{"id":"https://openalex.org/W4312877393","doi":"https://doi.org/10.1109/iwaenc53105.2022.9914717","title":"Does a PESQNet (Loss) Require a Clean Reference Input? The Original PESQ Does, But ACR Listening Tests Don\u2019t","display_name":"Does a PESQNet (Loss) Require a Clean Reference Input? The Original PESQ Does, But ACR Listening Tests Don\u2019t","publication_year":2022,"publication_date":"2022-09-05","ids":{"openalex":"https://openalex.org/W4312877393","doi":"https://doi.org/10.1109/iwaenc53105.2022.9914717"},"language":"en","primary_location":{"id":"doi:10.1109/iwaenc53105.2022.9914717","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iwaenc53105.2022.9914717","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 International Workshop on Acoustic Signal Enhancement (IWAENC)","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/A5070273121","display_name":"Ziyi Xu","orcid":"https://orcid.org/0000-0003-3046-1425"},"institutions":[{"id":"https://openalex.org/I94509681","display_name":"Technische Universit\u00e4t Braunschweig","ror":"https://ror.org/010nsgg66","country_code":"DE","type":"education","lineage":["https://openalex.org/I94509681"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Ziyi Xu","raw_affiliation_strings":["Technische Universität Braunschweig,Institute for Communications Technology,Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Technische Universität Braunschweig,Institute for Communications Technology,Germany","institution_ids":["https://openalex.org/I94509681"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5074981761","display_name":"Maximilian Strake","orcid":null},"institutions":[{"id":"https://openalex.org/I94509681","display_name":"Technische Universit\u00e4t Braunschweig","ror":"https://ror.org/010nsgg66","country_code":"DE","type":"education","lineage":["https://openalex.org/I94509681"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Maximilian Strake","raw_affiliation_strings":["Technische Universität Braunschweig,Institute for Communications Technology,Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Technische Universität Braunschweig,Institute for Communications Technology,Germany","institution_ids":["https://openalex.org/I94509681"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5002593702","display_name":"Tim Fingscheidt","orcid":"https://orcid.org/0000-0002-8895-5041"},"institutions":[{"id":"https://openalex.org/I94509681","display_name":"Technische Universit\u00e4t Braunschweig","ror":"https://ror.org/010nsgg66","country_code":"DE","type":"education","lineage":["https://openalex.org/I94509681"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Tim Fingscheidt","raw_affiliation_strings":["Technische Universität Braunschweig,Institute for Communications Technology,Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Technische Universität Braunschweig,Institute for Communications Technology,Germany","institution_ids":["https://openalex.org/I94509681"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I94509681"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":"25","issue":null,"first_page":"1","last_page":"5"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9929999709129333,"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":0.9929999709129333,"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":0.9884999990463257,"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/T10662","display_name":"Ultrasonics and Acoustic Wave Propagation","score":0.9882000088691711,"subfield":{"id":"https://openalex.org/subfields/2211","display_name":"Mechanics of Materials"},"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":0.9778393507003784},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7859820127487183},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6582340598106384},{"id":"https://openalex.org/keywords/active-listening","display_name":"Active listening","score":0.4853293001651764},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.4272104799747467},{"id":"https://openalex.org/keywords/metric","display_name":"Metric (unit)","score":0.41170552372932434},{"id":"https://openalex.org/keywords/speech-enhancement","display_name":"Speech enhancement","score":0.3406466841697693},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3272102475166321},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.14532062411308289},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.10014790296554565}],"concepts":[{"id":"https://openalex.org/C103734657","wikidata":"https://www.wikidata.org/wiki/Q2739975","display_name":"PESQ","level":4,"score":0.9778393507003784},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7859820127487183},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6582340598106384},{"id":"https://openalex.org/C177291462","wikidata":"https://www.wikidata.org/wiki/Q423038","display_name":"Active