{"id":"https://openalex.org/W4312448510","doi":"https://doi.org/10.1109/mmsp55362.2022.9949392","title":"Performance optimizations on U-Net speech enhancement models","display_name":"Performance optimizations on U-Net speech enhancement models","publication_year":2022,"publication_date":"2022-09-26","ids":{"openalex":"https://openalex.org/W4312448510","doi":"https://doi.org/10.1109/mmsp55362.2022.9949392"},"language":"en","primary_location":{"id":"doi:10.1109/mmsp55362.2022.9949392","is_oa":false,"landing_page_url":"https://doi.org/10.1109/mmsp55362.2022.9949392","pdf_url":null,"source":{"id":"https://openalex.org/S4363605768","display_name":"2022 IEEE 24th International Workshop on Multimedia Signal Processing (MMSP)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 IEEE 24th International Workshop on Multimedia Signal Processing (MMSP)","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/A5103960716","display_name":"Jerry Chee","orcid":null},"institutions":[{"id":"https://openalex.org/I205783295","display_name":"Cornell University","ror":"https://ror.org/05bnh6r87","country_code":"US","type":"education","lineage":["https://openalex.org/I205783295"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Jerry Chee","raw_affiliation_strings":["Cornell University,Department of Computer Science,Ithaca,USA","Department of Computer Science, Cornell University, Ithaca, USA"],"affiliations":[{"raw_affiliation_string":"Cornell University,Department of Computer Science,Ithaca,USA","institution_ids":["https://openalex.org/I205783295"]},{"raw_affiliation_string":"Department of Computer Science, Cornell University, Ithaca, USA","institution_ids":["https://openalex.org/I205783295"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5055277441","display_name":"Sebastian Braun","orcid":"https://orcid.org/0000-0001-9060-223X"},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Sebastian Braun","raw_affiliation_strings":["Microsoft Research, Microsoft,Redmond,USA","Microsoft Research, Microsoft, Redmond, USA"],"affiliations":[{"raw_affiliation_string":"Microsoft Research, Microsoft,Redmond,USA","institution_ids":["https://openalex.org/I1290206253"]},{"raw_affiliation_string":"Microsoft Research, Microsoft, Redmond, USA","institution_ids":["https://openalex.org/I1290206253"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5024067566","display_name":"Vishak Gopal","orcid":"https://orcid.org/0009-0005-3887-1439"},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Vishak Gopal","raw_affiliation_strings":["IC3-AI, Microsoft,Redmond,USA","IC3-AI, Microsoft, Redmond, USA"],"affiliations":[{"raw_affiliation_string":"IC3-AI, Microsoft,Redmond,USA","institution_ids":["https://openalex.org/I1290206253"]},{"raw_affiliation_string":"IC3-AI, Microsoft, Redmond, USA","institution_ids":["https://openalex.org/I1290206253"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5068040769","display_name":"Ross Cutler","orcid":"https://orcid.org/0000-0002-2004-3003"},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ross Cutler","raw_affiliation_strings":["IC3-AI, Microsoft,Redmond,USA","IC3-AI, Microsoft, Redmond, USA"],"affiliations":[{"raw_affiliation_string":"IC3-AI, Microsoft,Redmond,USA","institution_ids":["https://openalex.org/I1290206253"]},{"raw_affiliation_string":"IC3-AI, Microsoft, Redmond, USA","institution_ids":["https://openalex.org/I1290206253"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5103960716"],"corresponding_institution_ids":["https://openalex.org/I205783295"],"apc_list":null,"apc_paid":null,"fwci":0.1229,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.29415482,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":94},"biblio":{"volume":"119","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":1.0,"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":1.0,"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":0.9986000061035156,"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"}},{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9980000257492065,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.8372219800949097},{"id":"https://openalex.org/keywords/speedup","display_name":"Speedup","score":0.8075879812240601},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7690951228141785},{"id":"https://openalex.org/keywords/speech-enhancement","display_name":"Speech enhancement","score":0.641629159450531},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.6229504346847534},{"id":"https://openalex.org/keywords/metric","display_name":"Metric (unit)","score":0.5763233304023743},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.5376846194267273},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.48069673776626587},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.46679410338401794},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.46253183484077454},{"id":"https://openalex.org/keywords/baseline","display_name":"Baseline (sea)","score":0.4193416237831116},{"id":"https://openalex.org/keywords/performance-metric","display_name":"Performance metric","score":0.4107722043991089},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.38456517457962036},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3267168700695038},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.1816466748714447},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.0984933078289032}],"concepts":[{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.8372219800949097},{"id":"https://openalex.org/C68339613","wikidata":"https://www.wikidata.org/wiki/Q1549489","display_name":"Speedup","level":2,"score":0.8075879812240601},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7690951228141785},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.641629159450531},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.6229504346847534},{"id":"https://openalex.org/C176217482","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Metric (unit)","level":2,"score":0.5763233304023743},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.5376846194267273},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.48069673776626587},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.46679410338401794},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.46253183484077454},{"id":"https://openalex.org/C12725497","wikidata":"https://www.wikidata.org/wiki/Q810247","display_name":"Baseline (sea)","level":2,"score":0.4193416237831116},{"id":"https://openalex.org/C2780898871","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Performance metric","level":2,"score":0.4107722043991089},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.38456517457962036},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3267168700695038},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.1816466748714447},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.0984933078289032},{"id":"https://openalex.org/C111368507","wikidata":"https://www.wikidata.org/wiki/Q43518","display_name":"Oceanography","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C21547014","wikidata":"https://www.wikidata.org/wiki/Q1423657","display_name":"Operations management","level":1,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0},{"id":"https://openalex.org/C127313418","wikidata":"https://www.wikidata.org/wiki/Q1069","display_name":"Geology","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/mmsp55362.2022.9949392","is_oa":false,"landing_page_url":"https://doi.org/10.1109/mmsp55362.2022.9949392","pdf_url":null,"source":{"id":"https://openalex.org/S4363605768","display_name":"2022 IEEE 24th International Workshop on Multimedia Signal Processing (MMSP)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 IEEE 24th International Workshop on Multimedia Signal Processing (MMSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions","score":0.5199999809265137}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":47,"referenced_works":["https://openalex.org/W1686810756","https://openalex.org/W1897240248","https://openalex.org/W2194775991","https://openalex.org/W2609317876","https://openalex.org/W2773624778","https://openalex.org/W2805003733","https://openalex.org/W2883028206","https://openalex.org/W2889442120","https://openalex.org/W2896409484","https://openalex.org/W2915589364","https://openalex.org/W2928560789","https://openalex.org/W2950248853","https://openalex.org/W2962965870","https://openalex.org/W2963048316","https://openalex.org/W2963189033","https://openalex.org/W2964233199","https://openalex.org/W3016120385","https://openalex.org/W3034628778","https://openalex.org/W3035016149","https://openalex.org/W3092382944","https://openalex.org/W3160129476","https://openalex.org/W3161480375","https://openalex.org/W3163105696","https://openalex.org/W3163464523","https://openalex.org/W3164605550","https://openalex.org/W3195156220","https://openalex.org/W3195288392","https://openalex.org/W3196438592","https://openalex.org/W3197042120","https://openalex.org/W4225302959","https://openalex.org/W4287068746","https://openalex.org/W4287828539","https://openalex.org/W4288022794","https://openalex.org/W6637373629","https://openalex.org/W6679667936","https://openalex.org/W6684563725","https://openalex.org/W6726275242","https://openalex.org/W6751979845","https://openalex.org/W6755843862","https://openalex.org/W6759263581","https://openalex.org/W6769412281","https://openalex.org/W6774302960","https://openalex.org/W6779640062","https://openalex.org/W6779683180","https://openalex.org/W6784784916","https://openalex.org/W6797351737","https://openalex.org/W6798878592"],"related_works":["https://openalex.org/W2058965144","https://openalex.org/W2164382479","https://openalex.org/W98480971","https://openalex.org/W2150291671","https://openalex.org/W2027972911","https://openalex.org/W2146343568","https://openalex.org/W2013643406","https://openalex.org/W2157978810","https://openalex.org/W2597809628","https://openalex.org/W3046370962"],"abstract_inverted_index":{"Deep":[0],"learning":[1],"approaches-while":[2],"remarkably":[3],"successful":[4],"in":[5,8,15],"audio":[6],"enhancement-result":[7],"slower":[9],"inference":[10,42,80],"times":[11],"which":[12],"are":[13],"prohibitive":[14],"real-time":[16],"applications.":[17],"We":[18,78],"develop":[19],"a":[20,39,51,67,83],"practical":[21],"strategy":[22],"for":[23],"compressing":[24],"U-Net":[25],"style":[26],"deep":[27,32],"neural":[28],"network":[29],"architectures.":[30],"On":[31],"noise":[33],"suppression":[34],"(DNS)":[35],"models":[36],"we":[37,93],"achieve":[38],"state-of-the-art":[40],"7.25\u00d7":[41],"speed":[43,81],"up":[44],"over":[45],"the":[46],"baseline":[47],"CRUSE":[48],"model,":[49],"with":[50],"smooth":[52],"model":[53,95],"performance":[54],"degradation.":[55],"Our":[56],"method":[57],"is":[58],"friendly":[59],"to":[60],"practitioners":[61],"as":[62],"it":[63],"only":[64],"requires":[65],"setting":[66],"single":[68],"compression":[69,74],"parameter,":[70],"while":[71],"achieving":[72],"non-uniform":[73],"rates":[75],"across":[76],"layers.":[77],"report":[79],"because":[82],"parameter":[84],"or":[85],"memory":[86],"reduction":[87],"does":[88],"not":[89],"necessitate":[90],"speedup,":[91],"and":[92],"measure":[94],"quality":[96,103],"using":[97],"an":[98],"accurate":[99],"non-intrusive":[100],"objective":[101],"speech":[102],"metric.":[104]},"counts_by_year":[{"year":2024,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}