{"id":"https://openalex.org/W4403140128","doi":"https://doi.org/10.3390/fi16100360","title":"Employing Huber and TAP Losses to Improve Inter-SubNet in Speech Enhancement","display_name":"Employing Huber and TAP Losses to Improve Inter-SubNet in Speech Enhancement","publication_year":2024,"publication_date":"2024-10-04","ids":{"openalex":"https://openalex.org/W4403140128","doi":"https://doi.org/10.3390/fi16100360"},"language":"en","primary_location":{"id":"doi:10.3390/fi16100360","is_oa":true,"landing_page_url":"https://doi.org/10.3390/fi16100360","pdf_url":"https://www.mdpi.com/1999-5903/16/10/360/pdf?version=1728025924","source":{"id":"https://openalex.org/S34838331","display_name":"Future Internet","issn_l":"1999-5903","issn":["1999-5903"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310310987","host_organization_name":"Multidisciplinary Digital Publishing Institute","host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Future Internet","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.mdpi.com/1999-5903/16/10/360/pdf?version=1728025924","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5019048236","display_name":"Jeih-weih Hung","orcid":"https://orcid.org/0000-0001-9366-3070"},"institutions":[{"id":"https://openalex.org/I193365169","display_name":"National Chi Nan University","ror":"https://ror.org/03ha6v181","country_code":"TW","type":"education","lineage":["https://openalex.org/I193365169"]}],"countries":["TW"],"is_corresponding":true,"raw_author_name":"Jeih-Weih Hung","raw_affiliation_strings":["Department of Electrical Engineering, National Chi Nan University, No. 301, University Rd., Puli Township, Nantou County 545, Taiwan"],"affiliations":[{"raw_affiliation_string":"Department of Electrical Engineering, National Chi Nan University, No. 301, University Rd., Puli Township, Nantou County 545, Taiwan","institution_ids":["https://openalex.org/I193365169"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5107959275","display_name":"Pin-Chen Huang","orcid":null},"institutions":[{"id":"https://openalex.org/I193365169","display_name":"National Chi Nan University","ror":"https://ror.org/03ha6v181","country_code":"TW","type":"education","lineage":["https://openalex.org/I193365169"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Pin-Chen Huang","raw_affiliation_strings":["Department of Electrical Engineering, National Chi Nan University, No. 301, University Rd., Puli Township, Nantou County 545, Taiwan"],"affiliations":[{"raw_affiliation_string":"Department of Electrical Engineering, National Chi Nan University, No. 301, University Rd., Puli Township, Nantou County 545, Taiwan","institution_ids":["https://openalex.org/I193365169"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5107762854","display_name":"Li-Yin Li","orcid":null},"institutions":[{"id":"https://openalex.org/I193365169","display_name":"National Chi Nan University","ror":"https://ror.org/03ha6v181","country_code":"TW","type":"education","lineage":["https://openalex.org/I193365169"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Li-Yin Li","raw_affiliation_strings":["Department of Electrical Engineering, National Chi Nan University, No. 301, University Rd., Puli Township, Nantou County 545, Taiwan"],"affiliations":[{"raw_affiliation_string":"Department of Electrical Engineering, National Chi Nan University, No. 301, University Rd., Puli Township, Nantou County 