{"id":"https://openalex.org/W2103434133","doi":"https://doi.org/10.1109/icassp.2011.5947698","title":"Sparse coding of auditory features for machine hearing in interference","display_name":"Sparse coding of auditory features for machine hearing in interference","publication_year":2011,"publication_date":"2011-05-01","ids":{"openalex":"https://openalex.org/W2103434133","doi":"https://doi.org/10.1109/icassp.2011.5947698","mag":"2103434133"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2011.5947698","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2011.5947698","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2011 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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/A5026382065","display_name":"Richard F. Lyon","orcid":"https://orcid.org/0000-0003-2348-811X"},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Richard F. Lyon","raw_affiliation_strings":["Google, Inc., USA","Google, Inc, USA"],"affiliations":[{"raw_affiliation_string":"Google, Inc., USA","institution_ids":["https://openalex.org/I1291425158"]},{"raw_affiliation_string":"Google, Inc, USA","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5080625665","display_name":"Jay Ponte","orcid":null},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jay Ponte","raw_affiliation_strings":["Google, Inc., USA","Google, Inc, USA"],"affiliations":[{"raw_affiliation_string":"Google, Inc., USA","institution_ids":["https://openalex.org/I1291425158"]},{"raw_affiliation_string":"Google, Inc, USA","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5045719865","display_name":"Gal Chechik","orcid":"https://orcid.org/0000-0001-9164-5303"},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Gal Chechik","raw_affiliation_strings":["Google, Inc., USA","Google, Inc, USA"],"affiliations":[{"raw_affiliation_string":"Google, Inc., USA","institution_ids":["https://openalex.org/I1291425158"]},{"raw_affiliation_string":"Google, Inc, USA","institution_ids":["https://openalex.org/I1291425158"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5026382065"],"corresponding_institution_ids":["https://openalex.org/I1291425158"],"apc_list":null,"apc_paid":null,"fwci":0.9354,"has_fulltext":false,"cited_by_count":10,"citation_normalized_percentile":{"value":0.75047161,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"5876","last_page":"5879"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music 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/T11309","display_name":"Music 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/T10860","display_name":"Speech and Audio Processing","score":0.9997000098228455,"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":0.9940000176429749,"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/computer-science","display_name":"Computer science","score":0.7885297536849976},{"id":"https://openalex.org/keywords/vector-quantization","display_name":"Vector quantization","score":0.6788533926010132},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.6679777503013611},{"id":"https://openalex.org/keywords/neural-coding","display_name":"Neural coding","score":0.6412725448608398},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.578859269618988},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.5637481212615967},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5600538849830627},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5596320033073425},{"id":"https://openalex.org/keywords/sparse-approximation","display_name":"Sparse approximation","score":0.5072274208068848},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.46886661648750305},{"id":"https://openalex.org/keywords/mel-frequency-cepstrum","display_name":"Mel-frequency cepstrum","score":0.4425638020038605},{"id":"https://openalex.org/keywords/feature-vector","display_name":"Feature vector","score":0.4350626766681671},{"id":"https://openalex.org/keywords/support-vector-machine","display_name":"Support vector machine","score":0.4111708998680115},{"id":"https://openalex.org/keywords/coding","display_name":"Coding (social sciences)","score":0.41112473607063293},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.11255306005477905}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7885297536849976},{"id":"https://openalex.org/C199833920","wikidata":"https://www.wikidata.org/wiki/Q612536","display_name":"Vector quantization","level":2,"score":0.6788533926010132},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.6679777503013611},{"id":"https://openalex.org/C77637269","wikidata":"https://www.wikidata.org/wiki/Q7002051","display_name":"Neural