{"id":"https://openalex.org/W2091830613","doi":"https://doi.org/10.1109/icassp.2002.5743968","title":"Extracting noise-robust features from audio data","display_name":"Extracting noise-robust features from audio data","publication_year":2002,"publication_date":"2002-05-01","ids":{"openalex":"https://openalex.org/W2091830613","doi":"https://doi.org/10.1109/icassp.2002.5743968","mag":"2091830613"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2002.5743968","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2002.5743968","pdf_url":null,"source":{"id":"https://openalex.org/S4363607879","display_name":"IEEE International Conference on Acoustics Speech and Signal Processing","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"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/A5034285513","display_name":"Christopher J. C. Burges","orcid":null},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Christopher J. C. Burges","raw_affiliation_strings":["Microsoft Research, Redmond, WA, USA"],"affiliations":[{"raw_affiliation_string":"Microsoft Research, Redmond, WA, USA","institution_ids":["https://openalex.org/I1290206253"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5073032636","display_name":"John Platt","orcid":"https://orcid.org/0000-0002-5652-5303"},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"John C. Platt","raw_affiliation_strings":["Microsoft Research, Redmond, WA, USA"],"affiliations":[{"raw_affiliation_string":"Microsoft Research, Redmond, WA, USA","institution_ids":["https://openalex.org/I1290206253"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5103070252","display_name":"Soumya Jana","orcid":"https://orcid.org/0000-0002-2049-2239"},"institutions":[{"id":"https://openalex.org/I157725225","display_name":"University of Illinois Urbana-Champaign","ror":"https://ror.org/047426m28","country_code":"US","type":"education","lineage":["https://openalex.org/I157725225"]},{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Soumya Jana","raw_affiliation_strings":["Department of Electrical and Computer Engineering, University of Illinois, Urbana-Champaign, USA","Microsoft Research, Redmond, WA, USA"],"affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering, University of Illinois, Urbana-Champaign, USA","institution_ids":["https://openalex.org/I157725225"]},{"raw_affiliation_string":"Microsoft Research, Redmond, WA, USA","institution_ids":["https://openalex.org/I1290206253"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5034285513"],"corresponding_institution_ids":["https://openalex.org/I1290206253"],"apc_list":null,"apc_paid":null,"fwci":4.8622,"has_fulltext":false,"cited_by_count":52,"citation_normalized_percentile":{"value":0.96246872,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"I","last_page":"1021"},"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":0.9995999932289124,"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":0.988099992275238,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8128293752670288},{"id":"https://openalex.org/keywords/preprocessor","display_name":"Preprocessor","score":0.5823778510093689},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5336806178092957},{"id":"https://openalex.org/keywords/digital-audio","display_name":"Digital audio","score":0.5300343632698059},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.5103151202201843},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5006747245788574},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4950636923313141},{"id":"https://openalex.org/keywords/audio-analyzer","display_name":"Audio analyzer","score":0.45916587114334106},{"id":"https://openalex.org/keywords/distortion","display_name":"Distortion (music)","score":0.44902998208999634},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.4480951130390167},{"id":"https://openalex.org/keywords/fingerprint","display_name":"Fingerprint (computing)","score":0.4324088394641876},{"id":"https://openalex.org/keywords/audio-signal-processing","display_name":"Audio signal processing","score":0.4284650683403015},{"id":"https://openalex.org/keywords/dimensionality-reduction","display_name":"Dimensionality reduction","score":0.4205131530761719},{"id":"https://openalex.org/keywords/audio-signal","display_name":"Audio signal","score":0.393195241689682},{"id":"https://openalex.org/keywords/speech-coding","display_name":"Speech coding","score":0.20146167278289795}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8128293752670288},{"id":"https://openalex.org/C34736171","wikidata":"https://www.wikidata.org/wiki/Q918333","display_name":"Preprocessor","level":2,"score":0.5823778510093689},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5336806178092957},{"id":"https://openalex.org/C87687168","wikidata":"https://www.wikidata.org/wiki/Q173114","display_name":"Digital