{"id":"https://openalex.org/W4391021527","doi":"https://doi.org/10.1109/asru57964.2023.10389726","title":"Magnitude-and-Phase-Aware Speech Enhancement With Parallel Sequence Modeling","display_name":"Magnitude-and-Phase-Aware Speech Enhancement With Parallel Sequence Modeling","publication_year":2023,"publication_date":"2023-12-16","ids":{"openalex":"https://openalex.org/W4391021527","doi":"https://doi.org/10.1109/asru57964.2023.10389726"},"language":"en","primary_location":{"id":"doi:10.1109/asru57964.2023.10389726","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asru57964.2023.10389726","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","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/A5004726078","display_name":"Yuewei Zhang","orcid":"https://orcid.org/0000-0002-9124-0194"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuewei Zhang","raw_affiliation_strings":["Shanghai Jiao Tong University,Department of Electronic Engineering,Shanghai,China","Department of Electronic Engineering, Shanghai Jiao Tong University, Shanghai, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University,Department of Electronic Engineering,Shanghai,China","institution_ids":["https://openalex.org/I183067930"]},{"raw_affiliation_string":"Department of Electronic Engineering, Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5031888988","display_name":"Huanbin Zou","orcid":null},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Huanbin Zou","raw_affiliation_strings":["Tencent Video Cloud,Shanghai,China","Tencent Video Cloud, Shanghai, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tencent Video Cloud,Shanghai,China","institution_ids":["https://openalex.org/I2250653659"]},{"raw_affiliation_string":"Tencent Video Cloud, Shanghai, China","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5036446909","display_name":"Jie Zhu","orcid":"https://orcid.org/0000-0003-2133-4651"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jie Zhu","raw_affiliation_strings":["Shanghai Jiao Tong University,Department of Electronic Engineering,Shanghai,China","Department of Electronic Engineering, Shanghai Jiao Tong University, Shanghai, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University,Department of Electronic Engineering,Shanghai,China","institution_ids":["https://openalex.org/I183067930"]},{"raw_affiliation_string":"Department of Electronic Engineering, Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.2417,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.49882849,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"8"},"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":0.9993000030517578,"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":0.9958999752998352,"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/computer-science","display_name":"Computer science","score":0.6411393284797668},{"id":"https://openalex.org/keywords/sequence","display_name":"Sequence (biology)","score":0.518846869468689},{"id":"https://openalex.org/keywords/speech-enhancement","display_name":"Speech enhancement","score":0.48037537932395935},{"id":"https://openalex.org/keywords/phase","display_name":"Phase (matter)","score":0.44677355885505676},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.43236085772514343},{"id":"https://openalex.org/keywords/magnitude","display_name":"Magnitude (astronomy)","score":0.410503089427948},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.21250993013381958},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.14437931776046753}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6411393284797668},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.518846869468689},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.48037537932395935},{"id":"https://openalex.org/C44280652","wikidata":"https://www.wikidata.org/wiki/Q104837","display_name":"Phase (matter)","level":2,"score":0.44677355885505676},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.43236085772514343},{"id":"https://openalex.org/C126691448","wikidata":"https://www.wikidata.org/wiki/Q2028919","display_name":"Magnitude (astronomy)","level":2,"score":0.410503089427948},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.21250993013381958},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.14437931776046753},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.0},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","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},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/asru57964.2023.10389726","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asru57964.2023.10389726","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":28,"referenced_works":["https://openalex.org/W1552314771","https://openalex.org/W1983108229","https://openalex.org/W2046869671","https://openalex.org/W2070126272","https://openalex.org/W2094721231","https://openalex.org/W2128653836","https://openalex.org/W2133908567","https://openalex.org/W2144404214","https://openalex.org/W2603567530","https://openalex.org/W2889442120","https://openalex.org/W2940275453","https://openalex.org/W2963341071","https://openalex.org/W2963868408","https://openalex.org/W2991015288","https://openalex.org/W2991361823","https://openalex.org/W2998161426","https://openalex.org/W3015424358","https://openalex.org/W3017350693","https://openalex.org/W3095248373","https://openalex.org/W3096408984","https://openalex.org/W3097906045","https://openalex.org/W3097945073","https://openalex.org/W3160129476","https://openalex.org/W3201698955","https://openalex.org/W3213188934","https://openalex.org/W4296068619","https://openalex.org/W6680017764","https://openalex.org/W6757632829"],"related_works":["https://openalex.org/W2376418092","https://openalex.org/W2072983018","https://openalex.org/W1016952678","https://openalex.org/W2257644995","https://openalex.org/W1513444457","https://openalex.org/W4311345787","https://openalex.org/W2188141918","https://openalex.org/W3096184950","https://openalex.org/W4231424160","https://openalex.org/W2275432853"],"abstract_inverted_index":{"In":[0],"speech":[1],"enhancement":[2],"(SE),":[3],"phase":[4,106],"estimation":[5,107],"is":[6,42],"important":[7],"for":[8],"perceptual":[9],"quality,":[10],"so":[11],"many":[12],"methods":[13],"take":[14],"clean":[15],"speech\u2019s":[16],"complex":[17,25,37,46,97],"short-time":[18],"Fourier":[19],"transform":[20],"(STFT)":[21],"spectrum":[22],"or":[23,49],"the":[24,31,39,57,63,78,88,92,120,124],"ideal":[26],"ratio":[27],"mask":[28,80],"(cIRM)":[29],"as":[30,135],"learning":[32],"target.":[33,64],"To":[34],"predict":[35,56],"these":[36],"targets,":[38],"common":[40],"solution":[41],"to":[43,54,71,76,118],"design":[44],"a":[45,51,73,112],"neural":[47],"network,":[48],"use":[50,72],"real":[52,58,74],"network":[53,75,127],"separately":[55],"and":[59,81,137],"imaginary":[60],"parts":[61],"of":[62,91],"But":[65],"in":[66,123],"this":[67],"paper,":[68],"we":[69,110],"propose":[70],"estimate":[77],"magnitude":[79],"normalized":[82],"cIRM,":[83],"which":[84],"not":[85],"only":[86],"avoids":[87],"significant":[89],"increase":[90],"model":[93],"complexity":[94],"caused":[95],"by":[96],"networks,":[98],"but":[99],"also":[100],"shows":[101],"better":[102],"performance":[103],"than":[104],"previous":[105],"methods.":[108],"Meanwhile,":[109],"devise":[111],"parallel":[113],"sequence":[114],"modeling":[115],"(PSM)":[116],"block":[117,122],"improve":[119],"RNN":[121],"convolutional":[125],"recurrent":[126],"(CRN)-based":[128],"SE":[129,150],"model.":[130],"We":[131],"name":[132],"our":[133,146],"method":[134],"magnitude-and-phase-aware":[136],"PSM-based":[138],"CRN":[139],"(MPCRN).":[140],"The":[141],"experimental":[142],"results":[143],"illustrate":[144],"that":[145],"MPCRN":[147],"has":[148],"superior":[149],"performance.":[151]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}