{"id":"https://openalex.org/W3016057201","doi":"https://doi.org/10.1109/icassp40776.2020.9053283","title":"Enhancement of Coded Speech Using a Mask-Based Post-Filter","display_name":"Enhancement of Coded Speech Using a Mask-Based Post-Filter","publication_year":2020,"publication_date":"2020-04-09","ids":{"openalex":"https://openalex.org/W3016057201","doi":"https://doi.org/10.1109/icassp40776.2020.9053283","mag":"3016057201"},"language":"en","primary_location":{"id":"doi:10.1109/icassp40776.2020.9053283","doi":"https://doi.org/10.1109/icassp40776.2020.9053283","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp40776.2020.9053283","pdf_url":null,"source":{"id":"https://openalex.org/S4363607879","display_name":"IEEE International Conference on Acoustics Speech and Signal Processing","issn_l":"1520-6149","issn":["1520-6149","2379-190X"],"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":["jufo-2","norway-1"],"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":"ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"volume":null,"type":"conference-paper","is_traditional":true,"indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2010.05571","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5077147264","display_name":"Srikanth Korse","orcid":"https://orcid.org/0009-0008-7564-9628","observed_orcids":["https://orcid.org/0009-0008-7564-9628"]},"institutions":[{"id":"https://openalex.org/I4210124274","display_name":"Fraunhofer Institute for Integrated Circuits","ror":"https://ror.org/024ape423","country_code":"DE","type":"facility","lineage":["https://openalex.org/I4210124274","https://openalex.org/I4923324"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Srikanth Korse","raw_affiliation_strings":["Fraunhofer IIS, Erlangen, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Fraunhofer IIS, Erlangen, Germany","institution_ids":["https://openalex.org/I4210124274"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Kishan Gupta","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I4210124274","display_name":"Fraunhofer Institute for Integrated Circuits","ror":"https://ror.org/024ape423","country_code":"DE","type":"facility","lineage":["https://openalex.org/I4210124274","https://openalex.org/I4923324"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Kishan Gupta","raw_affiliation_strings":["Fraunhofer IIS, Erlangen, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Fraunhofer IIS, Erlangen, Germany","institution_ids":["https://openalex.org/I4210124274"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5054985419","display_name":"Guillaume Fuchs","orcid":"https://orcid.org/0009-0009-1045-6064","observed_orcids":["https://orcid.org/0009-0009-1045-6064"]},"institutions":[{"id":"https://openalex.org/I4210124274","display_name":"Fraunhofer Institute for Integrated Circuits","ror":"https://ror.org/024ape423","country_code":"DE","type":"facility","lineage":["https://openalex.org/I4210124274","https://openalex.org/I4923324"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Guillaume Fuchs","raw_affiliation_strings":["Fraunhofer IIS, Erlangen, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Fraunhofer IIS, Erlangen, Germany","institution_ids":["https://openalex.org/I4210124274"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I4210124274"],"apc_list":null,"apc_paid":null,"fwci":1.4874,"has_fulltext":true,"cited_by_count":18,"citation_normalized_percentile":{"value":0.84219587,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":88,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"6764","last_page":"6768"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9990000128746033,"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":0.9990000128746033,"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":0.0005000000237487257,"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/T10901","display_name":"Advanced Data Compression Techniques","score":0.0,"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/post-filter","display_name":"post-filter","score":0.6470000147819519},{"id":"https://openalex.org/keywords/speech-enhancement","display_name":"speech enhancement","score":0.6899999976158142},{"id":"https://openalex.org/keywords/time-frequency-masking","display_name":"time-frequency masking","score":0.6209999918937683},{"id":"https://openalex.org/keywords/amr-wb","display_name":"AMR-WB","score":0.6660000085830688},{"id":"https://openalex.org/keywords/quantization-noise","display_name":"quantization noise","score":0.949999988079071},{"id":"https://openalex.org/keywords/convolutional-encoder-decoder","display_name":"convolutional encoder-decoder","score":0.8830000162124634},{"id":"https://openalex.org/keywords/long-short-term-memory","display_name":"long short-term memory","score":0.8029999732971191},{"id":"https://openalex.org/keywords/fully-connected-neural-network","display_name":"fully connected neural network","score":0.8700000047683716}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7966547012329102},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7019172310829163},{"id":"https://openalex.org/C161765866","wikidata":"https://www.wikidata.org/wiki/Q184748","display_name":"Codec","level":2,"score":0.6220071315765381},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.6069319248199463},{"id":"https://openalex.org/C13895895","wikidata":"https://www.wikidata.org/wiki/Q3270773","display_name":"Speech coding","level":2,"score":0.5876267552375793},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.5832641124725342},{"id":"https://openalex.org/C106131492","wikidata":"https://www.wikidata.org/wiki/Q3072260","display_name":"Filter (signal processing)","level":2,"score":0.4905058741569519},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.4898702800273895},{"id":"https://openalex.org/C173391809","wikidata":"https://www.wikidata.org/wiki/Q2740189","display_name":"Wideband audio","level":5,"score":0.46718931198120117},{"id":"https://openalex.org/C28855332","wikidata":"https://www.wikidata.org/wiki/Q198099","display_name":"Quantization (signal processing)","level":2,"score":0.46376466751098633},{"id":"https://openalex.org/C2777402240","wikidata":"https://www.wikidata.org/wiki/Q6783436","display_name":"Masking (illustration)","level":2,"score":0.4397154152393341},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3690932095050812},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.21284893155097961},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.15349596738815308},{"id":"https://openalex.org/C9390403","wikidata":"https://www.wikidata.org/wiki/Q3966","display_name":"Computer hardware","level":1,"score":0.14388856291770935},{"id":"https://openalex.org/C64922751","wikidata":"https://www.wikidata.org/wiki/Q4650799","display_name":"Audio signal","level":3,"score":0.10900828242301941},{"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/C87687168","wikidata":"https://www.wikidata.org/wiki/Q173114","display_name":"Digital audio","level":4,"score":0.0},{"id":"https://openalex.org/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"score":0.0},{"id":"https://openalex.org/C153349607","wikidata":"https://www.wikidata.org/wiki/Q36649","display_name":"Visual arts","level":1,"score":0.0}],"mesh":[],"locations_count":5,"locations":[{"id":"doi:10.1109/icassp40776.2020.9053283","doi":"https://doi.org/10.1109/icassp40776.2020.9053283","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp40776.2020.9053283","pdf_url":null,"source":{"id":"https://openalex.org/S4363607879","display_name":"IEEE International Conference on Acoustics Speech and Signal Processing","issn_l":"1520-6149","issn":["1520-6149","2379-190X"],"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":["jufo-2","norway-1"],"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":"ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2010.05571","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2010.05571","pdf_url":"https://arxiv.org/pdf/2010.05571","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":"pmh:oai:fraunhofer.de:N-602763","doi":null,"is_oa":false,"landing_page_url":"http://publica.fraunhofer.de/documents/N-602763.html","pdf_url":null,"source":{"id":"https://openalex.org/S4306400801","display_name":"Publikationsdatenbank der Fraunhofer-Gesellschaft (Fraunhofer-Gesellschaft)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I4923324","host_organization_name":"Fraunhofer-Gesellschaft","host_organization_lineage":["https://openalex.org/I4923324"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Fraunhofer IIS","raw_type":"Conference Paper"},{"id":"pmh:oai:publica.fraunhofer.de:publica/408905","doi":null,"is_oa":false,"landing_page_url":"https://publica.fraunhofer.de/handle/publica/408905","pdf_url":null,"source":{"id":"https://openalex.org/S4306400318","display_name":"Fraunhofer-Publica (Fraunhofer-Gesellschaft)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I4923324","host_organization_name":"Fraunhofer-Gesellschaft","host_organization_lineage":["https://openalex.org/I4923324"],"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":"conference paper"},{"id":"doi:10.48550/arxiv.2010.05571","doi":"https://doi.org/10.48550/arxiv.2010.05571","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2010.05571","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":false,"raw_source_name":null,"raw_type":"article-journal"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2010.05571","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2010.05571","pdf_url":"https://arxiv.org/pdf/2010.05571","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3016057201.pdf","grobid_xml":"https://content.openalex.org/works/W3016057201.grobid-xml"},"referenced_works_count":18,"referenced_works":["https://openalex.org/W595351341","https://openalex.org/W1481955708","https://openalex.org/W1522301498","https://openalex.org/W1527477959","https://openalex.org/W2006129368","https://openalex.org/W2046869671","https://openalex.org/W2069681747","https://openalex.org/W2131094339","https://openalex.org/W2404892923","https://openalex.org/W2519091744","https://openalex.org/W2809824582","https://openalex.org/W2889240868","https://openalex.org/W2898322826","https://openalex.org/W2900004752","https://openalex.org/W2944079609","https://openalex.org/W2964121744","https://openalex.org/W3127686677","https://openalex.org/W6789826613"],"related_works":["https://openalex.org/W4226360164","https://openalex.org/W2809824582","https://openalex.org/W2131094339","https://openalex.org/W2889388677","https://openalex.org/W2740535370","https://openalex.org/W2900004752","https://openalex.org/W2889240868","https://openalex.org/W4225860133","https://openalex.org/W2152707162","https://openalex.org/W2088805212"],"abstract_inverted_index":{"The":[0,70],"quality":[1,22],"of":[2,23,84,99,108],"speech":[3,102],"codecs":[4],"deteriorates":[5],"at":[6],"low":[7],"bitrates":[8],"due":[9],"to":[10,19,62],"high":[11],"quantization":[12],"noise.":[13],"A":[14,42],"post-filter":[15,32,118],"is":[16,40],"generally":[17],"employed":[18],"enhance":[20],"the":[21,24,37,76,85,97,100,106,109,121],"coded":[25,101],"speech.":[26],"In":[27],"this":[28],"paper,":[29],"a":[30,48,54,64,115],"data-driven":[31],"relying":[33],"on":[34,75],"masking":[35],"in":[36,120],"time-frequency":[38,68],"domain":[39],"proposed.":[41],"fully":[43],"connected":[44],"neural":[45,111],"network":[46,52,59,112],"(FCNN),":[47],"convolutional":[49],"encoder-decoder":[50],"(CED)":[51],"and":[53,93,103],"long":[55],"short-term":[56],"memory":[57],"(LSTM)":[58],"are":[60],"implemeted":[61],"estimate":[63],"real-valued":[65],"mask":[66],"per":[67],"bin.":[69],"proposed":[71],"models":[72],"were":[73],"tested":[74],"five":[77],"lowest":[78],"operating":[79],"modes":[80],"(6.65":[81],"kbps-15.85":[82],"kbps)":[83],"Adaptive":[86],"Multi-Rate":[87],"Wideband":[88],"codec":[89],"(AMR-WB).":[90],"Both":[91],"objective":[92],"subjective":[94],"evaluations":[95],"confirm":[96],"enhancement":[98],"also":[104],"show":[105],"superiority":[107],"mask-based":[110],"system":[113],"over":[114],"conventional":[116],"heuristic":[117],"used":[119],"standard":[122],"like":[123],"ITU-T":[124],"G.718.":[125]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":5},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":3},{"year":2021,"cited_by_count":3},{"year":2020,"cited_by_count":1}],"updated_date":"2026-11-04T10:54:05.112534","created_date":"2020-04-17T00:00:00"}