{"id":"https://openalex.org/W2667475753","doi":"https://doi.org/10.1109/icassp.2017.7953198","title":"Environment aware speaker diarization for moving targets using parallel DNN-based recognizers","display_name":"Environment aware speaker diarization for moving targets using parallel DNN-based recognizers","publication_year":2017,"publication_date":"2017-03-01","ids":{"openalex":"https://openalex.org/W2667475753","doi":"https://doi.org/10.1109/icassp.2017.7953198","mag":"2667475753"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2017.7953198","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2017.7953198","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":"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/A5112035956","display_name":"Maryam Najafian","orcid":null},"institutions":[{"id":"https://openalex.org/I162577319","display_name":"The University of Texas at Dallas","ror":"https://ror.org/049emcs32","country_code":"US","type":"education","lineage":["https://openalex.org/I162577319"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Maryam Najafian","raw_affiliation_strings":["Center for Robust Speech Systems, University of Texas at Dallas, Richardson, TX, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Center for Robust Speech Systems, University of Texas at Dallas, Richardson, TX, USA","institution_ids":["https://openalex.org/I162577319"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5057910370","display_name":"John H. L. Hansen","orcid":"https://orcid.org/0000-0003-1382-9929"},"institutions":[{"id":"https://openalex.org/I162577319","display_name":"The University of Texas at Dallas","ror":"https://ror.org/049emcs32","country_code":"US","type":"education","lineage":["https://openalex.org/I162577319"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"John H. L. Hansen","raw_affiliation_strings":["Center for Robust Speech Systems, University of Texas at Dallas, Richardson, TX, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Center for Robust Speech Systems, University of Texas at Dallas, Richardson, TX, USA","institution_ids":["https://openalex.org/I162577319"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.5603,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.64671762,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":96},"biblio":{"volume":"7","issue":null,"first_page":"5450","last_page":"5454"},"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/T11309","display_name":"Music and Audio Processing","score":0.9991999864578247,"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":0.9990000128746033,"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/speaker-diarisation","display_name":"Speaker diarisation","score":0.8748325109481812},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8222250938415527},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.7172138690948486},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7141682505607605},{"id":"https://openalex.org/keywords/microphone","display_name":"Microphone","score":0.670547366142273},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.5696427226066589},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.5236760973930359},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.5033265948295593},{"id":"https://openalex.org/keywords/exploit","display_name":"Exploit","score":0.47812166810035706},{"id":"https://openalex.org/keywords/voice-activity-detection","display_name":"Voice activity detection","score":0.4515988230705261},{"id":"https://openalex.org/keywords/tracking","display_name":"Tracking (education)","score":0.4167852997779846},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.41349565982818604},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.40921133756637573},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3459899425506592},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.34323811531066895},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.0793183445930481},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.07478779554367065}],"concepts":[{"id":"https://openalex.org/C149838564","wikidata":"https://www.wikidata.org/wiki/Q7574248","display_name":"Speaker diarisation","level":3,"score":0.8748325109481812},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8222250938415527},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.7172138690948486},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7141682505607605},{"id":"https://openalex.org/C2778263558","wikidata":"https://www.wikidata.org/wiki/Q46384","display_name":"Microphone","level":3,"score":0.670547366142273},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.5696427226066589},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5236760973930359},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.5033265948295593},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.47812166810035706},{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.4515988230705261},{"id":"https://openalex.org/C2775936607","wikidata":"https://www.wikidata.org/wiki/Q466845","display_name":"Tracking (education)","level":2,"score":0.4167852997779846},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.41349565982818604},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.40921133756637573},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3459899425506592},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.34323811531066895},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0793183445930481},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.07478779554367065},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.0},{"id":"https://openalex.org/C19417346","wikidata":"https://www.wikidata.org/wiki/Q7922","display_name":"Pedagogy","level":1,"score":0.0},{"id":"https://openalex.org/C68115822","wikidata":"https://www.wikidata.org/wiki/Q1068172","display_name":"Sound pressure","level":2,"score":0.0},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp.2017.7953198","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2017.7953198","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":[{"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions","score":0.4399999976158142}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":41,"referenced_works":["https://openalex.org/W44815768","https://openalex.org/W76945434","https://openalex.org/W135246240","https://openalex.org/W142991516","https://openalex.org/W189596042","https://openalex.org/W1484181928","https://openalex.org/W1578701839","https://openalex.org/W1670780163","https://openalex.org/W1969685872","https://openalex.org/W2023582935","https://openalex.org/W2081074144","https://openalex.org/W2116064496","https://openalex.org/W2132211083","https://openalex.org/W2166980079","https://openalex.org/W2266728862","https://openalex.org/W2268837224","https://openalex.org/W2294933947","https://openalex.org/W2397149834","https://openalex.org/W2400702965","https://openalex.org/W2403894853","https://openalex.org/W2482460197","https://openalex.org/W2485217158","https://openalex.org/W2505434962","https://openalex.org/W2514325906","https://openalex.org/W2514794854","https://openalex.org/W2547178373","https://openalex.org/W2549762342","https://openalex.org/W2563473989","https://openalex.org/W2578415609","https://openalex.org/W2587126577","https://openalex.org/W2620757702","https://openalex.org/W2962732406","https://openalex.org/W4205130185","https://openalex.org/W6605762983","https://openalex.org/W6607775107","https://openalex.org/W6697306262","https://openalex.org/W6712137335","https://openalex.org/W6713242239","https://openalex.org/W6726425234","https://openalex.org/W6732217805","https://openalex.org/W6738902873"],"related_works":["https://openalex.org/W2206035908","https://openalex.org/W1977167953","https://openalex.org/W2149220986","https://openalex.org/W4247736853","https://openalex.org/W2162158162","https://openalex.org/W1493012537","https://openalex.org/W1999004162","https://openalex.org/W2125642021","https://openalex.org/W1521049138","https://openalex.org/W2023466863"],"abstract_inverted_index":{"Current":[0],"diarization":[1,37,96],"algorithms":[2],"are":[3],"commonly":[4],"applied":[5,38],"to":[6,39,48,101],"the":[7,18,40,85,94,99],"outputs":[8],"of":[9,20,74],"single":[10,45],"non-moving":[11],"microphones.":[12],"They":[13],"do":[14],"not":[15],"explicitly":[16],"identify":[17],"content":[19],"overlapped":[21,90],"segments":[22,80],"from":[23],"multiple":[24],"speakers":[25],"or":[26,104],"acoustic":[27,33],"events.":[28],"This":[29],"paper":[30],"presents":[31],"an":[32],"environment":[34],"aware":[35],"child-adult":[36],"audio":[41,79],"recorded":[42],"by":[43],"a":[44,60],"microphone":[46],"attached":[47],"moving":[49],"targets":[50],"under":[51],"realistic":[52],"high":[53],"noise":[54],"conditions.":[55],"The":[56],"proposed":[57],"system":[58],"exploits":[59],"parallel":[61],"deep":[62],"neural":[63],"network":[64],"and":[65],"hidden":[66],"Markov":[67],"model":[68],"based":[69],"approach":[70],"which":[71],"enables":[72],"tracking":[73],"rapid":[75],"turn":[76],"changes":[77],"in":[78],"as":[81,83],"well":[82],"capturing":[84],"cross":[86],"talk":[87],"labels":[88],"for":[89],"speech.":[91],"It":[92],"outperforms":[93],"state-of-the-art":[95],"systems":[97],"without":[98],"need":[100],"prior":[102],"clustering":[103],"front-end":[105],"speech":[106],"activity":[107],"detection.":[108]},"counts_by_year":[{"year":2019,"cited_by_count":2},{"year":2017,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}