{"id":"https://openalex.org/W1608376827","doi":"https://doi.org/10.1109/icassp.2015.7179067","title":"Two-stage speech/music classifier with decision smoothing and sharpening in the EVS codec","display_name":"Two-stage speech/music classifier with decision smoothing and sharpening in the EVS codec","publication_year":2015,"publication_date":"2015-04-01","ids":{"openalex":"https://openalex.org/W1608376827","doi":"https://doi.org/10.1109/icassp.2015.7179067","mag":"1608376827"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2015.7179067","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2015.7179067","pdf_url":null,"source":null,"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"},"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/A5035421144","display_name":"Vladim\u00edr Malenovsk\u00fd","orcid":null},"institutions":[{"id":"https://openalex.org/I4210161166","display_name":"VoiceAge (Canada)","ror":"https://ror.org/04gm72267","country_code":"CA","type":"company","lineage":["https://openalex.org/I4210161166"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Vladimir Malenovsky","raw_affiliation_strings":["VoiceAge Corp","VoiceAge Corp., Canada"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"VoiceAge Corp","institution_ids":["https://openalex.org/I4210161166"]},{"raw_affiliation_string":"VoiceAge Corp., Canada","institution_ids":["https://openalex.org/I4210161166"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5064493222","display_name":"Tommy Vaillancourt","orcid":null},"institutions":[{"id":"https://openalex.org/I4210161166","display_name":"VoiceAge (Canada)","ror":"https://ror.org/04gm72267","country_code":"CA","type":"company","lineage":["https://openalex.org/I4210161166"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Tommy Vaillancourt","raw_affiliation_strings":["VoiceAge Corp","VoiceAge Corp., Canada"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"VoiceAge Corp","institution_ids":["https://openalex.org/I4210161166"]},{"raw_affiliation_string":"VoiceAge Corp., Canada","institution_ids":["https://openalex.org/I4210161166"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100621319","display_name":"Zhe Wang","orcid":"https://orcid.org/0000-0002-3759-2041"},"institutions":[{"id":"https://openalex.org/I2250955327","display_name":"Huawei Technologies (China)","ror":"https://ror.org/00cmhce21","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250955327"]},{"id":"https://openalex.org/I4210160618","display_name":"Huawei Technologies (United Kingdom)","ror":"https://ror.org/056gzgs71","country_code":"GB","type":"company","lineage":["https://openalex.org/I2250955327","https://openalex.org/I4210160618"]}],"countries":["CN","GB"],"is_corresponding":false,"raw_author_name":"Wang Zhe","raw_affiliation_strings":["Huawei Technologies","Huawei Technologies, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Huawei Technologies","institution_ids":["https://openalex.org/I4210160618"]},{"raw_affiliation_string":"Huawei Technologies, China","institution_ids":["https://openalex.org/I2250955327"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5087025106","display_name":"Kihyun Choo","orcid":null},"institutions":[{"id":"https://openalex.org/I2250650973","display_name":"Samsung (South Korea)","ror":"https://ror.org/04w3jy968","country_code":"KR","type":"company","lineage":["https://openalex.org/I2250650973"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Kihyun Choo","raw_affiliation_strings":["Samsung Electronics Co., Ltd","Samsung Electronics Co. Ltd, Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Samsung Electronics Co., Ltd","institution_ids":["https://openalex.org/I2250650973"]},{"raw_affiliation_string":"Samsung Electronics Co. Ltd, Korea","institution_ids":["https://openalex.org/I2250650973"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5054070615","display_name":"Venkatraman Atti","orcid":null},"institutions":[{"id":"https://openalex.org/I19268510","display_name":"Qualcomm (United Kingdom)","ror":"https://ror.org/04d3djg48","country_code":"GB","type":"company","lineage":["https://openalex.org/I19268510","https://openalex.org/I4210087596"]},{"id":"https://openalex.org/I4210111675","display_name":"Market Matters","ror":"https://ror.org/021yan307","country_code":"US","type":"nonprofit","lineage":["https://openalex.org/I4210111675"]}],"countries":["GB","US"],"is_corresponding":false,"raw_author_name":"Venkatraman Atti","raw_affiliation_strings":["Qualcomm Inc","Qualcomm Inc., India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Qualcomm Inc","institution_ids":["https://openalex.org/I19268510","https://openalex.org/I4210111675"]},{"raw_affiliation_string":"Qualcomm Inc., India","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":5,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":2.0297,"has_fulltext":false,"cited_by_count":8,"citation_normalized_percentile":{"value":0.86917017,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"5718","last_page":"5722"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech 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"}},"topics":[{"id":"https://openalex.org/T10860","display_name":"Speech 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/T11309","display_name":"Music and Audio