{"id":"https://openalex.org/W3012016043","doi":"https://doi.org/10.1109/apsipaasc47483.2019.9023309","title":"Investigation of Neural Network Approaches for Unified Spectral and Prosodic Feature Enhancement","display_name":"Investigation of Neural Network Approaches for Unified Spectral and Prosodic Feature Enhancement","publication_year":2019,"publication_date":"2019-11-01","ids":{"openalex":"https://openalex.org/W3012016043","doi":"https://doi.org/10.1109/apsipaasc47483.2019.9023309","mag":"3012016043"},"language":"en","primary_location":{"id":"doi:10.1109/apsipaasc47483.2019.9023309","is_oa":false,"landing_page_url":"https://doi.org/10.1109/apsipaasc47483.2019.9023309","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5070819601","display_name":"Wei-Cheng Lin","orcid":"https://orcid.org/0000-0003-1933-1590"},"institutions":[{"id":"https://openalex.org/I4210086894","display_name":"Research Center for Information Technology Innovation, Academia Sinica","ror":"https://ror.org/000zgvm20","country_code":"TW","type":"facility","lineage":["https://openalex.org/I4210086894","https://openalex.org/I84653119"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Wei-Cheng Lin","raw_affiliation_strings":["Research Center for Information Technology Innovation, Academic Sinica, Taiwan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Research Center for Information Technology Innovation, Academic Sinica, Taiwan","institution_ids":["https://openalex.org/I4210086894"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5044008055","display_name":"Yu Tsao","orcid":"https://orcid.org/0000-0001-6956-0418"},"institutions":[{"id":"https://openalex.org/I4210086894","display_name":"Research Center for Information Technology Innovation, Academia Sinica","ror":"https://ror.org/000zgvm20","country_code":"TW","type":"facility","lineage":["https://openalex.org/I4210086894","https://openalex.org/I84653119"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Yu Tsao","raw_affiliation_strings":["Research Center for Information Technology Innovation, Academic Sinica, Taiwan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Research Center for Information Technology Innovation, Academic Sinica, Taiwan","institution_ids":["https://openalex.org/I4210086894"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100405410","display_name":"Fei Chen","orcid":"https://orcid.org/0000-0002-6988-492X"},"institutions":[{"id":"https://openalex.org/I3045169105","display_name":"Southern University of Science and Technology","ror":"https://ror.org/049tv2d57","country_code":"CN","type":"education","lineage":["https://openalex.org/I3045169105"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Fei Chen","raw_affiliation_strings":["Department of Electrical and Electronic Engineering, Southern University of Science and Technology, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electrical and Electronic Engineering, Southern University of Science and Technology, China","institution_ids":["https://openalex.org/I3045169105"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5071214181","display_name":"Hsin\u2010Min Wang","orcid":"https://orcid.org/0000-0003-3599-5071"},"institutions":[{"id":"https://openalex.org/I4210098366","display_name":"Institute of Information Science, Academia Sinica","ror":"https://ror.org/00z83z196","country_code":"TW","type":"facility","lineage":["https://openalex.org/I4210098366","https://openalex.org/I84653119"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Hsin-Min Wang","raw_affiliation_strings":["Institute of Information Science, Academic Sinica, Taiwan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Information Science, Academic Sinica, Taiwan","institution_ids":["https://openalex.org/I4210098366"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.3823,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.57064594,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":"pp","issue":null,"first_page":"1179","last_page":"1184"},"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/T10283","display_name":"Hearing Loss and Rehabilitation","score":0.9984999895095825,"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"}},{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9975000023841858,"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":0.7774227857589722},{"id":"https://openalex.org/keywords/speech-enhancement","display_name":"Speech enhancement","score":0.6309041380882263},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.5975780487060547},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5750781893730164},{"id":"https://openalex.org/keywords/mandarin-chinese","display_name":"Mandarin Chinese","score":0.5699982643127441},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.5497732758522034},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.5033144354820251},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4851273000240326},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4796217381954193},{"id":"https://openalex.org/keywords/intelligibility","display_name":"Intelligibility (philosophy)","score":0.43167075514793396},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.23167258501052856}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7774227857589722},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.6309041380882263},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.5975780487060547},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5750781893730164},{"id":"https://openalex.org/C138954614","wikidata":"https://www.wikidata.org/wiki/Q9192","display_name":"Mandarin