{"id":"https://openalex.org/W2134017361","doi":"https://doi.org/10.1109/icassp.2011.5947504","title":"Speech bandwidth extension using Gaussian mixture model-based estimation of the highband mel spectrum","display_name":"Speech bandwidth extension using Gaussian mixture model-based estimation of the highband mel spectrum","publication_year":2011,"publication_date":"2011-05-01","ids":{"openalex":"https://openalex.org/W2134017361","doi":"https://doi.org/10.1109/icassp.2011.5947504","mag":"2134017361"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2011.5947504","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2011.5947504","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2011 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/A5076286418","display_name":"Hannu Pulakka","orcid":null},"institutions":[{"id":"https://openalex.org/I9927081","display_name":"Aalto University","ror":"https://ror.org/020hwjq30","country_code":"FI","type":"education","lineage":["https://openalex.org/I9927081"]}],"countries":["FI"],"is_corresponding":true,"raw_author_name":"Hannu Pulakka","raw_affiliation_strings":["Department of Signal Processing and Acoustics, Aalto University, Finland","Department of Signal Processing and Acoustics, Aalto University, Finland#TAB#"],"affiliations":[{"raw_affiliation_string":"Department of Signal Processing and Acoustics, Aalto University, Finland","institution_ids":["https://openalex.org/I9927081"]},{"raw_affiliation_string":"Department of Signal Processing and Acoustics, Aalto University, Finland#TAB#","institution_ids":["https://openalex.org/I9927081"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5037747779","display_name":"Ulpu Remes","orcid":"https://orcid.org/0000-0003-1435-0207"},"institutions":[{"id":"https://openalex.org/I9927081","display_name":"Aalto University","ror":"https://ror.org/020hwjq30","country_code":"FI","type":"education","lineage":["https://openalex.org/I9927081"]}],"countries":["FI"],"is_corresponding":false,"raw_author_name":"Ulpu Remes","raw_affiliation_strings":["Adaptive Informatics Research Centre, Aalto University, Finland"],"affiliations":[{"raw_affiliation_string":"Adaptive Informatics Research Centre, Aalto University, Finland","institution_ids":["https://openalex.org/I9927081"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5053741868","display_name":"Kalle Palom\u00e4ki","orcid":null},"institutions":[{"id":"https://openalex.org/I9927081","display_name":"Aalto University","ror":"https://ror.org/020hwjq30","country_code":"FI","type":"education","lineage":["https://openalex.org/I9927081"]}],"countries":["FI"],"is_corresponding":false,"raw_author_name":"Kalle Palomaki","raw_affiliation_strings":["Adaptive Informatics Research Centre, Aalto University, Finland"],"affiliations":[{"raw_affiliation_string":"Adaptive Informatics Research Centre, Aalto University, Finland","institution_ids":["https://openalex.org/I9927081"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5043424064","display_name":"Mikko Kurimo","orcid":"https://orcid.org/0000-0001-5278-7974"},"institutions":[{"id":"https://openalex.org/I9927081","display_name":"Aalto University","ror":"https://ror.org/020hwjq30","country_code":"FI","type":"education","lineage":["https://openalex.org/I9927081"]}],"countries":["FI"],"is_corresponding":false,"raw_author_name":"Mikko Kurimo","raw_affiliation_strings":["Adaptive Informatics Research Centre, Aalto University, Finland"],"affiliations":[{"raw_affiliation_string":"Adaptive Informatics Research Centre, Aalto University, Finland","institution_ids":["https://openalex.org/I9927081"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5042186400","display_name":"Paavo Alku","orcid":"https://orcid.org/0000-0002-8173-9418"},"institutions":[{"id":"https://openalex.org/I9927081","display_name":"Aalto University","ror":"https://ror.org/020hwjq30","country_code":"FI","type":"education","lineage":["https://openalex.org/I9927081"]}],"countries":["FI"],"is_corresponding":false,"raw_author_name":"Paavo Alku","raw_affiliation_strings":["Department of Signal Processing and Acoustics, Aalto University, Finland","Department of Signal Processing and Acoustics, Aalto