{"id":"https://openalex.org/W2892110446","doi":"https://doi.org/10.1109/lsp.2018.2871419","title":"A Deep Learning Loss Function Based on the Perceptual Evaluation of the Speech Quality","display_name":"A Deep Learning Loss Function Based on the Perceptual Evaluation of the Speech Quality","publication_year":2018,"publication_date":"2018-09-21","ids":{"openalex":"https://openalex.org/W2892110446","doi":"https://doi.org/10.1109/lsp.2018.2871419","mag":"2892110446"},"language":"en","primary_location":{"id":"doi:10.1109/lsp.2018.2871419","is_oa":false,"landing_page_url":"https://doi.org/10.1109/lsp.2018.2871419","pdf_url":null,"source":{"id":"https://openalex.org/S120629676","display_name":"IEEE Signal Processing Letters","issn_l":"1070-9908","issn":["1070-9908","1558-2361"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Signal Processing Letters","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"http://hdl.handle.net/10481/71497","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5064609638","display_name":"Juan M. Mart\u00edn-Do\u00f1as","orcid":"https://orcid.org/0000-0003-4874-0166"},"institutions":[{"id":"https://openalex.org/I173304897","display_name":"Universidad de Granada","ror":"https://ror.org/04njjy449","country_code":"ES","type":"education","lineage":["https://openalex.org/I173304897"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"Juan Manuel Martin-Donas","raw_affiliation_strings":["Department of Signal Theory, Telematics and Communications, Universidad de Granada, Granada, Spain"],"raw_orcid":"https://orcid.org/0000-0003-4874-0166","affiliations":[{"raw_affiliation_string":"Department of Signal Theory, Telematics and Communications, Universidad de Granada, Granada, Spain","institution_ids":["https://openalex.org/I173304897"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5024291487","display_name":"\u00c1ngel M. G\u00f3mez","orcid":"https://orcid.org/0000-0002-9995-3068"},"institutions":[{"id":"https://openalex.org/I173304897","display_name":"Universidad de Granada","ror":"https://ror.org/04njjy449","country_code":"ES","type":"education","lineage":["https://openalex.org/I173304897"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"Angel Manuel Gomez","raw_affiliation_strings":["Department of Signal Theory, Telematics and Communications, Universidad de Granada, Granada, Spain"],"raw_orcid":"https://orcid.org/0000-0002-9995-3068","affiliations":[{"raw_affiliation_string":"Department of Signal Theory, Telematics and Communications, Universidad de Granada, Granada, Spain","institution_ids":["https://openalex.org/I173304897"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100720211","display_name":"Jos\u00e9 A. Gonz\u00e1lez","orcid":"https://orcid.org/0000-0002-5531-8994"},"institutions":[{"id":"https://openalex.org/I82767444","display_name":"Universidad de M\u00e1laga","ror":"https://ror.org/036b2ww28","country_code":"ES","type":"education","lineage":["https://openalex.org/I82767444"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"Jose A. Gonzalez","raw_affiliation_strings":["Department of Languages and Computer Sciences, Universidad de Malaga, Malaga, Spain"],"raw_orcid":"https://orcid.org/0000-0002-5531-8994","affiliations":[{"raw_affiliation_string":"Department of Languages and Computer Sciences, Universidad de Malaga, Malaga, Spain","institution_ids":["https://openalex.org/I82767444"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5078514616","display_name":"Antonio M. Peinado","orcid":"https://orcid.org/0000-0001-8214-6676"},"institutions":[{"id":"https://openalex.org/I173304897","display_name":"Universidad de Granada","ror":"https://ror.org/04njjy449","country_code":"ES","type":"education","lineage":["https://openalex.org/I173304897"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"Antonio M. Peinado","raw_affiliation_strings":["Department of Signal Theory, Telematics and Communications, Universidad de Granada, Granada, Spain"],"raw_orcid":"https://orcid.org/0000-0001-8214-6676","affiliations":[{"raw_affiliation_string":"Department of Signal Theory, Telematics and Communications, Universidad de Granada, Granada, Spain","institution_ids":["https://openalex.org/I173304897"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":10.4751,"has_fulltext":false,"cited_by_count":145,"citation_normalized_percentile":{"value":0.98794238,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":100},"biblio":{"volume":"25","issue":"11","first_page":"1680","last_page":"1684"},"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":0.998199999332428,"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":0.9970999956130981,"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/metric","display_name":"Metric (unit)","score":0.6934873461723328},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6919569373130798},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6554803252220154},{"id":"https://openalex.org/keywords/mean-squared-error","display_name":"Mean