{"id":"https://openalex.org/W4388820651","doi":"https://doi.org/10.1109/apsipaasc58517.2023.10317485","title":"Speech Enhancement with Multi-granularity Vector Quantization","display_name":"Speech Enhancement with Multi-granularity Vector Quantization","publication_year":2023,"publication_date":"2023-10-31","ids":{"openalex":"https://openalex.org/W4388820651","doi":"https://doi.org/10.1109/apsipaasc58517.2023.10317485"},"language":"en","primary_location":{"id":"doi:10.1109/apsipaasc58517.2023.10317485","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/apsipaasc58517.2023.10317485","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 Asia Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)","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/A5052168680","display_name":"Xiaoying Zhao","orcid":"https://orcid.org/0000-0001-7071-3901"},"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":"Xiaoying Zhao","raw_affiliation_strings":["University of Science and Technology of China (USTC),Hefei,China","University of Science and Technology of China (USTC), Hefei, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Science and Technology of China (USTC),Hefei,China","institution_ids":["https://openalex.org/I126520041"]},{"raw_affiliation_string":"University of Science and Technology of China (USTC), Hefei, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5045966396","display_name":"Qiushi Zhu","orcid":"https://orcid.org/0000-0002-1196-7781"},"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":"Qiushi Zhu","raw_affiliation_strings":["University of Science and Technology of China (USTC),NERC-SLIP,Hefei,China","NERC-SLIP, University of Science and Technology of China (USTC), Hefei, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Science and Technology of China (USTC),NERC-SLIP,Hefei,China","institution_ids":["https://openalex.org/I126520041"]},{"raw_affiliation_string":"NERC-SLIP, University of Science and Technology of China (USTC), Hefei, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100436848","display_name":"Jie Zhang","orcid":"https://orcid.org/0000-0003-1124-0854"},"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":"Jie Zhang","raw_affiliation_strings":["University of Science and Technology of China (USTC),NERC-SLIP,Hefei,China","NERC-SLIP, University of Science and Technology of China (USTC), Hefei, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Science and Technology of China (USTC),NERC-SLIP,Hefei,China","institution_ids":["https://openalex.org/I126520041"]},{"raw_affiliation_string":"NERC-SLIP, University of Science and Technology of China (USTC), Hefei, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101829888","display_name":"Yeping Zhou","orcid":"https://orcid.org/0009-0009-6458-3245"},"institutions":[{"id":"https://openalex.org/I917184967","display_name":"Bank of China","ror":"https://ror.org/02mt4s337","country_code":"CN","type":"other","lineage":["https://openalex.org/I917184967"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yeping Zhou","raw_affiliation_strings":["China Merchants Bank"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"China Merchants Bank","institution_ids":["https://openalex.org/I917184967"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5004561226","display_name":"Peiqi Liu","orcid":"https://orcid.org/0000-0002-0035-2458"},"institutions":[{"id":"https://openalex.org/I917184967","display_name":"Bank of China","ror":"https://ror.org/02mt4s337","country_code":"CN","type":"other","lineage":["https://openalex.org/I917184967"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Peiqi Liu","raw_affiliation_strings":["China Merchants Bank"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"China Merchants Bank","institution_ids":["https://openalex.org/I917184967"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":"32","issue":null,"first_page":"1937","last_page":"1942"},"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":0.9986000061035156,"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":0.9950000047683716,"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/vector-quantization","display_name":"Vector quantization","score":0.8096417784690857},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7300609946250916},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7004059553146362},{"id":"https://openalex.org/keywords/granularity","display_name":"Granularity","score":0.6823614835739136},{"id":"https://openalex.org/keywords/speech-enhancement","display_name":"Speech enhancement","score":0.6583364009857178},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.6270934343338013},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.5202549695968628},{"id":"https://openalex.org/keywords/speech-coding","display_name":"Speech coding","score":0.5173668265342712},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.505526065826416},{"id":"https://openalex.org/keywords/quantization","display_name":"Quantization (signal processing)","score":0.4979276657104492},{"id":"https://openalex.org/keywords/discretization","display_name":"Discretization","score":0.4748837351799011},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.4741460680961609},{"id":"https://openalex.org/keywords/codebook","display_name":"Codebook","score":0.46577024459838867},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.45711401104927063},{"id":"https://openalex.org/keywords/learning-vector-quantization","display_name":"Learning vector quantization","score":0.44275814294815063},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.4155917167663574},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.38901668787002563},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.17706531286239624},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.12095925211906433}],"concepts":[{"id":"https://openalex.org/C199833920","wikidata":"https://www.wikidata.org/wiki/Q612536","display_name":"Vector