{"id":"https://openalex.org/W20023308","doi":"https://doi.org/10.21437/icslp.1998-241","title":"Speaker detection in broadcast speech databases","display_name":"Speaker detection in broadcast speech databases","publication_year":1998,"publication_date":"1998-11-30","ids":{"openalex":"https://openalex.org/W20023308","doi":"https://doi.org/10.21437/icslp.1998-241","mag":"20023308"},"language":"en","primary_location":{"id":"doi:10.21437/icslp.1998-241","is_oa":false,"landing_page_url":"https://doi.org/10.21437/icslp.1998-241","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"5th International Conference on Spoken Language Processing (ICSLP 1998)","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/A5025786251","display_name":"A. E. Rosenberg","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Aaron E. Rosenberg","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5087320464","display_name":"Ivan Magrin\u2010Chagnolleau","orcid":"https://orcid.org/0000-0002-7935-1617"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ivan Magrin-Chagnolleau","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103091951","display_name":"Srinivas Parthasarathy","orcid":"https://orcid.org/0000-0001-8928-9821"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"S. Parthasarathy","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5083824997","display_name":"Qian Huang","orcid":"https://orcid.org/0000-0002-6795-5261"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Qian Huang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":21,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"paper 0202","last_page":"0"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9923999905586243,"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/T10860","display_name":"Speech and Audio Processing","score":0.9923999905586243,"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":0.9922000169754028,"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/T10901","display_name":"Advanced Data Compression Techniques","score":0.9599999785423279,"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/speech-recognition","display_name":"Speech recognition","score":0.6901115775108337},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6833299398422241},{"id":"https://openalex.org/keywords/mel-frequency-cepstrum","display_name":"Mel-frequency cepstrum","score":0.6204172372817993},{"id":"https://openalex.org/keywords/frame","display_name":"Frame (networking)","score":0.6008344292640686},{"id":"https://openalex.org/keywords/block","display_name":"Block (permutation group theory)","score":0.586030125617981},{"id":"https://openalex.org/keywords/mixture-model","display_name":"Mixture model","score":0.5852349400520325},{"id":"https://openalex.org/keywords/false-alarm","display_name":"False alarm","score":0.5772545337677002},{"id":"https://openalex.org/keywords/range","display_name":"Range (aeronautics)","score":0.5204722881317139},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.45629146695137024},{"id":"https://openalex.org/keywords/speaker-diarisation","display_name":"Speaker diarisation","score":0.4366067945957184},{"id":"https://openalex.org/keywords/ranging","display_name":"Ranging","score":0.4299178123474121},{"id":"https://openalex.org/keywords/constant-false-alarm-rate","display_name":"Constant false alarm rate","score":0.41370153427124023},{"id":"https://openalex.org/keywords/gaussian","display_name":"Gaussian","score":0.41155609488487244},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.3976373076438904},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.36568957567214966},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.34577247500419617},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.27710145711898804},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.1341860294342041},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.08522894978523254},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.07010012865066528}],"concepts":[{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6901115775108337},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6833299398422241},{"id":"https://openalex.org/C151989614","wikidata":"https://www.wikidata.org/wiki/Q440370","display_name":"Mel-frequency cepstrum","level":3,"score":0.6204172372817993},{"id":"https://openalex.org/C126042441","wikidata":"https://www.wikidata.org/wiki/Q1324888","display_name":"Frame (networking)","level":2,"score":0.6008344292640686},{"id":"https://openalex.org/C2777210771","wikidata":"https://www.wikidata.org/wiki/Q4927124","display_name":"Block (permutation group theory)","level":2,"score":0.586030125617981},{"id":"https://openalex.org/C61224824","wikidata":"https://www.wikidata.org/wiki/Q2260434","display_name":"Mixture model","level":2,"score":0.5852349400520325},{"id":"https://openalex.org/C2776836416","wikidata":"https://www.wikidata.org/wiki/Q1364844","display_name":"False