{"id":"https://openalex.org/W2048206318","doi":"https://doi.org/10.1109/icassp.2013.6638956","title":"Scale-space expansion of acoustic features improves speech event detection","display_name":"Scale-space expansion of acoustic features improves speech event detection","publication_year":2013,"publication_date":"2013-05-01","ids":{"openalex":"https://openalex.org/W2048206318","doi":"https://doi.org/10.1109/icassp.2013.6638956","mag":"2048206318"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2013.6638956","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2013.6638956","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 Acoustics, Speech and Signal Processing","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/A5088320958","display_name":"Neville Ryant","orcid":"https://orcid.org/0000-0003-2545-6912"},"institutions":[{"id":"https://openalex.org/I4210120198","display_name":"Pennsylvania Academic Library Consortium","ror":"https://ror.org/02m6s1q30","country_code":"US","type":"archive","lineage":["https://openalex.org/I4210120198"]},{"id":"https://openalex.org/I79576946","display_name":"University of Pennsylvania","ror":"https://ror.org/00b30xv10","country_code":"US","type":"education","lineage":["https://openalex.org/I79576946"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Neville Ryant","raw_affiliation_strings":["Linguistic Data Consortium, University of Pennsylvania, USA","Linguistic Data Consortium University of Pennsylvania Philadelphia PA USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Linguistic Data Consortium, University of Pennsylvania, USA","institution_ids":["https://openalex.org/I4210120198"]},{"raw_affiliation_string":"Linguistic Data Consortium University of Pennsylvania Philadelphia PA USA","institution_ids":["https://openalex.org/I79576946"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5043406907","display_name":"Jiahong Yuan","orcid":"https://orcid.org/0009-0008-2162-7167"},"institutions":[{"id":"https://openalex.org/I4210120198","display_name":"Pennsylvania Academic Library Consortium","ror":"https://ror.org/02m6s1q30","country_code":"US","type":"archive","lineage":["https://openalex.org/I4210120198"]},{"id":"https://openalex.org/I79576946","display_name":"University of Pennsylvania","ror":"https://ror.org/00b30xv10","country_code":"US","type":"education","lineage":["https://openalex.org/I79576946"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jiahong Yuan","raw_affiliation_strings":["Linguistic Data Consortium, University of Pennsylvania, USA","Linguistic Data Consortium University of Pennsylvania Philadelphia PA USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Linguistic Data Consortium, University of Pennsylvania, USA","institution_ids":["https://openalex.org/I4210120198"]},{"raw_affiliation_string":"Linguistic Data Consortium University of Pennsylvania Philadelphia PA USA","institution_ids":["https://openalex.org/I79576946"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5055868875","display_name":"Mark Liberman","orcid":"https://orcid.org/0000-0002-8605-9024"},"institutions":[{"id":"https://openalex.org/I4210120198","display_name":"Pennsylvania Academic Library Consortium","ror":"https://ror.org/02m6s1q30","country_code":"US","type":"archive","lineage":["https://openalex.org/I4210120198"]},{"id":"https://openalex.org/I79576946","display_name":"University of Pennsylvania","ror":"https://ror.org/00b30xv10","country_code":"US","type":"education","lineage":["https://openalex.org/I79576946"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Mark Liberman","raw_affiliation_strings":["Linguistic Data Consortium, University of Pennsylvania, USA","Linguistic Data Consortium University of Pennsylvania Philadelphia PA USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Linguistic Data Consortium, University of Pennsylvania, USA","institution_ids":["https://openalex.org/I4210120198"]},{"raw_affiliation_string":"Linguistic Data Consortium University of Pennsylvania Philadelphia PA USA","institution_ids":["https://openalex.org/I79576946"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.3221,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.58094688,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":94},"biblio":{"volume":"20","issue":null,"first_page":"6689","last_page":"6693"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9976000189781189,"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":0.9976000189781189,"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":0.9975000023841858,"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":0.9965999722480774,"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":0.7077332735061646},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6793027520179749},{"id":"https://openalex.org/keywords/scale","display_name":"Scale (ratio)","score":0.5710180401802063},{"id":"https://openalex.org/keywords/event","display_name":"Event (particle physics)","score":0.5228912234306335},{"id":"https://openalex.org/keywords/space","display_name":"Space (punctuation)","score":0.4913441240787506},{"id":"https://openalex.org/keywords/voice-activity-detection","display_name":"Voice activity detection","score":0.44862252473831177},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.39553701877593994},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.35679328441619873},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.32843437790870667},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.08725348114967346}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7077332735061646},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6793027520179749},{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.5710180401802063},{"id":"https://openalex.org/C2779662365","wikidata":"https://www.wikidata.org/wiki/Q5416694","display_name":"Event (particle physics)","level":2,"score":0.5228912234306335},{"id":"https://openalex.org/C2778572836","wikidata":"https://www.wikidata.org/wiki/Q380933","display_name":"Space (punctuation)","level":2,"score":0.4913441240787506},{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.44862252473831177},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.39553701877593994},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.35679328441619873},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.32843437790870667},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.08725348114967346},{"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/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp.2013.6638956","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2013.6638956","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 Acoustics, Speech and Signal Processing","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.4300000071525574,"display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":15,"referenced_works":["https://openalex.org/W4822889","https://openalex.org/W1965635292","https://openalex.org/W1973532433","https://openalex.org/W1985836220","https://openalex.org/W2003370853","https://openalex.org/W2110158442","https://openalex.org/W2111477235","https://openalex.org/W2113511941","https://openalex.org/W2113651538","https://openalex.org/W2130355536","https://openalex.org/W2133155955","https://openalex.org/W2144902422","https://openalex.org/W2145023731","https://openalex.org/W6677106874","https://openalex.org/W6681302627"],"related_works":["https://openalex.org/W191108438","https://openalex.org/W3135230428","https://openalex.org/W2904739811","https://openalex.org/W249088392","https://openalex.org/W2152158029","https://openalex.org/W2012540220","https://openalex.org/W2559837139","https://openalex.org/W2131711534","https://openalex.org/W2559040841","https://openalex.org/W114661351"],"abstract_inverted_index":{"In":[0],"a":[1],"system":[2],"for":[3],"detecting":[4],"and":[5,13,37,44,73],"measuring":[6],"phonetic":[7],"events":[8,34,43],"(here":[9],"bursts,":[10],"voice":[11],"onsets,":[12],"voice-onset":[14],"times),":[15],"we":[16],"show":[17],"that":[18],"the":[19,45,91],"addition":[20],"of":[21,33,42,90],"features":[22,59],"smoothed":[23],"at":[24],"multiple":[25],"scales":[26],"can":[27],"improve":[28],"both":[29],"recall":[30],"(the":[31,40],"proportion":[32],"correctly":[35],"identified)":[36],"measurement":[38],"accuracy":[39],"timing":[41],"difference":[46],"between":[47],"event":[48],"times,":[49],"relative":[50],"to":[51,81],"expert":[52],"human":[53],"judgments).":[54],"Multi-scale":[55],"(or":[56],"\u201cscale":[57],"space\u201d)":[58],"had":[60],"an":[61],"especially":[62],"strong":[63],"positive":[64],"effect":[65],"on":[66],"robustness":[67],"across":[68,84],"datasets":[69],"with":[70],"different":[71],"materials":[72],"recording":[74],"conditions.":[75],"Standard":[76],"machine-learning":[77],"classifiers":[78],"were":[79],"able":[80],"integrate":[82],"information":[83],"scales,":[85],"without":[86],"any":[87],"special":[88],"treatment":[89],"multi-scale":[92],"features.":[93]},"counts_by_year":[{"year":2016,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}