{"id":"https://openalex.org/W2113640091","doi":"https://doi.org/10.1109/icassp.2012.6287927","title":"How to put it into words - using random forests to extract symbol level descriptions from audio content for concept detection","display_name":"How to put it into words - using random forests to extract symbol level descriptions from audio content for concept detection","publication_year":2012,"publication_date":"2012-03-01","ids":{"openalex":"https://openalex.org/W2113640091","doi":"https://doi.org/10.1109/icassp.2012.6287927","mag":"2113640091"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2012.6287927","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2012.6287927","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2012 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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/A5076474156","display_name":"Po-Sen Huang","orcid":"https://orcid.org/0000-0003-1470-0991"},"institutions":[{"id":"https://openalex.org/I157725225","display_name":"University of Illinois Urbana-Champaign","ror":"https://ror.org/047426m28","country_code":"US","type":"education","lineage":["https://openalex.org/I157725225"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Po-Sen Huang","raw_affiliation_strings":["Beckman Institute, ECE Department, University of Illinois, Urbana Champaign, Urbana, IL, USA","Beckman Institute, ECE Department, University of Illinois at Urbana-Champaign, 61801, USA"],"affiliations":[{"raw_affiliation_string":"Beckman Institute, ECE Department, University of Illinois, Urbana Champaign, Urbana, IL, USA","institution_ids":["https://openalex.org/I157725225"]},{"raw_affiliation_string":"Beckman Institute, ECE Department, University of Illinois at Urbana-Champaign, 61801, USA","institution_ids":["https://openalex.org/I157725225"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5001835623","display_name":"Robert Mertens","orcid":"https://orcid.org/0000-0002-9442-4140"},"institutions":[{"id":"https://openalex.org/I1297971548","display_name":"International Computer Science Institute","ror":"https://ror.org/01ewh7m12","country_code":"US","type":"nonprofit","lineage":["https://openalex.org/I1297971548"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Robert Mertens","raw_affiliation_strings":["International Computer Science Institute, Berkeley, CA, USA","International Computer Science Institute, 1947 Center Street Suite 600, Berkeley, CA 94704, USA"],"affiliations":[{"raw_affiliation_string":"International Computer Science Institute, Berkeley, CA, USA","institution_ids":["https://openalex.org/I1297971548"]},{"raw_affiliation_string":"International Computer Science Institute, 1947 Center Street Suite 600, Berkeley, CA 94704, USA","institution_ids":["https://openalex.org/I1297971548"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5028124265","display_name":"Ajay Divakaran","orcid":"https://orcid.org/0000-0003-0371-5346"},"institutions":[{"id":"https://openalex.org/I1298353152","display_name":"SRI International","ror":"https://ror.org/05s570m15","country_code":"US","type":"nonprofit","lineage":["https://openalex.org/I1298353152"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ajay Divakaran","raw_affiliation_strings":["SRI International Sarnoff, Princeton, NJ, USA","SRI International Sarnoff, 201 Washington Road, Princeton, NJ 08540, USA"],"affiliations":[{"raw_affiliation_string":"SRI International Sarnoff, Princeton, NJ, USA","institution_ids":["https://openalex.org/I1298353152"]},{"raw_affiliation_string":"SRI International Sarnoff, 201 Washington Road, Princeton, NJ 08540, USA","institution_ids":["https://openalex.org/I1298353152"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5062323483","display_name":"Gerald Friedland","orcid":"https://orcid.org/0000-0002-9400-6539"},"institutions":[{"id":"https://openalex.org/I1297971548","display_name":"International Computer Science Institute","ror":"https://ror.org/01ewh7m12","country_code":"US","type":"nonprofit","lineage":["https://openalex.org/I1297971548"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Gerald Friedland","raw_affiliation_strings":["International Computer Science Institute, Berkeley, CA, USA","International Computer Science Institute, 1947 Center Street Suite 600, Berkeley, CA 94704, USA"],"affiliations":[{"raw_affiliation_string":"International Computer Science Institute, Berkeley, CA, USA","institution_ids":["https://openalex.org/I1297971548"]},{"raw_affiliation_string":"International Computer Science Institute, 1947 Center Street Suite 600, Berkeley, CA 94704, USA","institution_ids":["https://openalex.org/I1297971548"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5004778663","display_name":"Mark