{"id":"https://openalex.org/W20241248","doi":null,"title":"Vector-based Representation and Clustering of Audio Using Onomatopoeia Words","display_name":"Vector-based Representation and Clustering of Audio Using Onomatopoeia Words","publication_year":2006,"publication_date":"2006-01-01","ids":{"openalex":"https://openalex.org/W20241248","mag":"20241248"},"language":"en","primary_location":{"id":"pmh:oai:CiteSeerX.psu:10.1.1.333.3560","doi":null,"is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.333.3560","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"https://www.aaai.org/Papers/Symposia/Fall/2006/FS-06-01/FS06-01-012.pdf","raw_type":"text"},"volume":null,"type":"article","is_traditional":true,"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/A5113697636","display_name":"Shiva Sundaram","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I1174212","display_name":"University of Southern California","ror":"https://ror.org/03taz7m60","country_code":"US","type":"education","lineage":["https://openalex.org/I1174212"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Shiva Sundaram","raw_affiliation_strings":["University of Southern California"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Southern California","institution_ids":["https://openalex.org/I1174212"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5010028928","display_name":"Shrikanth Shri Narayanan","orcid":"https://orcid.org/0000-0002-1052-6204","observed_orcids":["https://orcid.org/0000-0002-1052-6204"]},"institutions":[{"id":"https://openalex.org/I1174212","display_name":"University of Southern California","ror":"https://ror.org/03taz7m60","country_code":"US","type":"education","lineage":["https://openalex.org/I1174212"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Shrikanth Narayanan","raw_affiliation_strings":["University of Southern California"],"raw_orcid":"https://orcid.org/0000-0002-1052-6204","affiliations":[{"raw_affiliation_string":"University of Southern California","institution_ids":["https://openalex.org/I1174212"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I1174212"],"apc_list":null,"apc_paid":null,"fwci":0.4094,"has_fulltext":false,"cited_by_count":16,"citation_normalized_percentile":{"value":0.71021644,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":87,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"55","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":0.9984999895095825,"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":0.9984999895095825,"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":0.0003000000142492354,"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"}},{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.0003000000142492354,"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/onomatopoeia","display_name":"onomatopoeia","score":0.9110000133514404},{"id":"https://openalex.org/keywords/sound-effects","display_name":"sound effects","score":0.7129999995231628},{"id":"https://openalex.org/keywords/audio-clustering","display_name":"audio clustering","score":0.8040000200271606},{"id":"https://openalex.org/keywords/distance-metrics","display_name":"distance measures","score":0.7630000114440918},{"id":"https://openalex.org/keywords/acoustic-perception","display_name":"acoustic perception","score":0.39500001072883606},{"id":"https://openalex.org/keywords/audio-description","display_name":"audio description","score":0.47099998593330383},{"id":"https://openalex.org/keywords/scene-understanding","display_name":"scene understanding","score":0.41499999165534973}],"concepts":[{"id":"https://openalex.org/C22432085","wikidata":"https://www.wikidata.org/wiki/Q170239","display_name":"Onomatopoeia","level":2,"score":0.9877159595489502},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6648539900779724},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.59477698802948},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5442694425582886},{"id":"https://openalex.org/C18020764","wikidata":"https://www.wikidata.org/wiki/Q2475268","display_name":"Sound symbolism","level":2,"score":0.5365313291549683},{"id":"https://openalex.org/C136197465","wikidata":"https://www.wikidata.org/wiki/Q1729295","display_name":"Variety (cybernetics)","level":2,"score":0.5241634845733643},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5223571062088013},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.4414738416671753},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4298582077026367},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.24062520265579224},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:CiteSeerX.psu:10.1.1.333.3560","doi":null,"is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.333.3560","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"https://www.aaai.org/Papers/Symposia/Fall/2006/FS-06-01/FS06-01-012.pdf","raw_type":"text"},{"id":"mag:20241248","doi":null,"is_oa":false,"landing_page_url":"https://www.aaai.org/Papers/Symposia/Fall/2006/FS-06-01/FS06-01-012.pdf","pdf_url":null,"source":{"id":"https://openalex.org/S4306420577","display_name":"National Conference on Artificial Intelligence","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":"National Conference on Artificial Intelligence","raw_type":null}],"best_oa_location":null,"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":9,"referenced_works":["https://openalex.org/W1499900670","https://openalex.org/W1552898570","https://openalex.org/W2038721957","https://openalex.org/W2107617395","https://openalex.org/W2131981197","https://openalex.org/W2144345993","https://openalex.org/W2146855196","https://openalex.org/W2168441989","https://openalex.org/W2799061466"],"related_works":["https://openalex.org/W2107615347","https://openalex.org/W2137337354","https://openalex.org/W310490195","https://openalex.org/W2287605030","https://openalex.org/W254077235","https://openalex.org/W2788310755","https://openalex.org/W2525342958","https://openalex.org/W2146078527","https://openalex.org/W2131709365","https://openalex.org/W3005733147"],"abstract_inverted_index":{"We":[0,49,113,132],"present":[1],"results":[2],"on":[3,9],"organization":[4],"of":[5,19,28,44,54,62,107,129,137,146,157],"audio":[6,63,90,130],"data":[7,91],"based":[8],"their":[10,32],"descriptions":[11,122,145],"using":[12],"onomatopoeia":[13,71],"words.":[14,72],"Onomatopoeia":[15],"words":[16],"are":[17,123],"imitative":[18],"sounds":[20],"that":[21,115,134],"directly":[22],"describe":[23],"and":[24,78,100],"represent":[25,126],"different":[26],"types":[27],"sound":[29,43,67],"sources":[30],"through":[31],"perceived":[33,127],"properties.":[34,112],"For":[35],"instance,":[36],"the":[37,42,89,93,97,101,104,120,158],"word":[38],"pop":[39],"aptly":[40],"describes":[41],"opening":[45],"a":[46,60,66,79,149],"champagne":[47],"bottle.":[48],"first":[50],"establish":[51],"this":[52,135],"type":[53],"audio-to-word":[55,102],"relationship":[56],"by":[57,151],"manually":[58],"tagging":[59],"variety":[61],"clips":[64,108],"from":[65],"effects":[68],"library":[69],"with":[70],"Using":[73],"principal":[74],"component":[75],"analysis":[76],"(PCA)":[77],"newly":[80],"proposed":[81],"distance":[82,98],"metric":[83,99],"for":[84],"word-level":[85],"clustering,":[86],"we":[87],"cluster":[88],"representing":[92],"clips.":[94],"Due":[95],"to":[96,125],"relationship,":[103],"resulting":[105],"clusters":[106],"have":[109],"similar":[110],"acoustic":[111,159],"found":[114],"as":[116],"language":[117],"level":[118],"units,":[119],"onomatopoeic":[121],"able":[124],"properties":[128],"signals.":[131],"believe":[133],"form":[136],"description":[138],"can":[139],"be":[140],"useful":[141],"in":[142,148],"relating":[143],"higher-level":[144],"events":[147],"scene":[150],"providing":[152],"an":[153],"intermediate":[154],"perceptual":[155],"understanding":[156],"event.":[160]},"counts_by_year":[{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":1},{"year":2018,"cited_by_count":1},{"year":2017,"cited_by_count":1},{"year":2016,"cited_by_count":1},{"year":2015,"cited_by_count":3},{"year":2014,"cited_by_count":2},{"year":2013,"cited_by_count":1}],"updated_date":"2026-09-26T08:19:03.415552","created_date":"2016-06-24T00:00:00"}