{"id":"https://openalex.org/W1618343984","doi":"https://doi.org/10.1109/iscas.2003.1205122","title":"Feature extraction based on perceptually non-uniform spectral compression for speech recognition","display_name":"Feature extraction based on perceptually non-uniform spectral compression for speech recognition","publication_year":2003,"publication_date":"2003-11-20","ids":{"openalex":"https://openalex.org/W1618343984","doi":"https://doi.org/10.1109/iscas.2003.1205122","mag":"1618343984"},"language":"en","primary_location":{"id":"doi:10.1109/iscas.2003.1205122","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iscas.2003.1205122","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2003 International Symposium on Circuits and Systems, 2003. ISCAS '03.","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/A5113691175","display_name":"K.K. Chu","orcid":null},"institutions":[{"id":"https://openalex.org/I168719708","display_name":"City University of Hong Kong","ror":"https://ror.org/03q8dnn23","country_code":"HK","type":"education","lineage":["https://openalex.org/I168719708"]}],"countries":["HK"],"is_corresponding":true,"raw_author_name":"K.K. Chu","raw_affiliation_strings":["Department of Electronic Engineering, City University of Hong Kong, Hong Kong, China","Dept. of Electron. Eng., City Univ. of Hong Kong, China"],"affiliations":[{"raw_affiliation_string":"Department of Electronic Engineering, City University of Hong Kong, Hong Kong, China","institution_ids":["https://openalex.org/I168719708"]},{"raw_affiliation_string":"Dept. of Electron. Eng., City Univ. of Hong Kong, China","institution_ids":["https://openalex.org/I168719708"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5011680578","display_name":"S.H. Leung","orcid":"https://orcid.org/0000-0003-2059-120X"},"institutions":[{"id":"https://openalex.org/I168719708","display_name":"City University of Hong Kong","ror":"https://ror.org/03q8dnn23","country_code":"HK","type":"education","lineage":["https://openalex.org/I168719708"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"S.H. Leung","raw_affiliation_strings":["Department of Electronic Engineering, City University of Hong Kong, Hong Kong, China","Dept. of Electron. Eng., City Univ. of Hong Kong, China"],"affiliations":[{"raw_affiliation_string":"Department of Electronic Engineering, City University of Hong Kong, Hong Kong, China","institution_ids":["https://openalex.org/I168719708"]},{"raw_affiliation_string":"Dept. of Electron. Eng., City Univ. of Hong Kong, China","institution_ids":["https://openalex.org/I168719708"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5113691175"],"corresponding_institution_ids":["https://openalex.org/I168719708"],"apc_list":null,"apc_paid":null,"fwci":0.8784,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.7312788,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":94},"biblio":{"volume":"3","issue":null,"first_page":"III","last_page":"726"},"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9965000152587891,"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"}},{"id":"https://openalex.org/T10901","display_name":"Advanced Data Compression Techniques","score":0.989300012588501,"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":0.6823726296424866},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6701300740242004},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.6376466751098633},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.5287981629371643},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.473020076751709},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.4695492386817932},{"id":"https://openalex.org/keywords/broadband","display_name":"Broadband","score":0.46439462900161743},{"id":"https://openalex.org/keywords/psychoacoustics","display_name":"Psychoacoustics","score":0.4105822443962097},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.1152222752571106}],"concepts":[{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6823726296424866},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6701300740242004},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.6376466751098633},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.5287981629371643},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.473020076751709},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.4695492386817932},{"id":"https://openalex.org/C509933004","wikidata":"https://www.wikidata.org/wiki/Q194163","display_name":"Broadband","level":2,"score":0.46439462900161743},{"id":"https://openalex.org/C9940772","wikidata":"https://www.wikidata.org/wiki/Q557399","display_name":"Psychoacoustics","level":3,"score":0.4105822443962097},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.1152222752571106},{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C169760540","wikidata":"https://www.wikidata.org/wiki/Q207011","display_name":"Neuroscience","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/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/iscas.2003.1205122","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iscas.2003.1205122","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2003 International Symposium on Circuits and Systems, 2003. ISCAS '03.","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16","score":0.5299999713897705},{"display_name":"Reduced inequalities","id":"https://metadata.un.org/sdg/10","score":0.4099999964237213}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":7,"referenced_works":["https://openalex.org/W1530838232","https://openalex.org/W1970825018","https://openalex.org/W1998095566","https://openalex.org/W2014057003","https://openalex.org/W2029654180","https://openalex.org/W2090861223","https://openalex.org/W6986728531"],"related_works":["https://openalex.org/W2016620782","https://openalex.org/W2469919065","https://openalex.org/W2047214610","https://openalex.org/W2190237714","https://openalex.org/W2801419377","https://openalex.org/W1983661076","https://openalex.org/W2623290525","https://openalex.org/W1936165815","https://openalex.org/W3107787087","https://openalex.org/W2067962069"],"abstract_inverted_index":{"The":[0,108],"power":[1,65],"law":[2],"of":[3,34,36,63,67,71,110,117],"hearing":[4],"used":[5],"in":[6,80,154,161],"approximating":[7],"the":[8,51,64,105,114,134,138,149],"loudness":[9],"function":[10],"has":[11,141],"an":[12],"exponent":[13],"that":[14,133],"decreases":[15],"from":[16,137],"about":[17],"0.3":[18],"for":[19,26,46,75,121],"a":[20,27,41,72],"narrow":[21],"band":[22],"tone":[23],"to":[24,58],"0.23":[25],"broadband":[28,93],"uniform-exciting":[29],"noise.":[30],"Exploiting":[31],"this":[32,38],"property":[33],"psychoacoustics":[35],"hearing,":[37],"paper":[39],"proposes":[40],"new":[42,119,139],"feature":[43,111,127,135],"extraction":[44,128],"method":[45,120],"robust":[47],"speech":[48],"recognition.":[49],"In":[50,87],"method,":[52],"larger":[53,97],"energy":[54,103],"compression":[55,74,98],"is":[56,131,157],"applied":[57],"broadband-like":[59],"high":[60],"frequency":[61,77],"bands":[62,78],"spectrum":[66],"each":[68],"frame,":[69],"instead":[70],"fixed":[73],"all":[76],"as":[79,99,104],"root":[81],"cepstral":[82],"analysis":[83],"or":[84],"PLP":[85],"analysis.":[86],"addition,":[88],"those":[89],"sound":[90],"segments":[91],"having":[92],"characteristics":[94],"are":[95,123],"given":[96],"well,":[100],"using":[101],"frame":[102],"measuring":[106],"index.":[107],"scatter":[109],"vectors":[112],"and":[113,144],"class":[115,146],"discrimination":[116,147],"our":[118],"phonemes":[122],"compared":[124],"against":[125],"traditional":[126,150],"techniques.":[129],"It":[130],"shown":[132],"derived":[136],"scheme":[140],"smaller":[142],"variation":[143],"better":[145],"than":[148],"features.":[151],"Significant":[152],"improvement":[153],"recognition":[155],"accuracy":[156],"also":[158],"obtained,":[159],"especially":[160],"very":[162],"low":[163],"SNR,":[164],"under":[165],"white":[166],"noise":[167],"environment.":[168]},"counts_by_year":[{"year":2024,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
