{"id":"https://openalex.org/W1604358271","doi":"https://doi.org/10.1109/icassp.2015.7178867","title":"Robust overlapped speech detection and its application in word-count estimation for Prof-Life-Log data","display_name":"Robust overlapped speech detection and its application in word-count estimation for Prof-Life-Log data","publication_year":2015,"publication_date":"2015-04-01","ids":{"openalex":"https://openalex.org/W1604358271","doi":"https://doi.org/10.1109/icassp.2015.7178867","mag":"1604358271"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2015.7178867","doi":"https://doi.org/10.1109/icassp.2015.7178867","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2015.7178867","pdf_url":null,"source":{"id":"https://openalex.org/S4363607879","display_name":"IEEE International Conference on Acoustics Speech and Signal Processing","issn_l":"1520-6149","issn":["1520-6149","2379-190X"],"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":["jufo-2","norway-1"],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2015 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"volume":null,"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/A5063419590","display_name":"Navid Shokouhi","orcid":"https://orcid.org/0000-0003-3705-622X","observed_orcids":["https://orcid.org/0000-0003-3705-622X"]},"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":"Navid Shokouhi","raw_affiliation_strings":["Center for Robust Speech Systems (CRSS), The University of Texas at Dallas, Richardson, TX, USA","[Center for Robust Speech Systems (CRSS), The University of Texas at Dallas, Richardson, 75080-3021, USA]"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Center for Robust Speech Systems (CRSS), The University of Texas at Dallas, Richardson, TX, USA","institution_ids":["https://openalex.org/I162577319"]},{"raw_affiliation_string":"[Center for Robust Speech Systems (CRSS), The University of Texas at Dallas, Richardson, 75080-3021, USA]","institution_ids":["https://openalex.org/I162577319"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5112244951","display_name":"Ali Ziaei","orcid":null,"observed_orcids":[]},"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":"Ali Ziaei","raw_affiliation_strings":["Center for Robust Speech Systems (CRSS), The University of Texas at Dallas, Richardson, TX, USA","[Center for Robust Speech Systems (CRSS), The University of Texas at Dallas, Richardson, 75080-3021, USA]"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Center for Robust Speech Systems (CRSS), The University of Texas at Dallas, Richardson, TX, USA","institution_ids":["https://openalex.org/I162577319"]},{"raw_affiliation_string":"[Center for Robust Speech Systems (CRSS), The University of Texas at Dallas, Richardson, 75080-3021, USA]","institution_ids":["https://openalex.org/I162577319"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5111469714","display_name":"Abhijeet Sangwan","orcid":null,"observed_orcids":[]},"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":"Abhijeet Sangwan","raw_affiliation_strings":["Center for Robust Speech Systems (CRSS), The University of Texas at Dallas, Richardson, TX, USA","[Center for Robust Speech Systems (CRSS), The University of Texas at Dallas, Richardson, 75080-3021, USA]"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Center for Robust Speech Systems (CRSS), The University of Texas at Dallas, Richardson, TX, USA","institution_ids":["https://openalex.org/I162577319"]},{"raw_affiliation_string":"[Center for Robust Speech Systems (CRSS), The University of Texas at Dallas, Richardson, 75080-3021, 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","observed_orcids":["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 (CRSS), The University of Texas at Dallas, Richardson, TX, USA","[Center for Robust Speech Systems (CRSS), The University of Texas at Dallas, Richardson, 75080-3021, USA]"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Center for Robust Speech Systems (CRSS), The University of Texas at Dallas, Richardson, TX, USA","institution_ids":["https://openalex.org/I162577319"]},{"raw_affiliation_string":"[Center for Robust Speech Systems (CRSS), The University of Texas at Dallas, Richardson, 75080-3021, USA]","institution_ids":["https://openalex.org/I162577319"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I162577319"],"apc_list":null,"apc_paid":null,"fwci":2.7861,"has_fulltext":false,"cited_by_count":23,"citation_normalized_percentile":{"value":0.92540162,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"4724","last_page":"4728"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.8622999787330627,"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":0.8622999787330627,"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":0.13420000672340393,"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":0.00139999995008111,"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/noise-robustness","display_name":"noise robustness","score":0.6980000138282776},{"id":"https://openalex.org/keywords/syllable-rate","display_name":"syllable rate","score":0.746999979019165},{"id":"https://openalex.org/keywords/syllable-detection","display_name":"syllable detection","score":0.8790000081062317},{"id":"https://openalex.org/keywords/multiparty-conversation","display_name":"multi-party conversation","score":0.6620000004768372},{"id":"https://openalex.org/keywords/speech-enhancement","display_name":"speech enhancement","score":0.382999986410141},{"id":"https://openalex.org/keywords/spectral-subtraction","display_name":"spectral subtraction","score":0.5889999866485596},{"id":"https://openalex.org/keywords/silence-removal","display_name":"silence