{"id":"https://openalex.org/W3082502994","doi":"https://doi.org/10.1109/spcom50965.2020.9179591","title":"Overlapped/Non-Overlapped Speech Transition Point Detection Using Bag-of-Audio-Words","display_name":"Overlapped/Non-Overlapped Speech Transition Point Detection Using Bag-of-Audio-Words","publication_year":2020,"publication_date":"2020-07-01","ids":{"openalex":"https://openalex.org/W3082502994","doi":"https://doi.org/10.1109/spcom50965.2020.9179591","mag":"3082502994"},"language":"en","primary_location":{"id":"doi:10.1109/spcom50965.2020.9179591","is_oa":false,"landing_page_url":"https://doi.org/10.1109/spcom50965.2020.9179591","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 International Conference on Signal Processing and Communications (SPCOM)","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/A5014495539","display_name":"Shikha Baghel","orcid":"https://orcid.org/0000-0002-9425-978X"},"institutions":[{"id":"https://openalex.org/I1317621060","display_name":"Indian Institute of Technology Guwahati","ror":"https://ror.org/0022nd079","country_code":"IN","type":"education","lineage":["https://openalex.org/I1317621060"]}],"countries":["IN"],"is_corresponding":true,"raw_author_name":"Shikha Baghel","raw_affiliation_strings":["Department of Electronics and Electrical Engineering, Indian Institute of Technology, Guwahati, Assam, India"],"affiliations":[{"raw_affiliation_string":"Department of Electronics and Electrical Engineering, Indian Institute of Technology, Guwahati, Assam, India","institution_ids":["https://openalex.org/I1317621060"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5052129812","display_name":"S. R. Mahadeva Prasanna","orcid":"https://orcid.org/0000-0002-8135-7938"},"institutions":[{"id":"https://openalex.org/I4210152718","display_name":"Indian Institute of Technology Dharwad","ror":"https://ror.org/0509djg30","country_code":"IN","type":"education","lineage":["https://openalex.org/I4210152718"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"S. R. Mahadeva Prasanna","raw_affiliation_strings":["Department of Electrical Engineering, Indian Institute of Technology, Dharwad, Dharwad, India"],"affiliations":[{"raw_affiliation_string":"Department of Electrical Engineering, Indian Institute of Technology, Dharwad, Dharwad, India","institution_ids":["https://openalex.org/I4210152718"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5086733387","display_name":"Prithwijit Guhal","orcid":null},"institutions":[{"id":"https://openalex.org/I1317621060","display_name":"Indian Institute of Technology Guwahati","ror":"https://ror.org/0022nd079","country_code":"IN","type":"education","lineage":["https://openalex.org/I1317621060"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Prithwijit Guhal","raw_affiliation_strings":["Department of Electronics and Electrical Engineering, Indian Institute of Technology, Guwahati, Assam, India"],"affiliations":[{"raw_affiliation_string":"Department of Electronics and Electrical Engineering, Indian Institute of Technology, Guwahati, Assam, India","institution_ids":["https://openalex.org/I1317621060"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5014495539"],"corresponding_institution_ids":["https://openalex.org/I1317621060"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.09842001,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"3","issue":null,"first_page":"1","last_page":"5"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9998000264167786,"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":0.9991999864578247,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/vocal-tract","display_name":"Vocal tract","score":0.8302526473999023},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.8096300363540649},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6942009925842285},{"id":"https://openalex.org/keywords/speaker-diarisation","display_name":"Speaker diarisation","score":0.6195375919342041},{"id":"https://openalex.org/keywords/signal","display_name":"SIGNAL (programming language)","score":0.5796374678611755},{"id":"https://openalex.org/keywords/linear-prediction","display_name":"Linear prediction","score":0.5606816411018372},{"id":"https://openalex.org/keywords/spectral-envelope","display_name":"Spectral envelope","score":0.4888131320476532},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.4867680072784424},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.4549027681350708},{"id":"https://openalex.org/keywords/residual","display_name":"Residual","score":0.4533689022064209},{"id":"https://openalex.org/keywords/speech-coding","display_name":"Speech coding","score":0.44827720522880554},{"id":"https://openalex.org/keywords/mel-frequency-cepstrum","display_name":"Mel-frequency cepstrum","score":0.44138211011886597},{"id":"https://openalex.org/keywords/loudspeaker","display_name":"Loudspeaker","score":0.4302579164505005},{"id":"https://openalex.org/keywords/envelope","display_name":"Envelope (radar)","score":0.4219835102558136},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3698861598968506},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.33108046650886536},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.3140002191066742},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.20785292983055115},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.11974844336509705},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.09376347064971924},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.09152311086654663}],"concepts":[{"id":"https://openalex.org/C47401133","wikidata":"https://www.wikidata.org/wiki/Q748953","display_name":"Vocal tract","level":2,"score":0.8302526473999023},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.8096300363540649},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6942009925842285},{"id":"https://openalex.org/C149838564","wikidata":"https://www.wikidata.org/wiki/Q7574248","display_name":"Speaker