{"id":"https://openalex.org/W1591608209","doi":"https://doi.org/10.21437/eurospeech.1997-464","title":"Improved bimodal speech recognition using tied-mixture HMMs and 5000 word audio-visual synchronous database","display_name":"Improved bimodal speech recognition using tied-mixture HMMs and 5000 word audio-visual synchronous database","publication_year":1997,"publication_date":"1997-09-22","ids":{"openalex":"https://openalex.org/W1591608209","doi":"https://doi.org/10.21437/eurospeech.1997-464","mag":"1591608209"},"language":"en","primary_location":{"id":"doi:10.21437/eurospeech.1997-464","is_oa":false,"landing_page_url":"https://doi.org/10.21437/eurospeech.1997-464","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"5th European Conference on Speech Communication and Technology (Eurospeech 1997)","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/A5020994673","display_name":"Satoshi Nakamura","orcid":"https://orcid.org/0000-0001-6956-3803"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Satoshi Nakamura","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5073071602","display_name":"Ron Nagai","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ron Nagai","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5021868389","display_name":"Kiyohiro Shikano","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Kiyohiro Shikano","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5020994673"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.7551,"has_fulltext":false,"cited_by_count":13,"citation_normalized_percentile":{"value":0.85701312,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"1623","last_page":"1626"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9456999897956848,"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":0.9456999897956848,"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/speech-recognition","display_name":"Speech recognition","score":0.7764173746109009},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7692815065383911},{"id":"https://openalex.org/keywords/audio-mining","display_name":"Audio mining","score":0.6664193868637085},{"id":"https://openalex.org/keywords/audio-visual","display_name":"Audio visual","score":0.6443138122558594},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.6191497445106506},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5168735980987549},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.4692383110523224},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.4198523759841919},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.360078901052475},{"id":"https://openalex.org/keywords/acoustic-model","display_name":"Acoustic model","score":0.32581526041030884},{"id":"https://openalex.org/keywords/multimedia","display_name":"Multimedia","score":0.20992961525917053},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.10589507222175598}],"concepts":[{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7764173746109009},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7692815065383911},{"id":"https://openalex.org/C157968479","wikidata":"https://www.wikidata.org/wiki/Q3079876","display_name":"Audio mining","level":4,"score":0.6664193868637085},{"id":"https://openalex.org/C3017588708","wikidata":"https://www.wikidata.org/wiki/Q758901","display_name":"Audio visual","level":2,"score":0.6443138122558594},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.6191497445106506},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5168735980987549},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.4692383110523224},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.4198523759841919},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.360078901052475},{"id":"https://openalex.org/C155635449","wikidata":"https://www.wikidata.org/wiki/Q4674699","display_name":"Acoustic model","level":3,"score":0.32581526041030884},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.20992961525917053},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.10589507222175598},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21437/eurospeech.1997-464","is_oa":false,"landing_page_url":"https://doi.org/10.21437/eurospeech.1997-464","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"5th European Conference on Speech Communication and Technology (Eurospeech 1997)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W2121652828","https://openalex.org/W2157598242","https://openalex.org/W3159882232","https://openalex.org/W4241650944","https://openalex.org/W2620660273","https://openalex.org/W4243125559","https://openalex.org/W2964829415","https://openalex.org/W2131711534","https://openalex.org/W642007152","https://openalex.org/W2341426843"],"abstract_inverted_index":{"EUROSPEECH1997:":[0],"the":[1],"5th":[2],"European":[3],"Conference":[4],"on":[5],"Speech":[6],"Communication":[7],"and":[8],"Technology":[9],",":[10],"September":[11],"22-25,":[12],"1997,":[14],"Rhodes,":[15],"Greece.":[17]},"counts_by_year":[{"year":2014,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}