{"id":"https://openalex.org/W2296050682","doi":"https://doi.org/10.21437/interspeech.2011-496","title":"Probabilistic spectrum envelope: categorized audio-features representation for NMF-based sound decomposition","display_name":"Probabilistic spectrum envelope: categorized audio-features representation for NMF-based sound decomposition","publication_year":2011,"publication_date":"2011-08-27","ids":{"openalex":"https://openalex.org/W2296050682","doi":"https://doi.org/10.21437/interspeech.2011-496","mag":"2296050682"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2011-496","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2011-496","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2011","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/A5041887072","display_name":"Toru Nakashika","orcid":"https://orcid.org/0000-0003-1863-6771"},"institutions":[{"id":"https://openalex.org/I65837984","display_name":"Kobe University","ror":"https://ror.org/03tgsfw79","country_code":"JP","type":"education","lineage":["https://openalex.org/I65837984"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Toru Nakashika","raw_affiliation_strings":["Kobe University,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Kobe University,","institution_ids":["https://openalex.org/I65837984"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5009283470","display_name":"Tetsuya Takiguchi","orcid":"https://orcid.org/0000-0001-5005-7679"},"institutions":[{"id":"https://openalex.org/I65837984","display_name":"Kobe University","ror":"https://ror.org/03tgsfw79","country_code":"JP","type":"education","lineage":["https://openalex.org/I65837984"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Tetsuya Takiguchi","raw_affiliation_strings":["Kobe University,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Kobe University,","institution_ids":["https://openalex.org/I65837984"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5040766342","display_name":"Yasuo Ariki","orcid":"https://orcid.org/0000-0003-3473-2026"},"institutions":[{"id":"https://openalex.org/I65837984","display_name":"Kobe University","ror":"https://ror.org/03tgsfw79","country_code":"JP","type":"education","lineage":["https://openalex.org/I65837984"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Yasuo Ariki","raw_affiliation_strings":["Kobe University,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Kobe University,","institution_ids":["https://openalex.org/I65837984"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I65837984"],"apc_list":null,"apc_paid":null,"fwci":0.278,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.52763397,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"1765","last_page":"1768"},"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":0.9991000294685364,"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/T11447","display_name":"Blind Source Separation Techniques","score":0.9958999752998352,"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/non-negative-matrix-factorization","display_name":"Non-negative matrix factorization","score":0.9179726839065552},{"id":"https://openalex.org/keywords/matrix-decomposition","display_name":"Matrix decomposition","score":0.703158438205719},{"id":"https://openalex.org/keywords/audio-signal","display_name":"Audio signal","score":0.6685121655464172},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6612846851348877},{"id":"https://openalex.org/keywords/probabilistic-logic","display_name":"Probabilistic logic","score":0.6573633551597595},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.5727869272232056},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5487299561500549},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5240324139595032},{"id":"https://openalex.org/keywords/source-separation","display_name":"Source separation","score":0.48952969908714294},{"id":"https://openalex.org/keywords/audio-signal-processing","display_name":"Audio signal processing","score":0.4298844039440155},{"id":"https://openalex.org/keywords/speech-coding","display_name":"Speech coding","score":0.2207813262939453}],"concepts":[{"id":"https://openalex.org/C152671427","wikidata":"https://www.wikidata.org/wiki/Q10843505","display_name":"Non-negative matrix factorization","level":4,"score":0.9179726839065552},{"id":"https://openalex.org/C42355184","wikidata":"https://www.wikidata.org/wiki/Q1361088","display_name":"Matrix