{"id":"https://openalex.org/W3047821330","doi":"https://doi.org/10.21437/interspeech.2020-2730","title":"A Perceptually-Motivated Approach for Low-Complexity, Real-Time Enhancement of Fullband Speech","display_name":"A Perceptually-Motivated Approach for Low-Complexity, Real-Time Enhancement of Fullband Speech","publication_year":2020,"publication_date":"2020-10-25","ids":{"openalex":"https://openalex.org/W3047821330","doi":"https://doi.org/10.21437/interspeech.2020-2730","mag":"3047821330"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2020-2730","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2020-2730","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2020","raw_type":"proceedings-article"},"type":"preprint","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2008.04259","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","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 (United States), Seattle, United States"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Amazon (United States), Seattle, United States","institution_ids":["https://openalex.org/I1311688040"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5036092393","display_name":"Umut Isik","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":"Umut Isik","raw_affiliation_strings":["Amazon (United States), Seattle, United States"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Amazon (United States), Seattle, United States","institution_ids":["https://openalex.org/I1311688040"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5053473725","display_name":"Neerad Phansalkar","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Neerad Phansalkar","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5091775011","display_name":"Ritwik Giri","orcid":"https://orcid.org/0000-0002-8599-3229"},"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":"Ritwik Giri","raw_affiliation_strings":["Amazon (United States), Seattle, United States"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Amazon (United States), Seattle, United States","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/I28290843","display_name":"University of Surrey","ror":"https://ror.org/00ks66431","country_code":"GB","type":"education","lineage":["https://openalex.org/I28290843"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Karim Helwani","raw_affiliation_strings":["University of Surrey, Guildford, United Kingdom"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Surrey, Guildford, United Kingdom","institution_ids":["https://openalex.org/I28290843"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5112751528","display_name":"Arvindh Krishnaswamy","orcid":null},"institutions":[{"id":"https://openalex.org/I4210089985","display_name":"Amazon (Germany)","ror":"https://ror.org/00b9ktm87","country_code":"DE","type":"company","lineage":["https://openalex.org/I1311688040","https://openalex.org/I4210089985"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Arvindh Krishnaswamy","raw_affiliation_strings":["Amazon"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Amazon","institution_ids":["https://openalex.org/I4210089985"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":6,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.4562,"has_fulltext":true,"cited_by_count":3,"citation_normalized_percentile":{"value":0.61270545,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"2482","last_page":"2486"},"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/T11233","display_name":"Advanced Adaptive Filtering Techniques","score":0.9975000023841858,"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"}},{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9962999820709229,"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/short-time-fourier-transform","display_name":"Short-time Fourier transform","score":0.7936620116233826},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7626794576644897},{"id":"https://openalex.org/keywords/spectral-envelope","display_name":"Spectral envelope","score":0.7245405316352844},{"id":"https://openalex.org/keywords/speech-enhancement","display_name":"Speech enhancement","score":0.7005113959312439},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6290262937545776},{"id":"https://openalex.org/keywords/fast-fourier-transform","display_name":"Fast Fourier transform","score":0.5223868489265442},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5176375508308411},{"id":"https://openalex.org/keywords/fourier-transform","display_name":"Fourier transform","score":0.5140865445137024},{"id":"https://openalex.org/keywords/envelope","display_name":"Envelope (radar)","score":0.4787246882915497},{"id":"https://openalex.org/keywords/computational-complexity-theory","display_name":"Computational complexity theory","score":0.4721935987472534},{"id":"https://openalex.org/keywords/time-domain","display_name":"Time domain","score":0.4426569640636444},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.4117893576622009},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.22631573677062988},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.1323501467704773},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.12816163897514343},{"id":"https://openalex.org/keywords/fourier-analysis","display_name":"Fourier analysis","score":0.11835694313049316}],"concepts":[{"id":"https://openalex.org/C166386157","wikidata":"https://www.wikidata.org/wiki/Q1477735","display_name":"Short-time Fourier transform","level":4,"score":0.7936620116233826},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7626794576644897},{"id":"https://openalex.org/C54926389","wikidata":"https://www.wikidata.org/wiki/Q7575188","display_name":"Spectral