{"id":"https://openalex.org/W2167882836","doi":"https://doi.org/10.1109/icme.2005.1521419","title":"Enhance Speaker Segmentation by Elaborating Utterance Detection","display_name":"Enhance Speaker Segmentation by Elaborating Utterance Detection","publication_year":2005,"publication_date":"2005-10-24","ids":{"openalex":"https://openalex.org/W2167882836","doi":"https://doi.org/10.1109/icme.2005.1521419","mag":"2167882836"},"language":"en","primary_location":{"id":"doi:10.1109/icme.2005.1521419","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icme.2005.1521419","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2005 IEEE International Conference on Multimedia and Expo","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/A5054067088","display_name":"Min Yang","orcid":"https://orcid.org/0000-0003-3814-2728"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Min Yang","raw_affiliation_strings":["College of Computer Science and Technical, University of Zhejiang, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"College of Computer Science and Technical, University of Zhejiang, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101973484","display_name":"Zhaohui Wu","orcid":"https://orcid.org/0000-0002-4319-3645"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhaohui Wu","raw_affiliation_strings":["College of Computer Science and Technical, University of Zhejiang, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"College of Computer Science and Technical, University of Zhejiang, China","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5054835275","display_name":"Yingchun Yang","orcid":"https://orcid.org/0000-0002-5582-7836"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yingchun Yang","raw_affiliation_strings":["College of Computer Science and Technical, University of Zhejiang, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"College of Computer Science and Technical, University of Zhejiang, China","institution_ids":[]}]}],"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":1,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":"41","issue":null,"first_page":"297","last_page":"300"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech 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/T10860","display_name":"Speech 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":0.9995999932289124,"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/T11309","display_name":"Music and Audio Processing","score":0.9994000196456909,"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/utterance","display_name":"Utterance","score":0.8456257581710815},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8158998489379883},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.7542173862457275},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7443704009056091},{"id":"https://openalex.org/keywords/speaker-verification","display_name":"Speaker verification","score":0.6189817190170288},{"id":"https://openalex.org/keywords/speaker-diarisation","display_name":"Speaker diarisation","score":0.5674706101417542},{"id":"https://openalex.org/keywords/classifier","display_name":"Classifier (UML)","score":0.5632407069206238},{"id":"https://openalex.org/keywords/detector","display_name":"Detector","score":0.5160224437713623},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.49700143933296204},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.482384592294693},{"id":"https://openalex.org/keywords/voice-activity-detection","display_name":"Voice activity detection","score":0.45434141159057617},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.42818811535835266},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.36438918113708496},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.35289621353149414}],"concepts":[{"id":"https://openalex.org/C2775852435","wikidata":"https://www.wikidata.org/wiki/Q258403","display_name":"Utterance","level":2,"score":0.8456257581710815},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8158998489379883},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.7542173862457275},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7443704009056091},{"id":"https://openalex.org/C2982762665","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker verification","level":3,"score":0.6189817190170288},{"id":"https://openalex.org/C149838564","wikidata":"https://www.wikidata.org/wiki/Q7574248","display_name":"Speaker diarisation","level":3,"score":0.5674706101417542},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.5632407069206238},{"id":"https://openalex.org/C94915269","wikidata":"https://www.wikidata.org/wiki/Q1834857","display_name":"Detector","level":2,"score":0.5160224437713623},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.49700143933296204},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.482384592294693},{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.45434141159057617},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.42818811535835266},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.36438918113708496},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.35289621353149414},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","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}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/icme.2005.1521419","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icme.2005.1521419","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2005 IEEE International Conference on Multimedia and Expo","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.332.5792","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.332.5792","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.cecs.uci.edu/~papers/icme05/defevent/papers/cr1196.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","score":0.550000011920929,"id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":9,"referenced_works":["https://openalex.org/W125260059","https://openalex.org/W1484181928","https://openalex.org/W2009422037","https://openalex.org/W2032474878","https://openalex.org/W2110215948","https://openalex.org/W2151299225","https://openalex.org/W2151305614","https://openalex.org/W2172081649","https://openalex.org/W6605093602"],"related_works":["https://openalex.org/W2206035908","https://openalex.org/W2162158162","https://openalex.org/W4235705411","https://openalex.org/W1521299571","https://openalex.org/W4247736853","https://openalex.org/W1493012537","https://openalex.org/W2175373321","https://openalex.org/W3141593045","https://openalex.org/W2134501921","https://openalex.org/W2144470400"],"abstract_inverted_index":{"In":[0],"this":[1,25,31,55],"paper,":[2],"we":[3],"introduce":[4],"an":[5],"elaborate":[6,26],"utterance":[7,27],"detection":[8],"algorithm":[9,32],"to":[10,29],"enhance":[11],"speaker":[12,64],"segmentation.":[13],"Silence":[14],"detector,":[15],"further":[16],"divider":[17],"and":[18,37],"audio":[19],"type":[20],"classifier":[21],"are":[22],"employed":[23],"in":[24],"detection,":[28],"make":[30],"adaptive":[33],"for":[34,63],"both":[35],"silent":[36],"noisy":[38],"environments.":[39],"Open-set":[40],"verification":[41],"testing":[42],"has":[43],"taken":[44],"on":[45],"the":[46],"Hub4-NE":[47],"broadcasts":[48],"database.":[49],"The":[50],"experiment":[51],"results":[52],"show":[53],"that":[54],"enhanced":[56],"segmentation":[57],"method":[58],"can":[59],"provide":[60],"better":[61],"information":[62],"models.":[65]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}