","wikidata":"https://www.wikidata.org/wiki/Q3270773","display_name":"Speech coding","level":2,"score":0.30350276827812195},{"id":"https://openalex.org/C98763669","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov chain","level":2,"score":0.298870325088501},{"id":"https://openalex.org/C155635449","wikidata":"https://www.wikidata.org/wiki/Q4674699","display_name":"Acoustic model","level":3,"score":0.2915322780609131},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.2851044237613678},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.24035418033599854},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.22655710577964783},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.15591731667518616},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.21437/interspeech.2015-202","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2015-202","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:86035","is_oa":true,"landing_page_url":"http://www.isca-speech.org/archive/interspeech_2015/i15_0553.html","pdf_url":"https://eprints.qut.edu.au/86035/33/cross%2Bdatabase%2Btraining.pdf","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:1106956463","is_oa":false,"landing_page_url":"https://eprints.qut.edu.au/86035/","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":{"id":"pmh:oai:eprints.qut.edu.au:86035","is_oa":true,"landing_page_url":"http://www.isca-speech.org/archive/interspeech_2015/i15_0553.html","pdf_url":"https://eprints.qut.edu.au/86035/33/cross%2Bdatabase%2Btraining.pdf","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"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W1106956463.pdf"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W2160752178","https://openalex.org/W2034480015","https://openalex.org/W2111988420","https://openalex.org/W2109087058","https://openalex.org/W1546363070","https://openalex.org/W2025546912","https://openalex.org/W2070726616","https://openalex.org/W2403836935","https://openalex.org/W1830938247","https://openalex.org/W1565144712","https://openalex.org/W59809757","https://openalex.org/W2189284781","https://openalex.org/W2384876858","https://openalex.org/W1543914610","https://openalex.org/W2171490696","https://openalex.org/W2077804127","https://openalex.org/W2957915669","https://openalex.org/W2142518644","https://openalex.org/W2156332321","https://openalex.org/W2141425367"],"abstract_inverted_index":{"Speech":[0],"recognition":[1,30,125],"can":[2],"be":[3],"improved":[4],"by":[5,126,147,171],"using":[6],"visual":[7,36,116],"information":[8],"in":[9,18,64,162],"the":[10,16,39,99,103,132,157,166,172],"form":[11],"of":[12,15,38,57,60,118],"lip":[13],"movements":[14],"speaker":[17],"addition":[19,65],"to":[20,32,54,66,77],"audio":[21,34,114,134,140,145,167],"information.":[22],"To":[23],"date,":[24],"state-of-the-art":[25],"techniques":[26],"for":[27,42,123],"audio-visual":[28,69,121],"speech":[29],"continue":[31],"use":[33,56],"and":[35,87,115,142,149],"data":[37,117],"same":[40],"database":[41,122],"training":[43],"their":[44],"models.":[45],"In":[46],"this":[47],"paper,":[48],"we":[49],"present":[50],"a":[51,67,119],"new":[52],"approach":[53,101,159],"make":[55],"one":[58],"modality":[59],"an":[61],"external":[62,133,139],"dataset":[63],"given":[68,120],"dataset.":[70],"By":[71],"so":[72],"doing,":[73],"it":[74],"is":[75,160,169],"possible":[76],"create":[78],"more":[79],"powerful":[80],"models":[81,109,135,146],"from":[82],"other":[83],"extensive":[84,138],"audio-only":[85],"databases":[86],"adapt":[88],"them":[89],"on":[90,113,137],"our":[91],"comparatively":[92],"smaller":[93],"multi-stream":[94],"databases.":[95],"Results":[96],"show":[97,155],"that":[98,156],"presented":[100],"outperforms":[102,131],"widely":[104],"adopted":[105],"synchronous":[106],"hidden":[107],"Markov":[108],"(HMM)":[110],"trained":[111,136],"jointly":[112],"phone":[124],"29%":[127],"relative.":[128],"It":[129],"also":[130,143,154],"datasets":[141],"internal":[144],"5.5%":[148],"46%":[150],"relative":[151],"respectively.":[152],"We":[153],"proposed":[158],"beneficial":[161],"noisy":[163],"environments":[164],"where":[165],"source":[168],"affected":[170],"environmental":[173],"noise.":[174]},"counts_by_year":[],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}