University, Finland#TAB#"],"affiliations":[{"raw_affiliation_string":"Department of Signal Processing and Acoustics, Aalto University, Finland","institution_ids":["https://openalex.org/I9927081"]},{"raw_affiliation_string":"Department of Signal Processing and Acoustics, Aalto University, Finland#TAB#","institution_ids":["https://openalex.org/I9927081"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5076286418"],"corresponding_institution_ids":["https://openalex.org/I9927081"],"apc_list":null,"apc_paid":null,"fwci":1.2478,"has_fulltext":false,"cited_by_count":37,"citation_normalized_percentile":{"value":0.80597306,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"5100","last_page":"5103"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9987999796867371,"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":0.9987999796867371,"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":0.9987000226974487,"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/T11233","display_name":"Advanced Adaptive Filtering Techniques","score":0.9976000189781189,"subfield":{"id":"https://openalex.org/subfields/2206","display_name":"Computational Mechanics"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/narrowband","display_name":"Narrowband","score":0.8760586977005005},{"id":"https://openalex.org/keywords/bandwidth-extension","display_name":"Bandwidth extension","score":0.7437127828598022},{"id":"https://openalex.org/keywords/bandwidth","display_name":"Bandwidth (computing)","score":0.6465242505073547},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6392853260040283},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6284111738204956},{"id":"https://openalex.org/keywords/wideband-audio","display_name":"Wideband audio","score":0.5836071372032166},{"id":"https://openalex.org/keywords/intelligibility","display_name":"Intelligibility (philosophy)","score":0.5403793454170227},{"id":"https://openalex.org/keywords/gaussian","display_name":"Gaussian","score":0.4868282675743103},{"id":"https://openalex.org/keywords/speech-enhancement","display_name":"Speech enhancement","score":0.43615081906318665},{"id":"https://openalex.org/keywords/speech-coding","display_name":"Speech coding","score":0.3790295124053955},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.3312365412712097},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.3209150433540344},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.26320987939834595},{"id":"https://openalex.org/keywords/background-noise","display_name":"Background noise","score":0.18796488642692566},{"id":"https://openalex.org/keywords/audio-signal","display_name":"Audio signal","score":0.16665473580360413},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.1351291537284851}],"concepts":[{"id":"https://openalex.org/C2776096036","wikidata":"https://www.wikidata.org/wiki/Q1140483","display_name":"Narrowband","level":2,"score":0.8760586977005005},{"id":"https://openalex.org/C9387945","wikidata":"https://www.wikidata.org/wiki/Q4854770","display_name":"Bandwidth extension","level":4,"score":0.7437127828598022},{"id":"https://openalex.org/C2776257435","wikidata":"https://www.wikidata.org/wiki/Q1576430","display_name":"Bandwidth (computing)","level":2,"score":0.6465242505073547},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6392853260040283},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6284111738204956},{"id":"https://openalex.org/C173391809","wikidata":"https://www.wikidata.org/wiki/Q2740189","display_name":"Wideband audio","level":5,"score":0.5836071372032166},{"id":"https://openalex.org/C60048801","wikidata":"https://www.wikidata.org/wiki/Q1433889","display_name":"Intelligibility (philosophy)","level":2,"score":0.5403793454170227},{"id":"https://openalex.org/C163716315","wikidata":"https://www.wikidata.org/wiki/Q901177","display_name":"Gaussian","level":2,"score":0.4868282675743103},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.43615081906318665},{"id":"https://openalex.org/C13895895","wikidata":"https://www.wikidata.org/wiki/Q3270773","display_name":"Speech