{"id":"https://openalex.org/W4387870028","doi":"https://doi.org/10.1109/mlsp55844.2023.10285965","title":"Low-Complexity Streaming Speech Super-Resolution","display_name":"Low-Complexity Streaming Speech Super-Resolution","publication_year":2023,"publication_date":"2023-09-17","ids":{"openalex":"https://openalex.org/W4387870028","doi":"https://doi.org/10.1109/mlsp55844.2023.10285965"},"language":"en","primary_location":{"id":"doi:10.1109/mlsp55844.2023.10285965","is_oa":false,"landing_page_url":"https://doi.org/10.1109/mlsp55844.2023.10285965","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE 33rd International Workshop on Machine Learning for Signal Processing (MLSP)","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/A5080981075","display_name":"Erfan Soltanmohammadi","orcid":null},"institutions":[{"id":"https://openalex.org/I1311688040","display_name":"Amazon (United States)","ror":"https://ror.org/04mv4n011","country_code":"US","type":"company","lineage":["https://openalex.org/I1311688040"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Erfan Soltanmohammadi","raw_affiliation_strings":["Amazon Web Services, Inc"],"affiliations":[{"raw_affiliation_string":"Amazon Web Services, Inc","institution_ids":["https://openalex.org/I1311688040"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5038903729","display_name":"Paris Smaragdis","orcid":null},"institutions":[{"id":"https://openalex.org/I1311688040","display_name":"Amazon (United States)","ror":"https://ror.org/04mv4n011","country_code":"US","type":"company","lineage":["https://openalex.org/I1311688040"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Paris Smaragdis","raw_affiliation_strings":["Amazon Web Services, Inc"],"affiliations":[{"raw_affiliation_string":"Amazon Web Services, Inc","institution_ids":["https://openalex.org/I1311688040"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5082904207","display_name":"Michael M. Goodwin","orcid":null},"institutions":[{"id":"https://openalex.org/I1311688040","display_name":"Amazon (United States)","ror":"https://ror.org/04mv4n011","country_code":"US","type":"company","lineage":["https://openalex.org/I1311688040"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Michael M. Goodwin","raw_affiliation_strings":["Amazon Web Services, Inc"],"affiliations":[{"raw_affiliation_string":"Amazon Web Services, Inc","institution_ids":["https://openalex.org/I1311688040"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5080981075"],"corresponding_institution_ids":["https://openalex.org/I1311688040"],"apc_list":null,"apc_paid":null,"fwci":0.5764,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.65495702,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":95,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"6"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9993000030517578,"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":0.9993000030517578,"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/T10688","display_name":"Image and Signal Denoising Methods","score":0.9983999729156494,"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/T11105","display_name":"Advanced Image Processing Techniques","score":0.9979000091552734,"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/computer-science","display_name":"Computer science","score":0.8385145664215088},{"id":"https://openalex.org/keywords/initialization","display_name":"Initialization","score":0.6024960875511169},{"id":"https://openalex.org/keywords/low-latency","display_name":"Low latency (capital markets)","score":0.5793099999427795},{"id":"https://openalex.org/keywords/bandwidth","display_name":"Bandwidth (computing)","score":0.5182499885559082},{"id":"https://openalex.org/keywords/latency","display_name":"Latency (audio)","score":0.49496573209762573},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.47718560695648193},{"id":"https://openalex.org/keywords/computer-engineering","display_name":"Computer engineering","score":0.4628185033798218},{"id":"https://openalex.org/keywords/computational-complexity-theory","display_name":"Computational complexity theory","score":0.46121323108673096},{"id":"https://openalex.org/keywords/streaming-algorithm","display_name":"Streaming algorithm","score":0.4418710470199585},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.4194045662879944},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4112551808357239},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.3102433681488037},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.17269155383110046},{"id":"https://openalex.org/keywords/computer-network","display_name":"Computer network","score":0.1460924744606018},{"id":"https://openalex.org/keywords/upper-and-lower-bounds","display_name":"Upper and lower bounds","score":0.10192731022834778}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8385145664215088},{"id":"https://openalex.org/C114466953","wikidata":"https://www.wikidata.org/wiki/Q6034165","display_name":"Initialization","level":2,"score":0.6024960875511169},{"id":"https://openalex.org/C46637626","wikidata":"https://www.wikidata.org/wiki/Q6693015","display_name":"Low latency (capital markets)","level":2,"score":0.5793099999427795},{"id":"https://openalex.org/C2776257435","wikidata":"https://www.wikidata.org/wiki/Q1576430","display_name":"Bandwidth (computing)","level":2,"score":0.5182499885559082},{"id":"https://openalex.org/C82876162","wikidata":"https://www.wikidata.org/wiki/Q17096504","display_name":"Latency (audio)","level":2,"score":0.49496573209762573},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.47718560695648193},{"id":"https://openalex.org/C113775141","wikidata":"https://www.wikidata.org/wiki/Q428691","display_name":"Computer engineering","level":1,"score":0.4628185033798218},{"id":"https://openalex.org/C179799912","wikidata":"https://www.wikidata.org/wiki/Q205084","display_name":"Computational complexity theory","level":2,"score":0.46121323108673096},{"id":"https://openalex.org/C187166803","wikidata":"https://www.wikidata.org/wiki/Q2835831","display_name":"Streaming algorithm","level":3,"score":0.4418710470199585},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.4194045662879944},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4112551808357239},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3102433681488037},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.17269155383110046},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.1460924744606018},{"id":"https://openalex.org/C77553402","wikidata":"https://www.wikidata.org/wiki/Q13222579","display_name":"Upper and lower bounds","level":2,"score":0.10192731022834778},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","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},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/mlsp55844.2023.10285965","is_oa":false,"landing_page_url":"https://doi.org/10.1109/mlsp55844.2023.10285965","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE 33rd International Workshop on Machine Learning for Signal Processing (MLSP)","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":0.5299999713897705}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":22,"referenced_works":["https://openalex.org/W1494198834","https://openalex.org/W1560013842","https://openalex.org/W1677182931","https://openalex.org/W1885185971","https://openalex.org/W2046820868","https://openalex.org/W2929274168","https://openalex.org/W2940120659","https://openalex.org/W2970006822","https://openalex.org/W2992005611","https://openalex.org/W3036167779","https://openalex.org/W3092028330","https://openalex.org/W3095802501","https://openalex.org/W3163465952","https://openalex.org/W3197334236","https://openalex.org/W3197990672","https://openalex.org/W3203491020","https://openalex.org/W4221155904","https://openalex.org/W4283215837","https://openalex.org/W6767111847","https://openalex.org/W6779823529","https://openalex.org/W6783867762","https://openalex.org/W6796217209"],"related_works":["https://openalex.org/W3204184292","https://openalex.org/W3176564347","https://openalex.org/W1985458517","https://openalex.org/W2355833770","https://openalex.org/W3031039437","https://openalex.org/W183202219","https://openalex.org/W4206945301","https://openalex.org/W2810731248","https://openalex.org/W3204387396","https://openalex.org/W4387870028"],"abstract_inverted_index":{"Speech":[0],"super-resolution":[1,109],"is":[2,26,47,57,111],"the":[3,7,164],"process":[4,140],"of":[5,11,23,34,74],"estimating":[6],"missing":[8],"frequency":[9,19,24],"content":[10],"a":[12,27,35,72,101,121,136],"speech":[13,108],"signal":[14],"from":[15],"its":[16],"existing":[17],"band-limited":[18],"content.":[20],"The":[21],"loss":[22],"components":[25],"common":[28,50],"occurrence":[29],"that":[30,82,110,125,145,159],"can":[31,126],"be":[32,127],"because":[33],"low":[36],"sampling":[37],"rate,":[38],"low-quality":[39],"microphones,":[40],"or":[41,93],"various":[42],"transmission":[43],"factors,":[44],"and":[45,69,104,141,149,155,174],"it":[46],"an":[48,142],"increasingly":[49],"problem":[51],"as":[52],"bandwidth":[53],"for":[54,77,113,130],"high-quality":[55],"communications":[56],"generally":[58],"available,":[59],"but":[60],"many":[61],"end":[62],"devices":[63],"are":[64,84],"still":[65],"using":[66],"older":[67],"standards":[68],"protocols.":[70],"Although":[71],"number":[73],"solutions":[75,166],"exist":[76],"this":[78,97,168],"problem,":[79],"we":[80,99],"note":[81],"most":[83],"not":[85],"amenable":[86],"to":[87,91,107],"real-world":[88,131],"use,":[89],"due":[90],"computational":[92],"algorithmic":[94],"constraints.":[95],"In":[96],"paper":[98],"present":[100],"compact,":[102],"efficient,":[103],"minimal-latency":[105],"solution":[106],"suitable":[112],"use":[114],"with":[115],"real-time":[116],"streaming":[117],"data.":[118],"We":[119,133],"propose":[120,135],"novel":[122,137],"causal":[123],"architecture":[124],"easily":[128],"deployed":[129],"use.":[132],"additionally":[134],"adversarial":[138],"training":[139],"initialization":[143],"procedure":[144],"speeds":[146],"up":[147],"convergence":[148],"results":[150,157],"in":[151,167],"improved":[152],"outputs.":[153],"Objective":[154],"subjective":[156],"show":[158],"our":[160],"proposed":[161],"model":[162],"outperforms":[163],"latest":[165],"space,":[169],"despite":[170],"being":[171],"significantly":[172],"smaller":[173],"faster.":[175]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":2}],"updated_date":"2026-04-23T09:07:50.710637","created_date":"2025-10-10T00:00:00"}