{"id":"https://openalex.org/W2162223626","doi":"https://doi.org/10.1109/ijcnn.2003.1223446","title":"An entropy based robust speech boundary detection algorithm for realistic noisy environments","display_name":"An entropy based robust speech boundary detection algorithm for realistic noisy environments","publication_year":2004,"publication_date":"2004-03-02","ids":{"openalex":"https://openalex.org/W2162223626","doi":"https://doi.org/10.1109/ijcnn.2003.1223446","mag":"2162223626"},"language":"en","primary_location":{"id":"doi:10.1109/ijcnn.2003.1223446","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcnn.2003.1223446","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the International Joint Conference on Neural Networks, 2003.","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/A5043941655","display_name":"K. Weaver","orcid":null},"institutions":[{"id":"https://openalex.org/I87216513","display_name":"Michigan State University","ror":"https://ror.org/05hs6h993","country_code":"US","type":"education","lineage":["https://openalex.org/I87216513"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"K. Weaver","raw_affiliation_strings":["Circuits, Systems and Neural Networks Laborator, Michigan State University, East Lansing, MI, USA"],"affiliations":[{"raw_affiliation_string":"Circuits, Systems and Neural Networks Laborator, Michigan State University, East Lansing, MI, USA","institution_ids":["https://openalex.org/I87216513"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5108364605","display_name":"Khurram Waheed","orcid":null},"institutions":[{"id":"https://openalex.org/I87216513","display_name":"Michigan State University","ror":"https://ror.org/05hs6h993","country_code":"US","type":"education","lineage":["https://openalex.org/I87216513"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"K. Waheed","raw_affiliation_strings":["Circuits, Systems and Neural Networks Laborator, Michigan State University, East Lansing, MI, USA"],"affiliations":[{"raw_affiliation_string":"Circuits, Systems and Neural Networks Laborator, Michigan State University, East Lansing, MI, USA","institution_ids":["https://openalex.org/I87216513"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5048892243","display_name":"F.M. Salem","orcid":"https://orcid.org/0000-0001-9099-5635"},"institutions":[{"id":"https://openalex.org/I87216513","display_name":"Michigan State University","ror":"https://ror.org/05hs6h993","country_code":"US","type":"education","lineage":["https://openalex.org/I87216513"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"F.M. Salem","raw_affiliation_strings":["Circuits, Systems and Neural Networks Laborator, Michigan State University, East Lansing, MI, USA"],"affiliations":[{"raw_affiliation_string":"Circuits, Systems and Neural Networks Laborator, Michigan State University, East Lansing, MI, USA","institution_ids":["https://openalex.org/I87216513"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5043941655"],"corresponding_institution_ids":["https://openalex.org/I87216513"],"apc_list":null,"apc_paid":null,"fwci":0.2804,"has_fulltext":false,"cited_by_count":8,"citation_normalized_percentile":{"value":0.60015101,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":"1","issue":null,"first_page":"680","last_page":"685"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9986000061035156,"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":0.9986000061035156,"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/T10901","display_name":"Advanced Data Compression Techniques","score":0.9937000274658203,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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":0.989300012588501,"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":0.7444764375686646},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.6262848973274231},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6118486523628235},{"id":"https://openalex.org/keywords/weighting","display_name":"Weighting","score":0.5348979234695435},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.4941599667072296},{"id":"https://openalex.org/keywords/voice-activity-detection","display_name":"Voice activity detection","score":0.45717814564704895},{"id":"https://openalex.org/keywords/preprocessor","display_name":"Preprocessor","score":0.42211493849754333},{"id":"https://openalex.org/keywords/entropy","display_name":"Entropy (arrow of