{"id":"https://openalex.org/W3048758284","doi":"https://doi.org/10.21437/interspeech.2020-3027","title":"PoCoNet: Better Speech Enhancement with Frequency-Positional Embeddings, Semi-Supervised Conversational Data, and Biased Loss","display_name":"PoCoNet: Better Speech Enhancement with Frequency-Positional Embeddings, Semi-Supervised Conversational Data, and Biased Loss","publication_year":2020,"publication_date":"2020-10-25","ids":{"openalex":"https://openalex.org/W3048758284","doi":"https://doi.org/10.21437/interspeech.2020-3027","mag":"3048758284"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2020-3027","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2020-3027","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/2008.04470","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","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/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/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/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/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/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":"Arvindh Krishnaswamy","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"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":6,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.3687,"has_fulltext":true,"cited_by_count":9,"citation_normalized_percentile":{"value":0.81541873,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"2487","last_page":"2491"},"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":0.9988999962806702,"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":0.9965000152587891,"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/computer-science","display_name":"Computer science","score":0.8020018339157104},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.6890028715133667},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.6144310235977173},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5324747562408447},{"id":"https://openalex.org/keywords/variety","display_name":"Variety (cybernetics)","score":0.49742391705513},{"id":"https://openalex.org/keywords/speech-enhancement","display_name":"Speech enhancement","score":0.4815092980861664},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.46416524052619934},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.42366689443588257},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.41965723037719727},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4064740240573883},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.07520037889480591}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8020018339157104},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.6890028715133667},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.6144310235977173},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5324747562408447},{"id":"https://openalex.org/C136197465","wikidata":"https://www.wikidata.org/wiki/Q1729295","display_name":"Variety (cybernetics)","level":2,"score":0.49742391705513},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.4815092980861664},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.46416524052619934},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.42366689443588257},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.41965723037719727},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4064740240573883},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.07520037889480591},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.21437/interspeech.2020-3027","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2020-3027","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:2008.04470","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2008.04470","pdf_url":"https://arxiv.org/pdf/2008.04470","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:3048758284","is_oa":true,"landing_page_url":"https://arxiv.org/pdf/2008.04470.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.2008.04470","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2008.04470","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:2008.04470","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2008.04470","pdf_url":"https://arxiv.org/pdf/2008.04470","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":{"grobid_xml":false,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3048758284.pdf"},"referenced_works_count":26,"referenced_works":["https://openalex.org/W1494198834","https://openalex.org/W1495679096","https://openalex.org/W1897240248","https://openalex.org/W2006129368","https://openalex.org/W2044893557","https://openalex.org/W2117678320","https://openalex.org/W2136682440","https://openalex.org/W2144404214","https://openalex.org/W2186615578","https://openalex.org/W2291877678","https://openalex.org/W2396130155","https://openalex.org/W2726515241","https://openalex.org/W2810843531","https://openalex.org/W2890401420","https://openalex.org/W2894785362","https://openalex.org/W2902132730","https://openalex.org/W2950893734","https://openalex.org/W2952218014","https://openalex.org/W2963091558","https://openalex.org/W2963103134","https://openalex.org/W2963453742","https://openalex.org/W2963868408","https://openalex.org/W2998678989","https://openalex.org/W3002439978","https://openalex.org/W3015791598","https://openalex.org/W3030102521"],"related_works":["https://openalex.org/W3097034112","https://openalex.org/W3199713199","https://openalex.org/W3214314684","https://openalex.org/W2963954250","https://openalex.org/W3005262054","https://openalex.org/W3031135612","https://openalex.org/W3142629163","https://openalex.org/W2994785103","https://openalex.org/W3206706278","https://openalex.org/W3149225678","https://openalex.org/W3041487835","https://openalex.org/W2922358226","https://openalex.org/W3163142165","https://openalex.org/W3007217021","https://openalex.org/W2962997440","https://openalex.org/W3168189696","https://openalex.org/W3095913803","https://openalex.org/W3160324929","https://openalex.org/W2971758476","https://openalex.org/W3004253052"],"abstract_inverted_index":{"Neural":[0],"network":[1,58],"applications":[2],"generally":[3],"benefit":[4],"from":[5,19],"larger-sized":[6],"models,":[7,13],"but":[8],"for":[9,47],"current":[10],"speech":[11,48,105,116],"enhancement":[12],"larger":[14],"scale":[15],"networks":[16,46],"often":[17],"suffer":[18],"decreased":[20],"robustness":[21],"to":[22,42,68],"the":[23,61,75,83,108,127,130],"variety":[24],"of":[25,63,85,129],"real-world":[26],"use":[27,62],"cases":[28],"beyond":[29],"what":[30],"is":[31,54,66],"encountered":[32],"in":[33,74],"training":[34,87],"data.":[35],"We":[36],"introduce":[37],"several":[38],"innovations":[39],"that":[40],"lead":[41],"better":[43,110],"large":[44],"neural":[45,57],"enhancement.":[49],"The":[50],"novel":[51],"PoCoNet":[52],"architecture":[53],"a":[55],"convolutional":[56],"that,":[59],"with":[60],"frequency-positional":[64],"embeddings,":[65],"able":[67],"more":[69],"efficiently":[70],"build":[71],"frequency-dependent":[72],"features":[73],"early":[76],"layers.":[77],"A":[78,98],"semi-supervised":[79],"method":[80],"helps":[81,107],"increase":[82],"amount":[84],"conversational":[86],"data":[88],"by":[89],"pre-enhancing":[90],"noisy":[91],"datasets,":[92],"improving":[93],"performance":[94],"on":[95,115],"real":[96],"recordings.":[97],"new":[99],"loss":[100],"function":[101],"biased":[102],"towards":[103],"preserving":[104],"quality":[106],"optimization":[109],"match":[111],"human":[112,123],"perceptual":[113],"opinions":[114],"quality.":[117],"Ablation":[118],"experiments":[119],"and":[120,122],"objective":[121],"opinion":[124],"metrics":[125],"show":[126],"benefits":[128],"proposed":[131],"improvements.":[132]},"counts_by_year":[{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":4},{"year":2020,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2022-07-26T00:00:00"}