{"id":"https://openalex.org/W2102018447","doi":"https://doi.org/10.1109/icassp.2004.1326825","title":"A dynamic programming approach to audio segmentation and speech/music discrimination","display_name":"A dynamic programming approach to audio segmentation and speech/music discrimination","publication_year":2004,"publication_date":"2004-09-28","ids":{"openalex":"https://openalex.org/W2102018447","doi":"https://doi.org/10.1109/icassp.2004.1326825","mag":"2102018447"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2004.1326825","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2004.1326825","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":"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/A5028244782","display_name":"Michael M. Goodwin","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"M.M. Goodwin","raw_affiliation_strings":["Creative Advanced Technology Center, Scotts Valley, CA, USA","[Creative Advanced Technology Center, Scotts Valley, CA, USA]"],"affiliations":[{"raw_affiliation_string":"Creative Advanced Technology Center, Scotts Valley, CA, USA","institution_ids":[]},{"raw_affiliation_string":"[Creative Advanced Technology Center, Scotts Valley, CA, USA]","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5108105021","display_name":"J. Laroche","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"J. Laroche","raw_affiliation_strings":["Creative Advanced Technology Center, Scotts Valley, CA, USA","[Creative Advanced Technology Center, Scotts Valley, CA, USA]"],"affiliations":[{"raw_affiliation_string":"Creative Advanced Technology Center, Scotts Valley, CA, USA","institution_ids":[]},{"raw_affiliation_string":"[Creative Advanced Technology Center, Scotts Valley, CA, USA]","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5028244782"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.5609,"has_fulltext":false,"cited_by_count":14,"citation_normalized_percentile":{"value":0.67252724,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":"4","issue":null,"first_page":"iv","last_page":"309"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9980999827384949,"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":0.9751999974250793,"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/feature","display_name":"Feature (linguistics)","score":0.7107133865356445},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6865012049674988},{"id":"https://openalex.org/keywords/dynamic-programming","display_name":"Dynamic programming","score":0.650596022605896},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.6379372477531433},{"id":"https://openalex.org/keywords/linear-discriminant-analysis","display_name":"Linear discriminant analysis","score":0.6174939274787903},{"id":"https://openalex.org/keywords/feature-vector","display_name":"Feature vector","score":0.613335371017456},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.6036069393157959},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.5535024404525757},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5346232056617737},{"id":"https://openalex.org/keywords/audio-signal","display_name":"Audio signal","score":0.5213619470596313},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5161015391349792},{"id":"https://openalex.org/keywords/signal","display_name":"SIGNAL (programming language)","score":0.49703148007392883},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.48098838329315186},{"id":"https://openalex.org/keywords/audio-signal-processing","display_name":"Audio signal processing","score":0.47784945368766785},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.4655298590660095},{"id":"https://openalex.org/keywords/market-segmentation","display_name":"Market segmentation","score":0.46133387088775635},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.4206576943397522},{"id":"https://openalex.org/keywords/speech-coding","display_name":"Speech coding","score":0.3911690413951874},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.17494386434555054}],"concepts":[{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.7107133865356445},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6865012049674988},{"id":"https://openalex.org/C37404715","wikidata":"https://www.wikidata.org/wiki/Q380679","display_name":"Dynamic programming","level":2,"score":0.650596022605896},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.6379372477531433},{"id":"https://openalex.org/C69738355","wikidata":"https://www.wikidata.org/wiki/Q1228929","display_name":"Linear discriminant analysis","level":2,"score":0.6174939274787903},{"id":"https://openalex.org/C83665646","wikidata":"https://www.wikidata.org/wiki/Q42139305","display_name":"Feature vector","level":2,"score":0.613335371017456},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.6036069393157959},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.5535024404525757},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5346232056617737},{"id":"https://openalex.org/C64922751","wikidata":"https://www.wikidata.org/wiki/Q4650799","display_name":"Audio signal","level":3,"score":0.5213619470596313},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5161015391349792},{"id":"https://openalex.org/C2779843651","wikidata":"https://www.wikidata.org/wiki/Q7390335","display_name":"SIGNAL (programming language)","level":2,"score":0.49703148007392883},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.48098838329315186},{"id":"https://openalex.org/C127220857","wikidata":"https://www.wikidata.org/wiki/Q2719318","display_name":"Audio signal processing","level":4,"score":0.47784945368766785},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.4655298590660095},{"id":"https://openalex.org/C125308379","wikidata":"https://www.wikidata.org/wiki/Q363057","display_name":"Market segmentation","level":2,"score":0.46133387088775635},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.4206576943397522},{"id":"https://openalex.org/C13895895","wikidata":"https://www.wikidata.org/wiki/Q3270773","display_name":"Speech coding","level":2,"score":0.3911690413951874},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.17494386434555054},{"id":"https://openalex.org/C162853370","wikidata":"https://www.wikidata.org/wiki/Q39809","display_name":"Marketing","level":1,"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/C144133560","wikidata":"https://www.wikidata.org/wiki/Q4830453","display_name":"Business","level":0,"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/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"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/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp.2004.1326825","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2004.1326825","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"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Reduced inequalities","score":0.6499999761581421,"id":"https://metadata.un.org/sdg/10"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":9,"referenced_works":["https://openalex.org/W1482605500","https://openalex.org/W2074188409","https://openalex.org/W2115307058","https://openalex.org/W2128838222","https://openalex.org/W2135346934","https://openalex.org/W2154642142","https://openalex.org/W2168249484","https://openalex.org/W6628911050","https://openalex.org/W6684713764"],"related_works":["https://openalex.org/W2069501481","https://openalex.org/W2289868279","https://openalex.org/W2063862874","https://openalex.org/W2154415461","https://openalex.org/W1923241916","https://openalex.org/W1546240199","https://openalex.org/W2109142991","https://openalex.org/W2970176078","https://openalex.org/W4231351862","https://openalex.org/W2969585518"],"abstract_inverted_index":{"We":[0,65,97],"consider":[1,66],"the":[2,17,24,54,67,70,90,93,99,102],"problem":[3],"of":[4,23,29,46,69,92,101],"segmenting":[5],"an":[6],"audio":[7],"signal":[8,25,41],"into":[9,36],"characteristic":[10],"regions":[11],"based":[12],"on":[13,85],"feature-set":[14],"similarities.":[15],"In":[16],"proposed":[18],"approach,":[19],"a":[20],"feature-space":[21,31],"representation":[22],"is":[26],"generated;":[27],"sequences":[28],"these":[30],"samples":[32],"are":[33,76,111],"then":[34],"aggregated":[35],"clusters":[37],"corresponding":[38],"to":[39,52,61,78,106],"distinct":[40],"regions.":[42],"The":[43],"algorithm":[44,105],"consists":[45],"using":[47],"linear":[48],"discriminant":[49],"analysis":[50],"(LDA)":[51],"condition":[53],"feature":[55],"space":[56],"and":[57,113],"dynamic":[58,71],"programming":[59],"(DP)":[60],"identify":[62],"data":[63,95],"clusters.":[64,96],"design":[68],"program":[72],"cost":[73,81],"functions;":[74],"we":[75],"able":[77],"derive":[79],"effective":[80],"functions":[82],"without":[83],"relying":[84],"significant":[86],"prior":[87],"information":[88],"about":[89],"structure":[91],"expected":[94],"demonstrate":[98],"application":[100],"LDA-DP":[103],"segmentation":[104],"speech/music":[107],"discrimination.":[108],"Experimental":[109],"results":[110],"given":[112],"discussed.":[114]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":1},{"year":2013,"cited_by_count":3}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}