{"id":"https://openalex.org/W2344582598","doi":"https://doi.org/10.1109/icassp.2016.7471667","title":"Learning compact structural representations for audio events using regressor banks","display_name":"Learning compact structural representations for audio events using regressor banks","publication_year":2016,"publication_date":"2016-03-01","ids":{"openalex":"https://openalex.org/W2344582598","doi":"https://doi.org/10.1109/icassp.2016.7471667","mag":"2344582598"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2016.7471667","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2016.7471667","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2016 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"type":"preprint","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/1604.08716","any_repository_has_fulltext":true},"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":true,"raw_author_name":"Huy Phan","raw_affiliation_strings":["Graduate School for Computing in Medicine and Life Sciences, University of Lubeck, Germany"],"affiliations":[{"raw_affiliation_string":"Graduate School for Computing in Medicine and Life Sciences, University of Lubeck, 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"],"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/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"],"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"],"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/A5000620878","display_name":"Ian McLoughlin","orcid":"https://orcid.org/0000-0001-7111-2008"},"institutions":[{"id":"https://openalex.org/I20581793","display_name":"University of Kent","ror":"https://ror.org/00xkeyj56","country_code":"GB","type":"education","lineage":["https://openalex.org/I20581793"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Ian McLoughlin","raw_affiliation_strings":["School of Computing, University of Kent, UK"],"affiliations":[{"raw_affiliation_string":"School of Computing, University of Kent, UK","institution_ids":["https://openalex.org/I20581793"]}]},{"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"],"affiliations":[{"raw_affiliation_string":"Institute for Signal Processing, University of L\u00fcbeck, Germany","institution_ids":["https://openalex.org/I9341345"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5058452657"],"corresponding_institution_ids":["https://openalex.org/I9341345"],"apc_list":null,"apc_paid":null,"fwci":1.2753,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.80218425,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":96},"biblio":{"volume":"23","issue":null,"first_page":"211","last_page":"215"},"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":0.9991999864578247,"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":0.9944999814033508,"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":0.6053487062454224},{"id":"https://openalex.org/keywords/event","display_name":"Event (particle physics)","score":0.6018394827842712},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5908024907112122},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.5659056305885315},{"id":"https://openalex.org/keywords/curse-of-dimensionality","display_name":"Curse of dimensionality","score":0.5409141778945923},{"id":"https://openalex.org/keywords/offset","display_name":"Offset (computer science)","score":0.5333113074302673},{"id":"https://openalex.org/keywords/random-forest","display_name":"Random forest","score":0.5107512474060059},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.4897501468658447},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.489629328250885},{"id":"https://openalex.org/keywords/class","display_name":"Class (philosophy)","score":0.4848252534866333},{"id":"https://openalex.org/keywords/audio-signal","display_name":"Audio signal","score":0.4800106883049011},{"id":"https://openalex.org/keywords/audio-signal-processing","display_name":"Audio signal processing","score":0.44563037157058716},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.37100887298583984},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.3587239682674408},{"id":"https://openalex.org/keywords/speech-coding","display_name":"Speech coding","score":0.09118828177452087}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6053487062454224},{"id":"https://openalex.org/C2779662365","wikidata":"https://www.wikidata.org/wiki/Q5416694","display_name":"Event (particle physics)","level":2,"score":0.6018394827842712},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5908024907112122},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.5659056305885315},{"id":"https://openalex.org/C111030470","wikidata":"https://www.wikidata.org/wiki/Q1430460","display_name":"Curse of dimensionality","level":2,"score":0.5409141778945923},{"id":"https://openalex.org/C175291020","wikidata":"https://www.wikidata.org/wiki/Q1156822","display_name":"Offset (computer science)","level":2,"score":0.5333113074302673},{"id":"https://openalex.org/C169258074","wikidata":"https://www.wikidata.org/wiki/Q245748","display_name":"Random forest","level":2,"score":0.5107512474060059},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.4897501468658447},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.489629328250885},{"id":"https://openalex.org/C2777212361","wikidata":"https://www.wikidata.org/wiki/Q5127848","display_name":"Class (philosophy)","level":2,"score":0.4848252534866333},{"id":"https://openalex.org/C64922751","wikidata":"https://www.wikidata.org/wiki/Q4650799","display_name":"Audio