{"id":"https://openalex.org/W3203816112","doi":"https://doi.org/10.1109/icassp43922.2022.9746037","title":"An Investigation of the Effectiveness of Phase for Audio Classification","display_name":"An Investigation of the Effectiveness of Phase for Audio Classification","publication_year":2022,"publication_date":"2022-04-27","ids":{"openalex":"https://openalex.org/W3203816112","doi":"https://doi.org/10.1109/icassp43922.2022.9746037","mag":"3203816112"},"language":"en","primary_location":{"id":"doi:10.1109/icassp43922.2022.9746037","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp43922.2022.9746037","pdf_url":null,"source":{"id":"https://openalex.org/S4363607702","display_name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"type":"article","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2110.02878","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5053472122","display_name":"Shunsuke Hidaka","orcid":"https://orcid.org/0000-0003-1001-4564"},"institutions":[{"id":"https://openalex.org/I4210134959","display_name":"Faculty of Design","ror":"https://ror.org/04bw0hg47","country_code":"SI","type":"education","lineage":["https://openalex.org/I4210134959"]},{"id":"https://openalex.org/I135598925","display_name":"Kyushu University","ror":"https://ror.org/00p4k0j84","country_code":"JP","type":"education","lineage":["https://openalex.org/I135598925"]}],"countries":["JP","SI"],"is_corresponding":true,"raw_author_name":"Shunsuke Hidaka","raw_affiliation_strings":["Kyushu University,Graduate School of Design,Japan","Graduate School of Design, Kyushu University, Japan"],"affiliations":[{"raw_affiliation_string":"Kyushu University,Graduate School of Design,Japan","institution_ids":["https://openalex.org/I135598925","https://openalex.org/I4210134959"]},{"raw_affiliation_string":"Graduate School of Design, Kyushu University, Japan","institution_ids":["https://openalex.org/I135598925"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5073627786","display_name":"Kohei Wakamiya","orcid":"https://orcid.org/0000-0001-9254-5910"},"institutions":[{"id":"https://openalex.org/I4210134959","display_name":"Faculty of Design","ror":"https://ror.org/04bw0hg47","country_code":"SI","type":"education","lineage":["https://openalex.org/I4210134959"]},{"id":"https://openalex.org/I135598925","display_name":"Kyushu University","ror":"https://ror.org/00p4k0j84","country_code":"JP","type":"education","lineage":["https://openalex.org/I135598925"]}],"countries":["JP","SI"],"is_corresponding":false,"raw_author_name":"Kohei Wakamiya","raw_affiliation_strings":["Kyushu University,Faculty of Design,Japan","Faculty of Design, Kyushu University, Japan"],"affiliations":[{"raw_affiliation_string":"Kyushu University,Faculty of Design,Japan","institution_ids":["https://openalex.org/I4210134959","https://openalex.org/I135598925"]},{"raw_affiliation_string":"Faculty of Design, Kyushu University, Japan","institution_ids":["https://openalex.org/I135598925"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5030837080","display_name":"Tokihiko Kaburagi","orcid":null},"institutions":[{"id":"https://openalex.org/I4210134959","display_name":"Faculty of Design","ror":"https://ror.org/04bw0hg47","country_code":"SI","type":"education","lineage":["https://openalex.org/I4210134959"]},{"id":"https://openalex.org/I135598925","display_name":"Kyushu University","ror":"https://ror.org/00p4k0j84","country_code":"JP","type":"education","lineage":["https://openalex.org/I135598925"]}],"countries":["JP","SI"],"is_corresponding":false,"raw_author_name":"Tokihiko Kaburagi","raw_affiliation_strings":["Kyushu University,Graduate School of Design,Japan","Graduate School of Design, Kyushu University, Japan"],"affiliations":[{"raw_affiliation_string":"Kyushu University,Graduate School of Design,Japan","institution_ids":["https://openalex.org/I135598925","https://openalex.org/I4210134959"]},{"raw_affiliation_string":"Graduate School of Design, Kyushu University, Japan","institution_ids":["https://openalex.org/I135598925"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5053472122"],"corresponding_institution_ids":["https://openalex.org/I135598925","https://openalex.org/I4210134959"],"apc_list":null,"apc_paid":null,"fwci":0.6106,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.6290932,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"3708","last_page":"3712"},"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":0.9991999864578247,"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/spectrogram","display_name":"Spectrogram","score":0.8458977341651917},{"id":"https://openalex.org/keywords/overfitting","display_name":"Overfitting","score":0.8073258399963379},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7214195728302002},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.701744794845581},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.5685189962387085},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.5455330610275269},{"id":"https://openalex.org/keywords/source-separation","display_name":"Source