Hasegawa\u2010Johnson","orcid":"https://orcid.org/0000-0002-5631-2893"},"institutions":[{"id":"https://openalex.org/I157725225","display_name":"University of Illinois Urbana-Champaign","ror":"https://ror.org/047426m28","country_code":"US","type":"education","lineage":["https://openalex.org/I157725225"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Mark Hasegawa-Johnson","raw_affiliation_strings":["Beckman Institute, ECE Department, University of Illinois, Urbana Champaign, Urbana, IL, USA","Beckman Institute, ECE Department, University of Illinois at Urbana-Champaign, 61801, USA"],"affiliations":[{"raw_affiliation_string":"Beckman Institute, ECE Department, University of Illinois, Urbana Champaign, Urbana, IL, USA","institution_ids":["https://openalex.org/I157725225"]},{"raw_affiliation_string":"Beckman Institute, ECE Department, University of Illinois at Urbana-Champaign, 61801, USA","institution_ids":["https://openalex.org/I157725225"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5076474156"],"corresponding_institution_ids":["https://openalex.org/I157725225"],"apc_list":null,"apc_paid":null,"fwci":0.7432,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.75317455,"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":"505","last_page":"508"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"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"}},"topics":[{"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/T11439","display_name":"Video Analysis and Summarization","score":0.9958000183105469,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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":0.9919999837875366,"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/computer-science","display_name":"Computer science","score":0.8111745119094849},{"id":"https://openalex.org/keywords/discriminative-model","display_name":"Discriminative model","score":0.6946624517440796},{"id":"https://openalex.org/keywords/random-forest","display_name":"Random forest","score":0.6745087504386902},{"id":"https://openalex.org/keywords/weighting","display_name":"Weighting","score":0.647179126739502},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5480437874794006},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5437101721763611},{"id":"https://openalex.org/keywords/class","display_name":"Class (philosophy)","score":0.535331130027771},{"id":"https://openalex.org/keywords/vocabulary","display_name":"Vocabulary","score":0.5284941792488098},{"id":"https://openalex.org/keywords/scheme","display_name":"Scheme (mathematics)","score":0.5117611885070801},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.48929306864738464},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.454630583524704},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4368263781070709},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.43405574560165405},{"id":"https://openalex.org/keywords/sort","display_name":"sort","score":0.43138980865478516},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.37508440017700195},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.373094379901886},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3723837435245514},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.23986870050430298},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.10818406939506531}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8111745119094849},{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.6946624517440796},{"id":"https://openalex.org/C169258074","wikidata":"https://www.wikidata.org/wiki/Q245748","display_name":"Random forest","level":2,"score":0.6745087504386902},{"id":"https://openalex.org/C183115368","wikidata":"https://www.wikidata.org/wiki/Q856577","display_name":"Weighting","level":2,"score":0.647179126739502},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5480437874794006},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5437101721763611},{"id":"https://openalex.org/C2777212361","wikidata":"https://www.wikidata.org/wiki/Q5127848","display_name":"Class (philosophy)","level":2,"score":0.535331130027771},{"id":"https://openalex.org/C2777601683","wikidata":"https://www.wikidata.org/wiki/Q6499736","display_name":"Vocabulary","level":2,"score":0.5284941792488098},{"id":"https://openalex.org/C77618280","wikidata":"https://www.wikidata.org/wiki/Q1155772","display_name":"Scheme (mathematics)","level":2,"score":0.5117611885070801},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.48929306864738464},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.454630583524704},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4368263781070709},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.43405574560165405},{"id":"https://openalex.org/C88548561","wikidata":"https://www.wikidata.org/wiki/Q347599","display_name":"sort","level":2,"score":0.43138980865478516},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.37508440017700195},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.373094379901886},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3723837435245514},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.23986870050430298},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.10818406939506531},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0},{"id":"https://openalex.org/C126838900","wikidata":"https://www.wikidata.org/wiki/Q77604","display_name":"Radiology","level":1,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"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/C71924100","wikidata":"https://www.wikidata.org/wiki/Q11190","display_name":"Medicine","level":0,"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/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","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/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/icassp.2012.6287927","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2012.6287927","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2012 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.294.4515","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.294.4515","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.ifp.illinois.edu/speech/pubs/2012/huang12icassp1.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.799.7409","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.799.7409","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.icsi.berkeley.edu/pubs/speech/ICSI_howtoputitintowords12.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Reduced inequalities","score":0.6299999952316284,"id":"https://metadata.un.org/sdg/10"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":14,"referenced_works":["https://openalex.org/W1493036841","https://openalex.org/W1986482242","https://openalex.org/W2021833436","https://openalex.org/W2098553397","https://openalex.org/W2112306108","https://openalex.org/W2119577488","https://openalex.org/W2137117795","https://openalex.org/W2164882318","https://openalex.org/W2274583232","https://openalex.org/W2396707013","https://openalex.org/W2911964244","https://openalex.org/W4296262844","https://openalex.org/W6694369573","https://openalex.org/W6712239252"],"related_works":["https://openalex.org/W2180954594","https://openalex.org/W4389116644","https://openalex.org/W2153315159","https://openalex.org/W3103844505","https://openalex.org/W2052835778","https://openalex.org/W259157601","https://openalex.org/W4205463238","https://openalex.org/W2049003611","https://openalex.org/W2127804977","https://openalex.org/W2108418243"],"abstract_inverted_index":{"This":[0],"paper":[1],"presents":[2],"a":[3,37,71],"system":[4],"that":[5,20],"uses":[6],"symbolic":[7],"representations":[8],"of":[9,17,28,36,40,98,107,132],"audio":[10,18,33,41,53,78],"concepts":[11],"as":[12,88],"words":[13,54],"for":[14,59,66],"the":[15,26,29,50,91,99,103,108,125,129,133],"descriptions":[16],"tracks,":[19],"enable":[21],"it":[22],"to":[23,46,89],"go":[24],"beyond":[25],"state":[27],"art,":[30],"which":[31],"is":[32],"event":[34],"classification":[35,48,97],"small":[38],"number":[39],"classes":[42],"in":[43,49],"constrained":[44],"settings,":[45],"large-scale":[47],"wild.":[51],"These":[52],"might":[55],"be":[56],"less":[57],"meaningful":[58],"an":[60,77],"annotator":[61],"but":[62],"they":[63],"are":[64],"descriptive":[65],"computer":[67],"algorithms.":[68],"We":[69],"devise":[70],"random-forest":[72],"vocabulary":[73],"learning":[74],"method":[75],"with":[76,102,116],"word":[79],"weighting":[80],"scheme":[81],"based":[82],"on":[83,124],"TF-IDF":[84],"and":[85,94,128],"TD-IDD,":[86],"so":[87],"combine":[90],"computational":[92],"simplicity":[93],"accurate":[95],"multi-class":[96],"random":[100,113],"forest":[101,114],"data-driven":[104],"discriminative":[105],"power":[106],"TF-IDF/TD-IDD":[109],"methods.":[110],"The":[111],"proposed":[112],"clustering":[115],"text-retrieval":[117],"methods":[118,123],"significantly":[119],"outperforms":[120],"two":[121],"state-of-the-art":[122],"dry-run":[126],"set":[127,131],"full":[130],"TRECVID":[134],"MED":[135],"2010":[136],"dataset.":[137]},"counts_by_year":[{"year":2023,"cited_by_count":1},{"year":2013,"cited_by_count":2},{"year":2012,"cited_by_count":1}],"updated_date":"2026-04-05T17:49:38.594831","created_date":"2025-10-10T00:00:00"}