coding","level":2,"score":0.6412725448608398},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.578859269618988},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.5637481212615967},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5600538849830627},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5596320033073425},{"id":"https://openalex.org/C124066611","wikidata":"https://www.wikidata.org/wiki/Q28684319","display_name":"Sparse approximation","level":2,"score":0.5072274208068848},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.46886661648750305},{"id":"https://openalex.org/C151989614","wikidata":"https://www.wikidata.org/wiki/Q440370","display_name":"Mel-frequency cepstrum","level":3,"score":0.4425638020038605},{"id":"https://openalex.org/C83665646","wikidata":"https://www.wikidata.org/wiki/Q42139305","display_name":"Feature vector","level":2,"score":0.4350626766681671},{"id":"https://openalex.org/C12267149","wikidata":"https://www.wikidata.org/wiki/Q282453","display_name":"Support vector machine","level":2,"score":0.4111708998680115},{"id":"https://openalex.org/C179518139","wikidata":"https://www.wikidata.org/wiki/Q5140297","display_name":"Coding (social sciences)","level":2,"score":0.41112473607063293},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.11255306005477905},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","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/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","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}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/icassp.2011.5947698","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2011.5947698","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2011 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.308.3904","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.308.3904","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://static.googleusercontent.com/external_content/untrusted_dlcp/research.google.com/en/us/pubs/archive/36864.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":9,"referenced_works":["https://openalex.org/W64644853","https://openalex.org/W1966273763","https://openalex.org/W1983476815","https://openalex.org/W2057550055","https://openalex.org/W2104298926","https://openalex.org/W2112790858","https://openalex.org/W2133285226","https://openalex.org/W2161278885","https://openalex.org/W2483766645"],"related_works":["https://openalex.org/W4246349004","https://openalex.org/W2181871477","https://openalex.org/W2061163896","https://openalex.org/W2432604435","https://openalex.org/W2890544631","https://openalex.org/W2089229568","https://openalex.org/W2019490789","https://openalex.org/W3088722891","https://openalex.org/W2067062989","https://openalex.org/W4205656132"],"abstract_inverted_index":{"A":[0],"key":[1],"problem":[2],"in":[3,18,84,97,139,156,172],"using":[4,76,127],"the":[5,12,94,100,133,163],"output":[6],"of":[7,86,90,124,154,166],"an":[8],"auditory":[9,51,69],"model":[10,35],"as":[11,32],"input":[13],"to":[14,23,53,79,179],"a":[15,19,25,43,48,73,103,173],"machine-learning":[16],"system":[17],"machine-hearing":[20],"application":[21],"is":[22,56],"find":[24],"good":[26],"feature-extraction":[27],"layer.":[28],"For":[29,58],"systems":[30],"such":[31],"PAMIR":[33],"(passive-aggressive":[34],"for":[36,102],"image":[37],"retrieval)":[38],"that":[39,96,132,151,169],"work":[40],"well":[41],"with":[42,93],"large":[44],"sparse":[45,54,82,144,167],"feature":[46,83],"vector,":[47],"conversion":[49],"from":[50,63],"images":[52],"features":[55,101,136,145,168],"needed.":[57],"audio-file":[59],"ranking":[60],"and":[61,115,130],"retrieval":[62],"text":[64],"queries,":[65],"based":[66],"on":[67],"stabilized":[68],"images,":[70],"we":[71],"took":[72],"multi-scale":[74],"approach,":[75],"vector":[77],"quantization":[78],"choose":[80],"one":[81],"each":[85],"many":[87],"overlapping":[88],"regions":[89,99],"different":[91],"scales,":[92],"hope":[95,153],"some":[98],"sound":[104,128],"would":[105],"be":[106,160,180],"stable":[107],"even":[108],"when":[109],"other":[110,117],"interfering":[111],"sounds":[112],"were":[113],"present":[114],"affecting":[116],"regions.":[118],"We":[119],"recently":[120],"extended":[121],"our":[122,152],"testing":[123],"this":[125],"approach":[126],"mixtures,":[129],"found":[131],"sparse-coded":[134],"auditory-image":[135],"degrade":[137],"less":[138],"interference":[140,157],"than":[141],"vector-quantized":[142],"MFCC":[143],"do.":[146],"This":[147],"initial":[148],"success":[149],"suggests":[150],"robustness":[155],"may":[158],"indeed":[159],"realizable,":[161],"via":[162],"general":[164],"idea":[165],"are":[170],"localized":[171,181],"domain":[174],"where":[175],"signal":[176],"components":[177],"tend":[178],"or":[182],"stable.":[183]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2019,"cited_by_count":1},{"year":2017,"cited_by_count":1},{"year":2016,"cited_by_count":1},{"year":2015,"cited_by_count":3},{"year":2013,"cited_by_count":2}],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}