{"id":"https://openalex.org/W1887859517","doi":"https://doi.org/10.1109/icme.2004.1394646","title":"Multiple events tracking in sound tracks","display_name":"Multiple events tracking in sound tracks","publication_year":2005,"publication_date":"2005-03-21","ids":{"openalex":"https://openalex.org/W1887859517","doi":"https://doi.org/10.1109/icme.2004.1394646","mag":"1887859517"},"language":"en","primary_location":{"id":"doi:10.1109/icme.2004.1394646","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icme.2004.1394646","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 Multimedia and Expo (ICME) (IEEE Cat. No.04TH8763)","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/A5049851642","display_name":"Micha\u00ebl Betser","orcid":null},"institutions":[{"id":"https://openalex.org/I2802519937","display_name":"Institut de Recherche en Informatique et Syst\u00e8mes Al\u00e9atoires","ror":"https://ror.org/00myn0z94","country_code":"FR","type":"facility","lineage":["https://openalex.org/I1294671590","https://openalex.org/I1294671590","https://openalex.org/I1326498283","https://openalex.org/I205703379","https://openalex.org/I2802204017","https://openalex.org/I2802519937","https://openalex.org/I28221208","https://openalex.org/I4210127572","https://openalex.org/I4210159245","https://openalex.org/I56067802"]},{"id":"https://openalex.org/I1294671590","display_name":"Centre National de la Recherche Scientifique","ror":"https://ror.org/02feahw73","country_code":"FR","type":"government","lineage":["https://openalex.org/I1294671590"]},{"id":"https://openalex.org/I1326498283","display_name":"Institut national de recherche en sciences et technologies du num\u00e9rique","ror":"https://ror.org/02kvxyf05","country_code":"FR","type":"government","lineage":["https://openalex.org/I1326498283"]}],"countries":["FR"],"is_corresponding":true,"raw_author_name":"M. Betser","raw_affiliation_strings":["IRISA (INRIA & CNRS) / METISS, Campus Universitaire de Beaulieu, Rennes","WSA INRIA & CNRS / METISS, Campus Universitaire de Beaulieu, Rennes, France"],"affiliations":[{"raw_affiliation_string":"IRISA (INRIA & CNRS) / METISS, Campus Universitaire de Beaulieu, Rennes","institution_ids":["https://openalex.org/I2802519937","https://openalex.org/I1326498283","https://openalex.org/I1294671590"]},{"raw_affiliation_string":"WSA INRIA & CNRS / METISS, Campus Universitaire de Beaulieu, Rennes, France","institution_ids":["https://openalex.org/I1326498283","https://openalex.org/I1294671590"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5008190208","display_name":"Guillaume Gravier","orcid":"https://orcid.org/0000-0002-2266-5682"},"institutions":[{"id":"https://openalex.org/I1294671590","display_name":"Centre National de la Recherche Scientifique","ror":"https://ror.org/02feahw73","country_code":"FR","type":"government","lineage":["https://openalex.org/I1294671590"]},{"id":"https://openalex.org/I2802519937","display_name":"Institut de Recherche en Informatique et Syst\u00e8mes Al\u00e9atoires","ror":"https://ror.org/00myn0z94","country_code":"FR","type":"facility","lineage":["https://openalex.org/I1294671590","https://openalex.org/I1294671590","https://openalex.org/I1326498283","https://openalex.org/I205703379","https://openalex.org/I2802204017","https://openalex.org/I2802519937","https://openalex.org/I28221208","https://openalex.org/I4210127572","https://openalex.org/I4210159245","https://openalex.org/I56067802"]},{"id":"https://openalex.org/I1326498283","display_name":"Institut national de recherche en sciences et technologies du num\u00e9rique","ror":"https://ror.org/02kvxyf05","country_code":"FR","type":"government","lineage":["https://openalex.org/I1326498283"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"G. Gravier","raw_affiliation_strings":["IRISA (INRIA & CNRS) / METISS, Campus Universitaire de Beaulieu, Rennes"],"affiliations":[{"raw_affiliation_string":"IRISA (INRIA & CNRS) / METISS, Campus Universitaire de Beaulieu, Rennes","institution_ids":["https://openalex.org/I2802519937","https://openalex.org/I1326498283","https://openalex.org/I1294671590"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5049851642"],"corresponding_institution_ids":["https://openalex.org/I1294671590","https://openalex.org/I1326498283","https://openalex.org/I2802519937"],"apc_list":null,"apc_paid":null,"fwci":0.9728,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.74523161,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1963","last_page":"1966"},"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9984999895095825,"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"}},{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9984999895095825,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8351074457168579},{"id":"https://openalex.org/keywords/event","display_name":"Event (particle physics)","score":0.6765353679656982},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.6337438821792603},{"id":"https://openalex.org/keywords/tracking","display_name":"Tracking (education)","score":0.5901064872741699},{"id":"https://openalex.org/keywords/viterbi-algorithm","display_name":"Viterbi algorithm","score":0.544041633605957},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.542707085609436},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.49732473492622375},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.4957936704158783},{"id":"https://openalex.org/keywords/audio-signal-processing","display_name":"Audio