{"id":"https://openalex.org/W2221268488","doi":"https://doi.org/10.1109/eusipco.2015.7362450","title":"Envelope modeling for speech and audio processing using distribution quantization","display_name":"Envelope modeling for speech and audio processing using distribution quantization","publication_year":2015,"publication_date":"2015-08-01","ids":{"openalex":"https://openalex.org/W2221268488","doi":"https://doi.org/10.1109/eusipco.2015.7362450","mag":"2221268488"},"language":"en","primary_location":{"id":"doi:10.1109/eusipco.2015.7362450","is_oa":false,"landing_page_url":"https://doi.org/10.1109/eusipco.2015.7362450","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2015 23rd European Signal Processing Conference (EUSIPCO)","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/A5023666920","display_name":"Tobias J\u00e4hnel","orcid":null},"institutions":[{"id":"https://openalex.org/I4210123192","display_name":"International Audio Laboratories Erlangen","ror":"https://ror.org/02mkz3e80","country_code":"DE","type":"facility","lineage":["https://openalex.org/I181369854","https://openalex.org/I4210123192","https://openalex.org/I4210124274","https://openalex.org/I4923324"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Tobias Jahnel","raw_affiliation_strings":["International Audio Laboratories Erlangen, Friedrich-Alexander-University Erlangen-Nurnberg (FAU)","International Audio Laboratories Erlangen, Friedrich-Alexander-University Erlangen-Ntirnberg (FAU)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"International Audio Laboratories Erlangen, Friedrich-Alexander-University Erlangen-Nurnberg (FAU)","institution_ids":["https://openalex.org/I4210123192"]},{"raw_affiliation_string":"International Audio Laboratories Erlangen, Friedrich-Alexander-University Erlangen-Ntirnberg (FAU)","institution_ids":["https://openalex.org/I4210123192"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5052130850","display_name":"Tom B\u00e4ckstr\u00f6m","orcid":"https://orcid.org/0000-0002-5590-2349"},"institutions":[{"id":"https://openalex.org/I4210123192","display_name":"International Audio Laboratories Erlangen","ror":"https://ror.org/02mkz3e80","country_code":"DE","type":"facility","lineage":["https://openalex.org/I181369854","https://openalex.org/I4210123192","https://openalex.org/I4210124274","https://openalex.org/I4923324"]},{"id":"https://openalex.org/I4210124274","display_name":"Fraunhofer Institute for Integrated Circuits","ror":"https://ror.org/024ape423","country_code":"DE","type":"facility","lineage":["https://openalex.org/I4210124274","https://openalex.org/I4923324"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Tom Backstrom","raw_affiliation_strings":["International Audio Laboratories Erlangen, Friedrich-Alexander-University Erlangen-Nurnberg (FAU)","Fraunhofer IIS, Erlangen, Germany","International Audio Laboratories Erlangen, Friedrich-Alexander-University Erlangen-Ntirnberg (FAU)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"International Audio Laboratories Erlangen, Friedrich-Alexander-University Erlangen-Nurnberg (FAU)","institution_ids":["https://openalex.org/I4210123192"]},{"raw_affiliation_string":"Fraunhofer IIS, Erlangen, Germany","institution_ids":["https://openalex.org/I4210124274"]},{"raw_affiliation_string":"International Audio Laboratories Erlangen, Friedrich-Alexander-University Erlangen-Ntirnberg (FAU)","institution_ids":["https://openalex.org/I4210123192"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5003431875","display_name":"Benjamin Schubert","orcid":"https://orcid.org/0000-0003-3412-1102"},"institutions":[{"id":"https://openalex.org/I4210124274","display_name":"Fraunhofer Institute for Integrated Circuits","ror":"https://ror.org/024ape423","country_code":"DE","type":"facility","lineage":["https://openalex.org/I4210124274","https://openalex.org/I4923324"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Benjamin Schubert","raw_affiliation_strings":["Fraunhofer IIS, Am Wolfsmantel 33, 91058 Erlangen, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Fraunhofer IIS, Am Wolfsmantel 33, 91058 