{"id":"https://openalex.org/W2034480015","doi":"https://doi.org/10.21437/interspeech.2007-285","title":"Fused HMM-adaptation of multi-stream HMMs for audio-visual speech recognition","display_name":"Fused HMM-adaptation of multi-stream HMMs for audio-visual speech recognition","alternate_titles":[],"publication_year":2007,"publication_date":"2007-08-27","ids":{"openalex":"https://openalex.org/W2034480015","doi":"https://doi.org/10.21437/interspeech.2007-285","mag":"2034480015"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2007-285","doi":"https://doi.org/10.21437/interspeech.2007-285","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2007-285","pdf_url":null,"source":{"id":"https://openalex.org/S4393918409","display_name":"Interspeech (USB)","issn_l":"2308-457X","issn":["2308-457X"],"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":["jufo-1","norway-1"],"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":"Interspeech 2007","raw_type":"proceedings-article"},"parent_works":[],"lineage":["https://openalex.org/W2034480015"],"child_works_count":0,"type":"conference-paper","is_traditional":true,"indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://eprints.qut.edu.au/13351/4/13351a.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5000014182","display_name":"David Dean","orcid":"https://orcid.org/0000-0003-1274-9775","observed_orcids":["https://orcid.org/0000-0003-1274-9775"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"David Dean","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5032604032","display_name":"Patrick Lucey","orcid":"https://orcid.org/0009-0009-7864-3659","observed_orcids":["https://orcid.org/0009-0009-7864-3659"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Patrick Lucey","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5055128383","display_name":"Sridha Sridharan","orcid":"https://orcid.org/0000-0003-4316-9001","observed_orcids":["https://orcid.org/0000-0003-4316-9001"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Sridha Sridharan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5111787845","display_name":"Tim Wark","orcid":"https://orcid.org/0009-0000-6670-3313","observed_orcids":["https://orcid.org/0009-0000-6670-3313"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Tim Wark","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":0.6866,"has_fulltext":true,"cited_by_count":15,"citation_normalized_percentile":{"value":0.61367258,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":88,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"666","last_page":"669"},"is_retracted":false,"is_pulled":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.6366999745368958,"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":0.6366999745368958,"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/T10860","display_name":"Speech and Audio Processing","score":0.35839998722076416,"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/T12031","display_name":"Speech and dialogue systems","score":0.0007999999797903001,"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/audio-visual-speech-recognition","display_name":"audio-visual speech recognition","score":0.9319999814033508},{"id":"https://openalex.org/keywords/noise-robustness","display_name":"noise robustness","score":0.7490000128746033},{"id":"https://openalex.org/keywords/xm2vts","display_name":"XM2VTS","score":0.8830000162124634}],"concepts":[{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.8541387915611267},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8478801250457764},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.833603024482727},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4631793797016144},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.4513515532016754},{"id":"https://openalex.org/C139807058","wikidata":"https://www.wikidata.org/wiki/Q352374","display_name":"Adaptation (eye)","level":2,"score":0.44885939359664917},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.4487435519695282},{"id":"https://openalex.org/C157968479","wikidata":"https://www.wikidata.org/wiki/Q3079876","display_name":"Audio mining","level":4,"score":0.41883131861686707},{"id":"https://openalex.org/C155635449","wikidata":"https://www.wikidata.org/wiki/Q4674699","display_name":"Acoustic