{"id":"https://openalex.org/W84008161","doi":"https://doi.org/10.21437/interspeech.2010-641","title":"Effects of modelling within- and between-frame temporal variations in power spectra on non-verbal sound recognition","display_name":"Effects of modelling within- and between-frame temporal variations in power spectra on non-verbal sound recognition","publication_year":2010,"publication_date":"2010-09-26","ids":{"openalex":"https://openalex.org/W84008161","doi":"https://doi.org/10.21437/interspeech.2010-641","mag":"84008161"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2010-641","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2010-641","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2010","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/A5064031454","display_name":"Nobuhide Yamakawa","orcid":null},"institutions":[{"id":"https://openalex.org/I22299242","display_name":"Kyoto University","ror":"https://ror.org/02kpeqv85","country_code":"JP","type":"education","lineage":["https://openalex.org/I22299242"]},{"id":"https://openalex.org/I4210129581","display_name":"Kyoto University of Education","ror":"https://ror.org/03zhhr656","country_code":"JP","type":"education","lineage":["https://openalex.org/I4210129581"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Nobuhide Yamakawa","raw_affiliation_strings":["Kyoto univ"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Kyoto univ","institution_ids":["https://openalex.org/I22299242","https://openalex.org/I4210129581"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5108346747","display_name":"Tetsuro Kitahara","orcid":null},"institutions":[{"id":"https://openalex.org/I104946051","display_name":"Nihon University","ror":"https://ror.org/05jk51a88","country_code":"JP","type":"education","lineage":["https://openalex.org/I104946051"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Tetsuro Kitahara","raw_affiliation_strings":["Nihon University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nihon University","institution_ids":["https://openalex.org/I104946051"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5065967819","display_name":"T\u00f4ru Takahashi","orcid":"https://orcid.org/0000-0002-8476-9751"},"institutions":[{"id":"https://openalex.org/I22299242","display_name":"Kyoto University","ror":"https://ror.org/02kpeqv85","country_code":"JP","type":"education","lineage":["https://openalex.org/I22299242"]},{"id":"https://openalex.org/I4210129581","display_name":"Kyoto University of Education","ror":"https://ror.org/03zhhr656","country_code":"JP","type":"education","lineage":["https://openalex.org/I4210129581"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Toru Takahashi","raw_affiliation_strings":["Kyoto univ"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Kyoto univ","institution_ids":["https://openalex.org/I22299242","https://openalex.org/I4210129581"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5049614400","display_name":"Kazunori Komatani","orcid":"https://orcid.org/0000-0002-6052-600X"},"institutions":[{"id":"https://openalex.org/I22299242","display_name":"Kyoto University","ror":"https://ror.org/02kpeqv85","country_code":"JP","type":"education","lineage":["https://openalex.org/I22299242"]},{"id":"https://openalex.org/I4210129581","display_name":"Kyoto University of Education","ror":"https://ror.org/03zhhr656","country_code":"JP","type":"education","lineage":["https://openalex.org/I4210129581"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Kazunori Komatani","raw_affiliation_strings":["Kyoto univ"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Kyoto univ","institution_ids":["https://openalex.org/I22299242","https://openalex.org/I4210129581"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5055922202","display_name":"Tetsuya Ogata","orcid":"https://orcid.org/0000-0001-7015-0379"},"institutions":[{"id":"https://openalex.org/I22299242","display_name":"Kyoto University","ror":"https://ror.org/02kpeqv85","country_code":"JP","type":"education","lineage":["https://openalex.org/I22299242"]},{"id":"https://openalex.org/I4210129581","display_name":"Kyoto University of Education","ror":"https://ror.org/03zhhr656","country_code":"JP","type":"education","lineage":["https://openalex.org/I4210129581"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Tetsuya Ogata","raw_affiliation_strings":["Kyoto univ"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Kyoto univ","institution_ids":["https://openalex.org/I22299242","https://openalex.org/I4210129581"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5005141184","display_name":"Hiroshi G. Okuno","orcid":"https://orcid.org/0000-0002-8704-4318"},"institutions":[{"id":"https://openalex.org/I22299242","display_name":"Kyoto University","ror":"https://ror.org/02kpeqv85","country_code":"JP","type":"education","lineage":["https://openalex.org/I22299242"]},{"id":"https://openalex.org/I4210129581","display_name":"Kyoto University of Education","ror":"https://ror.org/03zhhr656","country_code":"JP","type":"education","lineage":["https://openalex.org/I4210129581"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Hiroshi G. Okuno","raw_affiliation_strings":["Kyoto univ"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Kyoto