{"id":"https://openalex.org/W2106381530","doi":"https://doi.org/10.1109/icdsp.2002.1028281","title":"Visual speech recognition using support vector machines","display_name":"Visual speech recognition using support vector machines","publication_year":2003,"publication_date":"2003-06-25","ids":{"openalex":"https://openalex.org/W2106381530","doi":"https://doi.org/10.1109/icdsp.2002.1028281","mag":"2106381530"},"language":"en","primary_location":{"id":"doi:10.1109/icdsp.2002.1028281","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icdsp.2002.1028281","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2002 14th International Conference on Digital Signal Processing Proceedings. DSP 2002 (Cat. No.02TH8628)","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/A5076563006","display_name":"Mihaela Gordan","orcid":"https://orcid.org/0000-0002-5219-376X"},"institutions":[{"id":"https://openalex.org/I158333966","display_name":"Technical University of Cluj-Napoca","ror":"https://ror.org/03r8nwp71","country_code":"RO","type":"education","lineage":["https://openalex.org/I158333966"]}],"countries":["RO"],"is_corresponding":true,"raw_author_name":"M. Gordan","raw_affiliation_strings":["Technical University of Cluj Napoca, Cluj-Napoca, Romania"],"affiliations":[{"raw_affiliation_string":"Technical University of Cluj Napoca, Cluj-Napoca, Romania","institution_ids":["https://openalex.org/I158333966"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5065184406","display_name":"Constantine Kotropoulos","orcid":"https://orcid.org/0000-0001-9939-7930"},"institutions":[{"id":"https://openalex.org/I21370196","display_name":"Aristotle University of Thessaloniki","ror":"https://ror.org/02j61yw88","country_code":"GR","type":"education","lineage":["https://openalex.org/I21370196"]}],"countries":["GR"],"is_corresponding":false,"raw_author_name":"C. Kotropoulos","raw_affiliation_strings":["Department of Informatics, Aristotle University of Thessaloniki, Thessaloniki, Greece"],"affiliations":[{"raw_affiliation_string":"Department of Informatics, Aristotle University of Thessaloniki, Thessaloniki, Greece","institution_ids":["https://openalex.org/I21370196"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5061130224","display_name":"Ioannis Pitas","orcid":"https://orcid.org/0009-0006-7555-8641"},"institutions":[{"id":"https://openalex.org/I21370196","display_name":"Aristotle University of Thessaloniki","ror":"https://ror.org/02j61yw88","country_code":"GR","type":"education","lineage":["https://openalex.org/I21370196"]}],"countries":["GR"],"is_corresponding":false,"raw_author_name":"I. Pitas","raw_affiliation_strings":["Department of Informatics, Aristotle University of Thessaloniki, Thessaloniki, Greece"],"affiliations":[{"raw_affiliation_string":"Department of Informatics, Aristotle University of Thessaloniki, Thessaloniki, Greece","institution_ids":["https://openalex.org/I21370196"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5076563006"],"corresponding_institution_ids":["https://openalex.org/I158333966"],"apc_list":null,"apc_paid":null,"fwci":0.8889,"has_fulltext":false,"cited_by_count":11,"citation_normalized_percentile":{"value":0.75400415,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":"2","issue":null,"first_page":"1093","last_page":"1096"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9983000159263611,"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":0.9983000159263611,"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/T10824","display_name":"Image Retrieval and Classification Techniques","score":0.9943000078201294,"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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9940999746322632,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/viseme","display_name":"Viseme","score":0.7976968884468079},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7914232015609741},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7883813381195068},{"id":"https://openalex.org/keywords/viterbi-algorithm","display_name":"Viterbi algorithm","score":0.6611537337303162},{"id":"https://openalex.org/keywords/support-vector-machine","display_name":"Support vector machine","score":0.5764509439468384},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.5424739122390747},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5263888835906982},{"id":"https://openalex.org/keywords/viterbi-decoder","display_name":"Viterbi decoder","score":0.47095614671707153},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.466599702835083},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.440100759267807},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.41576242446899414},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.41541916131973267},{"id":"https://openalex.org/keywords/decoding-methods","display_name":"Decoding methods","score":0.38226598501205444},{"id":"https://openalex.org/keywords/acoustic-model","display_name":"Acoustic