time)","score":0.413167268037796},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.4031188488006592},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3121578097343445}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7444764375686646},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.6262848973274231},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6118486523628235},{"id":"https://openalex.org/C183115368","wikidata":"https://www.wikidata.org/wiki/Q856577","display_name":"Weighting","level":2,"score":0.5348979234695435},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.4941599667072296},{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.45717814564704895},{"id":"https://openalex.org/C34736171","wikidata":"https://www.wikidata.org/wiki/Q918333","display_name":"Preprocessor","level":2,"score":0.42211493849754333},{"id":"https://openalex.org/C106301342","wikidata":"https://www.wikidata.org/wiki/Q4117933","display_name":"Entropy (arrow of time)","level":2,"score":0.413167268037796},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.4031188488006592},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3121578097343445},{"id":"https://openalex.org/C71924100","wikidata":"https://www.wikidata.org/wiki/Q11190","display_name":"Medicine","level":0,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C126838900","wikidata":"https://www.wikidata.org/wiki/Q77604","display_name":"Radiology","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"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/ijcnn.2003.1223446","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcnn.2003.1223446","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the International Joint Conference on Neural Networks, 2003.","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":0.75}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":10,"referenced_works":["https://openalex.org/W182487737","https://openalex.org/W1493163583","https://openalex.org/W1532513216","https://openalex.org/W1560013842","https://openalex.org/W2073693905","https://openalex.org/W2144326614","https://openalex.org/W2150125142","https://openalex.org/W6607467561","https://openalex.org/W6629341784","https://openalex.org/W6633431331"],"related_works":["https://openalex.org/W3046039077","https://openalex.org/W2590770961","https://openalex.org/W3128402741","https://openalex.org/W2078418570","https://openalex.org/W4225315139","https://openalex.org/W642007152","https://openalex.org/W2401827384","https://openalex.org/W2355290951","https://openalex.org/W4385881881","https://openalex.org/W2052688117"],"abstract_inverted_index":{"This":[0,51,110],"paper":[1],"addresses":[2],"the":[3,49,57,76,97,107,119,129,163,177,189],"issue":[4],"of":[5,55,78,121,165,172,179,201,209],"automatic":[6],"word/sentence":[7],"boundary":[8,21,167],"detection":[9,22],"in":[10,42,61,96,118,128],"both":[11,60],"noiseless":[12,62],"and":[13,63,149],"noisy":[14],"backgrounds.":[15],"We":[16],"present":[17],"our":[18,133],"proposed":[19,135],"speech":[20,58,108,115,202],"algorithm":[23,52,161,190],"using":[24,155],"a":[25,69,94,102,170],"time-domain":[26,139],"entropic":[27,31],"contrast":[28,32],"function.":[29],"The":[30,160],"exhibits":[33],"well-behaved":[34],"characteristics":[35],"as":[36,68,84],"compared":[37],"to":[38,44,105,144],"energy-based":[39],"methods":[40],"resulting":[41],"immunity":[43],"endpoint":[45],"cut-of":[46],"issues":[47],"for":[48,152,176,183,197],"latter.":[50],"is":[53,141],"capable":[54],"estimating":[56],"boundaries":[59,194],"distinctive":[64],"noise":[65,82,124],"backgrounds":[66],"such":[67,83],"fan,":[70],"car":[71],"engine,":[72],"radio":[73],"etc.":[74,159],"For":[75,186],"case":[77,178],"wide-spectrum":[79],"colored":[80],"background":[81,123],"jazz,":[85],"opera,":[86],"songs,":[87],"rock":[88],"music":[89],"etc.,":[90],"we":[91],"further":[92],"propose":[93],"modification":[95],"preprocessing":[98],"stage":[99],"by":[100,169,205],"incorporating":[101],"frequency-weighting":[103],"scheme":[104,112],"emphasize":[106],"contents.":[109],"improved":[111],"provides":[113],"proper":[114],"segmentation":[116],"even":[117],"presence":[120],"wide-spectral":[122],"with":[125],"no":[126],"change":[127],"computational":[130,147],"cost":[131],"versus":[132],"earlier":[134],"algorithm.":[136],"A":[137],"complete":[138],"implementation":[140,200],"sought":[142],"due":[143],"its":[145,150],"lower":[146],"burden":[148],"suitability":[151],"real-time":[153],"implementations":[154],"DSPs,":[156],"FPGAs,":[157],"ASICs":[158],"improves":[162],"accuracy":[164],"word":[166],"estimates":[168],"factor":[171],"at":[173],"least":[174],"25%":[175],"isolated":[180],"(and":[181],"16%":[182],"connected)":[184],"speech.":[185],"continuous":[187],"speech,":[188],"can":[191],"determine":[192],"sentence":[193],"thus":[195],"allowing":[196],"power":[198],"efficient":[199],"recognition":[203],"engines":[204],"rejecting":[206],"extended":[207],"periods":[208],"silence.":[210]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2023,"cited_by_count":1},{"year":2015,"cited_by_count":1},{"year":2012,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