alarm","level":2,"score":0.5772545337677002},{"id":"https://openalex.org/C204323151","wikidata":"https://www.wikidata.org/wiki/Q905424","display_name":"Range (aeronautics)","level":2,"score":0.5204722881317139},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.45629146695137024},{"id":"https://openalex.org/C149838564","wikidata":"https://www.wikidata.org/wiki/Q7574248","display_name":"Speaker diarisation","level":3,"score":0.4366067945957184},{"id":"https://openalex.org/C115051666","wikidata":"https://www.wikidata.org/wiki/Q6522493","display_name":"Ranging","level":2,"score":0.4299178123474121},{"id":"https://openalex.org/C77052588","wikidata":"https://www.wikidata.org/wiki/Q644307","display_name":"Constant false alarm rate","level":2,"score":0.41370153427124023},{"id":"https://openalex.org/C163716315","wikidata":"https://www.wikidata.org/wiki/Q901177","display_name":"Gaussian","level":2,"score":0.41155609488487244},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.3976373076438904},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.36568957567214966},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.34577247500419617},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.27710145711898804},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.1341860294342041},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.08522894978523254},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.07010012865066528},{"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/C146978453","wikidata":"https://www.wikidata.org/wiki/Q3798668","display_name":"Aerospace engineering","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/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.21437/icslp.1998-241","is_oa":false,"landing_page_url":"https://doi.org/10.21437/icslp.1998-241","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"5th International Conference on Spoken Language Processing (ICSLP 1998)","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.12.9863","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.12.9863","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.ddl.ish-lyon.cnrs.fr/membres/imc/publications/icslp/icslp98-spk/icslp98-spk.pdf","raw_type":"text"},{"id":"pmh:oai:scholarship.rice.edu:1911/20304","is_oa":false,"landing_page_url":"http://hdl.handle.net/1911/20304","pdf_url":null,"source":{"id":"https://openalex.org/S4306401268","display_name":"Rice Digital Scholarship Archive (Rice University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I74775410","host_organization_name":"Rice University","host_organization_lineage":["https://openalex.org/I74775410"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Conference paper"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","score":0.6299999952316284,"id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W1963976507","https://openalex.org/W2206035908","https://openalex.org/W3119288895","https://openalex.org/W2185075503","https://openalex.org/W4247736853","https://openalex.org/W1983393909","https://openalex.org/W2162158162","https://openalex.org/W1493012537","https://openalex.org/W1999004162","https://openalex.org/W2175373321"],"abstract_inverted_index":{"Experiments":[0],"have":[1],"been":[2],"carried":[3],"out":[4],"to":[5,109,132,145,148],"assess":[6],"the":[7,31,46,127],"feasibility":[8],"of":[9,22,98,116,122,135],"detecting":[10],"target":[11,28,47,117,136],"speaker":[12,29,48],"segments":[13,137,152],"in":[14],"multi-speaker":[15],"broadcast":[16],"databases.":[17],"The":[18,27,104,120],"experimental":[19],"database":[20],"consists":[21],"NBC":[23],"Nightly":[24],"News":[25],"broadcasts.":[26],"is":[30,130],"news":[32],"anchor,":[33],"Tom":[34],"Brokaw.":[35],"Gaussian":[36],"mixture":[37],"models":[38,53],"are":[39,64,76,92,107,153],"constructed":[40],"from":[41,143],"labelled":[42,61],"training":[43],"data":[44],"for":[45,54,66,94],"as":[49,51],"well":[50],"background":[52],"other":[55],"speakers,":[56],"commercials,":[57],"and":[58],"music.":[59],"Four":[60],"30-min.":[62],"broadcasts":[63,129],"used":[65],"testing.":[67],"Mel-frequency":[68],"cepstral":[69,74],"features,":[70],"augmented":[71],"by":[72],"delta":[73],"features":[75],"calculated":[77,93],"over":[78,96,126,155],"20":[79],"msec.":[80,85],"windows":[81],"shifted":[82],"every":[83],"10":[84],"through":[86],"a":[87,101,110],"broadcast.":[88,159],"Likelihood":[89],"ratio":[90],"scores":[91,106],"eachtestframeaveraged":[95],"blocks":[97],"frames":[99],"with":[100,138],"specified":[102],"duration.":[103],"block":[105],"input":[108],"detection":[111,134],"routine":[112],"which":[113],"returns":[114],"estimates":[115],"segment":[118,139],"boundaries.":[119],"range":[121],"best":[123],"results":[124],"obtained":[125],"test":[128],"82%":[131],"100%":[133],"frame":[140],"accuracy":[141],"ranging":[142],"86%":[144],"95%.":[146],"0":[147],"2":[149],"false":[150],"alarm":[151],"detected":[154],"each":[156],"30":[157],"min.":[158]},"counts_by_year":[{"year":2016,"cited_by_count":2}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}