signal","level":3,"score":0.4800106883049011},{"id":"https://openalex.org/C127220857","wikidata":"https://www.wikidata.org/wiki/Q2719318","display_name":"Audio signal processing","level":4,"score":0.44563037157058716},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.37100887298583984},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.3587239682674408},{"id":"https://openalex.org/C13895895","wikidata":"https://www.wikidata.org/wiki/Q3270773","display_name":"Speech coding","level":2,"score":0.09118828177452087},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","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},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"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}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/icassp.2016.7471667","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2016.7471667","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2016 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:1604.08716","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1604.08716","pdf_url":"https://arxiv.org/pdf/1604.08716","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"pmh:oai:kar.kent.ac.uk:55054","is_oa":false,"landing_page_url":"https://kar.kent.ac.uk/55054/","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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Conference or workshop item"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:1604.08716","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1604.08716","pdf_url":"https://arxiv.org/pdf/1604.08716","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[{"display_name":"Life in Land","id":"https://metadata.un.org/sdg/15","score":0.7400000095367432}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":49,"referenced_works":["https://openalex.org/W1501987291","https://openalex.org/W1964442016","https://openalex.org/W1970578576","https://openalex.org/W1987011838","https://openalex.org/W2008415856","https://openalex.org/W2009504845","https://openalex.org/W2021096090","https://openalex.org/W2046972719","https://openalex.org/W2058224795","https://openalex.org/W2065529590","https://openalex.org/W2077159900","https://openalex.org/W2086384421","https://openalex.org/W2090431713","https://openalex.org/W2092216166","https://openalex.org/W2105068979","https://openalex.org/W2112020727","https://openalex.org/W2125337786","https://openalex.org/W2127612600","https://openalex.org/W2129634963","https://openalex.org/W2144459347","https://openalex.org/W2151316819","https://openalex.org/W2157821739","https://openalex.org/W2162915993","https://openalex.org/W2165880886","https://openalex.org/W2179324675","https://openalex.org/W2186582651","https://openalex.org/W2221333906","https://openalex.org/W2396889081","https://openalex.org/W2397348385","https://openalex.org/W2398880078","https://openalex.org/W2404382656","https://openalex.org/W2408491073","https://openalex.org/W2561557072","https://openalex.org/W2911964244","https://openalex.org/W2963922351","https://openalex.org/W2986994086","https://openalex.org/W3215500402","https://openalex.org/W4233392025","https://openalex.org/W4248702647","https://openalex.org/W4293171766","https://openalex.org/W4302070149","https://openalex.org/W6643125879","https://openalex.org/W6665099936","https://openalex.org/W6678951767","https://openalex.org/W6682352165","https://openalex.org/W6689016307","https://openalex.org/W6712405843","https://openalex.org/W6713358509","https://openalex.org/W6714426239"],"related_works":["https://openalex.org/W2289868279","https://openalex.org/W4231351862","https://openalex.org/W4212794605","https://openalex.org/W4315836293","https://openalex.org/W4243888788","https://openalex.org/W2769884427","https://openalex.org/W2088690926","https://openalex.org/W2098934641","https://openalex.org/W2157165686","https://openalex.org/W2371215329"],"abstract_inverted_index":{"We":[0],"introduce":[1],"a":[2,24,66],"new":[3],"learned":[4],"descriptor":[5,19,88,101],"for":[6,12],"audio":[7,127],"signals":[8],"which":[9],"is":[10,94,102],"efficient":[11],"event":[13,76,108,128],"representation.":[14],"The":[15,32,60],"entries":[16],"of":[17,26,56,82,99,107],"the":[18,29,39,51,57,74,79,83,97,100,105,134,139],"are":[20,34,68],"produced":[21],"by":[22,65],"evaluating":[23],"set":[25],"regressors":[27,33],"on":[28,120,126],"input":[30,46],"signal.":[31],"class-specific":[35],"and":[36,53],"trained":[37,119],"using":[38],"random":[40],"regression":[41],"forests":[42],"framework.":[43],"Given":[44],"an":[45],"signal,":[47],"each":[48],"regressor":[49,67],"estimates":[50],"onset":[52],"offset":[54],"positions":[55],"target":[58,75],"event.":[59],"estimation":[61],"confidence":[62],"scores":[63],"output":[64],"then":[69],"used":[70],"to":[71,104],"quantify":[72],"how":[73],"aligns":[77],"with":[78],"temporal":[80],"structure":[81],"corresponding":[84],"category.":[85],"Our":[86],"proposed":[87],"has":[89],"two":[90],"advantages.":[91],"First,":[92],"it":[93],"compact,":[95],"i.e.":[96],"dimensionality":[98],"equal":[103],"number":[106],"classes.":[109],"Second,":[110],"we":[111],"show":[112],"that":[113],"even":[114],"simple":[115],"linear":[116],"classification":[117,129],"models,":[118],"our":[121],"descriptor,":[122],"yield":[123],"better":[124],"accuracies":[125],"task":[130],"than":[131],"not":[132],"only":[133],"nonlinear":[135],"baselines":[136],"but":[137],"also":[138],"state-of-the-art":[140],"results.":[141]},"counts_by_year":[{"year":2018,"cited_by_count":2},{"year":2017,"cited_by_count":2},{"year":2016,"cited_by_count":1}],"updated_date":"2026-03-20T23:20:44.827607","created_date":"2025-10-10T00:00:00"}