{"id":"https://openalex.org/W2141907603","doi":"https://doi.org/10.1109/icassp.2004.1326833","title":"Audio content description with wavelets and neural nets","display_name":"Audio content description with wavelets and neural nets","publication_year":2004,"publication_date":"2004-09-28","ids":{"openalex":"https://openalex.org/W2141907603","doi":"https://doi.org/10.1109/icassp.2004.1326833","mag":"2141907603"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2004.1326833","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2004.1326833","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2004 IEEE International Conference on Acoustics, Speech, and Signal Processing","raw_type":"proceedings-article"},"type":"conference-paper","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/A5088068985","display_name":"Stephan Rein","orcid":null},"institutions":[{"id":"https://openalex.org/I4577782","display_name":"Technische Universit\u00e4t Berlin","ror":"https://ror.org/03v4gjf40","country_code":"DE","type":"education","lineage":["https://openalex.org/I4577782"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"S. Rein","raw_affiliation_strings":["Technische Universitat Berlin, Berlin, Berlin, DE","Tech. Univ. Berlin, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Technische Universitat Berlin, Berlin, Berlin, DE","institution_ids":["https://openalex.org/I4577782"]},{"raw_affiliation_string":"Tech. Univ. Berlin, Germany","institution_ids":["https://openalex.org/I4577782"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5031060437","display_name":"Martin Reisslein","orcid":"https://orcid.org/0000-0003-1606-233X"},"institutions":[{"id":"https://openalex.org/I4210154524","display_name":"European Council for an Energy Efficient Economy","ror":"https://ror.org/04xytpa07","country_code":"SE","type":"nonprofit","lineage":["https://openalex.org/I4210154524"]},{"id":"https://openalex.org/I55732556","display_name":"Arizona State University","ror":"https://ror.org/03efmqc40","country_code":"US","type":"education","lineage":["https://openalex.org/I55732556"]}],"countries":["SE","US"],"is_corresponding":false,"raw_author_name":"M. Reisslein","raw_affiliation_strings":["Arizona State University, USA","IAFSE-ECEE: Electrical Engineering"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Arizona State University, USA","institution_ids":["https://openalex.org/I55732556"]},{"raw_affiliation_string":"IAFSE-ECEE: Electrical Engineering","institution_ids":["https://openalex.org/I4210154524"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5053803378","display_name":"T. Sikora","orcid":"https://orcid.org/0009-0009-2721-6796"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"T. Sikora","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":"4","issue":null,"first_page":"iv","last_page":"341"},"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":0.9979000091552734,"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/T11349","display_name":"Music Technology and Sound Studies","score":0.9872999787330627,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/wavelet","display_name":"Wavelet","score":0.8078497052192688},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7257949709892273},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.6313976645469666},{"id":"https://openalex.org/keywords/content","display_name":"Content (measure theory)","score":0.6065983772277832},{"id":"https://openalex.org/keywords/measure","display_name":"Measure (data warehouse)","score":0.5905412435531616},{"id":"https://openalex.org/keywords/usability","display_name":"Usability","score":0.5784716606140137},{"id":"https://openalex.org/keywords/probabilistic-logic","display_name":"Probabilistic logic","score":0.5569903254508972},{"id":"https://openalex.org/keywords/conjunction","display_name":"Conjunction (astronomy)","score":0.5319650173187256},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4691779911518097},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4476555287837982},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.443755567073822},{"id":"https://openalex.org/keywords/dispersion","display_name":"Dispersion (optics)","score":0.42762452363967896},{"id":"https://openalex.org/keywords/the-internet","display_name":"The Internet","score":0.41653960943222046},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.34758082032203674},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.24420702457427979},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.16575196385383606},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.11221912503242493}],"concepts":[{"id":"https://openalex.org/C47432892","wikidata":"https://www.wikidata.org/wiki/Q831390","display_name":"Wavelet","level":2,"score":0.8078497052192688},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7257949709892273},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.6313976645469666},{"id":"https://openalex.org/C2778152352","wikidata":"https://www.wikidata.org/wiki/Q5165061","display_name":"Content (measure theory)","level":2,"score":0.6065983772277832},{"id":"https://openalex.org/C2780009758","wikidata":"https://www.wikidata.org/wiki/Q6804172","display_name":"Measure (data warehouse)","level":2,"score":0.5905412435531616},{"id":"https://openalex.org/C170130773","wikidata":"https://www.wikidata.org/wiki/Q216378","display_name":"Usability","level":2,"score":0.5784716606140137},{"id":"https://openalex.org/C49937458","wikidata":"https://www.wikidata.org/wiki/Q2599292","display_name":"Probabilistic logic","level":2,"score":0.5569903254508972},{"id":"https://openalex.org/C59656382","wikidata":"https://www.wikidata.org/wiki/Q191536","display_name":"Conjunction (astronomy)","level":2,"score":0.5319650173187256},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4691779911518097},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4476555287837982},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.443755567073822},{"id":"https://openalex.org/C177562468","wikidata":"https://www.wikidata.org/wiki/Q182893","display_name":"Dispersion (optics)","level":2,"score":0.42762452363967896},{"id":"https://openalex.org/C110875604","wikidata":"https://www.wikidata.org/wiki/Q75","display_name":"The Internet","level":2,"score":0.41653960943222046},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.34758082032203674},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.24420702457427979},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.16575196385383606},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.11221912503242493},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.0},{"id":"https://openalex.org/C1276947","wikidata":"https://www.wikidata.org/wiki/Q333","display_name":"Astronomy","level":1,"score":0.0},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","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/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/icassp.2004.1326833","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2004.1326833","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2004 IEEE International Conference on Acoustics, Speech, and Signal Processing","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.70.8228","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.70.8228","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.nue.tu-berlin.de/publications/papers/0400341.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":14,"referenced_works":["https://openalex.org/W1657145974","https://openalex.org/W1954587310","https://openalex.org/W2100488848","https://openalex.org/W2115101691","https://openalex.org/W2131981197","https://openalex.org/W2132522142","https://openalex.org/W2140266719","https://openalex.org/W2140685304","https://openalex.org/W2141907603","https://openalex.org/W2146171479","https://openalex.org/W2168441989","https://openalex.org/W3146388410","https://openalex.org/W6640934164","https://openalex.org/W6680559069"],"related_works":["https://openalex.org/W1573992054","https://openalex.org/W1599690842","https://openalex.org/W2753053412","https://openalex.org/W2665157442","https://openalex.org/W3108840034","https://openalex.org/W4388169484","https://openalex.org/W2363259562","https://openalex.org/W3036937347","https://openalex.org/W3149224203","https://openalex.org/W2914339338"],"abstract_inverted_index":{"Precision":[0],"audio":[1,37],"content":[2,38],"description":[3],"is":[4],"one":[5],"of":[6,10,21,24,32,53,79],"the":[7,19],"key":[8],"components":[9],"next":[11],"generation":[12],"Internet":[13],"multimedia":[14],"search":[15],"machines.":[16],"We":[17],"examine":[18],"usability":[20],"a":[22,44,62,76],"combination":[23],"39":[25],"different":[26,30],"wavelets":[27],"and":[28],"three":[29,71],"types":[31],"neural":[33,66],"nets":[34],"for":[35],"precision":[36],"description.":[39],"More":[40],"specifically,":[41],"we":[42],"develop":[43],"novel":[45],"wavelet":[46,54],"dispersion":[47,57],"measure":[48,58],"that":[49],"measures":[50],"obtained":[51],"ranks":[52],"coefficients.":[55],"Our":[56],"in":[59,82],"conjunction":[60],"with":[61],"probabilistic":[63],"radial":[64],"basis":[65],"network":[67],"trained":[68],"by":[69],"only":[70],"independent":[72],"example":[73],"sets":[74],"obtains":[75],"success":[77],"rate":[78],"approximately":[80],"78%":[81],"identifying":[83],"unknown":[84],"complex":[85],"classical":[86],"music":[87],"movements.":[88]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}
