{"id":"https://openalex.org/W2125052510","doi":"https://doi.org/10.1109/icassp.2013.6637754","title":"N-gram extension for bag-of-audio-words","display_name":"N-gram extension for bag-of-audio-words","publication_year":2013,"publication_date":"2013-05-01","ids":{"openalex":"https://openalex.org/W2125052510","doi":"https://doi.org/10.1109/icassp.2013.6637754","mag":"2125052510"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2013.6637754","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2013.6637754","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2013 IEEE International Conference on Acoustics, Speech and Signal Processing","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/A5045567366","display_name":"Stephanie Pancoast","orcid":null},"institutions":[{"id":"https://openalex.org/I4210099336","display_name":"Menlo School","ror":"https://ror.org/01240pn49","country_code":"US","type":"education","lineage":["https://openalex.org/I4210099336"]},{"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":true,"raw_author_name":"Stephanie Pancoast","raw_affiliation_strings":["SRI International, Menlo Park, CA, US","Speech Technol. & Res. Lab., SRI Int., Menlo Park, CA, USA"],"affiliations":[{"raw_affiliation_string":"SRI International, Menlo Park, CA, US","institution_ids":["https://openalex.org/I1298353152","https://openalex.org/I4210099336"]},{"raw_affiliation_string":"Speech Technol. & Res. Lab., SRI Int., Menlo Park, CA, USA","institution_ids":["https://openalex.org/I1298353152","https://openalex.org/I4210099336"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5076998541","display_name":"Murat Akbacak","orcid":null},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Murat Akbacak","raw_affiliation_strings":["Microsoft, Sunnyvale, CA, USA","Microsoft, Sunnyvale, CA, USA#TAB#"],"affiliations":[{"raw_affiliation_string":"Microsoft, Sunnyvale, CA, USA","institution_ids":["https://openalex.org/I1290206253"]},{"raw_affiliation_string":"Microsoft, Sunnyvale, CA, USA#TAB#","institution_ids":["https://openalex.org/I1290206253"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5045567366"],"corresponding_institution_ids":["https://openalex.org/I1298353152","https://openalex.org/I4210099336"],"apc_list":null,"apc_paid":null,"fwci":1.9235,"has_fulltext":false,"cited_by_count":7,"citation_normalized_percentile":{"value":0.88701342,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"778","last_page":"782"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12031","display_name":"Speech and dialogue systems","score":0.9970999956130981,"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"}},"topics":[{"id":"https://openalex.org/T12031","display_name":"Speech and dialogue systems","score":0.9970999956130981,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9965000152587891,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9927999973297119,"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/extension","display_name":"Extension (predicate logic)","score":0.7175902724266052},{"id":"https://openalex.org/keywords/n-gram","display_name":"n-gram","score":0.707973837852478},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6127620935440063},{"id":"https://openalex.org/keywords/gram","display_name":"Gram","score":0.5551493167877197},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4483081102371216},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.1370590627193451}],"concepts":[{"id":"https://openalex.org/C2778029271","wikidata":"https://www.wikidata.org/wiki/Q5421931","display_name":"Extension (predicate logic)","level":2,"score":0.7175902724266052},{"id":"https://openalex.org/C117884012","wikidata":"https://www.wikidata.org/wiki/Q94489","display_name":"n-gram","level":3,"score":0.707973837852478},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6127620935440063},{"id":"https://openalex.org/C161369605","wikidata":"https://www.wikidata.org/wiki/Q41803","display_name":"Gram","level":3,"score":0.5551493167877197},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4483081102371216},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.1370590627193451},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.0},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.0},{"id":"https://openalex.org/C523546767","wikidata":"https://www.wikidata.org/wiki/Q10876","display_name":"Bacteria","level":2,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp.2013.6637754","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2013.6637754","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2013 IEEE International Conference on Acoustics, Speech and Signal Processing","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.47999998927116394,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320306116","display_name":"U.S. Department of the Interior","ror":"https://ror.org/03v0pmy70"},{"id":"https://openalex.org/F4320333452","display_name":"Interior Business Center","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":10,"referenced_works":["https://openalex.org/W1530378878","https://openalex.org/W1976610042","https://openalex.org/W2010486494","https://openalex.org/W2027875450","https://openalex.org/W2036718463","https://openalex.org/W2158149960","https://openalex.org/W2274583232","https://openalex.org/W2408491073","https://openalex.org/W4285719527","https://openalex.org/W6683374986"],"related_works":["https://openalex.org/W2906970013","https://openalex.org/W3126081632","https://openalex.org/W2625039379","https://openalex.org/W2088254117","https://openalex.org/W4254593385","https://openalex.org/W2790582133","https://openalex.org/W1901380241","https://openalex.org/W311963822","https://openalex.org/W2789473152","https://openalex.org/W3132255358"],"abstract_inverted_index":{"Bag-of-audio-words":[0],"is":[1,28,35,72],"one":[2],"of":[3,24,70,84,101],"the":[4,25,48,68,75,82,85,98,117],"most":[5],"frequently":[6],"used":[7],"methods":[8],"for":[9],"incorporating":[10],"an":[11],"audio":[12,52,60],"component":[13],"into":[14],"multimedia":[15,118],"event":[16,119],"detection":[17,120],"and":[18,110],"related":[19],"tasks.":[20],"A":[21],"main":[22],"criticism":[23],"method,":[26],"however,":[27],"that":[29],"it":[30],"ignores":[31],"context.":[32],"Each":[33],"\u201cword\u201d":[34],"considered":[36],"in":[37],"isolation,":[38],"ignoring":[39],"its":[40,51],"neighbors.":[41],"We":[42,77],"address":[43],"this":[44,93],"issue":[45],"by":[46,50,64,74],"representing":[47],"document":[49],"word":[53],"N-grams.":[54],"Unlike":[55],"words":[56,61],"from":[57],"natural":[58],"language,":[59],"are":[62],"generated":[63],"clustering":[65],"algorithms":[66],"where":[67],"number":[69],"clusters":[71],"specified":[73],"researcher.":[76],"therefore":[78],"also":[79],"explore":[80],"how":[81],"performance":[83],"N-gram":[86],"representation":[87],"varies":[88],"with":[89],"codebook":[90],"size.":[91],"With":[92],"enhanced":[94],"representation,":[95],"we":[96],"find":[97],"average":[99],"probability":[100],"miss":[102],"noticeably":[103],"decreases":[104],"when":[105],"evaluated":[106],"on":[107,116],"TRECVID":[108],"2011":[109],"2012":[111],"datasets,":[112],"indicating":[113],"clear":[114],"improvements":[115],"task.":[121]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2021,"cited_by_count":1},{"year":2016,"cited_by_count":2},{"year":2015,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}