{"id":"https://openalex.org/W14086571","doi":null,"title":"Auditory segmentation based on event detection.","display_name":"Auditory segmentation based on event detection.","publication_year":2004,"publication_date":"2004-01-01","ids":{"openalex":"https://openalex.org/W14086571","mag":"14086571"},"language":"en","primary_location":{"id":"pmh:oai:CiteSeerX.psu:10.1.1.130.5372","doi":null,"is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.130.5372","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.cse.ohio-state.edu/~dwang/papers/Hu-Wang.sapa04.pdf","raw_type":"text"},"volume":null,"type":"article","indexed_in":[],"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/A5112457807","display_name":"Guoning Hu","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Guoning Hu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5051837453","display_name":"DeLiang Wang","orcid":"https://orcid.org/0000-0001-8195-6319","observed_orcids":["https://orcid.org/0000-0001-8195-6319"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"DeLiang Wang","raw_affiliation_strings":[],"raw_orcid":"https://orcid.org/0000-0001-8195-6319","affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.6988,"has_fulltext":false,"cited_by_count":7,"citation_normalized_percentile":{"value":0.86133371,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":88,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"62","last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.5307999849319458,"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":0.5307999849319458,"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":0.45829999446868896,"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":0.006800000090152025,"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/auditory-scene-analysis","display_name":"auditory scene analysis","score":0.9539999961853027},{"id":"https://openalex.org/keywords/event-detection","display_name":"event detection","score":0.8759999871253967},{"id":"https://openalex.org/keywords/multiscale-analysis","display_name":"multiscale analysis","score":0.9110000133514404},{"id":"https://openalex.org/keywords/scale-space-theory","display_name":"scale-space theory","score":0.9860000014305115},{"id":"https://openalex.org/keywords/speech-separation","display_name":"speech separation","score":0.5740000009536743},{"id":"https://openalex.org/keywords/unvoiced-speech","display_name":"unvoiced speech","score":0.7979999780654907},{"id":"https://openalex.org/keywords/source-segregation","display_name":"source segregation","score":0.367000013589859}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6537842750549316},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.5159407258033752},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.49075326323509216},{"id":"https://openalex.org/C2779662365","wikidata":"https://www.wikidata.org/wiki/Q5416694","display_name":"Event (particle physics)","level":2,"score":0.4556170105934143},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.34194979071617126},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.3344930410385132},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.32732826471328735},{"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}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:CiteSeerX.psu:10.1.1.130.5372","doi":null,"is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.130.5372","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.cse.ohio-state.edu/~dwang/papers/Hu-Wang.sapa04.pdf","raw_type":"text"},{"id":"mag:14086571","doi":null,"is_oa":false,"landing_page_url":"https://dblp.uni-trier.de/db/conf/interspeech/sapa2004.html#HuW04","pdf_url":null,"source":{"id":"https://openalex.org/S4393918409","display_name":"Interspeech (USB)","issn_l":"2308-457X","issn":["2308-457X"],"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":["jufo-1","norway-1"],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":"Conference of the International Speech Communication Association","raw_type":null}],"best_oa_location":null,"sustainable_development_goals":[],"sustainable_development_goals_aurora":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":10,"referenced_works":["https://openalex.org/W1536200267","https://openalex.org/W1575829986","https://openalex.org/W2013020033","https://openalex.org/W2044222806","https://openalex.org/W2075690349","https://openalex.org/W2097191389","https://openalex.org/W2145023731","https://openalex.org/W2147174722","https://openalex.org/W2149425615","https://openalex.org/W2150134853"],"related_works":["https://openalex.org/W7096869920","https://openalex.org/W2123157731","https://openalex.org/W2361003639","https://openalex.org/W2391095675","https://openalex.org/W4255513323","https://openalex.org/W2550493152","https://openalex.org/W2044222806","https://openalex.org/W10765870","https://openalex.org/W2391300577","https://openalex.org/W1940377967"],"abstract_inverted_index":{"Acoustic":[0],"signals":[1],"from":[2,56],"different":[3,33,125],"sources":[4],"in":[5,20],"a":[6,61,96],"natural":[7],"environment":[8],"form":[9],"an":[10,26,37,43],"auditory":[11,23,27,44,64,73],"scene.":[12],"Auditory":[13],"scene":[14,28,45],"analysis":[15],"(ASA)":[16],"is":[17,36,46,93,113],"the":[18,22],"process":[19],"which":[21,52],"system":[24,62,76],"segregates":[25],"into":[29,48,124],"streams":[30],"corresponding":[31,88],"to":[32],"sources.":[34],"Segmentation":[35],"important":[38],"stage":[39],"of":[40,51,72],"ASA":[41],"where":[42],"decomposed":[47],"segments,":[49],"each":[50],"contains":[53],"signal":[54],"mainly":[55],"one":[57],"source.":[58],"We":[59],"propose":[60],"for":[63],"segmentation":[65],"based":[66,99],"on":[67,100],"analyzing":[68],"onsets":[69,79,89],"and":[70,80,82,90,116,119],"offsets":[71],"events.":[74],"Our":[75],"first":[77],"detects":[78],"offsets,":[81],"then":[83],"generates":[84],"segments":[85],"by":[86],"matching":[87],"offsets.":[91],"This":[92],"achieved":[94],"through":[95],"multiscale":[97],"approach":[98],"scale-space":[101],"theory.":[102],"Systematic":[103],"evaluation":[104],"shows":[105],"that":[106],"much":[107],"target":[108,117],"speech,":[109,112],"including":[110],"unvoiced":[111],"correctly":[114],"segmented,":[115],"speech":[118],"interference":[120],"are":[121],"well":[122],"separated":[123],"segments.":[126],"1.":[127]},"counts_by_year":[{"year":2021,"cited_by_count":1},{"year":2015,"cited_by_count":1},{"year":2013,"cited_by_count":1}],"updated_date":"2026-10-31T12:09:11.096373","created_date":"2016-06-24T00:00:00"}