quantization","level":2,"score":0.8096417784690857},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7300609946250916},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7004059553146362},{"id":"https://openalex.org/C177774035","wikidata":"https://www.wikidata.org/wiki/Q1246948","display_name":"Granularity","level":2,"score":0.6823614835739136},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.6583364009857178},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.6270934343338013},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.5202549695968628},{"id":"https://openalex.org/C13895895","wikidata":"https://www.wikidata.org/wiki/Q3270773","display_name":"Speech coding","level":2,"score":0.5173668265342712},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.505526065826416},{"id":"https://openalex.org/C28855332","wikidata":"https://www.wikidata.org/wiki/Q198099","display_name":"Quantization (signal processing)","level":2,"score":0.4979276657104492},{"id":"https://openalex.org/C73000952","wikidata":"https://www.wikidata.org/wiki/Q17007827","display_name":"Discretization","level":2,"score":0.4748837351799011},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.4741460680961609},{"id":"https://openalex.org/C127759330","wikidata":"https://www.wikidata.org/wiki/Q637416","display_name":"Codebook","level":2,"score":0.46577024459838867},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.45711401104927063},{"id":"https://openalex.org/C40567965","wikidata":"https://www.wikidata.org/wiki/Q1820283","display_name":"Learning vector quantization","level":3,"score":0.44275814294815063},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.4155917167663574},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.38901668787002563},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.17706531286239624},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.12095925211906433},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/apsipaasc58517.2023.10317485","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/apsipaasc58517.2023.10317485","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 Asia Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions","score":0.5}],"awards":[],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":38,"referenced_works":["https://openalex.org/W2141998673","https://openalex.org/W2144404214","https://openalex.org/W2296167893","https://openalex.org/W2547875792","https://openalex.org/W2746457594","https://openalex.org/W2757519008","https://openalex.org/W2802304149","https://openalex.org/W2921144622","https://openalex.org/W2952218014","https://openalex.org/W2963341071","https://openalex.org/W2998832642","https://openalex.org/W3016912202","https://openalex.org/W3017350693","https://openalex.org/W3096408984","https://openalex.org/W3097945073","https://openalex.org/W3099330747","https://openalex.org/W3102190437","https://openalex.org/W3196965931","https://openalex.org/W3209059054","https://openalex.org/W4205955626","https://openalex.org/W4221140371","https://openalex.org/W4221162870","https://openalex.org/W4224933800","https://openalex.org/W4226132755","https://openalex.org/W4226403810","https://openalex.org/W4284957875","https://openalex.org/W4289242435","https://openalex.org/W4297841605","https://openalex.org/W4312095873","https://openalex.org/W4312388283","https://openalex.org/W4376456759","https://openalex.org/W6729448088","https://openalex.org/W6744762798","https://openalex.org/W6756251360","https://openalex.org/W6762114000","https://openalex.org/W6762931180","https://openalex.org/W6780218876","https://openalex.org/W6810007534"],"related_works":["https://openalex.org/W2148772884","https://openalex.org/W2017514583","https://openalex.org/W2100120615","https://openalex.org/W2147406819","https://openalex.org/W1929869830","https://openalex.org/W2387054321","https://openalex.org/W2352648934","https://openalex.org/W2170599662","https://openalex.org/W2145213141","https://openalex.org/W2377001183"],"abstract_inverted_index":{"Neural":[0],"network":[1],"based":[2],"speech":[3,49,54,83],"enhancement":[4],"(SE)":[5],"has":[6,22],"developed":[7],"rapidly":[8],"in":[9,56],"the":[10,14,62,89,100,105,118,124,129,134,138],"last":[11],"decade.":[12],"Meanwhile,":[13],"self-supervised":[15],"pre-trained":[16,95,142],"model":[17,96,131],"and":[18,111],"vector":[19],"quantization":[20],"(VQ)":[21],"achieved":[23],"excellent":[24],"performance":[25],"on":[26,35,123],"many":[27],"speech-related":[28],"tasks,":[29],"while":[30],"they":[31],"are":[32,97,114],"less":[33],"explored":[34],"SE.":[36],"As":[37],"it":[38],"was":[39],"shown":[40],"that":[41,108,128],"utilizing":[42],"a":[43,94],"VQ":[44,66,76],"module":[45],"to":[46,80,116],"discretize":[47],"noisy":[48],"representation":[50],"is":[51,144],"beneficial":[52],"for":[53],"denoising,":[55],"this":[57],"work":[58],"we":[59],"therefore":[60],"study":[61],"impact":[63,139],"of":[64,73,140],"using":[65],"at":[67],"different":[68,71],"layers":[69],"with":[70,99],"number":[72],"codebooks.":[74],"Different":[75],"modules":[77],"indeed":[78],"enable":[79],"extract":[81],"multiple-granularity":[82],"features.":[84],"Following":[85],"an":[86],"attention":[87],"mechanism,":[88],"contextual":[90],"features":[91,102],"extracted":[92,103],"by":[93,104],"fused":[98],"local":[101,112],"encoder,":[106],"such":[107],"both":[109],"global":[110],"information":[113],"preserved":[115],"reconstruct":[117],"enhanced":[119],"speech.":[120],"Experimental":[121],"results":[122],"Valentini":[125],"dataset":[126],"show":[127],"proposed":[130],"can":[132],"improve":[133],"SE":[135],"performance,":[136],"where":[137],"choosing":[141],"models":[143],"also":[145],"revealed.":[146]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}