{"id":"https://openalex.org/W2093337637","doi":"https://doi.org/10.1109/icassp.2014.6853978","title":"Intra-note segmentation via sticky HMM with DP emission","display_name":"Intra-note segmentation via sticky HMM with DP emission","publication_year":2014,"publication_date":"2014-05-01","ids":{"openalex":"https://openalex.org/W2093337637","doi":"https://doi.org/10.1109/icassp.2014.6853978","mag":"2093337637"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2014.6853978","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2014.6853978","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2014 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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/A5101503856","display_name":"Yuma Koizumi","orcid":"https://orcid.org/0000-0003-3645-6213"},"institutions":[{"id":"https://openalex.org/I204291657","display_name":"Hosei University","ror":"https://ror.org/00bx6dj65","country_code":"JP","type":"education","lineage":["https://openalex.org/I204291657"]}],"countries":["JP"],"is_corresponding":true,"raw_author_name":"Yuma Koizumi","raw_affiliation_strings":["Graduate School of Computer and Information Sciences, Hosei University, Koganei, Tokyo, Japan","Grad. Sch. of Comput. & Inf. Sci., Hosei Univ., Koganei, Japan"],"affiliations":[{"raw_affiliation_string":"Graduate School of Computer and Information Sciences, Hosei University, Koganei, Tokyo, Japan","institution_ids":["https://openalex.org/I204291657"]},{"raw_affiliation_string":"Grad. Sch. of Comput. & Inf. Sci., Hosei Univ., Koganei, Japan","institution_ids":["https://openalex.org/I204291657"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5108574981","display_name":"Katunobu Itou","orcid":null},"institutions":[{"id":"https://openalex.org/I204291657","display_name":"Hosei University","ror":"https://ror.org/00bx6dj65","country_code":"JP","type":"education","lineage":["https://openalex.org/I204291657"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Katunobu Itou","raw_affiliation_strings":["Graduate School of Computer and Information Sciences, Hosei University, Koganei, Tokyo, Japan","Grad. Sch. of Comput. & Inf. Sci., Hosei Univ., Koganei, Japan"],"affiliations":[{"raw_affiliation_string":"Graduate School of Computer and Information Sciences, Hosei University, Koganei, Tokyo, Japan","institution_ids":["https://openalex.org/I204291657"]},{"raw_affiliation_string":"Grad. Sch. of Comput. & Inf. Sci., Hosei Univ., Koganei, Japan","institution_ids":["https://openalex.org/I204291657"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5101503856"],"corresponding_institution_ids":["https://openalex.org/I204291657"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.15318287,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"2144","last_page":"2148"},"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":0.9991000294685364,"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":0.9977999925613403,"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/hidden-markov-model","display_name":"Hidden Markov model","score":0.8812768459320068},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.6992668509483337},{"id":"https://openalex.org/keywords/offset","display_name":"Offset (computer science)","score":0.6099437475204468},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6029954552650452},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5809739232063293},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.5255542993545532},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.5139314532279968},{"id":"https://openalex.org/keywords/markov-process","display_name":"Markov process","score":0.5015385150909424},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4427136778831482},{"id":"https://openalex.org/keywords/markov-model","display_name":"Markov model","score":0.4288838505744934},{"id":"https://openalex.org/keywords/mel-frequency-cepstrum","display_name":"Mel-frequency cepstrum","score":0.41592320799827576},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.26324689388275146},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.2557353675365448},{"id":"https://openalex.org/keywords/markov-chain","display_name":"Markov chain","score":0.2347623109817505},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.13691461086273193},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.0805361270904541}],"concepts":[{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.8812768459320068},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.6992668509483337},{"id":"https://openalex.org/C175291020","wikidata":"https://www.wikidata.org/wiki/Q1156822","display_name":"Offset (computer