removal","score":0.6000000238418579},{"id":"https://openalex.org/keywords/language-development-assessment","display_name":"language development assessment","score":0.4909999966621399}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.771723747253418},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7472612857818604},{"id":"https://openalex.org/C185429906","wikidata":"https://www.wikidata.org/wiki/Q1130160","display_name":"Estimator","level":2,"score":0.6653501987457275},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.5960208177566528},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.5785167813301086},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.4865102171897888},{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.4780500531196594},{"id":"https://openalex.org/C109089402","wikidata":"https://www.wikidata.org/wiki/Q8188","display_name":"Syllable","level":2,"score":0.426675021648407},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.32630687952041626},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.29853492975234985},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.15177705883979797},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.13821887969970703},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp.2015.7178867","doi":"https://doi.org/10.1109/icassp.2015.7178867","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2015.7178867","pdf_url":null,"source":{"id":"https://openalex.org/S4363607879","display_name":"IEEE International Conference on Acoustics Speech and Signal Processing","issn_l":"1520-6149","issn":["1520-6149","2379-190X"],"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":["jufo-2","norway-1"],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2015 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":17,"referenced_works":["https://openalex.org/W29573733","https://openalex.org/W1564393028","https://openalex.org/W2014893602","https://openalex.org/W2015143272","https://openalex.org/W2023098317","https://openalex.org/W2023582935","https://openalex.org/W2051758472","https://openalex.org/W2090056283","https://openalex.org/W2098396290","https://openalex.org/W2114537326","https://openalex.org/W2140990243","https://openalex.org/W2167543949","https://openalex.org/W2169264834","https://openalex.org/W2396990951","https://openalex.org/W2398830367","https://openalex.org/W2407942790","https://openalex.org/W4298742451"],"related_works":["https://openalex.org/W2487997950","https://openalex.org/W3008663086","https://openalex.org/W7127441738","https://openalex.org/W2157850507","https://openalex.org/W4407901405","https://openalex.org/W3198999445","https://openalex.org/W2962696180","https://openalex.org/W7097830753","https://openalex.org/W4415433074","https://openalex.org/W2124078061"],"abstract_inverted_index":{"The":[0,135,170],"ability":[1],"to":[2,35,45,79,114,186],"estimate":[3,80],"the":[4,81,92,116,121,132,146],"number":[5,117],"of":[6,16,52,56,83,94,118,131],"words":[7,119],"spoken":[8],"by":[9,158],"an":[10],"individual":[11],"over":[12,193],"a":[13,31,72,87,102,107,128,153,159],"certain":[14],"period":[15],"time":[17],"is":[18,39,99,139,150],"valuable":[19],"in":[20,41,60,64,86,91,162,178],"second":[21],"language":[22,27],"acquisition,":[23],"healthcare,":[24],"and":[25,165,204],"assessing":[26],"development.":[28],"However,":[29],"establishing":[30],"robust":[32,74],"automatic":[33],"framework":[34],"achieve":[36],"high":[37],"accuracy":[38],"non-trivial":[40],"realistic/naturalistic":[42],"scenarios":[43],"due":[44],"various":[46,163],"factors":[47],"such":[48],"as":[49],"different":[50,167],"styles":[51],"conversation":[53],"or":[54],"types":[55],"noise":[57,73,168],"that":[58],"appear":[59],"audio":[61,89],"recordings,":[62],"especially":[63],"multi-party":[65],"conversations.":[66],"In":[67],"this":[68],"study,":[69],"we":[70],"propose":[71],"overlapped":[75],"speech":[76,85,199],"detection":[77,172,184],"algorithm":[78],"likelihood":[82],"overlapping":[84],"given":[88],"file":[90],"presence":[93],"environment":[95],"noise.":[96],"This":[97],"information":[98],"embedded":[100],"into":[101],"word-count":[103,137,187],"estimator,":[104],"which":[105,197],"uses":[106],"linear":[108],"minimum":[109],"mean":[110],"square":[111],"estimator":[112,138],"(LMMSE)":[113],"predict":[115],"from":[120,145],"syllable":[122],"rate.":[123],"Syllables":[124],"are":[125],"detected":[126],"using":[127,152,201],"modified":[129],"version":[130],"mrate":[133],"algorithm.":[134],"proposed":[136],"tested":[140],"on":[141],"long":[142],"duration":[143],"files":[144],"Prof-Life-Log":[147],"corpus.":[148],"Data":[149],"recorded":[151],"LENA":[154],"recording":[155],"device,":[156],"worn":[157],"primary":[160],"speaker":[161],"environments":[164],"under":[166],"conditions.":[169,180],"overlap":[171,183],"system":[173],"significantly":[174],"outperforms":[175],"baseline":[176],"performance":[177],"noisy":[179],"Furthermore,":[181],"applying":[182],"results":[185],"estimation":[188],"achieves":[189],"35%":[190],"relative":[191],"improvement":[192],"our":[194],"previous":[195],"efforts,":[196],"included":[198],"enhancement":[200],"spectral":[202],"subtraction":[203],"silence":[205],"removal.":[206]},"counts_by_year":[{"year":2024,"cited_by_count":2},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":4},{"year":2020,"cited_by_count":2},{"year":2019,"cited_by_count":3},{"year":2018,"cited_by_count":2},{"year":2017,"cited_by_count":7},{"year":2015,"cited_by_count":1}],"updated_date":"2026-10-16T09:59:22.235173","created_date":"2016-06-24T00:00:00"}