squared error","score":0.6179342269897461},{"id":"https://openalex.org/keywords/psychoacoustics","display_name":"Psychoacoustics","score":0.5950157642364502},{"id":"https://openalex.org/keywords/auditory-masking","display_name":"Auditory masking","score":0.5847253799438477},{"id":"https://openalex.org/keywords/speech-enhancement","display_name":"Speech enhancement","score":0.5775130391120911},{"id":"https://openalex.org/keywords/pesq","display_name":"PESQ","score":0.480163037776947},{"id":"https://openalex.org/keywords/distortion","display_name":"Distortion (music)","score":0.47943705320358276},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.476377934217453},{"id":"https://openalex.org/keywords/masking","display_name":"Masking (illustration)","score":0.47613003849983215},{"id":"https://openalex.org/keywords/perception","display_name":"Perception","score":0.4594046175479889},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.42704060673713684},{"id":"https://openalex.org/keywords/mean-opinion-score","display_name":"Mean opinion score","score":0.41303202509880066},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4018503427505493},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.26936501264572144},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.2082020342350006},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.14367860555648804}],"concepts":[{"id":"https://openalex.org/C176217482","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Metric (unit)","level":2,"score":0.6934873461723328},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6919569373130798},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6554803252220154},{"id":"https://openalex.org/C139945424","wikidata":"https://www.wikidata.org/wiki/Q1940696","display_name":"Mean squared error","level":2,"score":0.6179342269897461},{"id":"https://openalex.org/C9940772","wikidata":"https://www.wikidata.org/wiki/Q557399","display_name":"Psychoacoustics","level":3,"score":0.5950157642364502},{"id":"https://openalex.org/C77801330","wikidata":"https://www.wikidata.org/wiki/Q1363413","display_name":"Auditory masking","level":3,"score":0.5847253799438477},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.5775130391120911},{"id":"https://openalex.org/C103734657","wikidata":"https://www.wikidata.org/wiki/Q2739975","display_name":"PESQ","level":4,"score":0.480163037776947},{"id":"https://openalex.org/C126780896","wikidata":"https://www.wikidata.org/wiki/Q899871","display_name":"Distortion (music)","level":4,"score":0.47943705320358276},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.476377934217453},{"id":"https://openalex.org/C2777402240","wikidata":"https://www.wikidata.org/wiki/Q6783436","display_name":"Masking (illustration)","level":2,"score":0.47613003849983215},{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.4594046175479889},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.42704060673713684},{"id":"https://openalex.org/C62897895","wikidata":"https://www.wikidata.org/wiki/Q1915482","display_name":"Mean opinion score","level":3,"score":0.41303202509880066},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4018503427505493},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.26936501264572144},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.2082020342350006},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.14367860555648804},{"id":"https://openalex.org/C153349607","wikidata":"https://www.wikidata.org/wiki/Q36649","display_name":"Visual arts","level":1,"score":0.0},{"id":"https://openalex.org/C169760540","wikidata":"https://www.wikidata.org/wiki/Q207011","display_name":"Neuroscience","level":1,"score":0.0},{"id":"https://openalex.org/C2776257435","wikidata":"https://www.wikidata.org/wiki/Q1576430","display_name":"Bandwidth (computing)","level":2,"score":0.0},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C194257627","wikidata":"https://www.wikidata.org/wiki/Q211554","display_name":"Amplifier","level":3,"score":0.0},{"id":"https://openalex.org/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"score":0.0},{"id":"https://openalex.org/C21547014","wikidata":"https://www.wikidata.org/wiki/Q1423657","display_name":"Operations management","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/lsp.2018.2871419","is_oa":false,"landing_page_url":"https://doi.org/10.1109/lsp.2018.2871419","pdf_url":null,"source":{"id":"https://openalex.org/S120629676","display_name":"IEEE Signal Processing Letters","issn_l":"1070-9908","issn":["1070-9908","1558-2361"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Signal Processing Letters","raw_type":"journal-article"},{"id":"pmh:oai:digibug.ugr.es:10481/71497","is_oa":true,"landing_page_url":"http://hdl.handle.net/10481/71497","pdf_url":null,"source":{"id":"https://openalex.org/S4306400567","display_name":"Institutional