{"id":"https://openalex.org/W4385807442","doi":"https://doi.org/10.21437/interspeech.2023-1441","title":"MP-SENet: A Speech Enhancement Model with Parallel Denoising of Magnitude and Phase Spectra","display_name":"MP-SENet: A Speech Enhancement Model with Parallel Denoising of Magnitude and Phase Spectra","publication_year":2023,"publication_date":"2023-08-14","ids":{"openalex":"https://openalex.org/W4385807442","doi":"https://doi.org/10.21437/interspeech.2023-1441"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2023-1441","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2023-1441","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"INTERSPEECH 2023","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/A5072371384","display_name":"Ye-Xin Lu","orcid":"https://orcid.org/0009-0009-8026-0702"},"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":"Ye-Xin Lu","raw_affiliation_strings":["National Engineering Research Center of Speech and Language Information Processing, University of Science and Technology of China, Hefei, P. R. China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Engineering Research Center of Speech and Language Information Processing, University of Science and Technology of China, Hefei, P. R. China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5014746276","display_name":"Yang Ai","orcid":"https://orcid.org/0009-0006-0157-4980"},"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":"Yang Ai","raw_affiliation_strings":["National Engineering Research Center of Speech and Language Information Processing, University of Science and Technology of China, Hefei, P. R. China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Engineering Research Center of Speech and Language Information Processing, University of Science and Technology of China, Hefei, P. R. China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5059767940","display_name":"Zhen-Hua Ling","orcid":"https://orcid.org/0000-0001-7853-5273"},"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":"Zhen-Hua Ling","raw_affiliation_strings":["National Engineering Research Center of Speech and Language Information Processing, University of Science and Technology of China, Hefei, P. R. China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Engineering Research Center of Speech and Language Information Processing, University of Science and Technology of China, Hefei, P. R. China","institution_ids":["https://openalex.org/I126520041"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I126520041"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":115,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"3834","last_page":"3838"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9962999820709229,"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":0.9962999820709229,"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":0.9768999814987183,"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/T13289","display_name":"Infant Health and Development","score":0.9021000266075134,"subfield":{"id":"https://openalex.org/subfields/3611","display_name":"Pharmacy"},"field":{"id":"https://openalex.org/fields/36","display_name":"Health Professions"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/magnitude","display_name":"Magnitude (astronomy)","score":0.704723060131073},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.702342689037323},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5110095739364624},{"id":"https://openalex.org/keywords/phase","display_name":"Phase (matter)","score":0.5015850067138672},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.46473148465156555},{"id":"https://openalex.org/keywords/reduction","display_name":"Reduction (mathematics)","score":0.4580875635147095},{"id":"https://openalex.org/keywords/spectral-line","display_name":"Spectral line","score":0.4294784367084503},{"id":"https://openalex.org/keywords/speech-enhancement","display_name":"Speech enhancement","score":0.4194071292877197},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.2925528585910797},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.2213478982448578},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.17010968923568726},{"id":"https://openalex.org/keywords/astrophysics","display_name":"Astrophysics","score":0.0658903419971466}],"concepts":[{"id":"https://openalex.org/C126691448","wikidata":"https://www.wikidata.org/wiki/Q2028919","display_name":"Magnitude (astronomy)","level":2,"score":0.704723060131073},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.702342689037323},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5110095739364624},{"id":"https://openalex.org/C44280652","wikidata":"https://www.wikidata.org/wiki/Q104837","display_name":"Phase (matter)","level":2,"score":0.5015850067138672},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.46473148465156555},{"id":"https://openalex.org/C111335779","wikidata":"https://www.wikidata.org/wiki/Q3454686","display_name":"Reduction (mathematics)","level":2,"score":0.4580875635147095},{"id":"https://openalex.org/C4839761","wikidata":"https://www.wikidata.org/wiki/Q212111","display_name":"Spectral line","level":2,"score":0.4294784367084503},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.4194071292877197},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2925528585910797},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.2213478982448578},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.17010968923568726},{"id":"https://openalex.org/C44870925","wikidata":"https://www.wikidata.org/wiki/Q37547","display_name":"Astrophysics","level":1,"score":0.0658903419971466},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"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/C1276947","wikidata":"https://www.wikidata.org/wiki/Q333","display_name":"Astronomy","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21437/interspeech.2023-1441","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2023-1441","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"INTERSPEECH 2023","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320335787","display_name":"Fundamental Research Funds for the Central Universities","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":28,"referenced_works":["https://openalex.org/W1677182931","https://openalex.org/W2044893557","https://openalex.org/W2070126272","https://openalex.org/W2094721231","https://openalex.org/W2291877678","https://openalex.org/W2502312327","https://openalex.org/W2603567530","https://openalex.org/W2801554275","https://openalex.org/W2908510526","https://openalex.org/W2937484199","https://openalex.org/W2940417587","https://openalex.org/W2949558265","https://openalex.org/W2963341071","https://openalex.org/W2991361823","https://openalex.org/W2998161426","https://openalex.org/W3015197852","https://openalex.org/W3016129867","https://openalex.org/W3097945073","https://openalex.org/W3158779859","https://openalex.org/W3197729725","https://openalex.org/W3201698955","https://openalex.org/W4221143458","https://openalex.org/W4221162870","https://openalex.org/W4232282348","https://openalex.org/W4286905522","https://openalex.org/W4287236406","https://openalex.org/W4372260247","https://openalex.org/W4385823093"],"related_works":["https://openalex.org/W2376418092","https://openalex.org/W2072983018","https://openalex.org/W1016952678","https://openalex.org/W2257644995","https://openalex.org/W4311345787","https://openalex.org/W2188141918","https://openalex.org/W3185336960","https://openalex.org/W2042652790","https://openalex.org/W2257646557","https://openalex.org/W1970662124"],"abstract_inverted_index":{"This":[0],"paper":[1],"proposes":[2],"MP-SENet,":[3],"a":[4,21,108],"novel":[5],"Speech":[6],"Enhancement":[7],"Network":[8],"which":[9,25],"directly":[10,60],"denoises":[11],"Magnitude":[12],"and":[13,28,46,57,65,74,90,117],"Phase":[14],"spectra":[15,64,68],"in":[16,24],"parallel.The":[17],"proposed":[18,105],"MP-SENet":[19,98,106],"adopts":[20],"codec":[22],"architecture":[23],"the":[26,42,97,113],"encoder":[27,35],"decoder":[29,49,56],"are":[30,93],"bridged":[31],"by":[32,69],"convolution-augmented":[33],"transformers.The":[34],"aims":[36],"to":[37,95],"encode":[38],"time-frequency":[39],"representations":[40],"from":[41],"input":[43],"noisy":[44],"magnitude":[45,54,63,83],"phase":[47,58,67,76,85],"spectra.The":[48],"is":[50],"composed":[51],"of":[52,110],"parallel":[53,75],"mask":[55],"decoder,":[59],"recovering":[61],"clean":[62],"clean-wrapped":[66],"incorporating":[70],"learnable":[71],"sigmoid":[72],"activation":[73],"estimation":[77],"architecture,":[78],"respectively.Multi-level":[79],"losses":[80],"defined":[81],"on":[82,112],"spectra,":[84,86,89],"short-time":[87],"complex":[88],"time-domain":[91],"waveforms":[92],"used":[94],"train":[96],"model":[99],"jointly.Experimental":[100],"results":[101],"show":[102],"that":[103],"our":[104],"achieves":[107],"PESQ":[109],"3.50":[111],"public":[114],"VoiceBank+DEMAND":[115],"dataset":[116],"outperforms":[118],"existing":[119],"advanced":[120],"speech":[121],"enhancement":[122],"methods.":[123]},"counts_by_year":[{"year":2026,"cited_by_count":25},{"year":2025,"cited_by_count":65},{"year":2024,"cited_by_count":25}],"updated_date":"2026-07-18T07:39:51.176621","created_date":"2023-08-15T00:00:00"}