{"id":"https://openalex.org/W4388820712","doi":"https://doi.org/10.1109/apsipaasc58517.2023.10317166","title":"Correlated Multi-Level Speech Enhancement for Robust Real-World ASR Applications Using Mask-Waveform-Feature Optimization","display_name":"Correlated Multi-Level Speech Enhancement for Robust Real-World ASR Applications Using Mask-Waveform-Feature Optimization","publication_year":2023,"publication_date":"2023-10-31","ids":{"openalex":"https://openalex.org/W4388820712","doi":"https://doi.org/10.1109/apsipaasc58517.2023.10317166"},"language":"en","primary_location":{"id":"doi:10.1109/apsipaasc58517.2023.10317166","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/apsipaasc58517.2023.10317166","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 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/A5100442521","display_name":"Hang Chen","orcid":"https://orcid.org/0000-0002-4355-6629"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Hang Chen","raw_affiliation_strings":["University of Science and Technology of China,China","University of Science and Technology of China, China"],"affiliations":[{"raw_affiliation_string":"University of Science and Technology of China,China","institution_ids":["https://openalex.org/I126520041"]},{"raw_affiliation_string":"University of Science and Technology of China, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5066595711","display_name":"Jun Du","orcid":"https://orcid.org/0000-0002-2387-0389"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jun Du","raw_affiliation_strings":["University of Science and Technology of China,China","University of Science and Technology of China, China"],"affiliations":[{"raw_affiliation_string":"University of Science and Technology of China,China","institution_ids":["https://openalex.org/I126520041"]},{"raw_affiliation_string":"University of Science and Technology of China, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100407584","display_name":"Zhe Wang","orcid":"https://orcid.org/0000-0001-9173-0022"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhe Wang","raw_affiliation_strings":["University of Science and Technology of China,China","University of Science and Technology of China, China"],"affiliations":[{"raw_affiliation_string":"University of Science and Technology of China,China","institution_ids":["https://openalex.org/I126520041"]},{"raw_affiliation_string":"University of Science and Technology of China, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5106483978","display_name":"Chenxi Wang","orcid":"https://orcid.org/0009-0006-3334-2092"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chenxi Wang","raw_affiliation_strings":["University of Science and Technology of China,China","University of Science and Technology of China, China"],"affiliations":[{"raw_affiliation_string":"University of Science and Technology of China,China","institution_ids":["https://openalex.org/I126520041"]},{"raw_affiliation_string":"University of Science and Technology of China, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101093993","display_name":"Yuling Ren","orcid":null},"institutions":[{"id":"https://openalex.org/I180662265","display_name":"China Mobile (China)","ror":"https://ror.org/05gftfe97","country_code":"CN","type":"company","lineage":["https://openalex.org/I180662265"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuling Ren","raw_affiliation_strings":["China Mobile Online Services Company Limited,China","China Mobile Online Services Company Limited, China"],"affiliations":[{"raw_affiliation_string":"China Mobile Online Services Company Limited,China","institution_ids":["https://openalex.org/I180662265"]},{"raw_affiliation_string":"China Mobile Online Services Company Limited, China","institution_ids":["https://openalex.org/I180662265"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5056608424","display_name":"Qinglong Li","orcid":"https://orcid.org/0000-0002-6720-7765"},"institutions":[{"id":"https://openalex.org/I180662265","display_name":"China Mobile (China)","ror":"https://ror.org/05gftfe97","country_code":"CN","type":"company","lineage":["https://openalex.org/I180662265"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qinglong Li","raw_affiliation_strings":["China Mobile Online Services Company Limited,China","China Mobile Online Services Company Limited, China"],"affiliations":[{"raw_affiliation_string":"China Mobile Online Services Company Limited,China","institution_ids":["https://openalex.org/I180662265"]},{"raw_affiliation_string":"China Mobile Online Services Company Limited, China","institution_ids":["https://openalex.org/I180662265"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5023339675","display_name":"Ruibo