Repository of the University of Granada (University of Granada)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I173304897","host_organization_name":"Universidad de Granada","host_organization_lineage":["https://openalex.org/I173304897"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"info:eu-repo/semantics/article"}],"best_oa_location":{"id":"pmh:oai:digibug.ugr.es:10481/71497","is_oa":true,"landing_page_url":"http://hdl.handle.net/10481/71497","pdf_url":null,"source":{"id":"https://openalex.org/S4306400567","display_name":"Institutional Repository of the University of Granada (University of Granada)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I173304897","host_organization_name":"Universidad de Granada","host_organization_lineage":["https://openalex.org/I173304897"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"info:eu-repo/semantics/article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.5799999833106995,"display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":43,"referenced_works":["https://openalex.org/W1522301498","https://openalex.org/W1597330042","https://openalex.org/W1963950237","https://openalex.org/W2044893557","https://openalex.org/W2069681747","https://openalex.org/W2078528584","https://openalex.org/W2099471712","https://openalex.org/W2127851351","https://openalex.org/W2141998673","https://openalex.org/W2151484683","https://openalex.org/W2168379380","https://openalex.org/W2512342189","https://openalex.org/W2516342150","https://openalex.org/W2517760955","https://openalex.org/W2524708987","https://openalex.org/W2527729766","https://openalex.org/W2605589342","https://openalex.org/W2620812332","https://openalex.org/W2746457594","https://openalex.org/W2774276265","https://openalex.org/W2774425939","https://openalex.org/W2778338786","https://openalex.org/W2891607145","https://openalex.org/W2962946126","https://openalex.org/W2963045393","https://openalex.org/W2963341071","https://openalex.org/W2963351212","https://openalex.org/W2964121744","https://openalex.org/W4320013936","https://openalex.org/W6631190155","https://openalex.org/W6682194319","https://openalex.org/W6711891804","https://openalex.org/W6725924526","https://openalex.org/W6726283100","https://openalex.org/W6726607834","https://openalex.org/W6727749278","https://openalex.org/W6735429107","https://openalex.org/W6736214761","https://openalex.org/W6738472138","https://openalex.org/W6742802039","https://openalex.org/W6747242544","https://openalex.org/W6754901823","https://openalex.org/W6766042943"],"related_works":["https://openalex.org/W3016109656","https://openalex.org/W2058482658","https://openalex.org/W2988616598","https://openalex.org/W1973895194","https://openalex.org/W3135613579","https://openalex.org/W4386746628","https://openalex.org/W2098715841","https://openalex.org/W4287113595","https://openalex.org/W3176271478","https://openalex.org/W1994891831"],"abstract_inverted_index":{"This":[0,22],"letter":[1],"proposes":[2],"a":[3,14,37,117],"perceptual":[4,27,79],"metric":[5,104,115],"for":[6,17,58,91],"speech":[7,31,50,93,109],"quality":[8,32,110],"evaluation,":[9],"which":[10,56],"is":[11,34,89],"suitable,":[12],"as":[13],"loss":[15,75,87,128],"function,":[16],"training":[18],"deep":[19,96],"learning":[20],"methods.":[21],"metric,":[23],"derived":[24],"from":[25,41,130],"the":[26,30,42,46,70,131],"evaluation":[28],"of":[29,45],"algorithm,":[33],"computed":[35],"in":[36,108],"per-frame":[38],"basis":[39],"and":[40,48,63,116],"power":[43],"spectra":[44],"reference":[47],"processed":[49],"signal.":[51],"Thus,":[52],"two":[53],"disturbance":[54],"terms,":[55],"account":[57],"distortion":[59],"once":[60],"auditory":[61],"masking":[62],"threshold":[64],"effects":[65],"are":[66],"factored":[67],"in,":[68],"amend":[69],"mean":[71],"square":[72],"error":[73],"(MSE)":[74],"function":[76,88],"by":[77],"introducing":[78],"criteria":[80],"based":[81],"on":[82],"human":[83],"psychoacoustics.":[84],"The":[85],"proposed":[86],"evaluated":[90],"noisy":[92],"enhancement":[94],"with":[95],"neural":[97],"networks.":[98],"Experimental":[99],"results":[100],"show":[101],"that":[102],"our":[103],"achieves":[105],"significant":[106],"gains":[107],"(evaluated":[111],"using":[112,123],"an":[113],"objective":[114],"listening":[118],"test)":[119],"when":[120],"compared":[121],"to":[122],"MSE":[124],"or":[125],"other":[126],"perceptual-based":[127],"functions":[129],"literature.":[132]},"counts_by_year":[{"year":2026,"cited_by_count":6},{"year":2025,"cited_by_count":21},{"year":2024,"cited_by_count":9},{"year":2023,"cited_by_count":22},{"year":2022,"cited_by_count":24},{"year":2021,"cited_by_count":29},{"year":2020,"cited_by_count":21},{"year":2019,"cited_by_count":12},{"year":2018,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}