coding","level":2,"score":0.3790295124053955},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3312365412712097},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.3209150433540344},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.26320987939834595},{"id":"https://openalex.org/C100675267","wikidata":"https://www.wikidata.org/wiki/Q1371624","display_name":"Background noise","level":2,"score":0.18796488642692566},{"id":"https://openalex.org/C64922751","wikidata":"https://www.wikidata.org/wiki/Q4650799","display_name":"Audio signal","level":3,"score":0.16665473580360413},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.1351291537284851},{"id":"https://openalex.org/C87687168","wikidata":"https://www.wikidata.org/wiki/Q173114","display_name":"Digital audio","level":4,"score":0.0},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","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}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/icassp.2011.5947504","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2011.5947504","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2011 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.990.8162","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.990.8162","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.mirlab.org/conference_papers/International_Conference/ICASSP%202011/pdfs/0005100.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":16,"referenced_works":["https://openalex.org/W1494395633","https://openalex.org/W2034562896","https://openalex.org/W2059154003","https://openalex.org/W2103133081","https://openalex.org/W2114450842","https://openalex.org/W2128251029","https://openalex.org/W2130890436","https://openalex.org/W2131094339","https://openalex.org/W2132462584","https://openalex.org/W2143855671","https://openalex.org/W2147152002","https://openalex.org/W2152250293","https://openalex.org/W2402261002","https://openalex.org/W6675925002","https://openalex.org/W6682013673","https://openalex.org/W6712926106"],"related_works":["https://openalex.org/W2162700463","https://openalex.org/W3150049111","https://openalex.org/W2113878160","https://openalex.org/W2110311073","https://openalex.org/W4388991820","https://openalex.org/W2152250293","https://openalex.org/W2111280847","https://openalex.org/W1578591928","https://openalex.org/W2170475202","https://openalex.org/W2948125348"],"abstract_inverted_index":{"The":[0,42,83,100],"quality":[1],"and":[2,51,80,92,113,127],"intelligibility":[3],"of":[4,75,108],"narrowband":[5,43,114,125],"telephone":[6],"speech":[7,50,126],"can":[8],"be":[9],"enhanced":[10],"by":[11],"artificial":[12,110,132],"bandwidth":[13,133],"extension.":[14],"This":[15],"study":[16],"combines":[17],"Gaussian":[18],"mixture":[19],"model-based":[20],"(GMM)":[21],"mel":[22,44,59,98],"spectrum":[23,45,60],"extension":[24,134],"with":[25],"a":[26,73,129],"filter":[27],"bank":[28],"implementation":[29],"for":[30,67],"generating":[31],"the":[32,37,52,58,62,68,96,106,109],"missing":[33],"spectral":[34],"content":[35],"in":[36,61,139],"highband":[38,69,111],"at":[39],"4-8":[40],"kHz.":[41],"is":[46,54,70,85,103,122,137],"calculated":[47],"from":[48],"input":[49],"GMM":[53],"used":[55],"to":[56,94],"estimate":[57],"highband.":[63],"An":[64],"excitation":[65,84],"signal":[66,112],"generated":[71],"as":[72,105],"combination":[74],"upsampled":[76],"linear":[77],"prediction":[78],"residual":[79],"modulated":[81],"noise.":[82],"divided":[86],"into":[87],"sub-bands":[88],"that":[89,119],"are":[90],"weighted":[91],"summed":[93],"realize":[95],"estimated":[97],"spectrum.":[99],"bandwidth-extended":[101],"output":[102],"obtained":[104],"sum":[107],"speech.":[115],"Listening":[116],"tests":[117],"indicate":[118],"this":[120],"method":[121,135],"preferred":[123],"over":[124,128],"previously":[130],"presented":[131],"which":[136],"implemented":[138],"some":[140],"mobile":[141],"phone":[142],"models.":[143]},"counts_by_year":[{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":3},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":9},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":3},{"year":2018,"cited_by_count":2},{"year":2017,"cited_by_count":2},{"year":2016,"cited_by_count":5},{"year":2015,"cited_by_count":2},{"year":2014,"cited_by_count":2},{"year":2013,"cited_by_count":2}],"updated_date":"2026-04-05T17:49:38.594831","created_date":"2025-10-10T00:00:00"}