separation","score":0.5207071900367737},{"id":"https://openalex.org/keywords/identification","display_name":"Identification (biology)","score":0.5083979964256287},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4987633228302002},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.4697190821170807},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.46706753969192505},{"id":"https://openalex.org/keywords/audio-signal-processing","display_name":"Audio signal processing","score":0.462786465883255},{"id":"https://openalex.org/keywords/phase","display_name":"Phase (matter)","score":0.43460750579833984},{"id":"https://openalex.org/keywords/time\u2013frequency-analysis","display_name":"Time\u2013frequency analysis","score":0.4263323247432709},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.4143944978713989},{"id":"https://openalex.org/keywords/audio-signal","display_name":"Audio signal","score":0.33083128929138184},{"id":"https://openalex.org/keywords/speech-coding","display_name":"Speech coding","score":0.2723298668861389},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.1447731852531433},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.09636059403419495}],"concepts":[{"id":"https://openalex.org/C45273575","wikidata":"https://www.wikidata.org/wiki/Q578970","display_name":"Spectrogram","level":2,"score":0.8458977341651917},{"id":"https://openalex.org/C22019652","wikidata":"https://www.wikidata.org/wiki/Q331309","display_name":"Overfitting","level":3,"score":0.8073258399963379},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7214195728302002},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.701744794845581},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.5685189962387085},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.5455330610275269},{"id":"https://openalex.org/C2776864781","wikidata":"https://www.wikidata.org/wiki/Q52617913","display_name":"Source separation","level":2,"score":0.5207071900367737},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.5083979964256287},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4987633228302002},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.4697190821170807},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.46706753969192505},{"id":"https://openalex.org/C127220857","wikidata":"https://www.wikidata.org/wiki/Q2719318","display_name":"Audio signal processing","level":4,"score":0.462786465883255},{"id":"https://openalex.org/C44280652","wikidata":"https://www.wikidata.org/wiki/Q104837","display_name":"Phase (matter)","level":2,"score":0.43460750579833984},{"id":"https://openalex.org/C142433447","wikidata":"https://www.wikidata.org/wiki/Q7806653","display_name":"Time\u2013frequency analysis","level":3,"score":0.4263323247432709},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.4143944978713989},{"id":"https://openalex.org/C64922751","wikidata":"https://www.wikidata.org/wiki/Q4650799","display_name":"Audio signal","level":3,"score":0.33083128929138184},{"id":"https://openalex.org/C13895895","wikidata":"https://www.wikidata.org/wiki/Q3270773","display_name":"Speech coding","level":2,"score":0.2723298668861389},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.1447731852531433},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.09636059403419495},{"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/C178790620","wikidata":"https://www.wikidata.org/wiki/Q11351","display_name":"Organic chemistry","level":1,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C59822182","wikidata":"https://www.wikidata.org/wiki/Q441","display_name":"Botany","level":1,"score":0.0},{"id":"https://openalex.org/C106131492","wikidata":"https://www.wikidata.org/wiki/Q3072260","display_name":"Filter (signal