model","score":0.16643235087394714},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.09897854924201965},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.0732465386390686},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.07002377510070801}],"concepts":[{"id":"https://openalex.org/C33767174","wikidata":"https://www.wikidata.org/wiki/Q371190","display_name":"Viseme","level":4,"score":0.7976968884468079},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7914232015609741},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7883813381195068},{"id":"https://openalex.org/C60582962","wikidata":"https://www.wikidata.org/wiki/Q83886","display_name":"Viterbi algorithm","level":3,"score":0.6611537337303162},{"id":"https://openalex.org/C12267149","wikidata":"https://www.wikidata.org/wiki/Q282453","display_name":"Support vector machine","level":2,"score":0.5764509439468384},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.5424739122390747},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5263888835906982},{"id":"https://openalex.org/C117379686","wikidata":"https://www.wikidata.org/wiki/Q6996459","display_name":"Viterbi decoder","level":3,"score":0.47095614671707153},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.466599702835083},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.440100759267807},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.41576242446899414},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.41541916131973267},{"id":"https://openalex.org/C57273362","wikidata":"https://www.wikidata.org/wiki/Q576722","display_name":"Decoding methods","level":2,"score":0.38226598501205444},{"id":"https://openalex.org/C155635449","wikidata":"https://www.wikidata.org/wiki/Q4674699","display_name":"Acoustic model","level":3,"score":0.16643235087394714},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.09897854924201965},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.0732465386390686},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.07002377510070801},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/icdsp.2002.1028281","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icdsp.2002.1028281","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2002 14th International Conference on Digital Signal Processing Proceedings. DSP 2002 (Cat. No.02TH8628)","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.5.941","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.5.941","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://poseidon.csd.auth.gr/papers/PUBLISHED/CONFERENCE/pdf/gordan2002c.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16","score":0.6200000047683716}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":15,"referenced_works":["https://openalex.org/W1576520375","https://openalex.org/W1601740268","https://openalex.org/W1618905105","https://openalex.org/W2033895145","https://openalex.org/W2099947851","https://openalex.org/W2142518644","https://openalex.org/W2148603752","https://openalex.org/W2159483987","https://openalex.org/W2404782708","https://openalex.org/W2511186018","https://openalex.org/W6634442568","https://openalex.org/W6636501900","https://openalex.org/W6681081894","https://openalex.org/W6712969915","https://openalex.org/W6725534959"],"related_works":["https://openalex.org/W2136652457","https://openalex.org/W2169849734","https://openalex.org/W2102309991","https://openalex.org/W2116722627","https://openalex.org/W2129150969","https://openalex.org/W2236912844","https://openalex.org/W1975869217","https://openalex.org/W1795315578","https://openalex.org/W2373954783","https://openalex.org/W2535886977"],"abstract_inverted_index":{"In":[0],"this":[1],"paper":[2],"we":[3],"propose":[4],"a":[5,23,33,54,61,68],"visual":[6,63,106],"speech":[7,42,64,107],"recognition":[8,65,70],"network":[9],"based":[10],"on":[11,60,72],"support":[12,34,48,102],"vector":[13,35,49,103],"machines.":[14],"Each":[15,28],"word":[16,69],"of":[17,26,41,75,101],"the":[18,38,47,73,76,84,89,99],"dictionary":[19],"is":[20,30,43],"described":[21,31],"as":[22,51],"temporal":[24,39],"sequence":[25],"visemes.":[27],"viseme":[29],"by":[32,45],"machine,":[36],"and":[37,92],"character":[40],"modeled":[44],"integrating":[46],"machines":[50,104],"nodes":[52],"into":[53],"Viterbi":[55,90],"decoding":[56],"lattice.":[57],"Experiments":[58],"conducted":[59],"small":[62],"task":[66],"show":[67],"rate":[71],"level":[74],"best":[77],"rates":[78],"previously":[79],"reported,":[80],"even":[81],"without":[82],"training":[83],"state":[85],"transition":[86],"probabilities":[87],"in":[88],"lattice":[91],"using":[93],"very":[94],"simple":[95],"features.":[96],"This":[97],"proves":[98],"suitability":[100],"for":[105],"recognition.":[108]},"counts_by_year":[{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":1},{"year":2019,"cited_by_count":1},{"year":2017,"cited_by_count":1},{"year":2015,"cited_by_count":1},{"year":2013,"cited_by_count":1}],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}
