{"id":"https://openalex.org/W2072045132","doi":"https://doi.org/10.1109/icalip.2014.7009891","title":"An audio feature extraction scheme based on spectral decomposition","display_name":"An audio feature extraction scheme based on spectral decomposition","publication_year":2014,"publication_date":"2014-07-01","ids":{"openalex":"https://openalex.org/W2072045132","doi":"https://doi.org/10.1109/icalip.2014.7009891","mag":"2072045132"},"language":"en","primary_location":{"id":"doi:10.1109/icalip.2014.7009891","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icalip.2014.7009891","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2014 International Conference on Audio, Language and Image Processing","raw_type":"proceedings-article"},"type":"conference-paper","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/A5100639251","display_name":"Xueyuan Zhang","orcid":"https://orcid.org/0000-0001-5617-1640"},"institutions":[{"id":"https://openalex.org/I90610280","display_name":"South China University of Technology","ror":"https://ror.org/0530pts50","country_code":"CN","type":"education","lineage":["https://openalex.org/I90610280"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xueyuan Zhang","raw_affiliation_strings":["School of Electronic and Information Engineering, South China University of Technology, Guangzhou, China","School of Electronic and Information#R#        Engineering, South China University of Technology, Guangzhou, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Electronic and Information Engineering, South China University of Technology, Guangzhou, China","institution_ids":["https://openalex.org/I90610280"]},{"raw_affiliation_string":"School of Electronic and Information#R#        Engineering, South China University of Technology, Guangzhou, China","institution_ids":["https://openalex.org/I90610280"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5013049258","display_name":"Zhuosheng Su","orcid":null},"institutions":[{"id":"https://openalex.org/I90610280","display_name":"South China University of Technology","ror":"https://ror.org/0530pts50","country_code":"CN","type":"education","lineage":["https://openalex.org/I90610280"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhuosheng Su","raw_affiliation_strings":["School of Electronic and Information Engineering, South China University of Technology, Guangzhou, China","School of Electronic and Information#R#        Engineering, South China University of Technology, Guangzhou, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Electronic and Information Engineering, South China University of Technology, Guangzhou, China","institution_ids":["https://openalex.org/I90610280"]},{"raw_affiliation_string":"School of Electronic and Information#R#        Engineering, South China University of Technology, Guangzhou, China","institution_ids":["https://openalex.org/I90610280"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5049207865","display_name":"Pei Lin","orcid":"https://orcid.org/0000-0002-3300-5241"},"institutions":[{"id":"https://openalex.org/I90610280","display_name":"South China University of Technology","ror":"https://ror.org/0530pts50","country_code":"CN","type":"education","lineage":["https://openalex.org/I90610280"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Pei Lin","raw_affiliation_strings":["School of Electronic and Information Engineering, South China University of Technology, Guangzhou, China","School of Electronic and Information#R#        Engineering, South China University of Technology, Guangzhou, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Electronic and Information Engineering, South China University of Technology, Guangzhou, China","institution_ids":["https://openalex.org/I90610280"]},{"raw_affiliation_string":"School of Electronic and Information#R#        Engineering, South China University of Technology, Guangzhou, China","institution_ids":["https://openalex.org/I90610280"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102706072","display_name":"Qianhua He","orcid":"https://orcid.org/0000-0002-9079-4566"},"institutions":[{"id":"https://openalex.org/I90610280","display_name":"South China University of Technology","ror":"https://ror.org/0530pts50","country_code":"CN","type":"education","lineage":["https://openalex.org/I90610280"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qianhua He","raw_affiliation_strings":["School of Electronic and Information Engineering, South China University of Technology, Guangzhou, China","School of Electronic and Information#R#        Engineering, South China University of Technology, Guangzhou, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Electronic and Information Engineering, South China University of Technology, Guangzhou, China","institution_ids":["https://openalex.org/I90610280"]},{"raw_affiliation_string":"School of Electronic and Information#R#        Engineering, South China University of Technology, Guangzhou, China","institution_ids":["https://openalex.org/I90610280"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5001480103","display_name":"Jichen Yang","orcid":"https://orcid.org/0000-0002-4954-8398"},"institutions":[{"id":"https://openalex.org/I90610280","display_name":"South China University of Technology","ror":"https://ror.org/0530pts50","country_code":"CN","type":"education","lineage":["https://openalex.org/I90610280"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jichen Yang","raw_affiliation_strings":["School of Electronic and Information Engineering, South China University of Technology, Guangzhou, China","School of Electronic and Information#R#        Engineering, South China University of Technology, Guangzhou, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Electronic and Information Engineering, South China University of Technology, Guangzhou, China","institution_ids":["https://openalex.org/I90610280"]},{"raw_affiliation_string":"School of Electronic and Information#R#        Engineering, South China University of Technology, Guangzhou, China","institution_ids":["https://openalex.org/I90610280"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I90610280"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":10,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"730","last_page":"733"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9998999834060669,"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/T11309","display_name":"Music and Audio Processing","score":0.9998999834060669,"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/T10860","display_name":"Speech and Audio Processing","score":0.9991999864578247,"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/T10283","display_name":"Hearing