processing)","level":2,"score":0.0},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/icassp43922.2022.9746037","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp43922.2022.9746037","pdf_url":null,"source":{"id":"https://openalex.org/S4363607702","display_name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2110.02878","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2110.02878","pdf_url":"https://arxiv.org/pdf/2110.02878","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2110.02878","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2110.02878","pdf_url":"https://arxiv.org/pdf/2110.02878","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[{"score":0.5699999928474426,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":56,"referenced_works":["https://openalex.org/W1522301498","https://openalex.org/W1731081199","https://openalex.org/W1836465849","https://openalex.org/W2030931454","https://openalex.org/W2048142341","https://openalex.org/W2065147844","https://openalex.org/W2095705004","https://openalex.org/W2128916826","https://openalex.org/W2567070169","https://openalex.org/W2606176153","https://openalex.org/W2726515241","https://openalex.org/W2797583228","https://openalex.org/W2883595988","https://openalex.org/W2936774411","https://openalex.org/W2938901746","https://openalex.org/W2940275453","https://openalex.org/W2942514267","https://openalex.org/W2944200841","https://openalex.org/W2948210185","https://openalex.org/W2949364537","https://openalex.org/W2952218014","https://openalex.org/W2955425717","https://openalex.org/W2962913459","https://openalex.org/W2963881567","https://openalex.org/W2963970792","https://openalex.org/W2964121744","https://openalex.org/W2964243274","https://openalex.org/W2970206392","https://openalex.org/W3032502780","https://openalex.org/W3093579165","https://openalex.org/W3095802501","https://openalex.org/W3096408984","https://openalex.org/W3099330747","https://openalex.org/W3124414150","https://openalex.org/W3132550238","https://openalex.org/W3163845842","https://openalex.org/W3210683364","https://openalex.org/W4287372095","https://openalex.org/W4298091485","https://openalex.org/W4393487040","https://openalex.org/W6631190155","https://openalex.org/W6637618735","https://openalex.org/W6638667902","https://openalex.org/W6674330103","https://openalex.org/W6731370813","https://openalex.org/W6736723571","https://openalex.org/W6738884980","https://openalex.org/W6740167877","https://openalex.org/W6748326514","https://openalex.org/W6750665317","https://openalex.org/W6762506163","https://openalex.org/W6762718338","https://openalex.org/W6779341498","https://openalex.org/W6784614252","https://openalex.org/W6789403026","https://openalex.org/W6803949091"],"related_works":["https://openalex.org/W1889291648","https://openalex.org/W3094316140","https://openalex.org/W3133205200","https://openalex.org/W2898145319","https://openalex.org/W4289363934","https://openalex.org/W2098101267","https://openalex.org/W2059119686","https://openalex.org/W3112881379","https://openalex.org/W2002298560","https://openalex.org/W2019256813"],"abstract_inverted_index":{"While":[0],"log-amplitude":[1],"mel-spectrogram":[2],"has":[3],"widely":[4],"been":[5],"used":[6],"as":[7,35],"the":[8,18,47,68,106,111,120,129,132,142],"feature":[9],"representation":[10,77],"for":[11,32,55,91,116],"processing":[12],"speech":[13,24,36],"based":[14,73],"on":[15,74],"deep":[16],"learning,":[17],"effectiveness":[19,48],"of":[20,23,49,53,135],"another":[21],"aspect":[22],"spectrum,":[25],"i.e.,":[26],"phase":[27,51,69,133,143],"information,":[28],"was":[29,114,123],"shown":[30],"recently":[31],"tasks":[33,118],"such":[34],"enhancement":[37],"and":[38,70,102],"source":[39],"separation.":[40],"In":[41],"this":[42],"study,":[43],"we":[44],"extensively":[45],"investigated":[46],"including":[50],"information":[52],"signals":[54],"eight":[56],"audio":[57,146],"classification":[58],"tasks.":[59],"We":[60],"constructed":[61],"a":[62,75,83],"learnable":[63],"front-end":[64],"that":[65,128],"can":[66],"compute":[67],"its":[71],"derivatives":[72],"time-frequency":[76],"with":[78],"mel-like":[79],"frequency":[80,122],"axis.":[81],"As":[82],"result,":[84],"experimental":[85],"results":[86,126],"showed":[87],"significant":[88],"performance":[89],"improvement":[90],"musical":[92,95],"pitch":[93],"detection,":[94,97],"instrument":[96],"language":[98],"identification,":[99,101],"speaker":[100],"birdsong":[103],"detection.":[104],"On":[105],"other":[107],"hand,":[108],"overfitting":[109],"to":[110],"recording":[112],"condition":[113],"observed":[115],"some":[117],"when":[119],"instantaneous":[121],"used.":[124],"The":[125],"implied":[127],"relationship":[130],"between":[131],"values":[134],"adjacent":[136],"elements":[137],"is":[138],"more":[139],"important":[140],"than":[141],"itself":[144],"in":[145],"classification.":[147]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":2}],"updated_date":"2026-03-20T23:20:44.827607","created_date":"2025-10-10T00:00:00"}