{"id":"https://openalex.org/W2786944864","doi":"https://doi.org/10.1109/apsipa.2017.8282018","title":"Codebook-driven speech enhancement using DNN and harmonic emphasis","display_name":"Codebook-driven speech enhancement using DNN and harmonic emphasis","publication_year":2017,"publication_date":"2017-12-01","ids":{"openalex":"https://openalex.org/W2786944864","doi":"https://doi.org/10.1109/apsipa.2017.8282018","mag":"2786944864"},"language":"en","primary_location":{"id":"doi:10.1109/apsipa.2017.8282018","is_oa":false,"landing_page_url":"https://doi.org/10.1109/apsipa.2017.8282018","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2017 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5056644602","display_name":"Yan Yang","orcid":"https://orcid.org/0000-0001-9922-2508"},"institutions":[{"id":"https://openalex.org/I37796252","display_name":"Beijing University of Technology","ror":"https://ror.org/037b1pp87","country_code":"CN","type":"education","lineage":["https://openalex.org/I37796252"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Yan Yang","raw_affiliation_strings":["Faculty of Information Technology, Beijing University of Technology, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Faculty of Information Technology, Beijing University of Technology, Beijing, China","institution_ids":["https://openalex.org/I37796252"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5070475244","display_name":"Changchun Bao","orcid":"https://orcid.org/0000-0002-5606-5343"},"institutions":[{"id":"https://openalex.org/I37796252","display_name":"Beijing University of Technology","ror":"https://ror.org/037b1pp87","country_code":"CN","type":"education","lineage":["https://openalex.org/I37796252"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Changchun Bao","raw_affiliation_strings":["Faculty of Information Technology, Beijing University of Technology, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Faculty of Information Technology, Beijing University of Technology, Beijing, China","institution_ids":["https://openalex.org/I37796252"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5114928911","display_name":"Xianyun Wang","orcid":"https://orcid.org/0009-0008-1230-5772"},"institutions":[{"id":"https://openalex.org/I37796252","display_name":"Beijing University of Technology","ror":"https://ror.org/037b1pp87","country_code":"CN","type":"education","lineage":["https://openalex.org/I37796252"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xianyun Wang","raw_affiliation_strings":["Faculty of Information Technology, Beijing University of Technology, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Faculty of Information Technology, Beijing University of Technology, Beijing, China","institution_ids":["https://openalex.org/I37796252"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5056644602"],"corresponding_institution_ids":["https://openalex.org/I37796252"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.2118954,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"34","issue":null,"first_page":"149","last_page":"154"},"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":0.9991999864578247,"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/T10283","display_name":"Hearing Loss and Rehabilitation","score":0.9968000054359436,"subfield":{"id":"https://openalex.org/subfields/2805","display_name":"Cognitive Neuroscience"},"field":{"id":"https://openalex.org/fields/28","display_name":"Neuroscience"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/codebook","display_name":"Codebook","score":0.9932829141616821},{"id":"https://openalex.org/keywords/linde\u2013buzo\u2013gray-algorithm","display_name":"Linde\u2013Buzo\u2013Gray algorithm","score":0.7078689336776733},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.692692756652832},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6457898616790771},{"id":"https://openalex.org/keywords/speech-enhancement","display_name":"Speech enhancement","score":0.6159152388572693},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.5813854932785034},{"id":"https://openalex.org/keywords/wiener-filter","display_name":"Wiener filter","score":0.5422637462615967},{"id":"https://openalex.org/keywords/selection","display_name":"Selection (genetic algorithm)","score":0.487899512052536},{"id":"https://openalex.org/keywords/filter","display_name":"Filter (signal processing)","score":0.4674108326435089},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.43295639753341675},{"id":"https://openalex.org/keywords/speech-coding","display_name":"Speech coding","score":0.42500314116477966},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.36404597759246826},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.2155875563621521},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.06987473368644714},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.05907094478607178}],"concepts":[{"id":"https://openalex.org/C127759330","wikidata":"https://www.wikidata.org/wiki/Q637416","display_name":"Codebook","level":2,"score":0.9932829141616821},{"id":"https://openalex.org/C93372532","wikidata":"https://www.wikidata.org/wiki/Q6552455","display_name":"Linde\u2013Buzo\u2013Gray