decomposition","level":3,"score":0.703158438205719},{"id":"https://openalex.org/C64922751","wikidata":"https://www.wikidata.org/wiki/Q4650799","display_name":"Audio signal","level":3,"score":0.6685121655464172},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6612846851348877},{"id":"https://openalex.org/C49937458","wikidata":"https://www.wikidata.org/wiki/Q2599292","display_name":"Probabilistic logic","level":2,"score":0.6573633551597595},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.5727869272232056},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5487299561500549},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5240324139595032},{"id":"https://openalex.org/C2776864781","wikidata":"https://www.wikidata.org/wiki/Q52617913","display_name":"Source separation","level":2,"score":0.48952969908714294},{"id":"https://openalex.org/C127220857","wikidata":"https://www.wikidata.org/wiki/Q2719318","display_name":"Audio signal processing","level":4,"score":0.4298844039440155},{"id":"https://openalex.org/C13895895","wikidata":"https://www.wikidata.org/wiki/Q3270773","display_name":"Speech coding","level":2,"score":0.2207813262939453},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C158693339","wikidata":"https://www.wikidata.org/wiki/Q190524","display_name":"Eigenvalues and eigenvectors","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21437/interspeech.2011-496","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2011-496","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2011","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":9,"referenced_works":["https://openalex.org/W97505134","https://openalex.org/W185399533","https://openalex.org/W2104298926","https://openalex.org/W2106469967","https://openalex.org/W2117155634","https://openalex.org/W2150415460","https://openalex.org/W2168793898","https://openalex.org/W2963613758","https://openalex.org/W4285719527"],"related_works":["https://openalex.org/W2037504162","https://openalex.org/W2774154397","https://openalex.org/W2146544734","https://openalex.org/W2921513691","https://openalex.org/W2156699640","https://openalex.org/W2098101267","https://openalex.org/W1979654135","https://openalex.org/W2156181515","https://openalex.org/W1984255382","https://openalex.org/W2576645943"],"abstract_inverted_index":{"NMF":[0,86,145],"(Non-negative":[1],"Matrix":[2],"Factorization)":[3],"has":[4,106],"been":[5],"one":[6],"of":[7,28,80,121,143],"the":[8,54,58,85,117,119,135],"most":[9],"useful":[10],"techniques":[11],"for":[12,32,57],"audio":[13],"signal":[14,81,154],"analysis":[15,82],"in":[16,23,40],"recent":[17],"years.":[18],"In":[19,72,90],"particular,":[20],"supervised":[21,144],"NMF,":[22],"which":[24],"a":[25,34,65,77,111,127,141],"large":[26],"number":[27],"samples":[29,56],"is":[30,36,61,94,124,138],"used":[31],"analyzing":[33],"signal,":[35],"garnering":[37],"much":[38],"attention":[39],"sound":[41],"source":[42,156],"separation":[43],"or":[44,103],"noise":[45],"reduction":[46],"research.":[47],"However,":[48],"because":[49],"such":[50],"methods":[51],"require":[52],"all":[53],"possible":[55],"analysis,":[59,155],"it":[60,93],"hard":[62],"to":[63],"build":[64],"practical":[66],"system":[67],"based":[68,129],"on":[69,130],"this":[70,73,91],"method.":[71],"paper,":[74],"we":[75],"propose":[76],"novel":[78],"method":[79],"that":[83,96],"combines":[84],"and":[87,146],"probabilistic":[88,112,161],"approaches.":[89],"approach,":[92],"assumed":[95],"each":[97,122],"audio-source":[98],"category":[99,123],"(such":[100],"as":[101],"phonemes":[102],"musical":[104],"instruments)":[105],"an":[107],"environment-invariant":[108],"feature,":[109],"called":[110],"spectrum":[113,137,162],"envelope":[114],"(PSE).":[115],"At":[116],"start,":[118],"PSE":[120],"learned":[125],"using":[126,140],"technique":[128],"Gaussian":[131,164],"Process":[132],"Regression.":[133],"Then,":[134],"observed":[136],"analyzed":[139],"combination":[142],"Genetic":[147],"Algorithm":[148],"with":[149],"pre-trained":[150],"PSEs.":[151],"Index":[152],"Terms:":[153],"separation,":[157],"non-negative":[158],"matrix":[159],"factorization,":[160],"envelope,":[163],"process,":[165],"genetic":[166],"algorithm":[167]},"counts_by_year":[{"year":2014,"cited_by_count":1}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}