{"id":"https://openalex.org/W3106828050","doi":"https://doi.org/10.12720/jcm.15.11.841-848","title":"Speech Separation in the Frequency Domain with Autoencoder","display_name":"Speech Separation in the Frequency Domain with Autoencoder","publication_year":2020,"publication_date":"2020-01-01","ids":{"openalex":"https://openalex.org/W3106828050","doi":"https://doi.org/10.12720/jcm.15.11.841-848","mag":"3106828050"},"language":"en","primary_location":{"id":"doi:10.12720/jcm.15.11.841-848","is_oa":true,"landing_page_url":"https://doi.org/10.12720/jcm.15.11.841-848","pdf_url":null,"source":{"id":"https://openalex.org/S184821498","display_name":"Journal of Communications","issn_l":"1796-2021","issn":["1796-2021","2374-4367"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4323867253","host_organization_name":"International Communication Association","host_organization_lineage":["https://openalex.org/P4323867253"],"host_organization_lineage_names":["International Communication Association"],"type":"journal"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Communications","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://doi.org/10.12720/jcm.15.11.841-848","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5049682757","display_name":"Hao D.","orcid":"https://orcid.org/0000-0002-9014-1506"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hao D. Do","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5058382277","display_name":"Son Tran","orcid":"https://orcid.org/0000-0002-8923-4553"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Son T. Tran","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5051044805","display_name":"Duc Thanh Chau","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Duc T. Chau","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.4848,"has_fulltext":false,"cited_by_count":14,"citation_normalized_percentile":{"value":0.83277209,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":93,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"841","last_page":"848"},"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/T11447","display_name":"Blind Source Separation Techniques","score":0.9993000030517578,"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":0.9977999925613403,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/autoencoder","display_name":"Autoencoder","score":0.730003833770752},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7222330570220947},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7079391479492188},{"id":"https://openalex.org/keywords/signal","display_name":"SIGNAL (programming language)","score":0.59747713804245},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.5604011416435242},{"id":"https://openalex.org/keywords/frequency-domain","display_name":"Frequency domain","score":0.5353909134864807},{"id":"https://openalex.org/keywords/filter","display_name":"Filter (signal processing)","score":0.49229443073272705},{"id":"https://openalex.org/keywords/passband","display_name":"Passband","score":0.48986050486564636},{"id":"https://openalex.org/keywords/speech-enhancement","display_name":"Speech enhancement","score":0.4818040728569031},{"id":"https://openalex.org/keywords/high-pass-filter","display_name":"High-pass filter","score":0.44256874918937683},{"id":"https://openalex.org/keywords/background-noise","display_name":"Background noise","score":0.4361548125743866},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.4131573438644409},{"id":"https://openalex.org/keywords/band-pass-filter","display_name":"Band-pass filter","score":0.3891715109348297},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3354465365409851},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.1879570484161377},{"id":"https://openalex.org/keywords/low-pass-filter","display_name":"Low-pass filter","score":0.1700340211391449},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.13083481788635254},{"id":"https://openalex.org/keywords/electronic-engineering","display_name":"Electronic engineering","score":0.11376580595970154},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.07775634527206421}],"concepts":[{"id":"https://openalex.org/C101738243","wikidata":"https://www.wikidata.org/wiki/Q786435","display_name":"Autoencoder","level":3,"score":0.730003833770752},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7222330570220947},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7079391479492188},{"id":"https://openalex.org/C2779843651","wikidata":"https://www.wikidata.org/wiki/Q7390335","display_name":"SIGNAL (programming language)","level":2,"score":0.59747713804245},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.5604011416435242},{"id":"https://openalex.org/C19118579","wikidata":"https://www.wikidata.org/wiki/Q786423","display_name":"Frequency domain","level":2,"score":0.5353909134864807},{"id":"https://openalex.org/C106131492","wikidata":"https://www.wikidata.org/wiki/Q3072260","display_name":"Filter (signal processing)","level":2,"score":0.49229443073272705},{"id":"https://openalex.org/C46416853","wikidata":"https://www.wikidata.org/wiki/Q254758","display_name":"Passband","level":3,"score":0.48986050486564636},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.4818040728569031},{"id":"https://openalex.org/C156137958","wikidata":"https://www.wikidata.org/wiki/Q262754","display_name":"High-pass filter","level":4,"score":0.44256874918937683},{"id":"https://openalex.org/C100675267","wikidata":"https://www.wikidata.org/wiki/Q1371624","display_name":"Background