Erlangen, Germany","institution_ids":["https://openalex.org/I4210124274"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.7284,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":{"value":0.67902363,"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":"584","last_page":"588"},"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/T10901","display_name":"Advanced Data Compression Techniques","score":0.9994999766349792,"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/T10688","display_name":"Image and Signal Denoising Methods","score":0.9991000294685364,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/spectral-envelope","display_name":"Spectral envelope","score":0.8333579897880554},{"id":"https://openalex.org/keywords/linear-prediction","display_name":"Linear prediction","score":0.6786211133003235},{"id":"https://openalex.org/keywords/quantization","display_name":"Quantization (signal processing)","score":0.6623113751411438},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5967317223548889},{"id":"https://openalex.org/keywords/speech-coding","display_name":"Speech coding","score":0.5443832278251648},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5382155776023865},{"id":"https://openalex.org/keywords/linear-predictive-coding","display_name":"Linear predictive coding","score":0.5260539054870605},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.47689464688301086},{"id":"https://openalex.org/keywords/entropy","display_name":"Entropy (arrow of time)","score":0.4356178045272827},{"id":"https://openalex.org/keywords/envelope","display_name":"Envelope (radar)","score":0.42581599950790405},{"id":"https://openalex.org/keywords/vector-quantization","display_name":"Vector quantization","score":0.4167774021625519},{"id":"https://openalex.org/keywords/signal-processing","display_name":"Signal processing","score":0.4122641682624817},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.3685610592365265},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.3362184762954712},{"id":"https://openalex.org/keywords/digital-signal-processing","display_name":"Digital signal processing","score":0.1482636034488678},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.13293969631195068},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.0916920006275177}],"concepts":[{"id":"https://openalex.org/C54926389","wikidata":"https://www.wikidata.org/wiki/Q7575188","display_name":"Spectral envelope","level":2,"score":0.8333579897880554},{"id":"https://openalex.org/C131109320","wikidata":"https://www.wikidata.org/wiki/Q581012","display_name":"Linear prediction","level":2,"score":0.6786211133003235},{"id":"https://openalex.org/C28855332","wikidata":"https://www.wikidata.org/wiki/Q198099","display_name":"Quantization (signal processing)","level":2,"score":0.6623113751411438},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5967317223548889},{"id":"https://openalex.org/C13895895","wikidata":"https://www.wikidata.org/wiki/Q3270773","display_name":"Speech coding","level":2,"score":0.5443832278251648},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5382155776023865},{"id":"https://openalex.org/C59883199","wikidata":"https://www.wikidata.org/wiki/Q1826438","display_name":"Linear predictive coding","level":3,"score":0.5260539054870605},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.47689464688301086},{"id":"https://openalex.org/C106301342","wikidata":"https://www.wikidata.org/wiki/Q4117933","display_name":"Entropy (arrow of time)","level":2,"score":0.4356178045272827},{"id":"https://openalex.org/C65155139","wikidata":"https://www.wikidata.org/wiki/Q5380912","display_name":"Envelope (radar)","level":3,"score":0.42581599950790405},{"id":"https://openalex.org/C199833920","wikidata":"https://www.wikidata.org/wiki/Q612536","display_name":"Vector quantization","level":2,"score":0.4167774021625519},{"id":"https://openalex.org/C104267543","wikidata":"https://www.wikidata.org/wiki/Q208163","display_name":"Signal processing","level":3,"score":0.4122641682624817},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3685610592365265},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.3362184762954712},{"id":"https://openalex.org/C84462506","wikidata":"https://www.wikidata.org/wiki/Q173142","display_name":"Digital