{"id":"https://openalex.org/W2398880078","doi":"https://doi.org/10.21437/interspeech.2012-652","title":"Pooling robust shift-invariant sparse representations of acoustic signals","display_name":"Pooling robust shift-invariant sparse representations of acoustic signals","publication_year":2012,"publication_date":"2012-09-09","ids":{"openalex":"https://openalex.org/W2398880078","doi":"https://doi.org/10.21437/interspeech.2012-652","mag":"2398880078"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2012-652","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2012-652","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2012","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/A5113913928","display_name":"Po-Sen Huang","orcid":null},"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"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Po-Sen Huang","raw_affiliation_strings":["***University of Illinois at Urbana-Champaign"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"***University of Illinois at Urbana-Champaign","institution_ids":["https://openalex.org/I157725225"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Jianchao Yang","orcid":null},"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"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jianchao Yang","raw_affiliation_strings":["***University of Illinois at Urbana-Champaign"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"***University of Illinois at Urbana-Champaign","institution_ids":["https://openalex.org/I157725225"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5004778663","display_name":"Mark Hasegawa\u2010Johnson","orcid":"https://orcid.org/0000-0002-5631-2893"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Mark Hasegawa-Johnson","raw_affiliation_strings":["Electrical and Computer Engineering"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Electrical and Computer Engineering","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100448893","display_name":"Feng Liang","orcid":"https://orcid.org/0000-0002-3868-4845"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Feng Liang","raw_affiliation_strings":["Information Trust Institute"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Information Trust Institute","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101457342","display_name":"Thomas S. Huang","orcid":"https://orcid.org/0000-0001-8474-5859"},"institutions":[{"id":"https://openalex.org/I4400573203","display_name":"Nature Inspires Creativity Engineers Lab","ror":"https://ror.org/02bczqy30","country_code":null,"type":"facility","lineage":["https://openalex.org/I201841394","https://openalex.org/I4400573203"]}],"countries":[],"is_corresponding":false,"raw_author_name":"Thomas S. Huang","raw_affiliation_strings":["Coordinated Science Lab"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Coordinated Science Lab","institution_ids":["https://openalex.org/I4400573203"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":9,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"2518","last_page":"2521"},"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":0.9991000294685364,"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/T11439","display_name":"Video Analysis and Summarization","score":0.9835000038146973,"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/pooling","display_name":"Pooling","score":0.9252042770385742},{"id":"https://openalex.org/keywords/discriminative-model","display_name":"Discriminative model","score":0.8118923902511597},{"id":"https://openalex.org/keywords/neural-coding","display_name":"Neural coding","score":0.7733327150344849},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7268447875976562},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6636244058609009},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.6180452108383179},{"id":"https://openalex.org/keywords/pyramid","display_name":"Pyramid (geometry)","score":0.6044602394104004},{"id":"https://openalex.org/keywords/feature-learning","display_name":"Feature learning","score":0.5982472896575928},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.4803706109523773},{"id":"https://openalex.org/keywords/invariant","display_name":"Invariant (physics)","score":0.4743686616420746},{"id":"https://openalex.org/keywords/coding","display_name":"Coding (social sciences)","score":0.4704540967941284},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.44267672300338745},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4213041663169861},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.35061267018318176},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.13019874691963196}],"concepts":[{"id":"https://openalex.org/C70437156","wikidata":"https://www.wikidata.org/wiki/Q7228652","display_name":"Pooling","level":2,"score":0.9252042770385742},{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.8118923902511597},{"id":"https://openalex.org/C77637269","wikidata":"https://www.wikidata.org/wiki/Q7002051","display_name":"Neural coding","level":2,"score":0.7733327150344849},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7268447875976562},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6636244058609009},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.6180452108383179},{"id":"https://openalex.org/C142575187","wikidata":"https://www.wikidata.org/wiki/Q3358290","display_name":"Pyramid (geometry)","level":2,"score":0.6044602394104004},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.5982472896575928},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.4803706109523773},{"id":"https://openalex.org/C190470478","wikidata":"https://www.wikidata.org/wiki/Q2370229","display_name":"Invariant (physics)","level":2,"score":0.4743686616420746},{"id":"https://openalex.org/C179518139","wikidata":"https://www.wikidata.org/wiki/Q5140297","display_name":"Coding (social sciences)","level":2,"score":0.4704540967941284},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.44267672300338745},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4213041663169861},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.35061267018318176},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.13019874691963196},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","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/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C37914503","wikidata":"https://www.wikidata.org/wiki/Q156495","display_name":"Mathematical physics","level":1,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.21437/interspeech.2012-652","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2012-652","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2012","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.294.4545","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.294.4545","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.ifp.illinois.edu/speech/pubs/2012/huang12interspeech.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.308.9391","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.308.9391","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.ifp.illinois.edu/~jyang29/papers/InterSpeech12.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Reduced inequalities","id":"https://metadata.un.org/sdg/10","score":0.75}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":14,"referenced_works":["https://openalex.org/W64644853","https://openalex.org/W1972715665","https://openalex.org/W2055761259","https://openalex.org/W2097018403","https://openalex.org/W2108815700","https://openalex.org/W2120077739","https://openalex.org/W2133285226","https://openalex.org/W2136922672","https://openalex.org/W2146792684","https://openalex.org/W2151693816","https://openalex.org/W2157059077","https://openalex.org/W2161760258","https://openalex.org/W2162915993","https://openalex.org/W2963909185"],"related_works":["https://openalex.org/W2022849497","https://openalex.org/W3081299480","https://openalex.org/W2407190427","https://openalex.org/W2907584218","https://openalex.org/W2919210741","https://openalex.org/W3002446410","https://openalex.org/W4390224712","https://openalex.org/W4322096758","https://openalex.org/W2797752778","https://openalex.org/W2144332008"],"abstract_inverted_index":{"In":[0,40],"recent":[1],"years,":[2],"designing":[3],"the":[4,45,51,71,82],"coding":[5,53],"and":[6,55,65],"pooling":[7,47,60],"structures":[8,31],"in":[9],"layered":[10],"networks":[11],"has":[12],"been":[13,34],"shown":[14],"to":[15,62],"be":[16],"a":[17,57],"useful":[18],"method":[19,61],"for":[20,25,37],"learning":[21,30],"high-level":[22],"feature":[23,67,76],"representations":[24],"visual":[26],"data.":[27],"Yet,":[28],"such":[29],"have":[32],"not":[33],"extensively":[35],"studied":[36],"audio":[38],"signals.":[39],"this":[41],"paper,":[42],"we":[43],"investigate":[44],"different":[46],"strategies":[48],"based":[49],"on":[50,81],"sparse":[52,89],"scheme":[54],"propose":[56],"temporal":[58],"pyramid":[59],"extract":[63],"discriminative":[64],"shift-invariant":[66],"representations.":[68],"We":[69],"demonstrate":[70],"superiority":[72],"of":[73],"our":[74],"new":[75],"representation":[77],"over":[78],"traditional":[79],"features":[80],"acoustic":[83,92],"event":[84,93],"classification":[85,94],"task.":[86],"Index":[87],"Terms:":[88],"coding,":[90],"pooling,":[91],"1.":[95]},"counts_by_year":[{"year":2018,"cited_by_count":1},{"year":2016,"cited_by_count":2},{"year":2015,"cited_by_count":1},{"year":2014,"cited_by_count":2},{"year":2013,"cited_by_count":3}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}
