{"id":"https://openalex.org/W2394954022","doi":"https://doi.org/10.1109/icassp.2016.7471755","title":"Discriminatively learned filter bank for acoustic features","display_name":"Discriminatively learned filter bank for acoustic features","publication_year":2016,"publication_date":"2016-03-01","ids":{"openalex":"https://openalex.org/W2394954022","doi":"https://doi.org/10.1109/icassp.2016.7471755","mag":"2394954022"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2016.7471755","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2016.7471755","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2016 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/A5069526951","display_name":"Takumi Kobayashi","orcid":"https://orcid.org/0000-0002-9244-317X"},"institutions":[{"id":"https://openalex.org/I73613424","display_name":"National Institute of Advanced Industrial Science and Technology","ror":"https://ror.org/01703db54","country_code":"JP","type":"government","lineage":["https://openalex.org/I73613424"]}],"countries":["JP"],"is_corresponding":true,"raw_author_name":"Takumi Kobayashi","raw_affiliation_strings":["National Institute of Advanced Industrial Science and Technology, Tsukuba, Ibaraki, Japan"],"affiliations":[{"raw_affiliation_string":"National Institute of Advanced Industrial Science and Technology, Tsukuba, Ibaraki, Japan","institution_ids":["https://openalex.org/I73613424"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5060905149","display_name":"Jiaxing Ye","orcid":"https://orcid.org/0000-0002-6680-1201"},"institutions":[{"id":"https://openalex.org/I73613424","display_name":"National Institute of Advanced Industrial Science and Technology","ror":"https://ror.org/01703db54","country_code":"JP","type":"government","lineage":["https://openalex.org/I73613424"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Jiaxing Ye","raw_affiliation_strings":["National Institute of Advanced Industrial Science and Technology, Tsukuba, Ibaraki, Japan"],"affiliations":[{"raw_affiliation_string":"National Institute of Advanced Industrial Science and Technology, Tsukuba, Ibaraki, Japan","institution_ids":["https://openalex.org/I73613424"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5069526951"],"corresponding_institution_ids":["https://openalex.org/I73613424"],"apc_list":null,"apc_paid":null,"fwci":0.7565,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.70287007,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":96},"biblio":{"volume":"6","issue":null,"first_page":"649","last_page":"653"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech 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/T10860","display_name":"Speech 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/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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9976999759674072,"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/filter-bank","display_name":"Filter bank","score":0.8949797749519348},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7819002270698547},{"id":"https://openalex.org/keywords/discriminative-model","display_name":"Discriminative model","score":0.7312752604484558},{"id":"https://openalex.org/keywords/filter","display_name":"Filter (signal processing)","score":0.7064720988273621},{"id":"https://openalex.org/keywords/mel-frequency-cepstrum","display_name":"Mel-frequency cepstrum","score":0.6107391715049744},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.5089399814605713},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.4932326674461365},{"id":"https://openalex.org/keywords/frequency-domain","display_name":"Frequency domain","score":0.47794273495674133},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4730500280857086},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.4709929823875427},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4384843707084656},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4034399390220642},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.24526312947273254}],"concepts":[{"id":"https://openalex.org/C100515483","wikidata":"https://www.wikidata.org/wiki/Q3268235","display_name":"Filter bank","level":3,"score":0.8949797749519348},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7819002270698547},{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.7312752604484558},{"id":"https://openalex.org/C106131492","wikidata":"https://www.wikidata.org/wiki/Q3072260","display_name":"Filter (signal