545, Taiwan","institution_ids":["https://openalex.org/I193365169"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5019048236"],"corresponding_institution_ids":["https://openalex.org/I193365169"],"apc_list":{"value":1400,"currency":"CHF","value_usd":1515},"apc_paid":{"value":1400,"currency":"CHF","value_usd":1515},"fwci":0.6903,"has_fulltext":true,"cited_by_count":2,"citation_normalized_percentile":{"value":0.69039165,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":99},"biblio":{"volume":"16","issue":"10","first_page":"360","last_page":"360"},"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":0.9991999864578247,"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":0.9987000226974487,"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":0.8927733302116394},{"id":"https://openalex.org/keywords/subnet","display_name":"Subnet","score":0.8777646422386169},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4585759937763214},{"id":"https://openalex.org/keywords/computer-network","display_name":"Computer network","score":0.3110523223876953}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8927733302116394},{"id":"https://openalex.org/C21099817","wikidata":"https://www.wikidata.org/wiki/Q7631721","display_name":"Subnet","level":2,"score":0.8777646422386169},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4585759937763214},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.3110523223876953}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.3390/fi16100360","is_oa":true,"landing_page_url":"https://doi.org/10.3390/fi16100360","pdf_url":"https://www.mdpi.com/1999-5903/16/10/360/pdf?version=1728025924","source":{"id":"https://openalex.org/S34838331","display_name":"Future Internet","issn_l":"1999-5903","issn":["1999-5903"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310310987","host_organization_name":"Multidisciplinary Digital Publishing Institute","host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Future Internet","raw_type":"journal-article"},{"id":"pmh:oai:RePEc:gam:jftint:v:16:y:2024:i:10:p:360-:d:1492093","is_oa":false,"landing_page_url":"https://www.mdpi.com/1999-5903/16/10/360/","pdf_url":null,"source":{"id":"https://openalex.org/S4306401271","display_name":"RePEc: Research Papers in Economics","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I77793887","host_organization_name":"Federal Reserve Bank of St. Louis","host_organization_lineage":["https://openalex.org/I77793887"],"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":"article"},{"id":"pmh:oai:doaj.org/article:db6e443806d14add8b0e393cb73adc56","is_oa":true,"landing_page_url":"https://doaj.org/article/db6e443806d14add8b0e393cb73adc56","pdf_url":null,"source":{"id":"https://openalex.org/S112646816","display_name":"SHILAP Revista de lepidopterolog\u00eda","issn_l":"0300-5267","issn":["0300-5267","2340-4078"],"is_oa":true,"is_in_doaj":true,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Future Internet, Vol 16, Iss 10, p 360 (2024)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.3390/fi16100360","is_oa":true,"landing_page_url":"https://doi.org/10.3390/fi16100360","pdf_url":"https://www.mdpi.com/1999-5903/16/10/360/pdf?version=1728025924","source":{"id":"https://openalex.org/S34838331","display_name":"Future Internet","issn_l":"1999-5903","issn":["1999-5903"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310310987","host_organization_name":"Multidisciplinary Digital Publishing Institute","host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Future Internet","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4403140128.pdf","grobid_xml":"https://content.openalex.org/works/W4403140128.grobid-xml"},"referenced_works_count":48,"referenced_works":["https://openalex.org/W1494198834","https://openalex.org/W2046033161","https://openalex.org/W2126926806","https://openalex.org/W2141998673","https://openalex.org/W2144404214","https://openalex.org/W2146324387","https://openalex.org/W2291877678","https://openalex.org/W2405774341","https://openalex.org/W2516342150","https://openalex.org/W2603567530","https://openalex.org/W2889442120","https://openalex.org/W2889669262","https://openalex.org/W2952218014","https://openalex.org/W2962843322","https://openalex.org/W2962935966","https://openalex.org/W2963341071","https://openalex.org/W2964058413","https://openalex.org/W2998161426","https://openalex.org/W3089552252","https://openalex.