model","level":3,"score":0.39274364709854126},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3786769509315491},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.35143041610717773},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.12725913524627686},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","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/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.21437/interspeech.2007-285","doi":"https://doi.org/10.21437/interspeech.2007-285","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2007-285","pdf_url":null,"source":{"id":"https://openalex.org/S4393918409","display_name":"Interspeech (USB)","issn_l":"2308-457X","issn":["2308-457X"],"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":["jufo-1","norway-1"],"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":"Interspeech 2007","raw_type":"proceedings-article"},{"id":"pmh:oai:eprints.qut.edu.au:13351","doi":null,"is_oa":true,"landing_page_url":"https://eprints.qut.edu.au/13351/3/13351.pdf","pdf_url":"https://eprints.qut.edu.au/13351/4/13351a.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,"listed_in":[],"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 8th Annual Conference of the International Speech Communication Association (Interspeech 2007)","raw_type":"Chapter in Book, Report or Conference volume"},{"id":"mag:2613899612","doi":null,"is_oa":false,"landing_page_url":"https://eprints.qut.edu.au/13351/","pdf_url":null,"source":null,"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":null}],"best_oa_location":{"id":"pmh:oai:eprints.qut.edu.au:13351","doi":null,"is_oa":true,"landing_page_url":"https://eprints.qut.edu.au/13351/3/13351.pdf","pdf_url":"https://eprints.qut.edu.au/13351/4/13351a.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,"listed_in":[],"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 8th Annual Conference of the International Speech Communication Association (Interspeech 2007)","raw_type":"Chapter in Book, Report or Conference volume"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2034480015.pdf","grobid_xml":"https://content.openalex.org/works/W2034480015.grobid-xml"},"referenced_works_count":8,"referenced_works":["https://openalex.org/W1482977908","https://openalex.org/W1527240141","https://openalex.org/W1546363070","https://openalex.org/W2061272711","https://openalex.org/W2073636254","https://openalex.org/W2096391593","https://openalex.org/W2103743127","https://openalex.org/W2153219412"],"related_works":["https://openalex.org/W7096027546","https://openalex.org/W2399057898","https://openalex.org/W86612347","https://openalex.org/W2107631382","https://openalex.org/W2164450870","https://openalex.org/W1546363070","https://openalex.org/W1978380426","https://openalex.org/W2135762233","https://openalex.org/W1503808328"],"abstract_inverted_index":{"A":[0],"technique":[1,17],"known":[2],"as":[3,12,37,46],"fused":[4],"hidden":[5],"Markov":[6],"models":[7,79],"(FHMMs)":[8],"was":[9],"recently":[10],"proposed":[11,47,68],"an":[13,122],"alternative":[14],"multi-stream":[15,78],"modelling":[16],"for":[18,28,51],"audio-visual":[19,29],"speaker":[20],"recognition.":[21],"In":[22,65],"this":[23],"paper":[24],"we":[25,109],"show":[26,110],"that":[27,111],"speech":[30,92],"recognition":[31],"(AVSR),":[32],"FHMMs":[33],"can":[34,72],"be":[35,73],"adopted":[36],"a":[38],"novel":[39],"method":[40,71],"of":[41,116,133],"training":[42],"synchronous":[43],"MSHMMs.":[44,101],"MSHMMs,":[45],"by":[48],"several":[49],"authors":[50],"use":[52],"in":[53,85,93,121,124,140],"AVSR,":[54],"are":[55],"jointly":[56],"trained":[57],"on":[58,105],"both":[59],"the":[60,77,86,90,94,106,112,117],"audio":[61,82,134],"and":[62,84,136],"visual":[63],"modalities.":[64],"contrast":[66],"our":[67],"FHMM":[69],"adaptation":[70],"used":[74],"to":[75,99],"adapt":[76],"from":[80],"single-stream":[81],"HMMs,":[83],"process,":[87],"better":[88],"model":[89,96],"video":[91,114],"final":[95],"when":[97],"compared":[98],"jointly-trained":[100,128],"By":[102],"experiments":[103],"conducted":[104],"XM2VTS":[107],"database":[108],"improved":[113],"performance":[115,126],"FHMM-adapted":[118],"MSHMMs":[119,129],"results":[120],"improvement":[123],"AVSR":[125],"over":[127],"at":[130],"all":[131],"levels":[132],"noise,":[135],"provide":[137],"significant":[138],"advantage":[139],"high":[141],"noise":[142],"environments.":[143]},"cited_by_api_url":"https://api.openalex.org/works?filter=cites:W2034480015","counts_by_year":[{"year":2017,"cited_by_count":3},{"year":2015,"cited_by_count":4},{"year":2014,"cited_by_count":2},{"year":2013,"cited_by_count":1}],"updated_date":"2026-11-14T11:04:58.165337","created_date":"2016-06-24T00:00:00"}
