{"id":"https://openalex.org/W1485877426","doi":"https://doi.org/10.21437/interspeech.2009-272","title":"Improving speaker segmentation via speaker identification and text segmentation","display_name":"Improving speaker segmentation via speaker identification and text segmentation","publication_year":2009,"publication_date":"2009-09-06","ids":{"openalex":"https://openalex.org/W1485877426","doi":"https://doi.org/10.21437/interspeech.2009-272","mag":"1485877426"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2009-272","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2009-272","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2009","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/A5036810731","display_name":"Runxin Li","orcid":null},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Runxin Li","raw_affiliation_strings":["Carnegie Mellon University, Pittsburgh, United States"],"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University, Pittsburgh, United States","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5058049725","display_name":"Tanja Schultz","orcid":"https://orcid.org/0000-0002-9809-7028"},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Tanja Schultz","raw_affiliation_strings":["Carnegie Mellon University, Pittsburgh, United States"],"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University, Pittsburgh, United States","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101665677","display_name":"Qin Jin","orcid":"https://orcid.org/0000-0003-4163-6067"},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Qin Jin","raw_affiliation_strings":["Carnegie Mellon University"],"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University","institution_ids":["https://openalex.org/I74973139"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5036810731"],"corresponding_institution_ids":["https://openalex.org/I74973139"],"apc_list":null,"apc_paid":null,"fwci":1.8065,"has_fulltext":false,"cited_by_count":10,"citation_normalized_percentile":{"value":0.86745014,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"904","last_page":"907"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9952999949455261,"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":0.9944000244140625,"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/computer-science","display_name":"Computer science","score":0.7470881938934326},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.7134382724761963},{"id":"https://openalex.org/keywords/speaker-identification","display_name":"Speaker identification","score":0.6711851954460144},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.6369502544403076},{"id":"https://openalex.org/keywords/speaker-diarisation","display_name":"Speaker diarisation","score":0.632628858089447},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5915932655334473},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.564749538898468},{"id":"https://openalex.org/keywords/identification","display_name":"Identification (biology)","score":0.5151925683021545},{"id":"https://openalex.org/keywords/image-segmentation","display_name":"Image segmentation","score":0.4356297552585602},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3879045248031616},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.33285805583000183}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7470881938934326},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.7134382724761963},{"id":"https://openalex.org/C2986627078","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker identification","level":3,"score":0.6711851954460144},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.6369502544403076},{"id":"https://openalex.org/C149838564","wikidata":"https://www.wikidata.org/wiki/Q7574248","display_name":"Speaker diarisation","level":3,"score":0.632628858089447},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5915932655334473},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.564749538898468},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.5151925683021545},{"id":"https://openalex.org/C124504099","wikidata":"https://www.wikidata.org/wiki/Q56933","display_name":"Image segmentation","level":3,"score":0.4356297552585602},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3879045248031616},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.33285805583000183},{"id":"https://openalex.org/C59822182","wikidata":"https://www.wikidata.org/wiki/Q441","display_name":"Botany","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.21437/interspeech.2009-272","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2009-272","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2009","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.149.5630","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.149.5630","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://csl.ira.uka.de/fileadmin/media/publication_files/Interspeech09_Li.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","score":0.7300000190734863,"id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":11,"referenced_works":["https://openalex.org/W3765491","https://openalex.org/W106647055","https://openalex.org/W1482605500","https://openalex.org/W2018627475","https://openalex.org/W2041823554","https://openalex.org/W2121750345","https://openalex.org/W2143203634","https://openalex.org/W2165880886","https://openalex.org/W2167797633","https://openalex.org/W2405439032","https://openalex.org/W2620921085"],"related_works":["https://openalex.org/W2206035908","https://openalex.org/W4318225096","https://openalex.org/W2126085626","https://openalex.org/W2545131480","https://openalex.org/W2087341511","https://openalex.org/W1521049138","https://openalex.org/W4247736853","https://openalex.org/W2997340161","https://openalex.org/W1964028329","https://openalex.org/W2136038945"],"abstract_inverted_index":{"Speaker":[0],"segmentation":[1,12,70,152],"is":[2],"an":[3],"essential":[4],"part":[5],"of":[6,76],"a":[7],"speaker":[8,16,29,37,57,62,77,82,99,109,140,145,147,149],"diarization":[9,38,83,100,141],"system.":[10,117],"Common":[11],"systems":[13],"usually":[14],"miss":[15],"change":[17,110],"points":[18],"when":[19],"speakers":[20],"switch":[21],"fast.":[22],"These":[23],"errors":[24],"seriously":[25],"confuse":[26],"the":[27,65,74,98,108,115,130],"following":[28],"clustering":[30],"step":[31],"and":[32,102],"result":[33],"in":[34,97,107,138],"high":[35],"overall":[36],"error":[39,101],"rates.":[40],"In":[41],"this":[42,51],"paper":[43],"two":[44,121],"methods":[45,71,89],"are":[46],"proposed":[47],"to":[48,60,72,92],"deal":[49],"with":[50],"problem:":[52],"The":[53],"first":[54],"approach":[55,67],"uses":[56],"identification":[58],"techniques":[59],"boost":[61],"segmentation.":[63,78],"And":[64],"second":[66],"applies":[68],"text":[69,151],"improve":[73],"performance":[75],"Experiments":[79],"on":[80],"Quaero":[81],"evaluation":[84],"data":[85],"shows":[86],"that":[87],"our":[88],"achieve":[90],"up":[91],"45":[93],"%":[94,104],"relative":[95,105],"reduction":[96],"64":[103],"increase":[106],"detection":[111],"recall":[112],"rate":[113],"over":[114,129],"baseline":[116,131],"Moreover,":[118],"both":[119],"these":[120],"approaches":[122],"can":[123,135],"be":[124,136],"considered":[125],"as":[126],"post-processing":[127],"steps":[128],"segmentation,":[132,148],"therefore,":[133],"they":[134],"applied":[137],"any":[139],"systems.":[142],"Index":[143],"Terms:":[144],"diarization,":[146],"identification,":[150]},"counts_by_year":[{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":1},{"year":2019,"cited_by_count":1},{"year":2017,"cited_by_count":2},{"year":2014,"cited_by_count":1},{"year":2012,"cited_by_count":3}],"updated_date":"2026-04-05T17:49:38.594831","created_date":"2025-10-10T00:00:00"}