{"id":"https://openalex.org/W2153584491","doi":"https://doi.org/10.1109/icassp.2008.4518627","title":"Perceptual wavelet filtering for robust speech recognition","display_name":"Perceptual wavelet filtering for robust speech recognition","publication_year":2008,"publication_date":"2008-03-01","ids":{"openalex":"https://openalex.org/W2153584491","doi":"https://doi.org/10.1109/icassp.2008.4518627","mag":"2153584491"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2008.4518627","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2008.4518627","pdf_url":null,"source":{"id":"https://openalex.org/S4210167542","display_name":"Proceedings of the ... IEEE International Conference on Acoustics, Speech, and Signal Processing","issn_l":"1520-6149","issn":["1520-6149","2379-190X"],"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2008 IEEE International Conference on Acoustics, Speech and Signal Processing","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/A5012795098","display_name":"Tuan Van Pham","orcid":"https://orcid.org/0000-0002-9225-0191"},"institutions":[{"id":"https://openalex.org/I4092182","display_name":"Graz University of Technology","ror":"https://ror.org/00d7xrm67","country_code":"AT","type":"education","lineage":["https://openalex.org/I4092182"]}],"countries":["AT"],"is_corresponding":true,"raw_author_name":"Tuan Van Pham","raw_affiliation_strings":["Signal Processing and Speech Communication Laboratory, Graz University of Technology, Graz, Austria"],"affiliations":[{"raw_affiliation_string":"Signal Processing and Speech Communication Laboratory, Graz University of Technology, Graz, Austria","institution_ids":["https://openalex.org/I4092182"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5006270785","display_name":"Michael Stark","orcid":"https://orcid.org/0000-0002-1481-9506"},"institutions":[{"id":"https://openalex.org/I4092182","display_name":"Graz University of Technology","ror":"https://ror.org/00d7xrm67","country_code":"AT","type":"education","lineage":["https://openalex.org/I4092182"]}],"countries":["AT"],"is_corresponding":false,"raw_author_name":"Michael Stark","raw_affiliation_strings":["Signal Processing and Speech Communication Laboratory, Graz University of Technology, Graz, Austria"],"affiliations":[{"raw_affiliation_string":"Signal Processing and Speech Communication Laboratory, Graz University of Technology, Graz, Austria","institution_ids":["https://openalex.org/I4092182"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5071861893","display_name":"Gernot Kubin","orcid":"https://orcid.org/0000-0002-8420-6051"},"institutions":[{"id":"https://openalex.org/I4092182","display_name":"Graz University of Technology","ror":"https://ror.org/00d7xrm67","country_code":"AT","type":"education","lineage":["https://openalex.org/I4092182"]}],"countries":["AT"],"is_corresponding":false,"raw_author_name":"Gernot Kubin","raw_affiliation_strings":["Signal Processing and Speech Communication Laboratory, Graz University of Technology, Graz, Austria"],"affiliations":[{"raw_affiliation_string":"Signal Processing and Speech Communication Laboratory, Graz University of Technology, Graz, Austria","institution_ids":["https://openalex.org/I4092182"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5012795098"],"corresponding_institution_ids":["https://openalex.org/I4092182"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.17183771,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"1","issue":null,"first_page":"4385","last_page":"4388"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":1.0,"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":1.0,"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/T11309","display_name":"Music and Audio Processing","score":0.9993000030517578,"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/T10688","display_name":"Image and Signal Denoising Methods","score":0.9987000226974487,"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/speech-recognition","display_name":"Speech recognition","score":0.7680675983428955},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7670918107032776},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.6276334524154663},{"id":"https://openalex.org/keywords/wavelet","display_name":"Wavelet","score":0.6090128421783447},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5819336175918579},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.5422784090042114},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.5384755730628967},{"id":"https://openalex.org/keywords/wavelet-transform","display_name":"Wavelet