{"id":"https://openalex.org/W4385485061","doi":"https://doi.org/10.1109/icasspw59220.2023.10193263","title":"Light-Weight Visualvoice: Neural Network Quantization On Audio Visual Speech Separation","display_name":"Light-Weight Visualvoice: Neural Network Quantization On Audio Visual Speech Separation","publication_year":2023,"publication_date":"2023-06-04","ids":{"openalex":"https://openalex.org/W4385485061","doi":"https://doi.org/10.1109/icasspw59220.2023.10193263"},"language":"en","primary_location":{"id":"doi:10.1109/icasspw59220.2023.10193263","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/icasspw59220.2023.10193263","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE International Conference on Acoustics, Speech, and Signal Processing Workshops (ICASSPW)","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/A5101452320","display_name":"Yifei Wu","orcid":"https://orcid.org/0009-0002-8201-6438"},"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":"Yifei Wu","raw_affiliation_strings":["Shanghai Jiao Tong University,MoE Key Lab of Artificial Intelligence, AI Institute X-LANCE Lab,Department of Computer Science and Engineering,Shanghai,China","Department of Computer Science and Engineering, MoE Key Lab of Artificial Intelligence, AI Institute X-LANCE Lab, Shanghai Jiao Tong University, Shanghai, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University,MoE Key Lab of Artificial Intelligence, AI Institute X-LANCE Lab,Department of Computer Science and Engineering,Shanghai,China","institution_ids":["https://openalex.org/I183067930"]},{"raw_affiliation_string":"Department of Computer Science and Engineering, MoE Key Lab of Artificial Intelligence, AI Institute X-LANCE Lab, Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5090224430","display_name":"Chenda Li","orcid":"https://orcid.org/0000-0003-0299-9914"},"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":"Chenda Li","raw_affiliation_strings":["Shanghai Jiao Tong University,MoE Key Lab of Artificial Intelligence, AI Institute X-LANCE Lab,Department of Computer Science and Engineering,Shanghai,China","Department of Computer Science and Engineering, MoE Key Lab of Artificial Intelligence, AI Institute X-LANCE Lab, Shanghai Jiao Tong University, Shanghai, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University,MoE Key Lab of Artificial Intelligence, AI Institute X-LANCE Lab,Department of Computer Science and Engineering,Shanghai,China","institution_ids":["https://openalex.org/I183067930"]},{"raw_affiliation_string":"Department of Computer Science and Engineering, MoE Key Lab of Artificial Intelligence, AI Institute X-LANCE Lab, Shanghai Jiao Tong University, Shanghai, China","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":["Shanghai Jiao Tong University,MoE Key Lab of Artificial Intelligence, AI Institute X-LANCE Lab,Department of Computer Science and Engineering,Shanghai,China","Department of Computer Science and Engineering, MoE Key Lab of Artificial Intelligence, AI Institute X-LANCE Lab, Shanghai Jiao Tong University, Shanghai, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University,MoE Key Lab of Artificial Intelligence, AI Institute X-LANCE Lab,Department of Computer Science and Engineering,Shanghai,China","institution_ids":["https://openalex.org/I183067930"]},{"raw_affiliation_string":"Department of Computer Science and Engineering, MoE Key Lab of Artificial Intelligence, AI Institute X-LANCE Lab, Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I183067930"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":"34","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":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/T11309","display_name":"Music and Audio Processing","score":0.9976000189781189,"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/T11233","display_name":"Advanced Adaptive Filtering Techniques","score":0.9968000054359436,"subfield":{"id":"https://openalex.org/subfields/2206","display_name":"Computational Mechanics"},"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/quantization","display_name":"Quantization (signal processing)","score":0.7602936625480652},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7485566139221191},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.5598470568656921},{"id":"https://openalex.org/keywords/divergence","display_name":"Divergence (linguistics)","score":0.49085456132888794},{"id":"https://openalex.org/keywords/trace","display_name":"TRACE (psycholinguistics)","score":0.47926947474479675},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.4316445589065552},{"id":"https://openalex.org/keywords/modal","display_name":"Modal","score":0.41831398010253906},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.40215685963630676},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.28709807991981506}],"concepts":[{"id":"https://openalex.org/C28855332","wikidata":"https://www.wikidata.org/wiki/Q198099","display_name":"Quantization (signal processing)","level":2,"score":0.7602936625480652},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7485566139221191},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5598470568656921},{"id":"https://openalex.org/C207390915","wikidata":"https://www.wikidata.org/wiki/Q1230525","display_name":"Divergence (linguistics)","level":2,"score":0.49085456132888794},{"id":"https://openalex.org/C75291252","wikidata":"https://www.wikidata.org/wiki/Q1315756","display_name":"TRACE (psycholinguistics)","level":2,"score":0.47926947474479675},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.4316445589065552},{"id":"https://openalex.org/C71139939","wikidata":"https://www.wikidata.org/wiki/Q910194","display_name":"Modal","level":2,"score":0.41831398010253906},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.40215685963630676},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.28709807991981506},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C188027245","wikidata":"https://www.wikidata.org/wiki/Q750446","display_name":"Polymer chemistry","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/icasspw59220.2023.10193263","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/icasspw59220.2023.10193263","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE International Conference on Acoustics, Speech, and Signal Processing Workshops (ICASSPW)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":45,"referenced_works":["https://openalex.org/W1724438581","https://openalex.org/W2739789140","https://openalex.org/W2747579829","https://openalex.org/W2786771851","https://openalex.org/W2803549871","https://openalex.org/W2892684141","https://openalex.org/W2903260438","https://openalex.org/W2903810591","https://openalex.org/W2916954108","https://openalex.org/W2963382930","https://openalex.org/W2963480671","https://openalex.org/W2964171275","https://openalex.org/W2970418186","https://openalex.org/W2982041622","https://openalex.org/W2999803881","https://openalex.org/W3015445830","https://openalex.org/W3035183452","https://openalex.org/W3036102031","https://openalex.org/W3097450720","https://openalex.org/W3099559063","https://openalex.org/W3138582970","https://openalex.org/W3151851237","https://openalex.org/W3173382920","https://openalex.org/W3182657421","https://openalex.org/W3212072588","https://openalex.org/W3214005787","https://openalex.org/W4213016094","https://openalex.org/W4288026258","https://openalex.org/W4288334594","https://openalex.org/W4289665794","https://openalex.org/W4295262505","https://openalex.org/W4385570274","https://openalex.org/W6637709462","https://openalex.org/W6693397755","https://openalex.org/W6748224102","https://openalex.org/W6754992056","https://openalex.org/W6756979132","https://openalex.org/W6758082782","https://openalex.org/W6760069825","https://openalex.org/W6763724728","https://openalex.org/W6767215405","https://openalex.org/W6770425567","https://openalex.org/W6779775157","https://openalex.org/W6803567761","https://openalex.org/W6804197425"],"related_works":["https://openalex.org/W1555873941","https://openalex.org/W2383986235","https://openalex.org/W2136711844","https://openalex.org/W2464849962","https://openalex.org/W3007092120","https://openalex.org/W1483845062","https://openalex.org/W2390095984","https://openalex.org/W2386387936","https://openalex.org/W3007745445","https://openalex.org/W2477564355"],"abstract_inverted_index":{"As":[0],"multi-modal":[1,150],"systems":[2],"show":[3],"superior":[4],"performance":[5,108],"on":[6],"more":[7],"tasks,":[8],"the":[9,20,37,61,83,88,96,110,128,132,141,149],"huge":[10],"amount":[11],"of":[12,19,40,87,148],"computational":[13],"resources":[14],"they":[15],"need":[16],"becomes":[17],"one":[18],"critical":[21],"problems":[22],"to":[23,35,59,81],"be":[24],"solved.":[25],"In":[26],"this":[27],"work,":[28],"we":[29,99,138],"explore":[30],"neural":[31],"network":[32],"quantization":[33],"methods":[34],"compress":[36],"resource":[38],"requirement":[39],"VisualVoice,":[41],"a":[42,101],"state-of-the-art":[43],"audio-visual":[44],"speech":[45],"separation":[46],"system.":[47,112,151],"The":[48,90,113],"model":[49],"is":[50],"firstly":[51],"fine-tuned":[52],"by":[53,94,144],"an":[54],"ADMM-based":[55],"quantization-aware":[56],"training":[57],"approach":[58],"produce":[60],"fixed-precision":[62,129],"quantized":[63],"version.":[64],"Then":[65],"three":[66],"strategies,":[67],"including":[68],"manual":[69],"selection,":[70],"Hessian":[71],"trace-based":[72],"selection":[73],"and":[74,107,131],"KL":[75,114],"divergence-based":[76,115],"greedy":[77],"search":[78],"are":[79],"explored":[80],"find":[82],"optimal":[84,97],"mixed-precision":[85,135],"setting":[86],"model.":[89],"result":[91],"shows":[92],"that":[93],"applying":[95],"strategy,":[98],"obtain":[100],"satisfying":[102],"trade-off":[103],"between":[104],"space,":[105],"speed":[106],"for":[109],"final":[111],"strategy":[116],"reaches":[117],"7.2":[118],"dB":[119],"in":[120],"SDR":[121],"at":[122],"3-bit":[123],"equivalent":[124],"setup,":[125],"which":[126],"outperforms":[127],"setup":[130],"other":[133],"two":[134],"strategies.":[136],"More-over,":[137],"also":[139],"discuss":[140],"influence":[142],"caused":[143],"quantizing":[145],"different":[146],"parts":[147]},"counts_by_year":[{"year":2024,"cited_by_count":5},{"year":2023,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}