univ","institution_ids":["https://openalex.org/I22299242","https://openalex.org/I4210129581"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":2.3704,"has_fulltext":false,"cited_by_count":15,"citation_normalized_percentile":{"value":0.88316391,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"2342","last_page":"2345"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music 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"}},"topics":[{"id":"https://openalex.org/T11309","display_name":"Music 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/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/T11447","display_name":"Blind Source Separation Techniques","score":0.9941999912261963,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/frame","display_name":"Frame (networking)","score":0.6937311291694641},{"id":"https://openalex.org/keywords/sound","display_name":"Sound (geography)","score":0.5677447319030762},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5310628414154053},{"id":"https://openalex.org/keywords/power","display_name":"Power (physics)","score":0.5212650895118713},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.45574143528938293},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4401235580444336},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.160100519657135},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.09858623147010803}],"concepts":[{"id":"https://openalex.org/C126042441","wikidata":"https://www.wikidata.org/wiki/Q1324888","display_name":"Frame (networking)","level":2,"score":0.6937311291694641},{"id":"https://openalex.org/C203718221","wikidata":"https://www.wikidata.org/wiki/Q491713","display_name":"Sound (geography)","level":2,"score":0.5677447319030762},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5310628414154053},{"id":"https://openalex.org/C163258240","wikidata":"https://www.wikidata.org/wiki/Q25342","display_name":"Power (physics)","level":2,"score":0.5212650895118713},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.45574143528938293},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4401235580444336},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.160100519657135},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.09858623147010803},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21437/interspeech.2010-641","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2010-641","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2010","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":15,"referenced_works":["https://openalex.org/W222076935","https://openalex.org/W621911156","https://openalex.org/W1508249674","https://openalex.org/W1990272741","https://openalex.org/W1996160964","https://openalex.org/W2043601359","https://openalex.org/W2056263517","https://openalex.org/W2058189943","https://openalex.org/W2099988344","https://openalex.org/W2100032013","https://openalex.org/W2130640900","https://openalex.org/W2137343183","https://openalex.org/W2151693816","https://openalex.org/W2156468046","https://openalex.org/W2781752978"],"related_works":["https://openalex.org/W2373012867","https://openalex.org/W2369067071","https://openalex.org/W2373884999","https://openalex.org/W2893763841","https://openalex.org/W1505515411","https://openalex.org/W2368779261","https://openalex.org/W2794438528","https://openalex.org/W4211182446","https://openalex.org/W4235181573","https://openalex.org/W2778699561"],"abstract_inverted_index":{"Research":[0],"on":[1,14,53],"environmental":[2,29,152],"sound":[3,26,124,150,153],"recognition":[4,46],"has":[5],"not":[6],"shown":[7],"great":[8],"development":[9],"in":[10,41],"comparison":[11],"with":[12,105,126,136],"that":[13,24,103],"speech":[15],"and":[16,56,61,129],"musical":[17],"signals.":[18],"One":[19],"of":[20,28,35,79,90,94,123,139],"the":[21,25,88],"reasons":[22],"is":[23],"category":[27],"sounds":[30,55,95,104],"covers":[31],"a":[32,69,83,127],"broad":[33],"range":[34],"acoustical":[36],"natures.":[37],"We":[38,51,65,85],"classified":[39],"them":[40],"order":[42],"to":[43,71],"explore":[44],"suitable":[45],"techniques":[47],"for":[48,75],"each":[49],"characteristic.":[50],"focus":[52],"impulsive":[54,107],"their":[57],"non-stationary":[58],"feature":[59],"within":[60],"between":[62],"analytic":[63],"frames.":[64],"used":[66],"matching-pursuit":[67],"as":[68],"framework":[70],"use":[72],"wavelet":[73],"analysis":[74],"extracting":[76],"temporal":[77],"variation":[78],"audio":[80,146],"features":[81],"inside":[82],"frame.":[84],"also":[86],"investigated":[87],"validity":[89],"modeling":[91],"decaying":[92,131],"patterns":[93],"using":[96,113],"Hidden":[97],"markov":[98],"models.":[99],"Experimental":[100],"results":[101],"indicate":[102],"multiple":[106,137],"signals":[108],"are":[109,142],"recognized":[110],"better":[111],"by":[112,118],"time-frequency":[114,155],"analyzing":[115],"bases":[116],"than":[117],"frequency":[119],"domain":[120],"analysis.":[121],"Classification":[122],"classes":[125],"long":[128],"clear":[130],"pattern":[132],"improves":[133],"when":[134],"HMMs":[135],"number":[138],"hidden":[140],"states":[141],"applied.":[143],"Index":[144],"Terms:":[145],"signal":[147],"classification,":[148],"non-speech":[149],"recognition,":[151,154],"analysis,":[156],"Matching-Pursuit":[157]},"counts_by_year":[{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":1},{"year":2017,"cited_by_count":2},{"year":2014,"cited_by_count":2},{"year":2013,"cited_by_count":3},{"year":2012,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}