transform","score":0.5300595164299011},{"id":"https://openalex.org/keywords/psychoacoustics","display_name":"Psychoacoustics","score":0.4939001202583313},{"id":"https://openalex.org/keywords/noise-measurement","display_name":"Noise measurement","score":0.45397332310676575},{"id":"https://openalex.org/keywords/speech-enhancement","display_name":"Speech enhancement","score":0.4101578891277313},{"id":"https://openalex.org/keywords/perception","display_name":"Perception","score":0.34467583894729614},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.13716769218444824}],"concepts":[{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7680675983428955},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7670918107032776},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.6276334524154663},{"id":"https://openalex.org/C47432892","wikidata":"https://www.wikidata.org/wiki/Q831390","display_name":"Wavelet","level":2,"score":0.6090128421783447},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5819336175918579},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.5422784090042114},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.5384755730628967},{"id":"https://openalex.org/C196216189","wikidata":"https://www.wikidata.org/wiki/Q2867","display_name":"Wavelet transform","level":3,"score":0.5300595164299011},{"id":"https://openalex.org/C9940772","wikidata":"https://www.wikidata.org/wiki/Q557399","display_name":"Psychoacoustics","level":3,"score":0.4939001202583313},{"id":"https://openalex.org/C29265498","wikidata":"https://www.wikidata.org/wiki/Q7047719","display_name":"Noise measurement","level":3,"score":0.45397332310676575},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.4101578891277313},{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.34467583894729614},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.13716769218444824},{"id":"https://openalex.org/C169760540","wikidata":"https://www.wikidata.org/wiki/Q207011","display_name":"Neuroscience","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp.2008.4518627","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2008.4518627","pdf_url":null,"source":{"id":"https://openalex.org/S4210167542","display_name":"Proceedings of the ... IEEE International Conference on Acoustics, Speech, and Signal Processing","issn_l":"1520-6149","issn":["1520-6149","2379-190X"],"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2008 IEEE International Conference on Acoustics, Speech and Signal Processing","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.6800000071525574,"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":7,"referenced_works":["https://openalex.org/W1992468098","https://openalex.org/W2079724595","https://openalex.org/W2106300174","https://openalex.org/W2147420216","https://openalex.org/W2154078233","https://openalex.org/W2158336491","https://openalex.org/W4255521522"],"related_works":["https://openalex.org/W3108403339","https://openalex.org/W2002243964","https://openalex.org/W2022538999","https://openalex.org/W3090086172","https://openalex.org/W2162712524","https://openalex.org/W1955763106","https://openalex.org/W2025188156","https://openalex.org/W4287867034","https://openalex.org/W2175872006","https://openalex.org/W4375869276"],"abstract_inverted_index":{"In":[0],"this":[1],"paper":[2],"an":[3,87],"enhanced":[4],"noise":[5,50,63],"reduction":[6,64],"for":[7,36],"robust":[8],"speech":[9,70],"recognition":[10,76],"is":[11,24,52,59],"implemented":[12],"by":[13],"means":[14],"of":[15,49],"a":[16],"perceptual":[17],"wavelet":[18,39],"filtering":[19,45],"algorithm.":[20],"The":[21,56],"psychoacoustic":[22],"model":[23],"applied":[25],"to":[26,31],"map":[27],"the":[28,32,47,79,90],"universal":[29,34],"thresholds":[30,35],"perceptually":[33],"each":[37],"critical":[38],"subband.":[40],"By":[41],"improving":[42],"our":[43],"quantile":[44],"method,":[46],"change":[48],"level":[51],"tracked":[53],"more":[54],"adaptively.":[55],"denoising":[57],"algorithm":[58],"compared":[60],"with":[61,78,89],"well-known":[62],"methods":[65],"embedded":[66],"in":[67],"different":[68],"state-of-the-art":[69],"recognizers.":[71],"We":[72],"achieve":[73],"almost":[74],"similar":[75],"performance":[77],"HTK":[80],"recognizer":[81,92],"on":[82,93],"AURORA3":[83],"SPEECHDAT-Car":[84],"corpus":[85],"and":[86],"improvement":[88],"Loquendo":[91],"SNOW-Factory":[94],"corpus.":[95]},"counts_by_year":[],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}