science)","level":2,"score":0.6099437475204468},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6029954552650452},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5809739232063293},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.5255542993545532},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.5139314532279968},{"id":"https://openalex.org/C159886148","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov process","level":2,"score":0.5015385150909424},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4427136778831482},{"id":"https://openalex.org/C163836022","wikidata":"https://www.wikidata.org/wiki/Q6771326","display_name":"Markov model","level":3,"score":0.4288838505744934},{"id":"https://openalex.org/C151989614","wikidata":"https://www.wikidata.org/wiki/Q440370","display_name":"Mel-frequency cepstrum","level":3,"score":0.41592320799827576},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.26324689388275146},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.2557353675365448},{"id":"https://openalex.org/C98763669","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov chain","level":2,"score":0.2347623109817505},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.13691461086273193},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0805361270904541},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","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/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp.2014.6853978","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2014.6853978","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2014 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":36,"referenced_works":["https://openalex.org/W49522132","https://openalex.org/W109946471","https://openalex.org/W175070741","https://openalex.org/W202042453","https://openalex.org/W206539541","https://openalex.org/W1519655822","https://openalex.org/W1560720482","https://openalex.org/W1805922134","https://openalex.org/W1905983571","https://openalex.org/W1967414607","https://openalex.org/W2008565517","https://openalex.org/W2032136667","https://openalex.org/W2037668034","https://openalex.org/W2107943497","https://openalex.org/W2114326880","https://openalex.org/W2120636621","https://openalex.org/W2127498532","https://openalex.org/W2135537007","https://openalex.org/W2140304104","https://openalex.org/W2148135014","https://openalex.org/W2172567136","https://openalex.org/W2288878799","https://openalex.org/W2505893087","https://openalex.org/W2972891548","https://openalex.org/W4285719527","https://openalex.org/W4390748465","https://openalex.org/W6601999543","https://openalex.org/W6604464690","https://openalex.org/W6608194034","https://openalex.org/W6608380424","https://openalex.org/W6631117800","https://openalex.org/W6638167735","https://openalex.org/W6678007500","https://openalex.org/W6685311013","https://openalex.org/W6696484452","https://openalex.org/W6860408554"],"related_works":["https://openalex.org/W2536059291","https://openalex.org/W1967754766","https://openalex.org/W2793122029","https://openalex.org/W2376309785","https://openalex.org/W2083904772","https://openalex.org/W2343281260","https://openalex.org/W2269356926","https://openalex.org/W2952740884","https://openalex.org/W2245703999","https://openalex.org/W4299139242"],"abstract_inverted_index":{"This":[0,88],"paper":[1],"presents":[2],"an":[3],"intra-note":[4,29],"segmentation":[5,30],"method":[6],"for":[7],"mono-phonic":[8],"recordings":[9],"based":[10],"on":[11,49],"acoustic":[12,39,54,110],"feature":[13,55,111],"variation;":[14],"each":[15,68],"musical":[16,113],"note":[17],"is":[18,34,47,56,86],"separated":[19],"into":[20],"onset,":[21],"steady":[22],"and":[23,52,124,130],"offset":[24],"states.":[25],"The":[26],"task":[27],"of":[28,38,108,122],"from":[31,133],"audio":[32],"signals":[33],"detecting":[35],"change":[36],"points":[37,129,132],"feature.":[40],"In":[41,70],"proposed":[42],"method,":[43,135],"the":[44,67,74,77,95,100,119],"Markov":[45,80],"process":[46],"assumed":[48],"state":[50,96],"transition,":[51],"time-varying":[53],"represented":[57],"by":[58,66,104],"three":[59],"Dirichlet":[60],"processes":[61],"(DP)":[62],"that":[63,118],"are":[64],"emitted":[65],"state.":[69],"order":[71],"to":[72,92],"express":[73],"generative":[75],"process,":[76],"sticky":[78],"hidden":[79],"model":[81,101],"(HMM)":[82],"with":[83],"DP":[84],"emission":[85],"employed.":[87],"modeling":[89],"allows":[90],"us":[91],"automatically":[93],"estimate":[94],"transition":[97],"while":[98],"avoiding":[99],"selection":[102],"problem":[103],"assuming":[105],"countably":[106],"infinite":[107],"possible":[109],"in":[112],"notes.":[114],"Experimental":[115],"result":[116],"shows":[117],"detection":[120],"accuracy":[121],"onset-to-steady":[123],"steady-to-offset":[125],"were":[126],"improved":[127],"2.3":[128],"20.7":[131],"previous":[134],"respectively.":[136]},"counts_by_year":[],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}