diarisation","level":3,"score":0.6195375919342041},{"id":"https://openalex.org/C2779843651","wikidata":"https://www.wikidata.org/wiki/Q7390335","display_name":"SIGNAL (programming language)","level":2,"score":0.5796374678611755},{"id":"https://openalex.org/C131109320","wikidata":"https://www.wikidata.org/wiki/Q581012","display_name":"Linear prediction","level":2,"score":0.5606816411018372},{"id":"https://openalex.org/C54926389","wikidata":"https://www.wikidata.org/wiki/Q7575188","display_name":"Spectral envelope","level":2,"score":0.4888131320476532},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.4867680072784424},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.4549027681350708},{"id":"https://openalex.org/C155512373","wikidata":"https://www.wikidata.org/wiki/Q287450","display_name":"Residual","level":2,"score":0.4533689022064209},{"id":"https://openalex.org/C13895895","wikidata":"https://www.wikidata.org/wiki/Q3270773","display_name":"Speech coding","level":2,"score":0.44827720522880554},{"id":"https://openalex.org/C151989614","wikidata":"https://www.wikidata.org/wiki/Q440370","display_name":"Mel-frequency cepstrum","level":3,"score":0.44138211011886597},{"id":"https://openalex.org/C157138929","wikidata":"https://www.wikidata.org/wiki/Q570","display_name":"Loudspeaker","level":2,"score":0.4302579164505005},{"id":"https://openalex.org/C65155139","wikidata":"https://www.wikidata.org/wiki/Q5380912","display_name":"Envelope (radar)","level":3,"score":0.4219835102558136},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3698861598968506},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.33108046650886536},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.3140002191066742},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.20785292983055115},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.11974844336509705},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.09376347064971924},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.09152311086654663},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C554190296","wikidata":"https://www.wikidata.org/wiki/Q47528","display_name":"Radar","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/spcom50965.2020.9179591","is_oa":false,"landing_page_url":"https://doi.org/10.1109/spcom50965.2020.9179591","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 International Conference on Signal Processing and Communications (SPCOM)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.6700000166893005,"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":15,"referenced_works":["https://openalex.org/W43416829","https://openalex.org/W1485675149","https://openalex.org/W1639266067","https://openalex.org/W1703370492","https://openalex.org/W2019330847","https://openalex.org/W2074394031","https://openalex.org/W2100971813","https://openalex.org/W2129901640","https://openalex.org/W2402428045","https://openalex.org/W2591682631","https://openalex.org/W2889145072","https://openalex.org/W3208240190","https://openalex.org/W6636614438","https://openalex.org/W6713312292","https://openalex.org/W6802591457"],"related_works":["https://openalex.org/W2128165264","https://openalex.org/W217710954","https://openalex.org/W2363301696","https://openalex.org/W1485754833","https://openalex.org/W2766167392","https://openalex.org/W2363056088","https://openalex.org/W62929309","https://openalex.org/W2383072803","https://openalex.org/W2068677590","https://openalex.org/W2011279701"],"abstract_inverted_index":{"Overlapped":[0,17],"speech":[1,9,18,46,54,85],"refers":[2],"to":[3,37,44,130],"an":[4,34],"audio":[5],"signal":[6,78],"which":[7],"contains":[8],"of":[10,21,25,42,50,59,73,84,89,94,116,121,139,143,183],"two":[11],"or":[12],"more":[13],"speakers":[14],"speaking":[15],"simultaneously.":[16],"is":[19,128,152,169],"one":[20,138],"the":[22,39,60,80,95,103,114,132,140,149,173,190],"main":[23,141],"sources":[24,142],"error":[26],"for":[27,189],"speaker":[28],"diarization":[29],"systems.":[30],"This":[31],"work":[32,151],"presents":[33],"initial":[35],"study":[36],"identify":[38],"transition":[40,133],"points":[41],"overlapped":[43,51,146],"non-overlapped":[45,53],"and":[47,52,66,97,164,187],"vice-versa.":[48],"Characteristics":[49],"are":[55,137,175],"examined":[56],"in":[57],"terms":[58],"vocal":[61,104],"tract":[62,105],"system,":[63],"excitation":[64,81],"source,":[65],"modulation":[67,109],"spectrum.":[68],"The":[69,87,108],"Hilbert":[70],"envelope":[71,120],"(HE)":[72],"Linear":[74],"Prediction":[75],"(LP)":[76],"residual":[77],"represents":[79],"source":[82],"characteristics":[83],"signal.":[86],"Sum":[88],"Ten":[90],"Largest":[91],"Peaks":[92],"(STLP)":[93],"spectrum":[96,110],"Mel-Frequency":[98],"Cepstral":[99],"Coefficients":[100],"(MFCCs)":[101],"represent":[102],"shape":[106],"information.":[107],"energy":[111],"(ModSE)":[112],"captures":[113],"information":[115],"slowly":[117],"varying":[118],"temporal":[119],"speech.":[122,147],"A":[123,159],"Bag-of-Audio-Words":[124],"(BoAW)":[125],"based":[126],"approach":[127],"used":[129,176],"detect":[131],"points.":[134],"News":[135],"debates":[136],"naturally":[144],"occurred":[145],"Therefore,":[148],"present":[150],"evaluated":[153],"on":[154],"Indian":[155],"news":[156],"debate":[157],"scenario.":[158],"high":[160],"Identification":[161],"Rate":[162,167],"(IR)":[163],"low":[165],"Spurious":[166],"(SR)":[168],"observed":[170],"when":[171],"all":[172],"features":[174],"simultaneously":[177],"as":[178],"a":[179],"16d":[180],"feature(13-MFCCs,":[181],"HE":[182],"LP":[184],"residual,":[185],"STLP":[186],"ModSE)":[188],"detection":[191],"task.":[192]},"counts_by_year":[],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}