{"id":"https://openalex.org/W1599383372","doi":"https://doi.org/10.21437/interspeech.2004-46","title":"An online audio indexing system","display_name":"An online audio indexing system","publication_year":2004,"publication_date":"2004-10-04","ids":{"openalex":"https://openalex.org/W1599383372","doi":"https://doi.org/10.21437/interspeech.2004-46","mag":"1599383372"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2004-46","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2004-46","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2004","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"http://infoscience.epfl.ch/record/82997","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5063781689","display_name":"Jitendra Ajmera","orcid":null},"institutions":[{"id":"https://openalex.org/I7495430","display_name":"Idiap Research Institute","ror":"https://ror.org/05932h694","country_code":"CH","type":"facility","lineage":["https://openalex.org/I7495430"]}],"countries":["CH"],"is_corresponding":true,"raw_author_name":"Jitendra Ajmera","raw_affiliation_strings":["IDIAP research institute"],"affiliations":[{"raw_affiliation_string":"IDIAP research institute","institution_ids":["https://openalex.org/I7495430"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5072372659","display_name":"Iain McCowan","orcid":null},"institutions":[{"id":"https://openalex.org/I7495430","display_name":"Idiap Research Institute","ror":"https://ror.org/05932h694","country_code":"CH","type":"facility","lineage":["https://openalex.org/I7495430"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Iain McCowan","raw_affiliation_strings":["IDIAP research institute"],"affiliations":[{"raw_affiliation_string":"IDIAP research institute","institution_ids":["https://openalex.org/I7495430"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5108187466","display_name":"Herv\u00e9 Bourlard","orcid":null},"institutions":[{"id":"https://openalex.org/I7495430","display_name":"Idiap Research Institute","ror":"https://ror.org/05932h694","country_code":"CH","type":"facility","lineage":["https://openalex.org/I7495430"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Herv\u00e9 Bourlard","raw_affiliation_strings":["IDIAP research institute"],"affiliations":[{"raw_affiliation_string":"IDIAP research institute","institution_ids":["https://openalex.org/I7495430"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5063781689"],"corresponding_institution_ids":["https://openalex.org/I7495430"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.10600042,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1601","last_page":"1604"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9998000264167786,"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":0.9998000264167786,"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":0.9872999787330627,"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/T13996","display_name":"Diverse Musicological Studies","score":0.9839000105857849,"subfield":{"id":"https://openalex.org/subfields/1210","display_name":"Music"},"field":{"id":"https://openalex.org/fields/12","display_name":"Arts and Humanities"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/search-engine-indexing","display_name":"Search engine indexing","score":0.758319616317749},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7550183534622192},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.38655585050582886},{"id":"https://openalex.org/keywords/multimedia","display_name":"Multimedia","score":0.35942232608795166}],"concepts":[{"id":"https://openalex.org/C75165309","wikidata":"https://www.wikidata.org/wiki/Q2258979","display_name":"Search engine indexing","level":2,"score":0.758319616317749},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7550183534622192},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.38655585050582886},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.35942232608795166}],"mesh":[],"locations_count":5,"locations":[{"id":"doi:10.21437/interspeech.2004-46","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2004-46","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2004","raw_type":"proceedings-article"},{"id":"pmh:oai:infoscience.tind.io:82997","is_oa":true,"landing_page_url":"https://infoscience.epfl.ch/handle/20.500.14299/228410","pdf_url":"http://infoscience.epfl.ch/record/82997","source":{"id":"https://openalex.org/S4306400487","display_name":"Infoscience (Ecole Polytechnique F\u00e9d\u00e9rale de