{"id":"https://openalex.org/W4392903975","doi":"https://doi.org/10.1109/icassp48485.2024.10448332","title":"NOLACE: Improving Low-Complexity Speech Codec Enhancement Through Adaptive Temporal Shaping","display_name":"NOLACE: Improving Low-Complexity Speech Codec Enhancement Through Adaptive Temporal Shaping","publication_year":2024,"publication_date":"2024-03-18","ids":{"openalex":"https://openalex.org/W4392903975","doi":"https://doi.org/10.1109/icassp48485.2024.10448332"},"language":"en","primary_location":{"id":"doi:10.1109/icassp48485.2024.10448332","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp48485.2024.10448332","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2024 - 2024 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/A5042244085","display_name":"Jan B\u00fcthe","orcid":"https://orcid.org/0000-0001-5872-4325"},"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":"Jan B\u00fcthe","raw_affiliation_strings":["Amazon Web Services,Palo Alto,USA","Amazon Web Services, Palo Alto, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Amazon Web Services,Palo Alto,USA","institution_ids":["https://openalex.org/I1311688040"]},{"raw_affiliation_string":"Amazon Web Services, Palo Alto, USA","institution_ids":["https://openalex.org/I1311688040"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5110745444","display_name":"Ahmed Mustafa","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":"Ahmed Mustafa","raw_affiliation_strings":["Amazon Web Services,Palo Alto,USA","Amazon Web Services, Palo Alto, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Amazon Web Services,Palo Alto,USA","institution_ids":["https://openalex.org/I1311688040"]},{"raw_affiliation_string":"Amazon Web Services, Palo Alto, USA","institution_ids":["https://openalex.org/I1311688040"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5021269794","display_name":"Jean-Marc Valin","orcid":"https://orcid.org/0000-0002-9883-6927"},"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":"Jean-Marc Valin","raw_affiliation_strings":["Amazon Web Services,Palo Alto,USA","Amazon Web Services, Palo Alto, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Amazon Web Services,Palo Alto,USA","institution_ids":["https://openalex.org/I1311688040"]},{"raw_affiliation_string":"Amazon Web Services, Palo Alto, USA","institution_ids":["https://openalex.org/I1311688040"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5014282181","display_name":"Karim Helwani","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":"Karim Helwani","raw_affiliation_strings":["Amazon Web Services,Palo Alto,USA","Amazon Web Services, Palo Alto, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Amazon Web Services,Palo Alto,USA","institution_ids":["https://openalex.org/I1311688040"]},{"raw_affiliation_string":"Amazon Web Services, Palo Alto, USA","institution_ids":["https://openalex.org/I1311688040"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5028244782","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,Palo Alto,USA","Amazon Web Services, Palo Alto, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Amazon Web Services,Palo Alto,USA","institution_ids":["https://openalex.org/I1311688040"]},{"raw_affiliation_string":"Amazon Web Services, Palo Alto, USA","institution_ids":["https://openalex.org/I1311688040"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":2.1383,"has_fulltext":false,"cited_by_count":7,"citation_normalized_percentile":{"value":0.88450784,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":95,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"476","last_page":"480"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9997000098228455,"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"}},"topics":[{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9997000098228455,"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/T10860","display_name":"Speech and Audio Processing","score":0.9997000098228455,"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":0.9984999895095825,"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/codec","display_name":"Codec","score":0.8355323076248169},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7549834251403809},{"id":"https://openalex.org/keywords/speech-coding","display_name":"Speech coding","score":0.6754531860351562},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6391118168830872},{"id":"https://openalex.org/keywords/coding","display_name":"Coding (social sciences)","score":0.5205077528953552},{"id":"https://openalex.org/keywords/codec2","display_name":"Codec2","score":0.5084789991378784},{"id":"https://openalex.org/keywords/speech-enhancement","display_name":"Speech enhancement","score":0.5079770684242249},{"id":"https://openalex.org/keywords/adaptive-multi-rate-audio-codec","display_name":"Adaptive Multi-Rate audio codec","score":0.46410903334617615},{"id":"https://openalex.org/keywords/decoding-methods","display_name":"Decoding methods","score":0.43290814757347107},{"id":"https://openalex.org/keywords/linear-predictive-coding","display_name":"Linear predictive coding","score":0.39919185638427734},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.36797887086868286},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.33909353613853455},{"id":"https://openalex.org/keywords/voice-activity-detection","display_name":"Voice activity