signal processing","score":0.49138298630714417},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.48616692423820496},{"id":"https://openalex.org/keywords/sound-quality","display_name":"Sound quality","score":0.461204469203949},{"id":"https://openalex.org/keywords/audio-analyzer","display_name":"Audio analyzer","score":0.44847720861434937},{"id":"https://openalex.org/keywords/audio-signal","display_name":"Audio signal","score":0.3989656865596771},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.36309999227523804},{"id":"https://openalex.org/keywords/speech-coding","display_name":"Speech coding","score":0.14831343293190002}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8351074457168579},{"id":"https://openalex.org/C2779662365","wikidata":"https://www.wikidata.org/wiki/Q5416694","display_name":"Event (particle physics)","level":2,"score":0.6765353679656982},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.6337438821792603},{"id":"https://openalex.org/C2775936607","wikidata":"https://www.wikidata.org/wiki/Q466845","display_name":"Tracking (education)","level":2,"score":0.5901064872741699},{"id":"https://openalex.org/C60582962","wikidata":"https://www.wikidata.org/wiki/Q83886","display_name":"Viterbi algorithm","level":3,"score":0.544041633605957},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.542707085609436},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.49732473492622375},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.4957936704158783},{"id":"https://openalex.org/C127220857","wikidata":"https://www.wikidata.org/wiki/Q2719318","display_name":"Audio signal processing","level":4,"score":0.49138298630714417},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.48616692423820496},{"id":"https://openalex.org/C167310288","wikidata":"https://www.wikidata.org/wiki/Q7564808","display_name":"Sound quality","level":2,"score":0.461204469203949},{"id":"https://openalex.org/C160372630","wikidata":"https://www.wikidata.org/wiki/Q4819855","display_name":"Audio analyzer","level":5,"score":0.44847720861434937},{"id":"https://openalex.org/C64922751","wikidata":"https://www.wikidata.org/wiki/Q4650799","display_name":"Audio signal","level":3,"score":0.3989656865596771},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.36309999227523804},{"id":"https://openalex.org/C13895895","wikidata":"https://www.wikidata.org/wiki/Q3270773","display_name":"Speech coding","level":2,"score":0.14831343293190002},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"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},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C19417346","wikidata":"https://www.wikidata.org/wiki/Q7922","display_name":"Pedagogy","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/icme.2004.1394646","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icme.2004.1394646","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 Multimedia and Expo (ICME) (IEEE Cat. No.04TH8763)","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.332.501","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.332.501","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.irisa.fr/metiss/guig/biblio/04/betser-icme-2004.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.514.4351","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.514.4351","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.irisa.fr/metiss/publis/betser-icme04.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":6,"referenced_works":["https://openalex.org/W171906295","https://openalex.org/W1547083988","https://openalex.org/W2104353650","https://openalex.org/W2616298955","https://openalex.org/W6606980649","https://openalex.org/W6632910081"],"related_works":["https://openalex.org/W2098934641","https://openalex.org/W1590604789","https://openalex.org/W2065633372","https://openalex.org/W2494533082","https://openalex.org/W2735200146","https://openalex.org/W4214771044","https://openalex.org/W4382560817","https://openalex.org/W4387698063","https://openalex.org/W2792033502","https://openalex.org/W3043119899"],"abstract_inverted_index":{"Detecting":[0],"and":[1],"tracking":[2],"broad":[3],"sound":[4,26],"classes":[5],"in":[6],"audio":[7,20,33],"documents":[8],"is":[9,30,50],"an":[10,57,95],"important":[11],"step":[12,49,60],"toward":[13],"structuration.":[14],"In":[15,64],"the":[16,68,71,83,91],"case":[17],"of":[18,70],"complex":[19],"scenes,":[21],"such":[22],"as":[23],"TV":[24],"broadcast":[25],"tracks,":[27],"one":[28],"problem":[29],"that":[31],"several":[32],"events":[34,85],"may":[35],"occur":[36],"simultaneously.":[37],"We":[38,88],"propose":[39],"a":[40,51],"two-step":[41,92],"approach":[42,93],"to":[43,66,82],"detect":[44],"superimposed":[45,84],"events.":[46],"The":[47],"first":[48],"blind":[52],"segmentation":[53],"step,":[54],"followed":[55],"by":[56],"event":[58,98],"detection":[59,86,99],"on":[61],"each":[62],"segment.":[63],"order":[65],"evaluate":[67],"quality":[69],"system":[72],"better,":[73],"new":[74],"performance":[75],"measures":[76],"have":[77],"been":[78],"introduced,":[79],"more":[80],"suited":[81],"task.":[87],"also":[89],"extend":[90],"with":[94],"equivalent":[96],"Viterbi-based":[97],"approach.":[100]},"counts_by_year":[],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}
