{"id":"https://openalex.org/W1974617697","doi":"https://doi.org/10.1109/aspaa.2011.6082335","title":"Learning contextual relevance of audio segments using discriminative models over AUD sequences","display_name":"Learning contextual relevance of audio segments using discriminative models over AUD sequences","publication_year":2011,"publication_date":"2011-10-01","ids":{"openalex":"https://openalex.org/W1974617697","doi":"https://doi.org/10.1109/aspaa.2011.6082335","mag":"1974617697"},"language":"en","primary_location":{"id":"doi:10.1109/aspaa.2011.6082335","is_oa":false,"landing_page_url":"https://doi.org/10.1109/aspaa.2011.6082335","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2011 IEEE Workshop on Applications of Signal Processing to Audio and Acoustics (WASPAA)","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/A5083515346","display_name":"Sourish Chaudhuri","orcid":null},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Sourish Chaudhuri","raw_affiliation_strings":["Language Technologies Institute, Carnegie Mellon University, Pittsburgh, PA, USA","Language Technologies Institute, Carnegie Mellon University, Pittsburgh, PA, 15213, USA"],"affiliations":[{"raw_affiliation_string":"Language Technologies Institute, Carnegie Mellon University, Pittsburgh, PA, USA","institution_ids":["https://openalex.org/I74973139"]},{"raw_affiliation_string":"Language Technologies Institute, Carnegie Mellon University, Pittsburgh, PA, 15213, USA","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5113017615","display_name":"Bhiksha Raj","orcid":null},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Bhiksha Raj","raw_affiliation_strings":["Language Technologies Institute, Carnegie Mellon University, Pittsburgh, PA, USA","Language Technologies Institute, Carnegie Mellon University, Pittsburgh, PA, 15213, USA"],"affiliations":[{"raw_affiliation_string":"Language Technologies Institute, Carnegie Mellon University, Pittsburgh, PA, USA","institution_ids":["https://openalex.org/I74973139"]},{"raw_affiliation_string":"Language Technologies Institute, Carnegie Mellon University, Pittsburgh, PA, 15213, USA","institution_ids":["https://openalex.org/I74973139"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5083515346"],"corresponding_institution_ids":["https://openalex.org/I74973139"],"apc_list":null,"apc_paid":null,"fwci":0.6125,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.64102735,"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":"197","last_page":"200"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":1.0,"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":1.0,"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":0.9997000098228455,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9933000206947327,"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/discriminative-model","display_name":"Discriminative model","score":0.8889117240905762},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8502691388130188},{"id":"https://openalex.org/keywords/relevance","display_name":"Relevance (law)","score":0.7020421624183655},{"id":"https://openalex.org/keywords/margin","display_name":"Margin (machine learning)","score":0.6804109811782837},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.6411913633346558},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5147483348846436},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.47398701310157776},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.44359079003334045},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3330842852592468},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.30764639377593994},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.09576460719108582}],"concepts":[{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.8889117240905762},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8502691388130188},{"id":"https://openalex.org/C158154518","wikidata":"https://www.wikidata.org/wiki/Q7310970","display_name":"Relevance (law)","level":2,"score":0.7020421624183655},{"id":"https://openalex.org/C774472","wikidata":"https://www.wikidata.org/wiki/Q6760393","display_name":"Margin (machine learning)","level":2,"score":0.6804109811782837},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.6411913633346558},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5147483348846436},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.47398701310157776},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.44359079003334045},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3330842852592468},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.30764639377593994},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.09576460719108582},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/aspaa.2011.6082335","is_oa":false,"landing_page_url":"https://doi.org/10.1109/aspaa.2011.6082335","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2011 IEEE Workshop on Applications of Signal Processing to Audio and Acoustics (WASPAA)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/10","score":0.7599999904632568,"display_name":"Reduced inequalities"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":12,"referenced_works":["https://openalex.org/W1498416817","https://openalex.org/W2036931824","https://openalex.org/W2103853614","https://openalex.org/W2112861900","https://openalex.org/W2118119027","https://openalex.org/W2124953143","https://openalex.org/W2169423212","https://openalex.org/W2396707013","https://openalex.org/W4285719527","https://openalex.org/W6629790064","https://openalex.org/W6678664012","https://openalex.org/W6684549341"],"related_works":["https://openalex.org/W2965546495","https://openalex.org/W4389116644","https://openalex.org/W2153315159","https://openalex.org/W3103844505","https://openalex.org/W259157601","https://openalex.org/W4205463238","https://openalex.org/W2761785940","https://openalex.org/W2110523656","https://openalex.org/W1482209366","https://openalex.org/W2521627374"],"abstract_inverted_index":{"Effective":[0],"retrieval":[1],"of":[2,11,20,48,60,89,99],"multimodal":[3],"data":[4,84],"involves":[5],"performing":[6],"accurate":[7],"segmentation":[8],"and":[9,22,105,110],"analysis":[10,69],"such":[12,43,53,65,114],"data.":[13],"With":[14],"easy":[15],"access":[16],"to":[17,57,85,108],"a":[18,76],"number":[19],"audio":[21,91],"video":[23],"sharing":[24],"platforms":[25],"online,":[26],"user-generated":[27],"content":[28,44],"with":[29,42],"considerably":[30],"less":[31],"than":[32],"ideal":[33],"recording":[34],"conditions":[35],"has":[36],"increased":[37],"rapidly.":[38],"One":[39],"major":[40],"issue":[41],"is":[45],"the":[46,58,90,97],"presence":[47,59],"semantically":[49],"irrelevant":[50],"segments":[51,115],"in":[52,64],"recordings.":[54],"This":[55],"leads":[56],"considerable":[61],"contextual":[62],"noise":[63],"recordings":[66],"that":[67,81,96],"makes":[68],"difficult.":[70],"In":[71],"this":[72],"paper,":[73],"we":[74],"present":[75],"discriminative":[77],"large-margin":[78],"based":[79],"approach":[80],"uses":[82],"annotated":[83],"understand":[86],"which":[87],"parts":[88],"are":[92],"relevant":[93],"(while":[94],"noting":[95],"notion":[98],"relevance":[100],"could":[101],"be":[102],"extremely":[103],"subjective":[104],"potentially":[106],"challenging":[107],"define),":[109],"can":[111],"automatically":[112],"extract":[113],"from":[116],"new":[117],"audio.":[118]},"counts_by_year":[{"year":2017,"cited_by_count":1},{"year":2012,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}