processing)","level":2,"score":0.7064720988273621},{"id":"https://openalex.org/C151989614","wikidata":"https://www.wikidata.org/wiki/Q440370","display_name":"Mel-frequency cepstrum","level":3,"score":0.6107391715049744},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.5089399814605713},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.4932326674461365},{"id":"https://openalex.org/C19118579","wikidata":"https://www.wikidata.org/wiki/Q786423","display_name":"Frequency domain","level":2,"score":0.47794273495674133},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4730500280857086},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.4709929823875427},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4384843707084656},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4034399390220642},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.24526312947273254},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"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/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp.2016.7471755","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2016.7471755","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2016 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/10","score":0.7200000286102295,"display_name":"Reduced inequalities"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":19,"referenced_works":["https://openalex.org/W16408605","https://openalex.org/W1491667773","https://openalex.org/W1654482605","https://openalex.org/W1969851134","https://openalex.org/W1974306283","https://openalex.org/W2017608047","https://openalex.org/W2042949540","https://openalex.org/W2051666418","https://openalex.org/W2088489891","https://openalex.org/W2095147901","https://openalex.org/W2097366995","https://openalex.org/W2098654823","https://openalex.org/W2150252476","https://openalex.org/W2161969291","https://openalex.org/W2163406054","https://openalex.org/W2168356304","https://openalex.org/W3005272312","https://openalex.org/W6674755931","https://openalex.org/W6684134493"],"related_works":["https://openalex.org/W2990982991","https://openalex.org/W2766680336","https://openalex.org/W2133320490","https://openalex.org/W4289830142","https://openalex.org/W1497065097","https://openalex.org/W2125446021","https://openalex.org/W3150393935","https://openalex.org/W2980055100","https://openalex.org/W2186790562","https://openalex.org/W2548564146"],"abstract_inverted_index":{"Filter":[0],"banks":[1,51,67,111],"on":[2,18,105,151,162],"a":[3,91,95,101],"frequency":[4],"domain":[5],"are":[6,31,77,127],"widely":[7],"applied":[8],"and":[9,14,76],"studied":[10],"mainly":[11,56],"for":[12,40],"MFCC":[13],"its":[15],"variant":[16],"methods":[17],"speech":[19],"recognition":[20],"tasks.":[21],"In":[22,148],"recent":[23],"years,":[24],"other":[25],"types":[26],"of":[27,84,109,123,139],"acoustic":[28,87,152],"features":[29,138],"which":[30,116],"derived":[32],"from":[33,81,98],"image":[34],"classification":[35],"literature":[36],"have":[37,68],"attracted":[38],"attentions":[39],"the":[41,49,63,82,106,144,149,155],"tasks":[42],"regarding":[43],"environmental":[44],"sounds.":[45],"For":[46],"those":[47],"features,":[48],"filter":[50,66,96,110,146],"can":[52],"also":[53],"be":[54],"employed":[55],"to":[57,72,93,135],"effectively":[58],"reduce":[59],"feature":[60],"dimensionality":[61],"along":[62],"frequency.":[64],"The":[65],"been":[69],"designed":[70],"according":[71],"human":[73],"auditory":[74],"process":[75],"not":[78],"necessarily":[79],"optimal":[80],"viewpoint":[83],"distinguishing":[85],"actual":[86],"data.":[88,124],"We":[89],"propose":[90],"method":[92,157],"build":[94],"bank":[97],"scratch":[99],"in":[100],"data-driven":[102],"manner":[103],"based":[104],"natural":[107],"properties":[108],"without":[112],"parametrically":[113],"modeling":[114],"them,":[115],"thereby":[117],"more":[118],"flexibly":[119],"describes":[120],"intrinsic":[121],"characteristics":[122],"Those":[125],"filters":[126],"optimized":[128],"by":[129],"incorporating":[130],"discriminative":[131],"criterion":[132],"so":[133],"as":[134],"provide":[136],"effective":[137],"high":[140],"performance":[141,160],"even":[142],"with":[143],"smaller-sized":[145],"bank.":[147],"experiments":[150],"scene":[153],"classification,":[154],"proposed":[156],"exhibits":[158],"favorable":[159],"especially":[161],"lower":[163],"dimensional":[164],"features.":[165]},"counts_by_year":[{"year":2019,"cited_by_count":2},{"year":2018,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}