Processing","score":0.9995999932289124,"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":0.9959999918937683,"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":0.7744163274765015},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7119351625442505},{"id":"https://openalex.org/keywords/codec","display_name":"Codec","score":0.6421927809715271},{"id":"https://openalex.org/keywords/sharpening","display_name":"Sharpening","score":0.6139967441558838},{"id":"https://openalex.org/keywords/classifier","display_name":"Classifier (UML)","score":0.6108978390693665},{"id":"https://openalex.org/keywords/smoothing","display_name":"Smoothing","score":0.6073206663131714},{"id":"https://openalex.org/keywords/speech-coding","display_name":"Speech coding","score":0.48686662316322327},{"id":"https://openalex.org/keywords/mixture-model","display_name":"Mixture model","score":0.47798389196395874},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.47083568572998047},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.370270311832428},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3534809350967407},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.09300494194030762}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7744163274765015},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7119351625442505},{"id":"https://openalex.org/C161765866","wikidata":"https://www.wikidata.org/wiki/Q184748","display_name":"Codec","level":2,"score":0.6421927809715271},{"id":"https://openalex.org/C2781137444","wikidata":"https://www.wikidata.org/wiki/Q237105","display_name":"Sharpening","level":2,"score":0.6139967441558838},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.6108978390693665},{"id":"https://openalex.org/C3770464","wikidata":"https://www.wikidata.org/wiki/Q775963","display_name":"Smoothing","level":2,"score":0.6073206663131714},{"id":"https://openalex.org/C13895895","wikidata":"https://www.wikidata.org/wiki/Q3270773","display_name":"Speech coding","level":2,"score":0.48686662316322327},{"id":"https://openalex.org/C61224824","wikidata":"https://www.wikidata.org/wiki/Q2260434","display_name":"Mixture model","level":2,"score":0.47798389196395874},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.47083568572998047},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.370270311832428},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3534809350967407},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.09300494194030762},{"id":"https://openalex.org/C9390403","wikidata":"https://www.wikidata.org/wiki/Q3966","display_name":"Computer hardware","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp.2015.7179067","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2015.7179067","pdf_url":null,"source":null,"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":[{"score":0.5099999904632568,"id":"https://metadata.un.org/sdg/10","display_name":"Reduced inequalities"},{"score":0.4300000071525574,"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":8,"referenced_works":["https://openalex.org/W1502874967","https://openalex.org/W1833279920","https://openalex.org/W2029261284","https://openalex.org/W2049633694","https://openalex.org/W2151305614","https://openalex.org/W2153112160","https://openalex.org/W3150877489","https://openalex.org/W6657567920"],"related_works":["https://openalex.org/W2329932281","https://openalex.org/W64535957","https://openalex.org/W2043790407","https://openalex.org/W2054007705","https://openalex.org/W2374470469","https://openalex.org/W2352448339","https://openalex.org/W2787189739","https://openalex.org/W2899318368","https://openalex.org/W2363660481","https://openalex.org/W2159899134"],"abstract_inverted_index":{"In":[0],"most":[1],"internationally":[2],"recognized":[3],"standardized":[4],"multi-mode":[5],"codecs,":[6],"signal":[7],"classification":[8,100],"is":[9],"performed":[10],"in":[11,85],"a":[12,43,58,76],"single":[13],"step":[14],"by":[15,36,74],"either":[16],"linear":[17],"discrimination":[18,31],"or":[19],"SNR-based":[20],"metrics.":[21],"The":[22,83],"speech/music":[23,104],"classifier":[24],"of":[25,45,123],"the":[26,54,91,113],"EVS":[27,55],"codec":[28],"achieves":[29],"greater":[30],"than":[32,126],"these":[33],"single-step":[34],"models":[35],"combining":[37],"Gaussian":[38],"mixture":[39],"modelling":[40],"(GMM)":[41],"with":[42,95,106],"series":[44],"context-based":[46],"improvement":[47],"layers.":[48],"Additionally,":[49],"unlike":[50],"traditional":[51],"GMM":[52],"classifiers":[53,105,128],"model":[56],"adopts":[57],"short":[59],"hangover":[60,97],"period,":[61],"allowing":[62],"it":[63],"to":[64,99,103,117],"track":[65],"transitions":[66],"between":[67],"music":[68],"and":[69,80,119,138],"speech.":[70],"Misclassifications":[71],"are":[72],"mitigated":[73],"applying":[75],"novel":[77],"decision":[78],"smoothing":[79],"sharpening":[81],"technique.":[82],"results":[84],"relatively":[86],"static":[87],"environments":[88,133],"demonstrate":[89],"that":[90,112],"new":[92,114],"two-stage":[93],"approach":[94,115],"selective":[96],"leads":[98,116],"accuracies":[101],"comparable":[102],"longer":[107],"hangovers.":[108],"They":[109],"also":[110],"show":[111],"faster":[118],"more":[120,130],"accurate":[121],"switching":[122],"coding":[124],"modes":[125],"conventional":[127],"for":[129],"complex":[131],"audio":[132],"such":[134],"as":[135],"advertisements,":[136],"jingles":[137],"speech":[139],"superimposed":[140],"on":[141],"music.":[142]},"counts_by_year":[{"year":2023,"cited_by_count":1},{"year":2018,"cited_by_count":3},{"year":2015,"cited_by_count":4}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}