{"id":"https://openalex.org/W4405709381","doi":"https://doi.org/10.1109/iscslp63861.2024.10800670","title":"Knowledge Distillation from Discriminative Model to Generative Model with Parallel Architecture for Speech Enhancement","display_name":"Knowledge Distillation from Discriminative Model to Generative Model with Parallel Architecture for Speech Enhancement","publication_year":2024,"publication_date":"2024-11-07","ids":{"openalex":"https://openalex.org/W4405709381","doi":"https://doi.org/10.1109/iscslp63861.2024.10800670"},"language":"en","primary_location":{"id":"doi:10.1109/iscslp63861.2024.10800670","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iscslp63861.2024.10800670","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE 14th International Symposium on Chinese Spoken Language Processing (ISCSLP)","raw_type":"proceedings-article"},"type":"article","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":null,"display_name":"Tingxiao Zhou","orcid":null},"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":true,"raw_author_name":"Tingxiao Zhou","raw_affiliation_strings":["Al Institute, Shanghai Jiao Tong University,Auditory Cognition and Computational Acoustics Lab, MoE Key Lab of Artificial Intelligence,Department of Computer Science and Engineering,Shanghai"],"affiliations":[{"raw_affiliation_string":"Al Institute, Shanghai Jiao Tong University,Auditory Cognition and Computational Acoustics Lab, MoE Key Lab of Artificial Intelligence,Department of Computer Science and Engineering,Shanghai","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101675228","display_name":"Leying Zhang","orcid":"https://orcid.org/0009-0008-1424-9604"},"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":"Leying Zhang","raw_affiliation_strings":["Al Institute, Shanghai Jiao Tong University,Auditory Cognition and Computational Acoustics Lab, MoE Key Lab of Artificial Intelligence,Department of Computer Science and Engineering,Shanghai"],"affiliations":[{"raw_affiliation_string":"Al Institute, Shanghai Jiao Tong University,Auditory Cognition and Computational Acoustics Lab, MoE Key Lab of Artificial Intelligence,Department of Computer Science and Engineering,Shanghai","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100341993","display_name":"Yanmin Qian","orcid":"https://orcid.org/0000-0002-0314-3790"},"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":"Yanmin Qian","raw_affiliation_strings":["Al Institute, Shanghai Jiao Tong University,Auditory Cognition and Computational Acoustics Lab, MoE Key Lab of Artificial Intelligence,Department of Computer Science and Engineering,Shanghai"],"affiliations":[{"raw_affiliation_string":"Al Institute, Shanghai Jiao Tong University,Auditory Cognition and Computational Acoustics Lab, MoE Key Lab of Artificial Intelligence,Department of Computer Science and Engineering,Shanghai","institution_ids":["https://openalex.org/I183067930"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I183067930"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.2573245,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"179","last_page":"183"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9549000263214111,"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":0.9549000263214111,"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/discriminative-model","display_name":"Discriminative model","score":0.8133164644241333},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7018108367919922},{"id":"https://openalex.org/keywords/generative-model","display_name":"Generative model","score":0.6121779084205627},{"id":"https://openalex.org/keywords/distillation","display_name":"Distillation","score":0.5389874577522278},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5080819129943848},{"id":"https://openalex.org/keywords/generative-grammar","display_name":"Generative grammar","score":0.5079334378242493},{"id":"https://openalex.org/keywords/architecture","display_name":"Architecture","score":0.44556817412376404},{"id":"https://openalex.org/keywords/speech-enhancement","display_name":"Speech