{"id":"https://openalex.org/W2612688029","doi":"https://doi.org/10.1109/icassp.2017.7953197","title":"Feature mapping for speaker diarization in noisy conditions","display_name":"Feature mapping for speaker diarization in noisy conditions","publication_year":2017,"publication_date":"2017-03-01","ids":{"openalex":"https://openalex.org/W2612688029","doi":"https://doi.org/10.1109/icassp.2017.7953197","mag":"2612688029"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2017.7953197","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2017.7953197","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2017 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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/A5030532441","display_name":"Weixin Zhu","orcid":null},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Weixin Zhu","raw_affiliation_strings":["National Engineering Laboratory of Speech and Language Information Processing, University of Science and Technology of China, Hefei, P.R.China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Engineering Laboratory of Speech and Language Information Processing, University of Science and Technology of China, Hefei, P.R.China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5038369085","display_name":"Wu Guo","orcid":"https://orcid.org/0000-0002-3779-7944"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wu Guo","raw_affiliation_strings":["National Engineering Laboratory of Speech and Language Information Processing, University of Science and Technology of China, Hefei, P.R.China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Engineering Laboratory of Speech and Language Information Processing, University of Science and Technology of China, Hefei, P.R.China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5076447478","display_name":"Guoping Hu","orcid":"https://orcid.org/0000-0002-7939-4588"},"institutions":[{"id":"https://openalex.org/I1302611135","display_name":"Ministry of Public Security of the People's Republic of China","ror":"https://ror.org/00bt9we26","country_code":"CN","type":"government","lineage":["https://openalex.org/I1302611135"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Guoping Hu","raw_affiliation_strings":["Ministry of Public Security, Key Laboratory of Intelligent Speech Technology, Hefei, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Ministry of Public Security, Key Laboratory of Intelligent Speech Technology, Hefei, China","institution_ids":["https://openalex.org/I1302611135"]}]}],"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":4,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"5445","last_page":"5449"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech 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/T10860","display_name":"Speech 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":0.9995999932289124,"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":0.9991000294685364,"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/speaker-diarisation","display_name":"Speaker diarisation","score":0.893775463104248},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7749884128570557},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6772618293762207},{"id":"https://openalex.org/keywords/fuse","display_name":"Fuse (electrical)","score":0.6654192209243774},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.5742394924163818},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.5661822557449341},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5058574080467224},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.48474952578544617},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4669222831726074},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.38076817989349365}],"concepts":[{"id":"https://openalex.org/C149838564","wikidata":"https://www.wikidata.org/wiki/Q7574248","display_name":"Speaker diarisation","level":3,"score":0.893775463104248},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7749884128570557},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6772618293762207},{"id":"https://openalex.org/C141353440","wikidata":"https://www.wikidata.org/wiki/Q182221","display_name":"Fuse (electrical)","level":2,"score":0.6654192209243774},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.5742394924163818},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.5661822557449341},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5058574080467224},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.48474952578544617},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4669222831726074},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.38076817989349365},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.0},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp.2017.7953197","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2017.7953197","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2017 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":18,"referenced_works":["https://openalex.org/W106647055","https://openalex.org/W184672293","https://openalex.org/W1482605500","https://openalex.org/W1598508708","https://openalex.org/W1607302042","https://openalex.org/W1965819578","https://openalex.org/W1969290787","https://openalex.org/W2040023846","https://openalex.org/W2078528584","https://openalex.org/W2106793713","https://openalex.org/W2140046090","https://openalex.org/W2240726287","https://openalex.org/W2283724112","https://openalex.org/W2289985966","https://openalex.org/W2396495723","https://openalex.org/W2400893182","https://openalex.org/W2405137844","https://openalex.org/W2408713104"],"related_works":["https://openalex.org/W2206035908","https://openalex.org/W2162158162","https://openalex.org/W4247736853","https://openalex.org/W1493012537","https://openalex.org/W1999004162","https://openalex.org/W2175373321","https://openalex.org/W2125642021","https://openalex.org/W1521049138","https://openalex.org/W2938358845","https://openalex.org/W2997340161"],"abstract_inverted_index":{"Speaker":[0],"diarization":[1,41],"in":[2,7],"noisy":[3,19],"conditions":[4],"is":[5,13,36,52],"addressed":[6],"this":[8],"paper.":[9],"The":[10,43],"regression-based":[11],"DNN":[12],"first":[14],"adopted":[15],"to":[16,22,38,69],"map":[17],"the":[18,23,31,40,48,70,85],"acoustic":[20],"features":[21,35],"clean":[24],"features,":[25,75],"and":[26,33,66],"then":[27],"consensus":[28],"clustering":[29],"of":[30],"original":[32],"mapped":[34],"used":[37],"fuse":[39],"results.":[42],"experiments":[44],"are":[45],"conducted":[46],"on":[47],"IFLY-DIAR-II":[49],"database,":[50],"which":[51],"a":[53,76],"Chinese":[54],"talk":[55],"show":[56],"database":[57],"with":[58],"various":[59],"noise":[60],"types,":[61],"such":[62],"as":[63],"music,":[64],"applause":[65],"laughter.":[67],"Compared":[68],"baseline":[71],"system":[72],"using":[73,84],"PLP":[74],"21.26%":[77],"relative":[78],"DER":[79],"improvement":[80],"can":[81],"be":[82],"achieved":[83],"proposed":[86],"algorithm.":[87]},"counts_by_year":[{"year":2020,"cited_by_count":1},{"year":2018,"cited_by_count":3}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}