{"id":"https://openalex.org/W3163243746","doi":"https://doi.org/10.1109/icassp39728.2021.9413439","title":"Real-Time Speech Frequency Bandwidth Extension","display_name":"Real-Time Speech Frequency Bandwidth Extension","publication_year":2021,"publication_date":"2021-05-13","ids":{"openalex":"https://openalex.org/W3163243746","doi":"https://doi.org/10.1109/icassp39728.2021.9413439","mag":"3163243746"},"language":"en","primary_location":{"id":"doi:10.1109/icassp39728.2021.9413439","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp39728.2021.9413439","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2021 - 2021 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/A5100331862","display_name":"Yunpeng Li","orcid":"https://orcid.org/0000-0003-4798-541X"},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Yunpeng Li","raw_affiliation_strings":["Google Research"],"affiliations":[{"raw_affiliation_string":"Google Research","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5033341878","display_name":"Marco Tagliasacchi","orcid":"https://orcid.org/0000-0002-7682-6795"},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Marco Tagliasacchi","raw_affiliation_strings":["Google Research"],"affiliations":[{"raw_affiliation_string":"Google Research","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103149673","display_name":"Oleg Rybakov","orcid":"https://orcid.org/0009-0007-0021-047X"},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Oleg Rybakov","raw_affiliation_strings":["Google Research"],"affiliations":[{"raw_affiliation_string":"Google Research","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5026288109","display_name":"Victor Ungureanu","orcid":null},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Victor Ungureanu","raw_affiliation_strings":["Google Research"],"affiliations":[{"raw_affiliation_string":"Google Research","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5011258273","display_name":"Dominik Roblek","orcid":"https://orcid.org/0000-0002-2155-450X"},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Dominik Roblek","raw_affiliation_strings":["Google Research"],"affiliations":[{"raw_affiliation_string":"Google Research","institution_ids":["https://openalex.org/I1291425158"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5100331862"],"corresponding_institution_ids":["https://openalex.org/I1291425158"],"apc_list":null,"apc_paid":null,"fwci":6.018,"has_fulltext":false,"cited_by_count":48,"citation_normalized_percentile":{"value":0.97198636,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":97,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"691","last_page":"695"},"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":0.9990000128746033,"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":0.9973000288009644,"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":0.8234939575195312},{"id":"https://openalex.org/keywords/bandwidth-extension","display_name":"Bandwidth extension","score":0.6889486908912659},{"id":"https://openalex.org/keywords/latency","display_name":"Latency (audio)","score":0.587502658367157},{"id":"https://openalex.org/keywords/bandwidth","display_name":"Bandwidth (computing)","score":0.5828316807746887},{"id":"https://openalex.org/keywords/voice-activity-detection","display_name":"Voice activity detection","score":0.5489715337753296},{"id":"https://openalex.org/keywords/frame","display_name":"Frame (networking)","score":0.4714948534965515},{"id":"https://openalex.org/keywords/extension","display_name":"Extension (predicate logic)","score":0.4635407626628876},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.4225393235683441},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.41638848185539246},{"id":"https://openalex.org/keywords/architecture","display_name":"Architecture","score":0.411379873752594},{"id":"https://openalex.org/keywords/real-time-computing","display_name":"Real-time computing","score":0.322983980178833},{"id":"https://openalex.org/keywords/speech-coding","display_name":"Speech coding","score":0.2844119668006897},{"id":"https://openalex.org/keywords/computer-network","display_name":"Computer network","score":0.18890240788459778},{"id":"https://openalex.org/keywords/audio-signal","display_name":"Audio signal","score":0.17417874932289124},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.12748152017593384}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8234939575195312},{"id":"https://openalex.org/C9387945","wikidata":"https://www.wikidata.org/wiki/Q4854770","display_name":"Bandwidth extension","level":4,"score":0.6889486908912659},{"id":"https://openalex.org/C82876162","wikidata":"https://www.wikidata.org/wiki/Q17096504","display_name":"Latency (audio)","level":2,"score":0.587502658367157},{"id":"https://openalex.org/C2776257435","wikidata":"https://www.wikidata.org/wiki/Q1576430","display_name":"Bandwidth (computing)","level":2,"score":0.5828316807746887},{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.5489715337753296},{"id":"https://openalex.org/C126042441","wikidata":"https://www.wikidata.org/wiki/Q1324888","display_name":"Frame (networking)","level":2,"score":0.4714948534965515},{"id":"https://openalex.org/C2778029271","wikidata":"https://www.wikidata.org/wiki/Q5421931","display_name":"Extension (predicate logic)","level":2,"score":0.4635407626628876},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.4225393235683441},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.41638848185539246},{"id":"https://openalex.org/C123657996","wikidata":"https://www.wikidata.org/wiki/Q12271","display_name":"Architecture","level":2,"score":0.411379873752594},{"id":"https://openalex.org/C79403827","wikidata":"https://www.wikidata.org/wiki/Q3988","display_name":"Real-time computing","level":1,"score":0.322983980178833},{"id":"https://openalex.org/C13895895","wikidata":"https://www.wikidata.org/wiki/Q3270773","display_name":"Speech coding","level":2,"score":0.2844119668006897},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.18890240788459778},{"id":"https://openalex.org/C64922751","wikidata":"https://www.wikidata.org/wiki/Q4650799","display_name":"Audio signal","level":3,"score":0.17417874932289124},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.12748152017593384},{"id":"https://openalex.org/C153349607","wikidata":"https://www.wikidata.org/wiki/Q36649","display_name":"Visual arts","level":1,"score":0.0},{"id":"https://openalex.org/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp39728.2021.9413439","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp39728.2021.9413439","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16","score":0.4099999964237213}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":35,"referenced_works":["https://openalex.org/W1885185971","https://openalex.org/W1901129140","https://openalex.org/W2163605009","https://openalex.org/W2284050935","https://openalex.org/W2302255633","https://openalex.org/W2526050071","https://openalex.org/W2527729766","https://openalex.org/W2536224642","https://openalex.org/W2802034954","https://openalex.org/W2810843531","https://openalex.org/W2924508610","https://openalex.org/W2929274168","https://openalex.org/W2944438111","https://openalex.org/W2963285578","https://openalex.org/W2963341071","https://openalex.org/W2963685250","https://openalex.org/W2963952344","https://openalex.org/W2964058413","https://openalex.org/W2970006822","https://openalex.org/W2972443522","https://openalex.org/W2998639482","https://openalex.org/W3025581723","https://openalex.org/W3095095816","https://openalex.org/W6684191040","https://openalex.org/W6685562342","https://openalex.org/W6695676441","https://openalex.org/W6698183232","https://openalex.org/W6735429107","https://openalex.org/W6741681139","https://openalex.org/W6753100508","https://openalex.org/W6760993068","https://openalex.org/W6767111847","https://openalex.org/W6780226713","https://openalex.org/W6782293762","https://openalex.org/W6936113694"],"related_works":["https://openalex.org/W2059847929","https://openalex.org/W1999397223","https://openalex.org/W642007152","https://openalex.org/W2401827384","https://openalex.org/W2355290951","https://openalex.org/W2069501481","https://openalex.org/W2595254936","https://openalex.org/W2052688117","https://openalex.org/W2991225285","https://openalex.org/W2536333783"],"abstract_inverted_index":{"In":[0,73],"this":[1],"paper":[2],"we":[3,75],"propose":[4,76],"a":[5,30,49,56,77,98,102],"lightweight":[6],"model":[7,40],"for":[8,118],"frequency":[9,18,27],"bandwidth":[10],"extension":[11],"of":[12,58,69,79,93,101],"speech":[13],"signals,":[14],"increasing":[15],"the":[16,25,35,70],"sampling":[17],"from":[19,34],"8kHz":[20],"to":[21,29,64],"16kHz":[22,36],"while":[23],"restoring":[24],"high":[26],"content":[28],"level":[31],"almost":[32],"indistinguishable":[33],"ground":[37],"truth.":[38],"The":[39,112],"architecture":[41],"is":[42],"based":[43],"on":[44,97],"SEANet":[45,80],"(Sound":[46],"EnhAncement":[47],"Network),":[48],"wave-to-wave":[50],"fully":[51],"convolutional":[52],"model,":[53],"which":[54],"uses":[55],"combination":[57],"feature":[59],"losses":[60,63],"and":[61],"adversarial":[62],"reconstruct":[65],"an":[66,90],"enhanced":[67],"version":[68],"input":[71],"speech.":[72],"addition,":[74],"variant":[78],"that":[81],"can":[82],"be":[83],"deployed":[84],"on-device":[85],"in":[86],"streaming":[87],"mode,":[88],"achieving":[89],"architectural":[91],"latency":[92,114],"16ms.":[94],"When":[95],"profiled":[96],"single":[99],"core":[100],"mobile":[103],"CPU,":[104],"processing":[105],"one":[106],"16ms":[107],"frame":[108],"takes":[109],"only":[110],"1.5ms.":[111],"low":[113],"makes":[115],"it":[116],"viable":[117],"bi-directional":[119],"voice":[120],"communication":[121],"systems.":[122]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":7},{"year":2024,"cited_by_count":20},{"year":2023,"cited_by_count":11},{"year":2022,"cited_by_count":4},{"year":2021,"cited_by_count":4}],"updated_date":"2026-04-23T09:07:50.710637","created_date":"2025-10-10T00:00:00"}