envelope","level":2,"score":0.7245405316352844},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.7005113959312439},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6290262937545776},{"id":"https://openalex.org/C75172450","wikidata":"https://www.wikidata.org/wiki/Q623950","display_name":"Fast Fourier transform","level":2,"score":0.5223868489265442},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5176375508308411},{"id":"https://openalex.org/C102519508","wikidata":"https://www.wikidata.org/wiki/Q6520159","display_name":"Fourier transform","level":2,"score":0.5140865445137024},{"id":"https://openalex.org/C65155139","wikidata":"https://www.wikidata.org/wiki/Q5380912","display_name":"Envelope (radar)","level":3,"score":0.4787246882915497},{"id":"https://openalex.org/C179799912","wikidata":"https://www.wikidata.org/wiki/Q205084","display_name":"Computational complexity theory","level":2,"score":0.4721935987472534},{"id":"https://openalex.org/C103824480","wikidata":"https://www.wikidata.org/wiki/Q185889","display_name":"Time domain","level":2,"score":0.4426569640636444},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.4117893576622009},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.22631573677062988},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.1323501467704773},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.12816163897514343},{"id":"https://openalex.org/C203024314","wikidata":"https://www.wikidata.org/wiki/Q1365258","display_name":"Fourier analysis","level":3,"score":0.11835694313049316},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.0},{"id":"https://openalex.org/C554190296","wikidata":"https://www.wikidata.org/wiki/Q47528","display_name":"Radar","level":2,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.21437/interspeech.2020-2730","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2020-2730","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2020","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2008.04259","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2008.04259","pdf_url":"https://arxiv.org/pdf/2008.04259","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"mag:3047821330","is_oa":true,"landing_page_url":"https://arxiv.org/pdf/2008.04259.pdf","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"arXiv (Cornell University)","raw_type":null},{"id":"doi:10.48550/arxiv.2008.04259","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2008.04259","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2008.04259","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2008.04259","pdf_url":"https://arxiv.org/pdf/2008.04259","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3047821330.pdf","grobid_xml":"https://content.openalex.org/works/W3047821330.grobid-xml"},"referenced_works_count":24,"referenced_works":["https://openalex.org/W1575718033","https://openalex.org/W2013020033","https://openalex.org/W2044893557","https://openalex.org/W2071941461","https://openalex.org/W2100351681","https://openalex.org/W2121973264","https://openalex.org/W2128301448","https://openalex.org/W2128653836","https://openalex.org/W2131094339","https://openalex.org/W2141411743","https://openalex.org/W2291877678","https://openalex.org/W2402901296","https://openalex.org/W2404892923","https://openalex.org/W2600556233","https://openalex.org/W2603567530","https://openalex.org/W2889373351","https://openalex.org/W2889442120","https://openalex.org/W2890401420","https://openalex.org/W2902132730","https://openalex.org/W2963103134","https://openalex.org/W2963868408","https://openalex.org/W2964199361","https://openalex.org/W3003901600","https://openalex.org/W3030102521"],"related_works":["https://openalex.org/W3095248373","https://openalex.org/W2033594129","https://openalex.org/W2370100170","https://openalex.org/W2792227696","https://openalex.org/W2784507976","https://openalex.org/W2170212447","https://openalex.org/W2990433241","https://openalex.org/W2747006289","https://openalex.org/W3210202203","https://openalex.org/W2765475970","https://openalex.org/W2399672261","https://openalex.org/W2166861700","https://openalex.org/W2100209102","https://openalex.org/W2383148018","https://openalex.org/W3110551121","https://openalex.org/W1489832123","https://openalex.org/W2185332410","https://openalex.org/W2911043226","https://openalex.org/W3038255278","https://openalex.org/W2963260340"],"abstract_inverted_index":{"Over":[0],"the":[1,32,33,64,69,72],"past":[2],"few":[3],"years,":[4],"speech":[5,60,83],"enhancement":[6,78],"methods":[7,16],"based":[8,17],"on":[9,18,56,63,68],"deep":[10],"learning":[11],"have":[12],"greatly":[13],"surpassed":[14],"traditional":[15],"spectral":[19,22,65],"subtraction":[20],"and":[21,67],"estimation.":[23],"Many":[24],"of":[25,59,71,79,88],"these":[26],"new":[27],"techniques":[28],"operate":[29],"directly":[30],"in":[31,40],"short-time":[34],"Fourier":[35],"transform":[36],"(STFT)":[37],"domain,":[38],"resulting":[39],"a":[41,89],"high":[42],"computational":[43],"complexity.":[44],"In":[45],"this":[46],"work,":[47],"we":[48],"propose":[49],"PercepNet,":[50],"an":[51],"efficient":[52],"approach":[53],"that":[54],"relies":[55],"human":[57],"perception":[58],"by":[61],"focusing":[62],"envelope":[66],"periodicity":[70],"speech.":[73],"We":[74],"demonstrate":[75],"high-quality,":[76],"real-time":[77],"fullband":[80],"(48":[81],"kHz)":[82],"with":[84],"less":[85],"than":[86],"5%":[87],"CPU":[90],"core.":[91]},"counts_by_year":[{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":2}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2022-07-26T00:00:00"}