{"id":"https://openalex.org/W66497246","doi":"https://doi.org/10.21437/interspeech.2007-297","title":"An extension 2DPCA based visual feature extraction method for audio-visual speech recognition","display_name":"An extension 2DPCA based visual feature extraction method for audio-visual speech recognition","publication_year":2007,"publication_date":"2007-08-27","ids":{"openalex":"https://openalex.org/W66497246","doi":"https://doi.org/10.21437/interspeech.2007-297","mag":"66497246"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2007-297","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2007-297","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2007","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/A5003025692","display_name":"Guanyong Wu","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Guanyong Wu","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5101723282","display_name":"Jie Zhu","orcid":"https://orcid.org/0000-0002-3555-5247"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jie Zhu","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5003025692"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.00605875,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"714","last_page":"717"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9715999960899353,"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":0.9715999960899353,"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/computer-science","display_name":"Computer science","score":0.8007466197013855},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7105639576911926},{"id":"https://openalex.org/keywords/audio-visual","display_name":"Audio visual","score":0.7102327942848206},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.7058873772621155},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6068623065948486},{"id":"https://openalex.org/keywords/audio-mining","display_name":"Audio mining","score":0.5744229555130005},{"id":"https://openalex.org/keywords/extension","display_name":"Extension (predicate logic)","score":0.5505715012550354},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4643310606479645},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.46295008063316345},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.3439943790435791},{"id":"https://openalex.org/keywords/acoustic-model","display_name":"Acoustic model","score":0.28564685583114624},{"id":"https://openalex.org/keywords/multimedia","display_name":"Multimedia","score":0.08454304933547974}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8007466197013855},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7105639576911926},{"id":"https://openalex.org/C3017588708","wikidata":"https://www.wikidata.org/wiki/Q758901","display_name":"Audio visual","level":2,"score":0.7102327942848206},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.7058873772621155},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6068623065948486},{"id":"https://openalex.org/C157968479","wikidata":"https://www.wikidata.org/wiki/Q3079876","display_name":"Audio mining","level":4,"score":0.5744229555130005},{"id":"https://openalex.org/C2778029271","wikidata":"https://www.wikidata.org/wiki/Q5421931","display_name":"Extension (predicate logic)","level":2,"score":0.5505715012550354},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4643310606479645},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.46295008063316345},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.3439943790435791},{"id":"https://openalex.org/C155635449","wikidata":"https://www.wikidata.org/wiki/Q4674699","display_name":"Acoustic model","level":3,"score":0.28564685583114624},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.08454304933547974},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"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":1,"locations":[{"id":"doi:10.21437/interspeech.2007-297","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2007-297","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2007","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W3159882232","https://openalex.org/W4241650944","https://openalex.org/W4243125559","https://openalex.org/W1541790149","https://openalex.org/W4241778367","https://openalex.org/W2752054555","https://openalex.org/W2527828870","https://openalex.org/W2184127972","https://openalex.org/W4214489098","https://openalex.org/W2103924733"],"abstract_inverted_index":null,"counts_by_year":[{"year":2017,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}