Lausanne)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"report"},{"id":"pmh:oai:infoscience.tind.io:83069","is_oa":true,"landing_page_url":"https://infoscience.epfl.ch/handle/20.500.14299/228503","pdf_url":"https://infoscience.epfl.ch/record/83069/files/rr03-39b.pdf","source":{"id":"https://openalex.org/S4306400487","display_name":"Infoscience (Ecole Polytechnique F\u00e9d\u00e9rale de Lausanne)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"conference proceedings"},{"id":"pmh:oai:infoscience.epfl.ch:82997","is_oa":true,"landing_page_url":"http://infoscience.epfl.ch/record/82997","pdf_url":null,"source":{"id":"https://openalex.org/S4306400487","display_name":"Infoscience (Ecole Polytechnique F\u00e9d\u00e9rale de Lausanne)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Text"},{"id":"pmh:oai:infoscience.epfl.ch:83069","is_oa":true,"landing_page_url":"http://infoscience.epfl.ch/record/83069","pdf_url":null,"source":{"id":"https://openalex.org/S4306400487","display_name":"Infoscience (Ecole Polytechnique F\u00e9d\u00e9rale de Lausanne)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Text"}],"best_oa_location":{"id":"pmh:oai:infoscience.tind.io:82997","is_oa":true,"landing_page_url":"https://infoscience.epfl.ch/handle/20.500.14299/228410","pdf_url":"http://infoscience.epfl.ch/record/82997","source":{"id":"https://openalex.org/S4306400487","display_name":"Infoscience (Ecole Polytechnique F\u00e9d\u00e9rale de Lausanne)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"report"},"sustainable_development_goals":[{"score":0.5699999928474426,"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320331353","display_name":"National Center of Competence in Research Chemical Biology","ror":"https://ror.org/033f9yy33"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W1599383372.pdf","grobid_xml":"https://content.openalex.org/works/W1599383372.grobid-xml"},"referenced_works_count":9,"referenced_works":["https://openalex.org/W811578723","https://openalex.org/W1479881079","https://openalex.org/W1482605500","https://openalex.org/W1591300715","https://openalex.org/W2085457662","https://openalex.org/W2127914268","https://openalex.org/W2138406164","https://openalex.org/W2156255174","https://openalex.org/W2171700247"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2748952813","https://openalex.org/W3024364549","https://openalex.org/W4206019083","https://openalex.org/W2048865712","https://openalex.org/W1976265003","https://openalex.org/W2370378377","https://openalex.org/W4237510188","https://openalex.org/W2130160813","https://openalex.org/W2054476758"],"abstract_inverted_index":{"This":[0,23],"paper":[1],"presents":[2],"overview":[3],"of":[4,15,45,52,142,154],"an":[5,103,122],"online":[6],"audio":[7,21,32,144],"indexing":[8,145],"system,":[9],"which":[10],"creates":[11],"a":[12],"searchable":[13],"index":[14],"speech":[16,71,82,94,118],"content":[17],"embedded":[18],"in":[19,121],"digitized":[20],"files.":[22],"system":[24,41,146],"is":[25,55],"based":[26],"on":[27],"our":[28],"recently":[29],"proposed":[30],"offline":[31,157],"segmentation":[33],"techniques.":[34],"As":[35],"the":[36,40,46,137,152,155],"data":[37],"arrives":[38],"continuously,":[39],"first":[42],"finds":[43],"boundaries":[44],"acoustically":[47],"homogenous":[48],"segments.":[49,131],"Next,":[50],"each":[51,140],"these":[53],"segments":[54,83,97],"classified":[56],"as":[57,68],"speech,":[58],"music":[59],"or":[60],"{\\\\it":[61],"mixture}":[62],"classes,":[63],"where":[64,70],"mixtures":[65],"are":[66,76,84,98,109],"defined":[67],"regions":[69],"and":[72,79,95,128,147],"other":[73,113],"non-speech":[74],"sounds":[75],"present":[77],"simultaneously":[78],"noticeably.":[80],"The":[81,93,106],"then":[85],"clustered":[86],"together":[87,111],"to":[88,100,125],"provide":[89],"consistent":[90],"speaker":[91],"labels.":[92],"mixture":[96],"converted":[99],"text":[101],"via":[102],"ASR":[104],"system.":[105],"resulting":[107],"words":[108],"time-stamped":[110],"with":[112,151],"metadata":[114],"information":[115],"(speaker":[116],"identity,":[117],"confidence":[119],"score)":[120],"XML":[123],"file":[124],"rapidly":[126],"identify":[127],"access":[129],"target":[130],"In":[132],"this":[133,143],"paper,":[134],"we":[135],"analyze":[136],"performance":[138,153],"at":[139],"stage":[141],"also":[148],"compare":[149],"it":[150],"corresponding":[156],"modules.":[158]},"counts_by_year":[],"updated_date":"2026-04-15T08:11:43.952461","created_date":"2025-10-10T00:00:00"}