Chinese","level":2,"score":0.5699982643127441},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.5497732758522034},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5033144354820251},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4851273000240326},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4796217381954193},{"id":"https://openalex.org/C60048801","wikidata":"https://www.wikidata.org/wiki/Q1433889","display_name":"Intelligibility (philosophy)","level":2,"score":0.43167075514793396},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.23167258501052856},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/apsipaasc47483.2019.9023309","is_oa":false,"landing_page_url":"https://doi.org/10.1109/apsipaasc47483.2019.9023309","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 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","score":0.4399999976158142,"id":"https://metadata.un.org/sdg/16"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":44,"referenced_works":["https://openalex.org/W1875231349","https://openalex.org/W1897240248","https://openalex.org/W1952003395","https://openalex.org/W1992475611","https://openalex.org/W2034300186","https://openalex.org/W2044893557","https://openalex.org/W2141998673","https://openalex.org/W2159591770","https://openalex.org/W2239141610","https://openalex.org/W2296101733","https://openalex.org/W2296167893","https://openalex.org/W2298367083","https://openalex.org/W2397226255","https://openalex.org/W2405774341","https://openalex.org/W2491101527","https://openalex.org/W2492342376","https://openalex.org/W2516342150","https://openalex.org/W2527611302","https://openalex.org/W2538120366","https://openalex.org/W2586068394","https://openalex.org/W2594607416","https://openalex.org/W2605589342","https://openalex.org/W2608338293","https://openalex.org/W2649558613","https://openalex.org/W2746457594","https://openalex.org/W2755891984","https://openalex.org/W2789324345","https://openalex.org/W2809824582","https://openalex.org/W2887435286","https://openalex.org/W2899406861","https://openalex.org/W2910717919","https://openalex.org/W2962866211","https://openalex.org/W2962896155","https://openalex.org/W2963045393","https://openalex.org/W2964069186","https://openalex.org/W6639350448","https://openalex.org/W6639532686","https://openalex.org/W6712317276","https://openalex.org/W6713658392","https://openalex.org/W6737196085","https://openalex.org/W6742802039","https://openalex.org/W6744261651","https://openalex.org/W6748511257","https://openalex.org/W6749868174"],"related_works":["https://openalex.org/W2990005675","https://openalex.org/W2374317326","https://openalex.org/W1603321096","https://openalex.org/W2394766824","https://openalex.org/W1986772939","https://openalex.org/W2037635165","https://openalex.org/W2738829087","https://openalex.org/W2542062716","https://openalex.org/W1505346162","https://openalex.org/W4200562864"],"abstract_inverted_index":{"Most":[0],"speech":[1,172],"enhancement":[2,38,131,221],"(SE)":[3],"systems":[4,157],"focus":[5],"on":[6,18,142],"the":[7,23,28,64,69,72,79,92,97,106,111,115,140,143,167,171,181,188,193,215,218],"spectral":[8,24,65,116],"feature":[9,37,89,98,130,220],"or":[10],"raw-waveform":[11],"enhancement.":[12],"However,":[13],"many":[14],"speech-related":[15],"applications":[16],"rely":[17],"other":[19],"features":[20,43],"rather":[21],"than":[22],"features,":[25],"such":[26,204],"as":[27,205],"intensity":[29,73,160],"and":[30,67,74,119,135,161,174,209,222],"fundamental":[31],"frequency":[32],"(f0).":[33],"Therefore,":[34],"a":[35,59,148],"unified":[36,129,219],"for":[39,226],"different":[40],"types":[41],"of":[42,71,100,114,139,170,187,217],"is":[44,84],"worth":[45],"investigating.":[46],"In":[47],"this":[48],"work,":[49],"we":[50,103],"train":[51,105],"our":[52],"neural":[53],"network":[54],"(NN)-based":[55],"SE":[56,93,107,183],"system":[57,108],"in":[58,147],"manner":[60],"that":[61,95,154,192],"simultaneously":[62],"minimizes":[63],"loss":[66,113],"preserves":[68],"correctness":[70],"f0":[75,162,199],"contours":[76,200],"extracted":[77],"from":[78,197],"enhanced":[80],"speech.":[81],"The":[82,137],"idea":[83],"to":[85,91],"introduce":[86],"an":[87],"NN-based":[88],"extractor":[90],"framework":[94],"imitates":[96],"extraction":[99,163],"Praat.":[101],"Then,":[102],"can":[104],"by":[109],"minimizing":[110],"combined":[112],"feature,":[117],"intensity,":[118],"f0.":[120],"We":[121],"investigate":[122],"three":[123,156],"bidirectional":[124],"long":[125],"short-term":[126],"memory":[127],"(BLSTM)-based":[128],"systems:":[132],"fixed-concat,":[133],"joint-concat,":[134],"multi-task.":[136],"results":[138,190],"experiments":[141],"Taiwan":[144],"Mandarin":[145],"hearing":[146],"noise":[149],"test":[150],"dataset":[151],"(TMHINT)":[152],"demonstrate":[153],"all":[155],"show":[158],"improved":[159],"accuracy":[164],"without":[165],"sacrificing":[166],"perceptual":[168],"evaluation":[169],"quality":[173],"short-time":[175],"objective":[176],"intelligibility":[177],"scores":[178],"compared":[179],"with":[180],"baseline":[182],"system.":[184],"Further":[185],"analysis":[186],"experimental":[189],"shows":[191],"improvement":[194],"mostly":[195],"comes":[196],"better":[198],"under":[201],"difficult":[202],"conditions":[203],"low":[206],"signal-to-noise":[207],"ratio":[208],"nonstationary":[210],"noises.":[211],"Our":[212],"work":[213],"demonstrates":[214],"advantage":[216],"provides":[223],"new":[224],"insights":[225],"SE.":[227]},"counts_by_year":[{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":1}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}