detection","score":0.2634713053703308},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.261730432510376},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.16563686728477478},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.13237863779067993},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.09952327609062195}],"concepts":[{"id":"https://openalex.org/C161765866","wikidata":"https://www.wikidata.org/wiki/Q184748","display_name":"Codec","level":2,"score":0.8355323076248169},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7549834251403809},{"id":"https://openalex.org/C13895895","wikidata":"https://www.wikidata.org/wiki/Q3270773","display_name":"Speech coding","level":2,"score":0.6754531860351562},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6391118168830872},{"id":"https://openalex.org/C179518139","wikidata":"https://www.wikidata.org/wiki/Q5140297","display_name":"Coding (social sciences)","level":2,"score":0.5205077528953552},{"id":"https://openalex.org/C75217168","wikidata":"https://www.wikidata.org/wiki/Q1105653","display_name":"Codec2","level":4,"score":0.5084789991378784},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.5079770684242249},{"id":"https://openalex.org/C177067256","wikidata":"https://www.wikidata.org/wiki/Q4676210","display_name":"Adaptive Multi-Rate audio codec","level":4,"score":0.46410903334617615},{"id":"https://openalex.org/C57273362","wikidata":"https://www.wikidata.org/wiki/Q576722","display_name":"Decoding methods","level":2,"score":0.43290814757347107},{"id":"https://openalex.org/C59883199","wikidata":"https://www.wikidata.org/wiki/Q1826438","display_name":"Linear predictive coding","level":3,"score":0.39919185638427734},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.36797887086868286},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.33909353613853455},{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.2634713053703308},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.261730432510376},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.16563686728477478},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.13237863779067993},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.09952327609062195},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp48485.2024.10448332","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp48485.2024.10448332","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":27,"referenced_works":["https://openalex.org/W1494198834","https://openalex.org/W2131094339","https://openalex.org/W2593414223","https://openalex.org/W2750167318","https://openalex.org/W2809824582","https://openalex.org/W2895654193","https://openalex.org/W2972519044","https://openalex.org/W3016057201","https://openalex.org/W3092791109","https://openalex.org/W3096468295","https://openalex.org/W3163662330","https://openalex.org/W3167533889","https://openalex.org/W3197273793","https://openalex.org/W3198020407","https://openalex.org/W3215615641","https://openalex.org/W4225860133","https://openalex.org/W4226360164","https://openalex.org/W4284972581","https://openalex.org/W4307323391","https://openalex.org/W4372270198","https://openalex.org/W4375868823","https://openalex.org/W4375869380","https://openalex.org/W4386764386","https://openalex.org/W6777664437","https://openalex.org/W6777781272","https://openalex.org/W6778625279","https://openalex.org/W6779192484"],"related_works":["https://openalex.org/W2060409740","https://openalex.org/W2159307410","https://openalex.org/W1542588102","https://openalex.org/W137020845","https://openalex.org/W1570121624","https://openalex.org/W2121846146","https://openalex.org/W2378944441","https://openalex.org/W1999835922","https://openalex.org/W1551277881","https://openalex.org/W3211091508"],"abstract_inverted_index":{"Speech":[0],"codec":[1,127],"enhancement":[2],"methods":[3,15,34],"are":[4,16,40,156],"designed":[5],"to":[6,31,108,123],"remove":[7],"distortions":[8],"added":[9],"by":[10,59],"speech":[11],"codecs.":[12],"While":[13],"classical":[14,63],"very":[17],"low":[18],"in":[19,43,67,113],"complexity":[20,44],"and":[21,128,138,146,154],"add":[22],"zero":[23],"delay,":[24],"their":[25],"effectiveness":[26],"is":[27,88],"rather":[28],"limited.":[29],"Compared":[30],"that,":[32],"DNN-based":[33],"deliver":[35],"higher":[36],"quality":[37,81],"but":[38],"they":[39],"typically":[41],"high":[42,105],"and/or":[45],"require":[46],"delay.":[47],"The":[48],"recently":[49],"proposed":[50],"Linear":[51],"Adaptive":[52,116],"Coding":[53,117],"Enhancer":[54,118],"(LACE)":[55],"addresses":[56],"this":[57,93],"problem":[58],"combining":[60],"DNNs":[61],"with":[62,160],"long-term/short-term":[64],"post-filtering":[65],"resulting":[66,112],"a":[68,97],"causal":[69],"low-complexity":[70],"model.":[71],"A":[72],"short-coming":[73],"of":[74],"the":[75,85,109,114,125,135],"LACE":[76,110,141,153],"model":[77,86,111,142],"is,":[78],"however,":[79],"that":[80,103,130,152],"quickly":[82],"saturates":[83],"when":[84,158],"size":[87],"scaled":[89],"up.":[90],"To":[91],"mitigate":[92],"problem,":[94],"we":[95],"propose":[96],"novel":[98],"adatpive":[99],"temporal":[100,106],"shaping":[101],"module":[102],"adds":[104],"resolution":[107],"Non-Linear":[115],"(NoLACE).":[119],"We":[120,149],"adapt":[121],"NoLACE":[122,131,155],"enhance":[124],"Opus":[126,136],"show":[129,151],"significantly":[132],"outperforms":[133],"both":[134],"baseline":[137],"an":[139,161],"enlarged":[140],"at":[143],"6,":[144],"9":[145],"12":[147],"kb/s.":[148],"also":[150],"well-behaved":[157],"used":[159],"ASR":[162],"system.":[163]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":3}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}