algorithm","level":3,"score":0.7078689336776733},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.692692756652832},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6457898616790771},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.6159152388572693},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.5813854932785034},{"id":"https://openalex.org/C18537770","wikidata":"https://www.wikidata.org/wiki/Q25523","display_name":"Wiener filter","level":2,"score":0.5422637462615967},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.487899512052536},{"id":"https://openalex.org/C106131492","wikidata":"https://www.wikidata.org/wiki/Q3072260","display_name":"Filter (signal processing)","level":2,"score":0.4674108326435089},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.43295639753341675},{"id":"https://openalex.org/C13895895","wikidata":"https://www.wikidata.org/wiki/Q3270773","display_name":"Speech coding","level":2,"score":0.42500314116477966},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.36404597759246826},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.2155875563621521},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.06987473368644714},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.05907094478607178}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/apsipa.2017.8282018","is_oa":false,"landing_page_url":"https://doi.org/10.1109/apsipa.2017.8282018","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2017 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16","score":0.5400000214576721}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":31,"referenced_works":["https://openalex.org/W44815768","https://openalex.org/W1546892833","https://openalex.org/W1904365287","https://openalex.org/W1970924839","https://openalex.org/W1985090574","https://openalex.org/W2015354467","https://openalex.org/W2025515167","https://openalex.org/W2048510784","https://openalex.org/W2067295501","https://openalex.org/W2069681747","https://openalex.org/W2070395501","https://openalex.org/W2086139506","https://openalex.org/W2096779346","https://openalex.org/W2121294245","https://openalex.org/W2128653836","https://openalex.org/W2132083787","https://openalex.org/W2148154194","https://openalex.org/W2149425615","https://openalex.org/W2155889651","https://openalex.org/W2159514726","https://openalex.org/W2160311847","https://openalex.org/W2176732407","https://openalex.org/W2290323437","https://openalex.org/W2291877678","https://openalex.org/W2403111940","https://openalex.org/W2406854920","https://openalex.org/W2514956789","https://openalex.org/W3147539069","https://openalex.org/W6601785968","https://openalex.org/W6640036494","https://openalex.org/W6646555135"],"related_works":["https://openalex.org/W2096936443","https://openalex.org/W2081863301","https://openalex.org/W2352648934","https://openalex.org/W2365109233","https://openalex.org/W145510127","https://openalex.org/W2374856816","https://openalex.org/W1977098967","https://openalex.org/W2377001183","https://openalex.org/W2367622526","https://openalex.org/W2365863649"],"abstract_inverted_index":{"This":[0],"paper":[1],"presents":[2],"a":[3],"novel":[4],"approach":[5,97],"for":[6],"estimating":[7],"auto-regressive":[8],"parameters":[9],"of":[10,26,54,61,92,102],"speech":[11,19,27,50,62,93],"and":[12,28,63,94],"noise":[13,29,64,133],"in":[14],"the":[15,52,57,81,99,112,121,126,141,149],"codebook-driven":[16,82,109,114,150],"Wiener":[17,83,151],"filtering":[18],"enhancement.":[20],"The":[21,153],"deep":[22],"neural":[23],"networks":[24],"(DNN)":[25],"are":[30,45,65],"trained":[31],"separately":[32],"to":[33,119,138,147],"select":[34],"their":[35,76],"matched":[36],"codebook":[37,59,70,90,104],"entries":[38,60,91,105],"offline.":[39],"At":[40,79],"online":[41],"stage,":[42],"acoustic":[43],"features":[44],"firstly":[46],"extracted":[47],"from":[48,75],"noisy":[49],"as":[51],"input":[53],"DNNs.":[55,78],"Then,":[56],"optimal":[58,89,103],"selected":[66],"based":[67],"on":[68],"all":[69],"entries'":[71],"selection":[72,100],"probabilities":[73],"derived":[74],"respective":[77],"last,":[80],"filter":[84],"is":[85,116,145],"constructed":[86],"by":[87],"these":[88],"noise.":[95],"Such":[96],"increases":[98],"accuracy":[101],"comparing":[106],"with":[107,165],"conventional":[108,113],"methods.":[110],"Since":[111],"method":[115,160],"only":[117],"used":[118],"model":[120],"spectral":[122,127],"shape":[123],"but":[124],"not":[125],"details,":[128],"which":[129],"brings":[130],"much":[131],"residual":[132],"between":[134],"harmonics.":[135],"In":[136],"order":[137],"solve":[139],"that,":[140],"harmonic":[142],"emphasis":[143],"technique":[144],"adopted":[146],"update":[148],"filter.":[152],"test":[154],"results":[155],"confirm":[156],"that":[157],"our":[158],"proposed":[159],"achieves":[161],"better":[162],"performance":[163],"compared":[164],"some":[166],"existing":[167],"approaches.":[168]},"counts_by_year":[],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}