listening","level":2,"score":0.4853293001651764},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.4272104799747467},{"id":"https://openalex.org/C176217482","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Metric (unit)","level":2,"score":0.41170552372932434},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.3406466841697693},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3272102475166321},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.14532062411308289},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.10014790296554565},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","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},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0},{"id":"https://openalex.org/C46312422","wikidata":"https://www.wikidata.org/wiki/Q11024","display_name":"Communication","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/iwaenc53105.2022.9914717","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iwaenc53105.2022.9914717","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 International Workshop on Acoustic Signal Enhancement (IWAENC)","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":0.7799999713897705}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":34,"referenced_works":["https://openalex.org/W1506438021","https://openalex.org/W1983108229","https://openalex.org/W2067295501","https://openalex.org/W2125114513","https://openalex.org/W2291877678","https://openalex.org/W2786835328","https://openalex.org/W2889273017","https://openalex.org/W2892110446","https://openalex.org/W2892129657","https://openalex.org/W2892356933","https://openalex.org/W2962843322","https://openalex.org/W2962866211","https://openalex.org/W2963045393","https://openalex.org/W2963341071","https://openalex.org/W2987307811","https://openalex.org/W2987989623","https://openalex.org/W2997901485","https://openalex.org/W2998155746","https://openalex.org/W3015844538","https://openalex.org/W3092864146","https://openalex.org/W3096949857","https://openalex.org/W3097312999","https://openalex.org/W3097906045","https://openalex.org/W3144479330","https://openalex.org/W3161480375","https://openalex.org/W3163464523","https://openalex.org/W3191448984","https://openalex.org/W3197042120","https://openalex.org/W3198130028","https://openalex.org/W3212906118","https://openalex.org/W4253928870","https://openalex.org/W6738472138","https://openalex.org/W6769953873","https://openalex.org/W6890361730"],"related_works":["https://openalex.org/W3016109656","https://openalex.org/W2058482658","https://openalex.org/W1973895194","https://openalex.org/W3135613579","https://openalex.org/W3209446892","https://openalex.org/W4386746628","https://openalex.org/W1980687383","https://openalex.org/W2792294082","https://openalex.org/W4388016426","https://openalex.org/W2105126898"],"abstract_inverted_index":{"Perceptual":[0],"evaluation":[1],"of":[2,81,114,196],"speech":[3,9,59,84,118,190],"quality":[4],"(PESQ)":[5],"requires":[6],"a":[7,29,44,57,66,69,116,188],"clean":[8,58,117,189],"reference":[10,119,191],"as":[11,36,65,178],"input,":[12,192],"but":[13],"predicts":[14],"the":[15,52,73,78,82,87,104,112,128,133,137,144,170,174,182,194],"results":[16],"from":[17],"(reference-free)":[18],"absolute":[19],"category":[20],"rating":[21],"(ACR)":[22],"tests.":[23],"In":[24],"this":[25],"work,":[26],"we":[27,90,159],"train":[28],"fully":[30],"convolutional":[31],"recurrent":[32],"neural":[33],"network":[34],"(FCRN)":[35],"deep":[37],"noise":[38],"suppression":[39],"(DNS)":[40],"model,":[41],"with":[42,132,147,173],"either":[43],"non-intrusive":[45,105,175],"or":[46],"an":[47,148],"intrusive":[48,88],"PESQNet,":[49,89,100],"where":[50],"only":[51,163],"latter":[53],"has":[54],"access":[55],"to":[56,76,103,107,110,169],"reference.":[60],"The":[61],"PESQNet":[62,106,135,183],"is":[63],"used":[64],"mediator":[67],"providing":[68],"perceptual":[70],"loss":[71,150],"during":[72,121],"DNS":[74,122,129,140,171,201],"training":[75],"maximize":[77],"PESQ":[79,155],"score":[80],"enhanced":[83],"signal.":[85],"For":[86],"investigate":[91],"two":[92],"topologies,":[93],"called":[94],"early-fusion":[95],"(EF)":[96],"and":[97,101,109,143,153],"middle-fusion":[98],"(MF)":[99],"compare":[102],"evaluate":[108],"quantify":[111],"benefits":[113,165],"employing":[115],"input":[120],"training.":[123,202],"Detailed":[124],"analyses":[125],"show":[126,161],"that":[127,162],"model":[130],"trained":[131,146,172],"MF-intrusive":[134],"outperforms":[136],"Interspeech":[138],"2021":[139],"Challenge":[141],"baseline":[142],"one":[145],"MSE":[149],"by":[151],"0.23":[152],"0.12":[154],"points,":[156],"respectively.":[157],"Furthermore,":[158],"can":[160],"marginal":[164],"are":[166],"obtained":[167],"compared":[168],"PESQNet.":[176],"Therefore,":[177],"ACR":[179],"listening":[180],"tests,":[181],"does":[184],"not":[185],"necessarily":[186],"require":[187],"opening":[193],"possibility":[195],"using":[197],"real":[198],"data":[199],"for":[200]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}