audio","level":4,"score":0.5300343632698059},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.5103151202201843},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5006747245788574},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4950636923313141},{"id":"https://openalex.org/C160372630","wikidata":"https://www.wikidata.org/wiki/Q4819855","display_name":"Audio analyzer","level":5,"score":0.45916587114334106},{"id":"https://openalex.org/C126780896","wikidata":"https://www.wikidata.org/wiki/Q899871","display_name":"Distortion (music)","level":4,"score":0.44902998208999634},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.4480951130390167},{"id":"https://openalex.org/C2777826928","wikidata":"https://www.wikidata.org/wiki/Q3745713","display_name":"Fingerprint (computing)","level":2,"score":0.4324088394641876},{"id":"https://openalex.org/C127220857","wikidata":"https://www.wikidata.org/wiki/Q2719318","display_name":"Audio signal processing","level":4,"score":0.4284650683403015},{"id":"https://openalex.org/C70518039","wikidata":"https://www.wikidata.org/wiki/Q16000077","display_name":"Dimensionality reduction","level":2,"score":0.4205131530761719},{"id":"https://openalex.org/C64922751","wikidata":"https://www.wikidata.org/wiki/Q4650799","display_name":"Audio signal","level":3,"score":0.393195241689682},{"id":"https://openalex.org/C13895895","wikidata":"https://www.wikidata.org/wiki/Q3270773","display_name":"Speech coding","level":2,"score":0.20146167278289795},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0},{"id":"https://openalex.org/C2776257435","wikidata":"https://www.wikidata.org/wiki/Q1576430","display_name":"Bandwidth (computing)","level":2,"score":0.0},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.0},{"id":"https://openalex.org/C194257627","wikidata":"https://www.wikidata.org/wiki/Q211554","display_name":"Amplifier","level":3,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp.2002.5743968","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2002.5743968","pdf_url":null,"source":{"id":"https://openalex.org/S4363607879","display_name":"IEEE International Conference on Acoustics Speech and Signal Processing","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE International Conference on Acoustics Speech and Signal Processing","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.7099999785423279,"display_name":"Reduced inequalities","id":"https://metadata.un.org/sdg/10"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":9,"referenced_works":["https://openalex.org/W15206351","https://openalex.org/W2054804336","https://openalex.org/W2110215948","https://openalex.org/W2111331420","https://openalex.org/W2115101691","https://openalex.org/W2152928896","https://openalex.org/W3017143921","https://openalex.org/W4285719527","https://openalex.org/W6600634494"],"related_works":["https://openalex.org/W2970176078","https://openalex.org/W2098934641","https://openalex.org/W2289868279","https://openalex.org/W1526651343","https://openalex.org/W2069094726","https://openalex.org/W1975359510","https://openalex.org/W2363106653","https://openalex.org/W1496727373","https://openalex.org/W2020952589","https://openalex.org/W3110605476"],"abstract_inverted_index":{"A":[0],"key":[1],"problem":[2],"faced":[3],"by":[4],"audio":[5,16,67,88,93,99,115],"identification,":[6],"classification,":[7],"and":[8,74],"retrieval":[9],"systems":[10],"is":[11],"the":[12,48,84],"mapping":[13],"of":[14,39,54,86,113],"high-dimensional":[15],"input":[17,43,68,108],"data":[18],"into":[19,44],"informative":[20],"lower-dimensional":[21],"feature":[22],"vectors.":[23],"This":[24],"paper":[25],"explores":[26],"an":[27,91],"automatic":[28],"dimensionality":[29],"reduction":[30],"algorithm":[31],"called":[32],"Distortion":[33],"Discriminant":[34],"Analysis":[35],"(DDA).":[36],"Each":[37],"layer":[38],"DDA":[40,70,82],"projects":[41],"its":[42],"directions":[45],"which":[46],"maximize":[47],"SNR":[49],"for":[50],"a":[51,62],"given":[52],"set":[53],"distortions.":[55,79],"Multiple":[56],"layers":[57],"efficiently":[58],"extract":[59],"features":[60],"over":[61],"wide":[63],"temporal":[64],"window.":[65],"The":[66],"to":[69,76,83],"undergoes":[71],"perceptually-relevant":[72],"preprocessing":[73],"de-equalization,":[75],"further":[77],"suppress":[78],"We":[80,101],"apply":[81],"task":[85],"identifying":[87],"clips":[89],"in":[90],"incoming":[92],"stream,":[94],"based":[95],"on":[96,106],"matching":[97,107],"stored":[98,114],"fingerprints.":[100],"show":[102],"excellent":[103],"test":[104],"results":[105],"fingerprints":[109],"against":[110],"36":[111],"hours":[112],"data.":[116]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2018,"cited_by_count":1},{"year":2017,"cited_by_count":1},{"year":2016,"cited_by_count":2},{"year":2012,"cited_by_count":3}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}