{"id":"https://openalex.org/W2221333906","doi":"https://doi.org/10.1109/eusipco.2015.7362844","title":"Audio phrases for audio event recognition","display_name":"Audio phrases for audio event recognition","publication_year":2015,"publication_date":"2015-08-01","ids":{"openalex":"https://openalex.org/W2221333906","doi":"https://doi.org/10.1109/eusipco.2015.7362844","mag":"2221333906"},"language":"en","primary_location":{"id":"doi:10.1109/eusipco.2015.7362844","is_oa":false,"landing_page_url":"https://doi.org/10.1109/eusipco.2015.7362844","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2015 23rd European Signal Processing Conference (EUSIPCO)","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/A5058452657","display_name":"Huy Phan","orcid":"https://orcid.org/0000-0003-4096-785X"},"institutions":[{"id":"https://openalex.org/I9341345","display_name":"University of L\u00fcbeck","ror":"https://ror.org/00t3r8h32","country_code":"DE","type":"education","lineage":["https://openalex.org/I9341345"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Huy Phan","raw_affiliation_strings":["Graduate School for Computing in Medicine and Life Sciences, University of L\u00fcbeck, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Graduate School for Computing in Medicine and Life Sciences, University of L\u00fcbeck, Germany","institution_ids":["https://openalex.org/I9341345"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5044379875","display_name":"Lars Hertel","orcid":null},"institutions":[{"id":"https://openalex.org/I9341345","display_name":"University of L\u00fcbeck","ror":"https://ror.org/00t3r8h32","country_code":"DE","type":"education","lineage":["https://openalex.org/I9341345"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Lars Hertel","raw_affiliation_strings":["Institute for Signal Processing, University of L\u00fcbeck, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute for Signal Processing, University of L\u00fcbeck, Germany","institution_ids":["https://openalex.org/I9341345"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5048584044","display_name":"Marco Maa\u00df","orcid":"https://orcid.org/0000-0001-7422-147X"},"institutions":[{"id":"https://openalex.org/I9341345","display_name":"University of L\u00fcbeck","ror":"https://ror.org/00t3r8h32","country_code":"DE","type":"education","lineage":["https://openalex.org/I9341345"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Marco Maass","raw_affiliation_strings":["Institute for Signal Processing, University of L\u00fcbeck, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute for Signal Processing, University of L\u00fcbeck, Germany","institution_ids":["https://openalex.org/I9341345"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5074089177","display_name":"Radoslaw Mazur","orcid":null},"institutions":[{"id":"https://openalex.org/I9341345","display_name":"University of L\u00fcbeck","ror":"https://ror.org/00t3r8h32","country_code":"DE","type":"education","lineage":["https://openalex.org/I9341345"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Radoslaw Mazur","raw_affiliation_strings":["Institute for Signal Processing, University of L\u00fcbeck, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute for Signal Processing, University of L\u00fcbeck, Germany","institution_ids":["https://openalex.org/I9341345"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5063948113","display_name":"Alfred Mertins","orcid":"https://orcid.org/0000-0001-5718-577X"},"institutions":[{"id":"https://openalex.org/I9341345","display_name":"University of L\u00fcbeck","ror":"https://ror.org/00t3r8h32","country_code":"DE","type":"education","lineage":["https://openalex.org/I9341345"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Alfred Mertins","raw_affiliation_strings":["Institute for Signal Processing, University of L\u00fcbeck, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute for Signal Processing, University of L\u00fcbeck, Germany","institution_ids":["https://openalex.org/I9341345"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":2.3197,"has_fulltext":false,"cited_by_count":9,"citation_normalized_percentile":{"value":0.89458853,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"2546","last_page":"2550"},"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":0.9983000159263611,"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":0.9973000288009644,"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/codebook","display_name":"Codebook","score":0.8087100982666016},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7949253916740417},{"id":"https://openalex.org/keywords/audio-mining","display_name":"Audio mining","score":0.70296311378479},{"id":"https://openalex.org/keywords/discriminative-model","display_name":"Discriminative model","score":0.6886904835700989},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.647589921951294},{"id":"https://openalex.org/keywords/audio-signal","display_name":"Audio signal","score":0.5969759225845337},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5657437443733215},{"id":"https://openalex.org/keywords/event","display_name":"Event (particle physics)","score":0.5292230248451233},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.5051329731941223},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.46928179264068604},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.46569618582725525},{"id":"https://openalex.org/keywords/audio-analyzer","display_name":"Audio analyzer","score":0.4307395815849304},{"id":"https://openalex.org/keywords/speech-coding","display_name":"Speech coding","score":0.4151776432991028},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.400146484375},{"id":"https://openalex.org/keywords/audio-signal-processing","display_name":"Audio signal processing","score":0.39861857891082764},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3928753733634949},{"id":"https://openalex.org/keywords/acoustic-model","display_name":"Acoustic model","score":0.327384352684021},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.19778817892074585},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.0652601420879364}],"concepts":[{"id":"https://openalex.org/C127759330","wikidata":"https://www.wikidata.org/wiki/Q637416","display_name":"Codebook","level":2,"score":0.8087100982666016},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7949253916740417},{"id":"https://openalex.org/C157968479","wikidata":"https://www.wikidata.org/wiki/Q3079876","display_name":"Audio