{"id":"https://openalex.org/W2892129657","doi":"https://doi.org/10.1109/icassp.2018.8461965","title":"Training Supervised Speech Separation System to Improve STOI and PESQ Directly","display_name":"Training Supervised Speech Separation System to Improve STOI and PESQ Directly","publication_year":2018,"publication_date":"2018-04-01","ids":{"openalex":"https://openalex.org/W2892129657","doi":"https://doi.org/10.1109/icassp.2018.8461965","mag":"2892129657"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2018.8461965","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2018.8461965","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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/A5108035744","display_name":"Hui Zhang","orcid":"https://orcid.org/0000-0003-0601-3905"},"institutions":[{"id":"https://openalex.org/I2722730","display_name":"Inner Mongolia University","ror":"https://ror.org/0106qb496","country_code":"CN","type":"education","lineage":["https://openalex.org/I2722730"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hui Zhang","raw_affiliation_strings":["College of Computer Science, Inner Mongolia University, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"College of Computer Science, Inner Mongolia University, China","institution_ids":["https://openalex.org/I2722730"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100693230","display_name":"Xueliang Zhang","orcid":"https://orcid.org/0000-0002-0406-1105"},"institutions":[{"id":"https://openalex.org/I2722730","display_name":"Inner Mongolia University","ror":"https://ror.org/0106qb496","country_code":"CN","type":"education","lineage":["https://openalex.org/I2722730"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xueliang Zhang","raw_affiliation_strings":["College of Computer Science, Inner Mongolia University, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"College of Computer Science, Inner Mongolia University, China","institution_ids":["https://openalex.org/I2722730"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5076174513","display_name":"Guanglai Gao","orcid":"https://orcid.org/0009-0005-5513-1192"},"institutions":[{"id":"https://openalex.org/I2722730","display_name":"Inner Mongolia University","ror":"https://ror.org/0106qb496","country_code":"CN","type":"education","lineage":["https://openalex.org/I2722730"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Guanglai Gao","raw_affiliation_strings":["College of Computer Science, Inner Mongolia University, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"College of Computer Science, Inner Mongolia University, China","institution_ids":["https://openalex.org/I2722730"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I2722730"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":67,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"5374","last_page":"5378"},"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/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"}},{"id":"https://openalex.org/T11233","display_name":"Advanced Adaptive Filtering Techniques","score":0.9980999827384949,"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/pesq","display_name":"PESQ","score":0.9836293458938599},{"id":"https://openalex.org/keywords/intelligibility","display_name":"Intelligibility (philosophy)","score":0.7680505514144897},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6070449948310852},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5415530204772949},{"id":"https://openalex.org/keywords/gradient-descent","display_name":"Gradient descent","score":0.5076667070388794},{"id":"https://openalex.org/keywords/speech-enhancement","display_name":"Speech enhancement","score":0.4307178258895874},{"id":"https://openalex.org/keywords/separation","display_name":"Separation (statistics)","score":0.4137461483478546},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.32810020446777344},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.200813889503479},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.16689884662628174},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.11828926205635071}],"concepts":[{"id":"https://openalex.org/C103734657","wikidata":"https://www.wikidata.org/wiki/Q2739975","display_name":"PESQ","level":4,"score":0.9836293458938599},{"id":"https://openalex.org/C60048801","wikidata":"https://www.wikidata.org/wiki/Q1433889","display_name":"Intelligibility (philosophy)","level":2,"score":0.7680505514144897},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6070449948310852},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5415530204772949},{"id":"https://openalex.org/C153258448","wikidata":"https://www.wikidata.org/wiki/Q1199743","display_name":"Gradient descent","level":3,"score":0.5076667070388794},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.4307178258895874},{"id":"https://openalex.org/C2776061190","wikidata":"https://www.wikidata.org/wiki/Q7451805","display_name":"Separation (statistics)","level":2,"score":0.4137461483478546},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.32810020446777344},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.200813889503479},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.16689884662628174},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.11828926205635071},{"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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp.2018.8461965","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2018.8461965","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.7900000214576721,"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":24,"referenced_works":["https://openalex.org/W1495679096","https://openalex.org/W1522301498","https://openalex.org/W1552314771","https://openalex.org/W1790748249","https://openalex.org/W1963950237","https://openalex.org/W1974387177","https://openalex.org/W1989364685","https://openalex.org/W2044893557","https://openalex.org/W2069681747","https://openalex.org/W2121973264","https://openalex.org/W2122982914","https://openalex.org/W2124289529","https://openalex.org/W2137104525","https://openalex.org/W2141998673","https://openalex.org/W2144404214","https://openalex.org/W2149479912","https://openalex.org/W2344535577","https://openalex.org/W2517760955","https://openalex.org/W2752404792","https://openalex.org/W2778338786","https://openalex.org/W2962866211","https://openalex.org/W3124794156","https://openalex.org/W6681845865","https://openalex.org/W6780493881"],"related_works":["https://openalex.org/W2058482658","https://openalex.org/W1823208675","https://openalex.org/W2342810974","https://openalex.org/W3016109656","https://openalex.org/W2513767140","https://openalex.org/W1973895194","https://openalex.org/W2546593254","https://openalex.org/W3135613579","https://openalex.org/W2037635165","https://openalex.org/W4200562864"],"abstract_inverted_index":{"Supervised":[0],"speech":[1,11,50,65,138],"separation":[2,66,139],"methods":[3],"train":[4],"learning":[5],"machine":[6],"to":[7,12,56,107,127],"cast":[8],"the":[9,13,31,38,57,80,93,109,112,117,123,129,137,145],"noisy":[10],"target":[14],"clean":[15],"speech.":[16],"Most":[17],"of":[18,49,111],"them":[19],"use":[20],"mean-square":[21],"error":[22],"(MSE)":[23],"as":[24,68],"loss":[25,81],"function.":[26,82],"However,":[27,83],"MSE":[28],"is":[29,105],"not":[30],"perfect":[32],"choice":[33],"because":[34],"it":[35],"doesn't":[36],"match":[37],"human":[39,58],"auditory":[40,59],"perception.":[41],"Short-time":[42],"objective":[43],"intelligibility":[44],"(STOI)":[45],"and":[46,61,73,114,131],"perceptual":[47],"evaluation":[48,69],"quality":[51],"(PESQ)":[52],"are":[53,85,120],"closely":[54],"related":[55],"perception":[60],"widely":[62],"used":[63,106,121],"in":[64,122],"research":[67],"criteria.":[70],"Therefore,":[71],"STOI":[72,113,130],"PESQ":[74,132],"may":[75],"be":[76,90,142],"better":[77],"choices":[78],"for":[79],"they":[84],"nondifferentiable":[86],"functions":[87],"which":[88],"cannot":[89],"optimized":[91],"by":[92,144],"conventional":[94],"gradient":[95,102,124],"descent":[96,125],"algorithm.":[97],"In":[98],"this":[99],"work,":[100],"a":[101],"approximation":[103],"method":[104],"calculate":[108],"gradients":[110,119],"PESQ.":[115],"Then":[116],"calculated":[118],"algorithm":[126],"optimize":[128],"directly.":[133],"Experimental":[134],"results":[135],"show":[136],"performance":[140],"can":[141],"improved":[143],"proposed":[146],"method.":[147]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":10},{"year":2022,"cited_by_count":13},{"year":2021,"cited_by_count":8},{"year":2020,"cited_by_count":15},{"year":2019,"cited_by_count":11},{"year":2018,"cited_by_count":4}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}