org/W3096408984","https://openalex.org/W3097034112","https://openalex.org/W3099330747","https://openalex.org/W3160085755","https://openalex.org/W3162493033","https://openalex.org/W3162501355","https://openalex.org/W3163090501","https://openalex.org/W3190196596","https://openalex.org/W3197284240","https://openalex.org/W3197729725","https://openalex.org/W3198680319","https://openalex.org/W4221143458","https://openalex.org/W4221149546","https://openalex.org/W4225309689","https://openalex.org/W4232282348","https://openalex.org/W4244026860","https://openalex.org/W4308455602","https://openalex.org/W4309627611","https://openalex.org/W4311328492","https://openalex.org/W4372259751","https://openalex.org/W4372347394","https://openalex.org/W4382788965","https://openalex.org/W4383097821","https://openalex.org/W4385807442","https://openalex.org/W4385973379","https://openalex.org/W4387938956","https://openalex.org/W4388734419","https://openalex.org/W4392909811","https://openalex.org/W6770282137"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2748952813","https://openalex.org/W2102539527","https://openalex.org/W2131631951","https://openalex.org/W2356206668","https://openalex.org/W2130707537","https://openalex.org/W3200778902","https://openalex.org/W1977409556","https://openalex.org/W2361602549","https://openalex.org/W2389187633"],"abstract_inverted_index":{"In":[0,70,140],"this":[1],"study,":[2],"improvements":[3,185,218],"are":[4],"made":[5],"to":[6,83,154],"Inter-SubNet,":[7,41],"a":[8,15,75,133,146],"state-of-the-art":[9],"speech":[10,17,137,187],"enhancement":[11,18,188],"method.":[12],"Inter-SubNet":[13,48,91,178],"is":[14,49],"single-channel":[16],"framework":[19],"that":[20,177],"enhances":[21],"the":[22,38,50,59,106,117,156,161,166,170,180],"sub-band":[23],"spectral":[24,29,56],"model":[25,80],"by":[26,47,58,92],"integrating":[27,94,211],"global":[28],"information,":[30],"such":[31],"as":[32,62,66],"cross-band":[33],"relationships":[34],"and":[35,150,173,202,206,221,225],"patterns.":[36],"Despite":[37],"success":[39],"of":[40,54,112,136,148,163,200,219],"one":[42],"crucial":[43],"aspect":[44],"probably":[45],"overlooked":[46],"unequal":[51],"perceptual":[52,95,113],"weighting":[53],"different":[55],"regions":[57],"human":[60],"ear,":[61],"it":[63],"employs":[64],"MSE":[65,72,98,102,192,215],"its":[67],"loss":[68,73,96,99,103,182,193,196,213,216],"function.":[69],"addition,":[71,141],"has":[74],"potential":[76,157],"convergence":[77,158],"concern":[78],"for":[79,127,160],"learning":[81,107],"due":[82],"gradient":[84],"explosion.":[85],"Hence,":[86],"we":[87,115,142,175],"propose":[88],"further":[89],"enhancing":[90],"either":[93],"with":[97,179,194,214],"or":[100],"modifying":[101],"directly":[104],"in":[105,186,198,204,223],"process.":[108],"Among":[109],"various":[110],"types":[111],"loss,":[114,122,145,153],"adopt":[116],"temporal":[118],"acoustic":[119,129],"parameter":[120],"(TAP)":[121],"which":[123],"provides":[124],"detailed":[125],"estimation":[126],"low-level":[128],"descriptors,":[130],"thereby":[131],"offering":[132],"comprehensive":[134],"evaluation":[135,167],"signal":[138],"distortion.":[139],"leverage":[143],"Huber":[144,195],"combination":[147],"L1":[149],"L2":[151],"(MSE)":[152],"avoid":[155],"issue":[159],"training":[162],"Inter-SubNet.":[164],"By":[165],"conducted":[168],"on":[169],"VoiceBank-DEMAND":[171],"database":[172],"task,":[174],"see":[176],"modified":[181],"function":[183],"reveals":[184],"performance.":[189],"Specifically,":[190],"replacing":[191],"results":[197],"increases":[199],"0.057":[201],"0.38":[203],"WB-PESQ":[205,224],"SI-SDR":[207],"metrics,":[208],"respectively.":[209],"Additionally,":[210],"TAP":[212],"yields":[217],"0.115":[220],"0.196":[222],"CSIG":[226],"metrics.":[227]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1}],"updated_date":"2026-04-05T17:49:38.594831","created_date":"2025-10-10T00:00:00"}