{"id":"https://openalex.org/W166377290","doi":"https://doi.org/10.21437/eurospeech.1997-395","title":"Noisy speech enhancement by fusion of auditory and visual information: a study of vowel transitions","display_name":"Noisy speech enhancement by fusion of auditory and visual information: a study of vowel transitions","publication_year":1997,"publication_date":"1997-09-22","ids":{"openalex":"https://openalex.org/W166377290","doi":"https://doi.org/10.21437/eurospeech.1997-395","mag":"166377290"},"language":"en","primary_location":{"id":"doi:10.21437/eurospeech.1997-395","is_oa":false,"landing_page_url":"https://doi.org/10.21437/eurospeech.1997-395","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/A5020392160","display_name":"Laurent Girin","orcid":"https://orcid.org/0000-0002-9214-8760"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Laurent Girin","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5082124101","display_name":"Gang Feng","orcid":"https://orcid.org/0000-0001-8508-8416"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Gang Feng","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5001142101","display_name":"Jean\u2010Luc Schwartz","orcid":"https://orcid.org/0000-0001-8969-9185"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jean-Luc Schwartz","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.02559415,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"2555","last_page":"2558"},"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/T11233","display_name":"Advanced Adaptive Filtering Techniques","score":0.9904999732971191,"subfield":{"id":"https://openalex.org/subfields/2206","display_name":"Computational Mechanics"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11447","display_name":"Blind Source Separation Techniques","score":0.9799000024795532,"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":0.7092394828796387},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7057123184204102},{"id":"https://openalex.org/keywords/speech-enhancement","display_name":"Speech enhancement","score":0.6427467465400696},{"id":"https://openalex.org/keywords/vowel","display_name":"Vowel","score":0.6065911054611206},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.6037536263465881},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.5860916972160339},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.5629134178161621},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.522713303565979},{"id":"https://openalex.org/keywords/white-noise","display_name":"White noise","score":0.49676424264907837},{"id":"https://openalex.org/keywords/noise-measurement","display_name":"Noise measurement","score":0.46099284291267395},{"id":"https://openalex.org/keywords/additive-white-gaussian-noise","display_name":"Additive white Gaussian noise","score":0.4563593864440918},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.449365496635437},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.06626421213150024}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7092394828796387},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7057123184204102},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.6427467465400696},{"id":"https://openalex.org/C2779581591","wikidata":"https://www.wikidata.org/wiki/Q36244","display_name":"Vowel","level":2,"score":0.6065911054611206},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.6037536263465881},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.5860916972160339},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.5629134178161621},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.522713303565979},{"id":"https://openalex.org/C112633086","wikidata":"https://www.wikidata.org/wiki/Q381287","display_name":"White noise","level":2,"score":0.49676424264907837},{"id":"https://openalex.org/C29265498","wikidata":"https://www.wikidata.org/wiki/Q7047719","display_name":"Noise measurement","level":3,"score":0.46099284291267395},{"id":"https://openalex.org/C169334058","wikidata":"https://www.wikidata.org/wiki/Q353292","display_name":"Additive white Gaussian noise","level":3,"score":0.4563593864440918},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.449365496635437},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.06626421213150024},{"id":"https://openalex.org/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","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/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21437/eurospeech.1997-395","is_oa":false,"landing_page_url":"https://doi.org/10.21437/eurospeech.1997-395","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":[{"display_name":"Reduced inequalities","id":"https://metadata.un.org/sdg/10","score":0.4000000059604645}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":5,"referenced_works":["https://openalex.org/W59650859","https://openalex.org/W1488856050","https://openalex.org/W2014621385","https://openalex.org/W2022554507","https://openalex.org/W2487271655"],"related_works":["https://openalex.org/W1974392290","https://openalex.org/W3103566292","https://openalex.org/W1607924090","https://openalex.org/W2002243964","https://openalex.org/W2022538999","https://openalex.org/W3090086172","https://openalex.org/W1955763106","https://openalex.org/W2025188156","https://openalex.org/W1582097743","https://openalex.org/W4375869276"],"abstract_inverted_index":{"This":[0],"paper":[1],"deals":[2],"with":[3,56],"a":[4,77],"noisy":[5],"speech":[6],"enhancement":[7],"technique":[8],"based":[9],"on":[10,31],"the":[11,21,25,32,50,63],"fusion":[12],"of":[13,24,40,52,62],"auditory":[14],"and":[15,27,76],"visual":[16],"information.":[17,41],"We":[18],"first":[19],"present":[20],"global":[22],"structure":[23],"system,":[26],"then":[28],"we":[29,34],"focus":[30],"tool":[33],"used":[35],"to":[36],"melt":[37],"both":[38],"sources":[39],"The":[42,80],"whole":[43],"noise":[44],"reduction":[45],"system":[46,64],"is":[47,68],"implemented":[48],"in":[49,65],"context":[51,67],"vowel":[53],"transitions":[54],"corrupted":[55],"white":[57],"noise.":[58],"A":[59],"complete":[60],"evaluation":[61],"this":[66],"presented,":[69],"including":[70],"distance":[71],"measures,":[72],"gaussian":[73],"classification":[74],"scores,":[75],"perceptive":[78],"test.":[79],"results":[81],"are":[82],"very":[83],"promising.":[84]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}