mining","level":4,"score":0.70296311378479},{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.6886904835700989},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.647589921951294},{"id":"https://openalex.org/C64922751","wikidata":"https://www.wikidata.org/wiki/Q4650799","display_name":"Audio signal","level":3,"score":0.5969759225845337},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5657437443733215},{"id":"https://openalex.org/C2779662365","wikidata":"https://www.wikidata.org/wiki/Q5416694","display_name":"Event (particle physics)","level":2,"score":0.5292230248451233},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.5051329731941223},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.46928179264068604},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.46569618582725525},{"id":"https://openalex.org/C160372630","wikidata":"https://www.wikidata.org/wiki/Q4819855","display_name":"Audio analyzer","level":5,"score":0.4307395815849304},{"id":"https://openalex.org/C13895895","wikidata":"https://www.wikidata.org/wiki/Q3270773","display_name":"Speech coding","level":2,"score":0.4151776432991028},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.400146484375},{"id":"https://openalex.org/C127220857","wikidata":"https://www.wikidata.org/wiki/Q2719318","display_name":"Audio signal processing","level":4,"score":0.39861857891082764},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3928753733634949},{"id":"https://openalex.org/C155635449","wikidata":"https://www.wikidata.org/wiki/Q4674699","display_name":"Acoustic model","level":3,"score":0.327384352684021},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.19778817892074585},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0652601420879364},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"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/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"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":"doi:10.1109/eusipco.2015.7362844","is_oa":false,"landing_page_url":"https://doi.org/10.1109/eusipco.2015.7362844","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2015 23rd European Signal Processing Conference (EUSIPCO)","raw_type":"proceedings-article"},{"id":"pmh:oai:kar.kent.ac.uk:72687","is_oa":false,"landing_page_url":"https://doi.org/10.1109/EUSIPCO.2015.7362844>)","pdf_url":null,"source":{"id":"https://openalex.org/S4377196264","display_name":"Kent Academic Repository (University of Kent)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I20581793","host_organization_name":"University of Kent","host_organization_lineage":["https://openalex.org/I20581793"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":null,"raw_type":"PeerReviewed"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/10","score":0.699999988079071,"display_name":"Reduced inequalities"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":28,"referenced_works":["https://openalex.org/W1590295743","https://openalex.org/W1964442016","https://openalex.org/W1970578576","https://openalex.org/W2005122913","https://openalex.org/W2009504845","https://openalex.org/W2046972719","https://openalex.org/W2049705550","https://openalex.org/W2058929792","https://openalex.org/W2089390156","https://openalex.org/W2092216166","https://openalex.org/W2104170135","https://openalex.org/W2111904301","https://openalex.org/W2125052510","https://openalex.org/W2129634963","https://openalex.org/W2130640900","https://openalex.org/W2144269124","https://openalex.org/W2157821739","https://openalex.org/W2162915993","https://openalex.org/W2165880886","https://openalex.org/W2186582651","https://openalex.org/W2207353249","https://openalex.org/W2396889081","https://openalex.org/W2497513162","https://openalex.org/W2911964244","https://openalex.org/W6675679986","https://openalex.org/W6676794877","https://openalex.org/W6688243554","https://openalex.org/W6712405843"],"related_works":["https://openalex.org/W2098934641","https://openalex.org/W2157598242","https://openalex.org/W27741130","https://openalex.org/W1969715806","https://openalex.org/W2020966186","https://openalex.org/W2784103281","https://openalex.org/W1620668332","https://openalex.org/W2175408845","https://openalex.org/W1479881079","https://openalex.org/W1503775422"],"abstract_inverted_index":{"The":[0,32],"bag-of-audio-words":[1],"approach":[2,97],"has":[3],"been":[4],"widely":[5],"used":[6],"for":[7],"audio":[8,19,61,68,72,84],"event":[9],"recognition.":[10],"In":[11],"these":[12],"models,":[13],"a":[14,24,29,100,104],"local":[15],"feature":[16],"of":[17,39,60,66,111],"an":[18,53,95],"signal":[20,33],"is":[21,34],"matched":[22,41],"to":[23,28,77,98,107],"code":[25,42],"word":[26],"according":[27],"learned":[30],"codebook.":[31],"then":[35],"represented":[36],"by":[37],"frequencies":[38],"the":[40,45,58,79,82,116,121,132,136,140],"words":[43,85],"on":[44,57,115,139],"whole":[46],"signal.":[47],"We":[48],"present":[49],"in":[50,103],"this":[51],"paper":[52],"improved":[54],"model":[55],"based":[56],"idea":[59],"phrases":[62],"which":[63],"are":[64,75],"sequences":[65],"multiple":[67],"words.":[69],"By":[70],"using":[71],"phrases,":[73],"we":[74,92],"able":[76],"capture":[78],"relationship":[80],"between":[81],"isolated":[83],"and":[86],"produce":[87],"more":[88],"semantic":[89],"descriptors.":[90],"Furthermore,":[91],"also":[93,135],"propose":[94],"efficient":[96],"learn":[99],"compact":[101],"codebook":[102],"discriminative":[105],"manner":[106],"deal":[108],"with":[109,124],"high-dimensionality":[110],"bag-of-audio-phrases":[112,127],"representations.":[113],"Experiments":[114],"Freiburg-106":[117],"dataset":[118],"show":[119],"that":[120],"recognition":[122],"performance":[123],"our":[125],"proposed":[126],"descriptor":[128],"outperforms":[129],"not":[130],"only":[131],"baselines":[133],"but":[134],"state-of-the-art":[137],"results":[138],"dataset.":[141]},"counts_by_year":[{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":1},{"year":2017,"cited_by_count":1},{"year":2016,"cited_by_count":5},{"year":2015,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}