Liu","orcid":"https://orcid.org/0000-0002-5163-966X"},"institutions":[{"id":"https://openalex.org/I180662265","display_name":"China Mobile (China)","ror":"https://ror.org/05gftfe97","country_code":"CN","type":"company","lineage":["https://openalex.org/I180662265"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ruibo Liu","raw_affiliation_strings":["China Mobile Online Services Company Limited,China","China Mobile Online Services Company Limited, China"],"affiliations":[{"raw_affiliation_string":"China Mobile Online Services Company Limited,China","institution_ids":["https://openalex.org/I180662265"]},{"raw_affiliation_string":"China Mobile Online Services Company Limited, China","institution_ids":["https://openalex.org/I180662265"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5066868860","display_name":"Chin\u2010Hui Lee","orcid":"https://orcid.org/0000-0002-1892-2551"},"institutions":[{"id":"https://openalex.org/I130701444","display_name":"Georgia Institute of Technology","ror":"https://ror.org/01zkghx44","country_code":"US","type":"education","lineage":["https://openalex.org/I130701444"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Chin-Hui Lee","raw_affiliation_strings":["Georgia Institute of Technology,USA","Georgia Institute of Technology, USA"],"affiliations":[{"raw_affiliation_string":"Georgia Institute of Technology,USA","institution_ids":["https://openalex.org/I130701444"]},{"raw_affiliation_string":"Georgia Institute of Technology, USA","institution_ids":["https://openalex.org/I130701444"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":8,"corresponding_author_ids":["https://openalex.org/A5100442521"],"corresponding_institution_ids":["https://openalex.org/I126520041"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.16267134,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"96","last_page":"101"},"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":0.9998000264167786,"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":0.9986000061035156,"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/speech-recognition","display_name":"Speech recognition","score":0.7139810919761658},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7092176079750061},{"id":"https://openalex.org/keywords/intelligibility","display_name":"Intelligibility (philosophy)","score":0.5841740965843201},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.5286282300949097},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.5214123725891113},{"id":"https://openalex.org/keywords/speech-enhancement","display_name":"Speech enhancement","score":0.5127604603767395},{"id":"https://openalex.org/keywords/mean-squared-error","display_name":"Mean squared error","score":0.5126937627792358},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.507564902305603},{"id":"https://openalex.org/keywords/waveform","display_name":"Waveform","score":0.4917748272418976},{"id":"https://openalex.org/keywords/entropy","display_name":"Entropy (arrow of time)","score":0.4486074447631836},{"id":"https://openalex.org/keywords/correlation","display_name":"Correlation","score":0.4451625347137451},{"id":"https://openalex.org/keywords/pearson-product-moment-correlation-coefficient","display_name":"Pearson product-moment correlation coefficient","score":0.42546534538269043},{"id":"https://openalex.org/keywords/noise-measurement","display_name":"Noise measurement","score":0.42009884119033813},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.27016007900238037},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.18551033735275269},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.10412085056304932}],"concepts":[{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7139810919761658},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7092176079750061},{"id":"https://openalex.org/C60048801","wikidata":"https://www.wikidata.org/wiki/Q1433889","display_name":"Intelligibility (philosophy)","level":2,"score":0.5841740965843201},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.5286282300949097},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.5214123725891113},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.5127604603767395},{"id":"https://openalex.org/C139945424","wikidata":"https://www.wikidata.org/wiki/Q1940696","display_name":"Mean squared error","level":2,"score":0.5126937627792358},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.507564902305603},{"id":"https://openalex.org/C197424946","wikidata":"https://www.wikidata.org/wiki/Q1165717","display_name":"Waveform","level":3,"score":0.4917748272418976},{"id":"https://openalex.org/C106301342","wikidata":"https://www.wikidata.org/wiki/Q4117933","display_name":"Entropy (arrow of