{"id":"https://openalex.org/W172154728","doi":"https://doi.org/10.21437/icslp.2002-123","title":"Audio-visual continuous speech recognition using a coupled hidden Markov model","display_name":"Audio-visual continuous speech recognition using a coupled hidden Markov model","publication_year":2002,"publication_date":"2002-09-16","ids":{"openalex":"https://openalex.org/W172154728","doi":"https://doi.org/10.21437/icslp.2002-123","mag":"172154728"},"language":"en","primary_location":{"id":"doi:10.21437/icslp.2002-123","is_oa":false,"landing_page_url":"https://doi.org/10.21437/icslp.2002-123","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"7th International Conference on Spoken Language Processing (ICSLP 2002)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5100783771","display_name":"Xiaoxing Liu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xiaoxing Liu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100845144","display_name":"Yibao Zhao","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yibao Zhao","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5027964715","display_name":"Xiaobo Pi","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xiaobo Pi","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5052554057","display_name":"Luhong Liang","orcid":"https://orcid.org/0009-0001-4190-006X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Luhong Liang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5113481101","display_name":"Ara Nefian","orcid":null},"institutions":[{"id":"https://openalex.org/I1343180700","display_name":"Intel (United States)","ror":"https://ror.org/01ek73717","country_code":"US","type":"company","lineage":["https://openalex.org/I1343180700"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ara V. Nefian","raw_affiliation_strings":["Intel#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Intel#TAB#","institution_ids":["https://openalex.org/I1343180700"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":3.0282,"has_fulltext":false,"cited_by_count":42,"citation_normalized_percentile":{"value":0.92228662,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"213","last_page":"216"},"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":0.9790999889373779,"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/T11309","display_name":"Music and Audio Processing","score":0.9789999723434448,"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/hidden-markov-model","display_name":"Hidden Markov model","score":0.8449012041091919},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.8365408778190613},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7678367495536804},{"id":"https://openalex.org/keywords/audio-visual","display_name":"Audio visual","score":0.5623888969421387},{"id":"https://openalex.org/keywords/audio-mining","display_name":"Audio mining","score":0.5085071325302124},{"id":"https://openalex.org/keywords/markov-model","display_name":"Markov model","score":0.49214404821395874},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.46845173835754395},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.46312791109085083},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.44452357292175293},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.41010138392448425},{"id":"https://openalex.org/keywords/acoustic-model","display_name":"Acoustic model","score":0.3936713635921478},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.3624284863471985},{"id":"https://openalex.org/keywords/markov-chain","display_name":"Markov chain","score":0.23486614227294922},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.21060818433761597},{"id":"https://openalex.org/keywords/multimedia","display_name":"Multimedia","score":0.1065712571144104}],"concepts":[{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.8449012041091919},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.8365408778190613},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7678367495536804},{"id":"https://openalex.org/C3017588708","wikidata":"https://www.wikidata.org/wiki/Q758901","display_name":"Audio visual","level":2,"score":0.5623888969421387},{"id":"https://openalex.org/C157968479","wikidata":"https://www.wikidata.org/wiki/Q3079876","display_name":"Audio mining","level":4,"score":0.5085071325302124},{"id":"https://openalex.org/C163836022","wikidata":"https://www.wikidata.org/wiki/Q6771326","display_name":"Markov model","level":3,"score":0.49214404821395874},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.46845173835754395},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.46312791109085083},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.44452357292175293},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.41010138392448425},{"id":"https://openalex.org/C155635449","wikidata":"https://www.wikidata.org/wiki/Q4674699","display_name":"Acoustic model","level":3,"score":0.3936713635921478},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.3624284863471985},{"id":"https://openalex.org/C98763669","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov chain","level":2,"score":0.23486614227294922},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.21060818433761597},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.1065712571144104}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.21437/icslp.2002-123","is_oa":false,"landing_page_url":"https://doi.org/10.21437/icslp.2002-123","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"7th International Conference on Spoken Language Processing (ICSLP 2002)","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.490.639","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.490.639","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.anefian.com/research/liu02_audio.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":10,"referenced_works":["https://openalex.org/W88081813","https://openalex.org/W1560013842","https://openalex.org/W1576996184","https://openalex.org/W2112348857","https://openalex.org/W2121486117","https://openalex.org/W2164450870","https://openalex.org/W2166480741","https://openalex.org/W2171265988","https://openalex.org/W2799061466","https://openalex.org/W3099202502"],"related_works":["https://openalex.org/W4255044973","https://openalex.org/W2499802997","https://openalex.org/W2112059504","https://openalex.org/W2727729836","https://openalex.org/W1960256358","https://openalex.org/W2548037963","https://openalex.org/W2157598242","https://openalex.org/W2464377622","https://openalex.org/W2394963835","https://openalex.org/W4385611764"],"abstract_inverted_index":{"With":[0],"the":[1,4,33,44,63,67,70,87,92,96,100],"increase":[2],"in":[3,29,41],"computational":[5],"complexity":[6],"of":[7,62,69,99,108],"recent":[8],"computers,":[9],"audio-visual":[10],"speech":[11,27,37,103],"recognition":[12,28,38,104],"(AVSR)":[13],"became":[14],"an":[15],"attractive":[16],"research":[17],"topic":[18],"that":[19,86],"can":[20,65],"lead":[21],"to":[22],"a":[23,53],"robust":[24],"solution":[25],"for":[26],"noisy":[30],"environments.":[31],"In":[32],"audio":[34,45,71,101],"visual":[35,47,73],"continuous":[36],"system":[39,89,105],"presented":[40],"this":[42],"paper,":[43],"and":[46,72],"observation":[48],"sequences":[49],"are":[50],"integrated":[51],"using":[52],"coupled":[54],"hidden":[55],"Markov":[56],"model":[57],"(CHMM).":[58],"The":[59,82],"statistical":[60],"properties":[61],"CHMM":[64],"describe":[66],"asyncrony":[68],"features":[74],"while":[75],"preserv-ing":[76],"their":[77],"natural":[78],"correlation":[79],"over":[80,111],"time.":[81],"experimental":[83],"re-sults":[84],"show":[85],"current":[88],"tested":[90],"on":[91],"XM2VTS":[93],"database":[94],"reduces":[95],"error":[97],"rate":[98],"only":[102],"at":[106],"SNR":[107],"0db":[109],"by":[110],"55%.":[112],"1.":[113]},"counts_by_year":[{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2020,"cited_by_count":2},{"year":2017,"cited_by_count":2},{"year":2014,"cited_by_count":2},{"year":2013,"cited_by_count":1},{"year":2012,"cited_by_count":3}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}