noise","level":2,"score":0.4361548125743866},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.4131573438644409},{"id":"https://openalex.org/C147788027","wikidata":"https://www.wikidata.org/wiki/Q2718101","display_name":"Band-pass filter","level":2,"score":0.3891715109348297},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3354465365409851},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.1879570484161377},{"id":"https://openalex.org/C44682112","wikidata":"https://www.wikidata.org/wiki/Q918242","display_name":"Low-pass filter","level":3,"score":0.1700340211391449},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.13083481788635254},{"id":"https://openalex.org/C24326235","wikidata":"https://www.wikidata.org/wiki/Q126095","display_name":"Electronic engineering","level":1,"score":0.11376580595970154},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.07775634527206421},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.12720/jcm.15.11.841-848","is_oa":true,"landing_page_url":"https://doi.org/10.12720/jcm.15.11.841-848","pdf_url":null,"source":{"id":"https://openalex.org/S184821498","display_name":"Journal of Communications","issn_l":"1796-2021","issn":["1796-2021","2374-4367"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4323867253","host_organization_name":"International Communication Association","host_organization_lineage":["https://openalex.org/P4323867253"],"host_organization_lineage_names":["International Communication Association"],"type":"journal"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Communications","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.12720/jcm.15.11.841-848","is_oa":true,"landing_page_url":"https://doi.org/10.12720/jcm.15.11.841-848","pdf_url":null,"source":{"id":"https://openalex.org/S184821498","display_name":"Journal of Communications","issn_l":"1796-2021","issn":["1796-2021","2374-4367"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4323867253","host_organization_name":"International Communication Association","host_organization_lineage":["https://openalex.org/P4323867253"],"host_organization_lineage_names":["International Communication Association"],"type":"journal"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Communications","raw_type":"journal-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions","score":0.44999998807907104}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":25,"referenced_works":["https://openalex.org/W1557133539","https://openalex.org/W1572270261","https://openalex.org/W1984358550","https://openalex.org/W1998152369","https://openalex.org/W2012879768","https://openalex.org/W2013419672","https://openalex.org/W2014430549","https://openalex.org/W2021196544","https://openalex.org/W2025118363","https://openalex.org/W2032669786","https://openalex.org/W2056939573","https://openalex.org/W2065156808","https://openalex.org/W2065346482","https://openalex.org/W2068311305","https://openalex.org/W2076198712","https://openalex.org/W2080466662","https://openalex.org/W2088079069","https://openalex.org/W2108325737","https://openalex.org/W2127851351","https://openalex.org/W2134806932","https://openalex.org/W2136411979","https://openalex.org/W2139930049","https://openalex.org/W2147267642","https://openalex.org/W2763577515","https://openalex.org/W2981062766"],"related_works":["https://openalex.org/W2103163823","https://openalex.org/W2945382667","https://openalex.org/W2120771489","https://openalex.org/W2051376034","https://openalex.org/W2955597484","https://openalex.org/W3110551121","https://openalex.org/W2089240210","https://openalex.org/W2135485548","https://openalex.org/W2131486661","https://openalex.org/W111365173"],"abstract_inverted_index":{"Speech":[0],"separation":[1],"plays":[2],"an":[3,56],"important":[4],"role":[5],"in":[6,72,116,120],"a":[7,45,51,59],"speech-related":[8],"system":[9],"because":[10],"it":[11],"can":[12,68,90,105,127],"denoise,":[13],"extract":[14,69,106],"and":[15,19,25,58,108,118],"enhance":[16],"speech":[17,38,64,71,111],"signal,":[18],"after":[20],"all":[21],"improve":[22],"the":[23,28,37,70,73,95,110,123,129,133,138],"accuracy":[24],"performance":[26],"of":[27,40,84,135],"system.":[29],"In":[30],"recent":[31],"years,":[32],"many":[33,82],"approaches":[34],"only":[35,77],"separate":[36,63],"out":[39],"commonly":[41],"high-frequency":[42,78],"noise":[43,79],"or":[44],"particular":[46,144],"background":[47,86,97],"sound.":[48],"We":[49],"propose":[50],"more":[52],"powerful":[53],"approach,":[54],"combining":[55],"autoencoder":[57],"bandpass":[60],"filter":[61],"to":[62,131,141],"signals.":[65],"This":[66],"combination":[67],"mixture":[74],"with":[75,113],"not":[76],"but":[80],"also":[81],"kinds":[83],"different":[85],"sounds.":[87,98],"Our":[88],"approach":[89],"be":[91],"flexibly":[92],"applied":[93],"for":[94,143],"new":[96],"Experimental":[99],"results":[100],"show":[101],"that":[102],"our":[103],"model":[104],"fastly":[107],"effectively":[109],"signal":[112,140],"9.01":[114],"dB":[115],"SIR":[117],"11.26":[119],"SDR.":[121],"On":[122],"other":[124],"hand,":[125],"we":[126],"adjust":[128],"passband":[130],"identify":[132],"range":[134],"frequency":[136],"at":[137],"output":[139],"apply":[142],"applications.":[145]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":5},{"year":2022,"cited_by_count":3},{"year":2021,"cited_by_count":2}],"updated_date":"2026-05-21T06:26:12.895304","created_date":"2020-12-07T00:00:00"}