time)","level":2,"score":0.4486074447631836},{"id":"https://openalex.org/C117220453","wikidata":"https://www.wikidata.org/wiki/Q5172842","display_name":"Correlation","level":2,"score":0.4451625347137451},{"id":"https://openalex.org/C55078378","wikidata":"https://www.wikidata.org/wiki/Q1136628","display_name":"Pearson product-moment correlation coefficient","level":2,"score":0.42546534538269043},{"id":"https://openalex.org/C29265498","wikidata":"https://www.wikidata.org/wiki/Q7047719","display_name":"Noise measurement","level":3,"score":0.42009884119033813},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.27016007900238037},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.18551033735275269},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.10412085056304932},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C554190296","wikidata":"https://www.wikidata.org/wiki/Q47528","display_name":"Radar","level":2,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/apsipaasc58517.2023.10317166","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/apsipaasc58517.2023.10317166","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 Asia Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":40,"referenced_works":["https://openalex.org/W1552314771","https://openalex.org/W1995536493","https://openalex.org/W2044893557","https://openalex.org/W2062164080","https://openalex.org/W2069681747","https://openalex.org/W2115086266","https://openalex.org/W2126942983","https://openalex.org/W2128653836","https://openalex.org/W2141998673","https://openalex.org/W2146324387","https://openalex.org/W2160815625","https://openalex.org/W2168379380","https://openalex.org/W2194775991","https://openalex.org/W2296167893","https://openalex.org/W2397728357","https://openalex.org/W2398042854","https://openalex.org/W2400339399","https://openalex.org/W2517616541","https://openalex.org/W2584390378","https://openalex.org/W2711861986","https://openalex.org/W2749337587","https://openalex.org/W2890820256","https://openalex.org/W2899829828","https://openalex.org/W2937998856","https://openalex.org/W2962892438","https://openalex.org/W2972320711","https://openalex.org/W2972686263","https://openalex.org/W3103003256","https://openalex.org/W3147539069","https://openalex.org/W3168662520","https://openalex.org/W3205012673","https://openalex.org/W3209490467","https://openalex.org/W4237532635","https://openalex.org/W4245919820","https://openalex.org/W4296068829","https://openalex.org/W4297841387","https://openalex.org/W4385245566","https://openalex.org/W6631190155","https://openalex.org/W6739901393","https://openalex.org/W6762114000"],"related_works":["https://openalex.org/W1986772939","https://openalex.org/W2037635165","https://openalex.org/W2738829087","https://openalex.org/W2542062716","https://openalex.org/W1505346162","https://openalex.org/W4200562864","https://openalex.org/W2401089611","https://openalex.org/W2092735486","https://openalex.org/W2117416982","https://openalex.org/W2022538999"],"abstract_inverted_index":{"Our":[0],"proposed":[1],"correlated":[2],"multi-level":[3],"optimization":[4,43],"approach":[5,52,85,106],"enhances":[6],"speech":[7,122,130],"recognition":[8,77,117],"performance":[9],"for":[10],"high-performance":[11],"acoustic":[12],"models":[13],"in":[14,78,93,125],"real-world":[15],"applications.":[16],"By":[17],"combining":[18],"mean":[19],"squared":[20],"error":[21,97],"of":[22,41,60,90,128],"mask,":[23],"scale-invariant":[24],"source-to-noise":[25],"ratio,":[26],"and":[27,111],"cross-entropy":[28],"loss":[29,62],"functions,":[30],"as":[31,33,38,114,116],"well":[32,115],"adopting":[34],"Pearson":[35],"correlation":[36,48,69],"coefficient":[37],"a":[39,87],"part":[40],"the":[42,47,58,68,94,126],"goal":[44],"to":[45,54],"measure":[46],"between":[49,70],"them,":[50],"our":[51,84,105],"aims":[53],"not":[55],"only":[56],"reduce":[57],"value":[59],"each":[61],"during":[63],"training":[64],"but":[65],"also":[66],"increase":[67],"them.":[71],"Experimental":[72],"results":[73],"on":[74],"continuous":[75],"Mandarin":[76],"mobile":[79],"phone":[80],"scenarios":[81],"show":[82],"that":[83],"achieves":[86],"relative":[88],"reduction":[89],"about":[91],"25.29%":[92],"average":[95],"character":[96],"rate":[98],"across":[99],"five":[100],"signal-to-noise":[101],"ratio":[102],"levels.":[103],"Notably,":[104],"improves":[107],"objective":[108],"perception":[109],"qualities":[110],"intelligibility":[112],"measures,":[113],"accuracies,":[118],"surpassing":[119],"some":[120],"advanced":[121],"enhancement":[123],"techniques":[124],"context":[127],"automatic":[129],"recognition.":[131]},"counts_by_year":[],"updated_date":"2025-12-23T23:11:35.936235","created_date":"2025-10-10T00:00:00"}