{"id":"https://openalex.org/W1986765635","doi":"https://doi.org/10.1109/icme.2013.6607486","title":"Lost in segmentation: Three approaches for speech/non-speech detection in consumer-produced videos","display_name":"Lost in segmentation: Three approaches for speech/non-speech detection in consumer-produced videos","publication_year":2013,"publication_date":"2013-07-01","ids":{"openalex":"https://openalex.org/W1986765635","doi":"https://doi.org/10.1109/icme.2013.6607486","mag":"1986765635"},"language":"en","primary_location":{"id":"doi:10.1109/icme.2013.6607486","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icme.2013.6607486","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2013 IEEE International Conference on Multimedia and Expo (ICME)","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/A5073250019","display_name":"Benjamin Elizalde","orcid":"https://orcid.org/0000-0001-6461-5790"},"institutions":[{"id":"https://openalex.org/I1297971548","display_name":"International Computer Science Institute","ror":"https://ror.org/01ewh7m12","country_code":"US","type":"nonprofit","lineage":["https://openalex.org/I1297971548"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Benjamin Elizalde","raw_affiliation_strings":["International Computer Science Institute, Berkeley, CA, USA","Int. Comput. Sci. Inst., Berkeley, CA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"International Computer Science Institute, Berkeley, CA, USA","institution_ids":["https://openalex.org/I1297971548"]},{"raw_affiliation_string":"Int. Comput. Sci. Inst., Berkeley, CA, USA","institution_ids":["https://openalex.org/I1297971548"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5062323483","display_name":"Gerald Friedland","orcid":"https://orcid.org/0000-0002-9400-6539"},"institutions":[{"id":"https://openalex.org/I1297971548","display_name":"International Computer Science Institute","ror":"https://ror.org/01ewh7m12","country_code":"US","type":"nonprofit","lineage":["https://openalex.org/I1297971548"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Gerald Friedland","raw_affiliation_strings":["International Computer Science Institute, Berkeley, CA, USA","Int. Comput. Sci. Inst., Berkeley, CA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"International Computer Science Institute, Berkeley, CA, USA","institution_ids":["https://openalex.org/I1297971548"]},{"raw_affiliation_string":"Int. Comput. Sci. Inst., Berkeley, CA, USA","institution_ids":["https://openalex.org/I1297971548"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I1297971548"],"apc_list":null,"apc_paid":null,"fwci":0.7045,"has_fulltext":false,"cited_by_count":8,"citation_normalized_percentile":{"value":0.6389252,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"6"},"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/T11309","display_name":"Music 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":0.9961000084877014,"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":0.800838828086853},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6663006544113159},{"id":"https://openalex.org/keywords/support-vector-machine","display_name":"Support vector machine","score":0.633185863494873},{"id":"https://openalex.org/keywords/mixture-model","display_name":"Mixture model","score":0.631930410861969},{"id":"https://openalex.org/keywords/voice-activity-detection","display_name":"Voice activity detection","score":0.6113162636756897},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.583342432975769},{"id":"https://openalex.org/keywords/speech-enhancement","display_name":"Speech enhancement","score":0.5658400058746338},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.5570623278617859},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4918403625488281},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.4852159321308136},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.44294026494026184},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.33357739448547363},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.12102457880973816},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.08567777276039124},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.06184786558151245}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.800838828086853},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6663006544113159},{"id":"https://openalex.org/C12267149","wikidata":"https://www.wikidata.org/wiki/Q282453","display_name":"Support vector machine","level":2,"score":0.633185863494873},{"id":"https://openalex.org/C61224824","wikidata":"https://www.wikidata.org/wiki/Q2260434","display_name":"Mixture model","level":2,"score":0.631930410861969},{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.6113162636756897},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.583342432975769},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.5658400058746338},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.5570623278617859},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4918403625488281},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.4852159321308136},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.44294026494026184},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.33357739448547363},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.12102457880973816},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.08567777276039124},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.06184786558151245},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/icme.2013.6607486","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icme.2013.6607486","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2013 IEEE International Conference on Multimedia and Expo (ICME)","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.800.445","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.800.445","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"https://www.icsi.berkeley.edu/pubs/speech/losttranslation13.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions","score":0.6299999952316284}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":13,"referenced_works":["https://openalex.org/W1582482241","https://openalex.org/W1583620810","https://openalex.org/W2081074144","https://openalex.org/W2103018059","https://openalex.org/W2121127941","https://openalex.org/W2122514667","https://openalex.org/W2168175751","https://openalex.org/W2399255709","https://openalex.org/W2402212287","https://openalex.org/W2403186097","https://openalex.org/W2546191734","https://openalex.org/W2613634265","https://openalex.org/W6712478597"],"related_works":["https://openalex.org/W2120771489","https://openalex.org/W2051376034","https://openalex.org/W2294333436","https://openalex.org/W2101357962","https://openalex.org/W2955597484","https://openalex.org/W3110551121","https://openalex.org/W2653598178","https://openalex.org/W2747006289","https://openalex.org/W4252682934","https://openalex.org/W2089240210"],"abstract_inverted_index":{"Traditional":[0],"speech/non-speech":[1,57,66,104],"segmentation":[2],"systems":[3],"have":[4],"been":[5,21],"designed":[6,94],"for":[7,56],"specific":[8],"acoustic":[9],"conditions,":[10],"such":[11,37],"as":[12,38],"broadcast":[13],"news":[14],"or":[15],"meetings.":[16],"However,":[17],"little":[18],"research":[19],"has":[20,34],"done":[22],"on":[23,59,69,75,83,106],"consumer-produced":[24,60,107],"audio.":[25,61],"This":[26,47],"type":[27],"of":[28,52,102],"media":[29,108],"is":[30],"constantly":[31],"growing":[32],"and":[33,44,80,110,129,143],"complex":[35],"characteristics":[36],"low":[39],"quality":[40],"recordings,":[41],"environmental":[42],"noise":[43],"overlapping":[45],"sounds.":[46],"paper":[48],"discusses":[49],"an":[50],"evaluation":[51],"three":[53],"different":[54],"approaches":[55,63,113],"detection":[58,105,116],"The":[62,121],"are":[64],"state-of-the-art":[65,127],"detectors-one":[67],"based":[68],"Gaussian":[70],"Mixture":[71],"Models":[72],"(GMM),":[73],"another":[74],"Support":[76],"Vector":[77],"Machines":[78],"(SVM),":[79],"the":[81,88,100,125],"last":[82],"Neural":[84],"Networks":[85],"(NN).":[86],"Using":[87],"TRECVID":[89],"MED":[90],"2012":[91],"database,":[92],"we":[93],"training/testing":[95],"sets":[96],"combinations":[97],"to":[98,114],"aid":[99],"understanding":[101],"what":[103],"entails":[109],"how":[111],"traditional":[112],"this":[115,119],"performed":[117],"in":[118],"domain.":[120],"results":[122],"revealed":[123],"that":[124],"cross-domain":[126],"GMM":[128],"SVM":[130],"systems'":[131],"tests":[132],"underperformed":[133],"a":[134],"one-layer":[135],"NN":[136],"algorithm,":[137],"which":[138],"had":[139],"20%":[140],"higher":[141],"accuracy":[142],"computed":[144],"audio":[145],"5":[146],"times":[147],"faster.":[148]},"counts_by_year":[{"year":2018,"cited_by_count":2},{"year":2017,"cited_by_count":3},{"year":2016,"cited_by_count":2},{"year":2014,"cited_by_count":1}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}