{"id":"https://openalex.org/W200131022","doi":"https://doi.org/10.21437/interspeech.2010-148","title":"Using phoneme recognition and text-dependent speaker verification to improve speaker segmentation for Chinese speech","display_name":"Using phoneme recognition and text-dependent speaker verification to improve speaker segmentation for Chinese speech","publication_year":2010,"publication_date":"2010-09-26","ids":{"openalex":"https://openalex.org/W200131022","doi":"https://doi.org/10.21437/interspeech.2010-148","mag":"200131022"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2010-148","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2010-148","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2010","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/A5107031356","display_name":"Gang Wang","orcid":null},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Gang Wang","raw_affiliation_strings":["Tsinghua University, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5087450445","display_name":"Xiao\u2010Jun Wu","orcid":"https://orcid.org/0000-0002-0310-5778"},"institutions":[{"id":"https://openalex.org/I111599522","display_name":"Jiangnan University","ror":"https://ror.org/04mkzax54","country_code":"CN","type":"education","lineage":["https://openalex.org/I111599522"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaojun Wu","raw_affiliation_strings":["Jiangnan University, Wuxi, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Jiangnan University, Wuxi, China","institution_ids":["https://openalex.org/I111599522"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5084318285","display_name":"Thomas Fang Zheng","orcid":"https://orcid.org/0000-0002-0249-4767"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Thomas Fang Zheng","raw_affiliation_strings":["Tsinghua University, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1457","last_page":"1460"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"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"}},"topics":[{"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/T10860","display_name":"Speech and Audio Processing","score":0.986299991607666,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9728000164031982,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.8610106706619263},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8233649134635925},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.7651705741882324},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.7337679266929626},{"id":"https://openalex.org/keywords/speaker-diarisation","display_name":"Speaker diarisation","score":0.7267510890960693},{"id":"https://openalex.org/keywords/dynamic-time-warping","display_name":"Dynamic time warping","score":0.7223184108734131},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4875795245170593},{"id":"https://openalex.org/keywords/speech-segmentation","display_name":"Speech segmentation","score":0.46552082896232605},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.43237653374671936},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.43110042810440063}],"concepts":[{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.8610106706619263},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8233649134635925},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.7651705741882324},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.7337679266929626},{"id":"https://openalex.org/C149838564","wikidata":"https://www.wikidata.org/wiki/Q7574248","display_name":"Speaker diarisation","level":3,"score":0.7267510890960693},{"id":"https://openalex.org/C88516994","wikidata":"https://www.wikidata.org/wiki/Q1268863","display_name":"Dynamic time warping","level":2,"score":0.7223184108734131},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4875795245170593},{"id":"https://openalex.org/C207030507","wikidata":"https://www.wikidata.org/wiki/Q2266173","display_name":"Speech segmentation","level":3,"score":0.46552082896232605},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.43237653374671936},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.43110042810440063}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.21437/interspeech.2010-148","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2010-148","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2010","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.703.7431","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.703.7431","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://cslt.riit.tsinghua.edu.cn/%7Efzheng/PAPERS/2010/1009E_InterSpeech_phoneme-based-speaker-segmentation_WG%28ZF%29.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.5799999833106995}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":17,"referenced_works":["https://openalex.org/W119794901","https://openalex.org/W1482605500","https://openalex.org/W1484181928","https://openalex.org/W1558681748","https://openalex.org/W2041823554","https://openalex.org/W2057752423","https://openalex.org/W2062497323","https://openalex.org/W2069976350","https://openalex.org/W2070176749","https://openalex.org/W2090724554","https://openalex.org/W2101025008","https://openalex.org/W2125642021","https://openalex.org/W2144760012","https://openalex.org/W2151299225","https://openalex.org/W2166980079","https://openalex.org/W2169516439","https://openalex.org/W2170695863"],"related_works":["https://openalex.org/W2419138286","https://openalex.org/W2507549656","https://openalex.org/W2050318184","https://openalex.org/W101156158","https://openalex.org/W2182848507","https://openalex.org/W2387825067","https://openalex.org/W2506414444","https://openalex.org/W2125642021","https://openalex.org/W2144208207","https://openalex.org/W2099333848"],"abstract_inverted_index":{"Speaker":[0],"segmentation":[1,16,47],"is":[2,65,72,90],"widely":[3],"used":[4],"in":[5,96],"many":[6],"tasks":[7],"such":[8],"as":[9],"multi-speaker":[10],"detection":[11],"and":[12,61,79,119],"speaker":[13,23,63,82,125],"tracking.":[14],"The":[15],"performance":[17,21,40,48,111],"depends":[18],"on":[19,58,85,92],"the":[20,35,38,46,93,116,120],"of":[22,37],"verification":[24],"(SV)":[25],"between":[26],"two":[27,97],"short":[28,42,130],"utterances":[29,43,131],"to":[30],"a":[31,49,55,69,76],"large":[32],"extent,":[33],"so":[34],"improvement":[36],"SV":[39],"for":[41],"would":[44],"give":[45],"great":[50],"help.":[51],"In":[52],"this":[53],"paper,":[54],"method":[56,118],"based":[57,84],"phoneme":[59,70,77,95,127],"recognition":[60,64,83],"text-dependent":[62,81],"proposed.":[66],"During":[67],"segmentation,":[68,126],"sequence":[71],"first":[73],"recognized":[74],"using":[75],"recognizer":[78],"then":[80],"dynamic":[86],"time":[87],"warping":[88],"(DTW)":[89],"performed":[91],"same":[94],"adjacent":[98],"windows.":[99],"Experiments":[100],"over":[101],"Chinese":[102],"Corpus":[103],"Consortium":[104],"(CCC)":[105],"MSS":[106],"database":[107],"showed":[108],"that":[109],"better":[110],"was":[112],"achieved":[113],"compared":[114],"with":[115],"BIC":[117],"GLR":[121],"method.":[122],"Index":[123],"Terms:":[124],"recognition,":[128],"text-dependent,":[129]},"counts_by_year":[{"year":2021,"cited_by_count":1},{"year":2018,"cited_by_count":2}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}