enhancement","score":0.42567309737205505},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.38583558797836304},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3702389597892761}],"concepts":[{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.8133164644241333},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7018108367919922},{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.6121779084205627},{"id":"https://openalex.org/C204030448","wikidata":"https://www.wikidata.org/wiki/Q101017","display_name":"Distillation","level":2,"score":0.5389874577522278},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5080819129943848},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.5079334378242493},{"id":"https://openalex.org/C123657996","wikidata":"https://www.wikidata.org/wiki/Q12271","display_name":"Architecture","level":2,"score":0.44556817412376404},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.42567309737205505},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.38583558797836304},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3702389597892761},{"id":"https://openalex.org/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"score":0.0},{"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/C178790620","wikidata":"https://www.wikidata.org/wiki/Q11351","display_name":"Organic chemistry","level":1,"score":0.0},{"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/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/iscslp63861.2024.10800670","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iscslp63861.2024.10800670","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE 14th International Symposium on Chinese Spoken Language Processing (ISCSLP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.8199999928474426,"display_name":"Reduced inequalities","id":"https://metadata.un.org/sdg/10"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":33,"referenced_works":["https://openalex.org/W1552314771","https://openalex.org/W2135284480","https://openalex.org/W2407386500","https://openalex.org/W2516001803","https://openalex.org/W2760103357","https://openalex.org/W2885308148","https://openalex.org/W2952218014","https://openalex.org/W2964058413","https://openalex.org/W3161480375","https://openalex.org/W3197912330","https://openalex.org/W3198686072","https://openalex.org/W3198804855","https://openalex.org/W4221144097","https://openalex.org/W4226185896","https://openalex.org/W4302095631","https://openalex.org/W4372268522","https://openalex.org/W4375869120","https://openalex.org/W4380434618","https://openalex.org/W4384080510","https://openalex.org/W4386065380","https://openalex.org/W4391021752","https://openalex.org/W4392903897","https://openalex.org/W4392903977","https://openalex.org/W4392931780","https://openalex.org/W4394904176","https://openalex.org/W4396542462","https://openalex.org/W6740493225","https://openalex.org/W6755312952","https://openalex.org/W6777776875","https://openalex.org/W6779823529","https://openalex.org/W6798721538","https://openalex.org/W6851724922","https://openalex.org/W6856531013"],"related_works":["https://openalex.org/W4396941953","https://openalex.org/W2093104230","https://openalex.org/W2987280934","https://openalex.org/W4390874210","https://openalex.org/W4384918963","https://openalex.org/W4365211920","https://openalex.org/W2128027845","https://openalex.org/W3014948380","https://openalex.org/W4386184937","https://openalex.org/W4394728283"],"abstract_inverted_index":{"Generative":[0],"speech":[1,98],"enhancement":[2,29],"methods,":[3,6],"especially":[4],"diffusion":[5],"have":[7],"recently":[8],"gained":[9],"attention.":[10],"However,":[11],"current":[12],"generative":[13,50],"methods":[14,26],"face":[15],"several":[16],"unresolved":[17],"issues,":[18],"such":[19],"as":[20],"lagging":[21],"performance":[22,91],"compared":[23],"to":[24,37,49,64,79],"discriminative":[25,48],"on":[27,75],"conventional":[28],"metrics":[30],"and":[31,52,72,100],"slower":[32],"inference":[33,101],"speeds.":[34],"In":[35],"order":[36],"address":[38],"these":[39],"challenges,":[40],"we":[41,53],"propose":[42],"a":[43,55,59],"knowledge":[44],"distillation":[45],"approach":[46,88],"from":[47],"models,":[51],"design":[54],"parallel":[56],"architecture":[57],"with":[58],"latent":[60],"vector":[61],"fusion":[62],"module":[63],"leverage":[65],"their":[66],"respective":[67],"strengths.":[68],"We":[69],"conduct":[70],"experiments":[71],"ablation":[73],"studies":[74],"the":[76],"LibriMix":[77],"dataset":[78],"validate":[80],"its":[81],"effectiveness.":[82],"The":[83],"results":[84],"demonstrate":[85],"that":[86],"our":[87],"substantially":[89],"improves":[90],"over":[92],"baseline":[93],"systems":[94],"in":[95],"terms":[96],"of":[97],"quality":[99],"speed.":[102]},"counts_by_year":[],"updated_date":"2026-04-21T08:09:41.155169","created_date":"2025-10-10T00:00:00"}