signal processing","level":2,"score":0.1482636034488678},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.13293969631195068},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0916920006275177},{"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/C554190296","wikidata":"https://www.wikidata.org/wiki/Q47528","display_name":"Radar","level":2,"score":0.0},{"id":"https://openalex.org/C9390403","wikidata":"https://www.wikidata.org/wiki/Q3966","display_name":"Computer hardware","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/eusipco.2015.7362450","is_oa":false,"landing_page_url":"https://doi.org/10.1109/eusipco.2015.7362450","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2015 23rd European Signal Processing Conference (EUSIPCO)","raw_type":"proceedings-article"},{"id":"pmh:oai:publica.fraunhofer.de:publica/394155","is_oa":false,"landing_page_url":"https://publica.fraunhofer.de/handle/publica/394155","pdf_url":null,"source":{"id":"https://openalex.org/S4306400318","display_name":"Fraunhofer-Publica (Fraunhofer-Gesellschaft)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I4923324","host_organization_name":"Fraunhofer-Gesellschaft","host_organization_lineage":["https://openalex.org/I4923324"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"conference paper"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.4099999964237213,"id":"https://metadata.un.org/sdg/10","display_name":"Reduced inequalities"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":18,"referenced_works":["https://openalex.org/W1523644733","https://openalex.org/W1545060512","https://openalex.org/W1590793133","https://openalex.org/W1594615639","https://openalex.org/W1970308149","https://openalex.org/W1995319862","https://openalex.org/W1998752217","https://openalex.org/W2009674825","https://openalex.org/W2068641562","https://openalex.org/W2079337129","https://openalex.org/W2151626637","https://openalex.org/W2154291215","https://openalex.org/W2568428461","https://openalex.org/W4210849719","https://openalex.org/W4301513688","https://openalex.org/W6631257896","https://openalex.org/W6632700671","https://openalex.org/W6635534829"],"related_works":["https://openalex.org/W2363056088","https://openalex.org/W2363301696","https://openalex.org/W2383072803","https://openalex.org/W2106898123","https://openalex.org/W2808395304","https://openalex.org/W4312036005","https://openalex.org/W1921152853","https://openalex.org/W1994313308","https://openalex.org/W2068677590","https://openalex.org/W2011279701"],"abstract_inverted_index":{"Envelope":[0],"models":[1,68],"are":[2,100,115],"common":[3],"in":[4,91],"speech":[5],"and":[6,55,97,117,121],"audio":[7,23],"processing:":[8],"for":[9,15,29,103],"example,":[10],"linear":[11,53,98,126],"prediction":[12,54,99],"is":[13,107],"used":[14],"modeling":[16],"the":[17,46,50,56,64,83,110],"spectral":[18],"envelope":[19,39,67],"of":[20,48,52,58,66,93,112],"speech,":[21],"whereas":[22,102],"coders":[24],"use":[25],"scale":[26,59],"factor":[27,60],"bands":[28],"perceptual":[30],"masking":[31],"models.":[32],"In":[33],"this":[34],"work":[35],"we":[36],"introduce":[37],"an":[38],"model":[40],"called":[41],"distribution":[42,95,105,113],"quantizer":[43],"(DQ),":[44],"with":[45,69],"objective":[47],"combining":[49],"accuracy":[51],"flexibility":[57],"bands.":[61],"We":[62],"evaluate":[63],"performance":[65],"respect":[70],"to":[71,74,82,123],"their":[72,80],"ability":[73],"reduce":[75],"entropy":[76],"as":[77,79],"well":[78],"correlation":[81],"original":[84],"signal":[85],"magnitude.":[86],"The":[87],"experiments":[88],"show":[89],"that":[90],"terms":[92],"entropy,":[94],"quantization":[96,106,114],"comparable,":[101],"correlation,":[104],"better.":[108],"Furthermore":[109],"coefficients":[111],"independent":[116],"thus":[118],"more":[119],"flexible":[120],"easier":[122],"quantize":[124],"than":[125],"predictive":[127],"coefficients.":[128]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2021,"cited_by_count":1},{"year":2019,"cited_by_count":1},{"year":2016,"cited_by_count":3}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}