Loss and Rehabilitation","score":0.9898999929428101,"subfield":{"id":"https://openalex.org/subfields/2805","display_name":"Cognitive Neuroscience"},"field":{"id":"https://openalex.org/fields/28","display_name":"Neuroscience"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.6921361684799194},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6248840689659119},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.6129266023635864},{"id":"https://openalex.org/keywords/timbre","display_name":"Timbre","score":0.5963780283927917},{"id":"https://openalex.org/keywords/psychoacoustics","display_name":"Psychoacoustics","score":0.5855425596237183},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5317638516426086},{"id":"https://openalex.org/keywords/mel-frequency-cepstrum","display_name":"Mel-frequency cepstrum","score":0.5182380676269531},{"id":"https://openalex.org/keywords/dimension","display_name":"Dimension (graph theory)","score":0.5066109895706177},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4896264672279358},{"id":"https://openalex.org/keywords/basis","display_name":"Basis (linear algebra)","score":0.4828360676765442},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.4663523733615875},{"id":"https://openalex.org/keywords/residual","display_name":"Residual","score":0.46541714668273926},{"id":"https://openalex.org/keywords/matching","display_name":"Matching (statistics)","score":0.4520440697669983},{"id":"https://openalex.org/keywords/spectral-envelope","display_name":"Spectral envelope","score":0.4436420798301697},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.2982480227947235},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.20198258757591248}],"concepts":[{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.6921361684799194},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6248840689659119},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.6129266023635864},{"id":"https://openalex.org/C2776539107","wikidata":"https://www.wikidata.org/wiki/Q176501","display_name":"Timbre","level":3,"score":0.5963780283927917},{"id":"https://openalex.org/C9940772","wikidata":"https://www.wikidata.org/wiki/Q557399","display_name":"Psychoacoustics","level":3,"score":0.5855425596237183},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5317638516426086},{"id":"https://openalex.org/C151989614","wikidata":"https://www.wikidata.org/wiki/Q440370","display_name":"Mel-frequency cepstrum","level":3,"score":0.5182380676269531},{"id":"https://openalex.org/C33676613","wikidata":"https://www.wikidata.org/wiki/Q13415176","display_name":"Dimension (graph theory)","level":2,"score":0.5066109895706177},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4896264672279358},{"id":"https://openalex.org/C12426560","wikidata":"https://www.wikidata.org/wiki/Q189569","display_name":"Basis (linear algebra)","level":2,"score":0.4828360676765442},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.4663523733615875},{"id":"https://openalex.org/C155512373","wikidata":"https://www.wikidata.org/wiki/Q287450","display_name":"Residual","level":2,"score":0.46541714668273926},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.4520440697669983},{"id":"https://openalex.org/C54926389","wikidata":"https://www.wikidata.org/wiki/Q7575188","display_name":"Spectral envelope","level":2,"score":0.4436420798301697},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.2982480227947235},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.20198258757591248},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C558565934","wikidata":"https://www.wikidata.org/wiki/Q2743","display_name":"Musical","level":2,"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/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"score":0.0},{"id":"https://openalex.org/C202444582","wikidata":"https://www.wikidata.org/wiki/Q837863","display_name":"Pure mathematics","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},{"id":"https://openalex.org/C169760540","wikidata":"https://www.wikidata.org/wiki/Q207011","display_name":"Neuroscience","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},{"id":"https://openalex.org/C153349607","wikidata":"https://www.wikidata.org/wiki/Q36649","display_name":"Visual arts","level":1,"score":0.0},{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.0},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icalip.2014.7009891","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icalip.2014.7009891","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2014 International Conference on Audio, Language and Image Processing","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":11,"referenced_works":["https://openalex.org/W1579239598","https://openalex.org/W1981371750","https://openalex.org/W2013301451","https://openalex.org/W2015433306","https://openalex.org/W2081353817","https://openalex.org/W2096482524","https://openalex.org/W2119662931","https://openalex.org/W2130640900","https://openalex.org/W2139689188","https://openalex.org/W2144345993","https://openalex.org/W2165525622"],"related_works":["https://openalex.org/W2181704672","https://openalex.org/W4256456190","https://openalex.org/W2191904591","https://openalex.org/W1499296618","https://openalex.org/W2062136349","https://openalex.org/W4232277401","https://openalex.org/W2087458648","https://openalex.org/W2607529793","https://openalex.org/W1986860206","https://openalex.org/W2031332132"],"abstract_inverted_index":{"This":[0],"paper":[1],"presents":[2],"an":[3],"audio":[4,46,67],"feature":[5,47,61,77],"extraction":[6],"scheme":[7],"based":[8],"on":[9,64],"spectral":[10,30,80],"decomposition":[11,14],"where":[12],"the":[13,51,75],"is":[15,48,62],"performed":[16],"iteratively":[17],"by":[18,24,50],"matching-pursuit":[19],"in":[20],"frequency":[21],"domain.":[22],"Motivated":[23],"psychoacoustic":[25],"studies,":[26],"a":[27,65],"set":[28],"of":[29,53],"basis":[31,54],"vectors":[32,55],"are":[33],"constructed":[34],"to":[35],"extract":[36],"pitch,":[37],"timbre":[38],"and":[39,81],"residual":[40],"inharmonic":[41],"components":[42],"from":[43],"spectrum.":[44],"The":[45,59,71],"represented":[49],"scales":[52],"after":[56],"dimension":[57],"reduction.":[58],"proposed":[60,76],"evaluated":[63],"13-category":[66],"effect":[68],"classification":[69],"task.":[70],"experimental":[72],"results":[73],"show":[74],"outperforms":[78],"other":[79],"cepstral":[82],"features.":[83]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":3},{"year":2021,"cited_by_count":1},{"year":2019,"cited_by_count":1},{"year":2017,"cited_by_count":1},{"year":2016,"cited_by_count":3}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}
