{"id":"https://openalex.org/W4389474152","doi":"https://doi.org/10.1109/taslp.2023.3332545","title":"Wav2code: Restore Clean Speech Representations via Codebook Lookup for Noise-Robust ASR","display_name":"Wav2code: Restore Clean Speech Representations via Codebook Lookup for Noise-Robust ASR","publication_year":2023,"publication_date":"2023-12-08","ids":{"openalex":"https://openalex.org/W4389474152","doi":"https://doi.org/10.1109/taslp.2023.3332545"},"language":"en","primary_location":{"id":"doi:10.1109/taslp.2023.3332545","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taslp.2023.3332545","pdf_url":null,"source":{"id":"https://openalex.org/S4210169297","display_name":"IEEE/ACM Transactions on Audio Speech and Language Processing","issn_l":"2329-9290","issn":["2329-9290","2329-9304"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE/ACM Transactions on Audio, Speech, and Language Processing","raw_type":"journal-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":"https://openalex.org/A5101619807","display_name":"Yuchen Hu","orcid":"https://orcid.org/0000-0002-0696-6434"},"institutions":[{"id":"https://openalex.org/I172675005","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302","country_code":"SG","type":"education","lineage":["https://openalex.org/I172675005"]}],"countries":["SG"],"is_corresponding":true,"raw_author_name":"Yuchen Hu","raw_affiliation_strings":["School of Computer Science and Engineering, Nanyang Technological University (NTU), Singapore"],"raw_orcid":"https://orcid.org/0000-0002-0696-6434","affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering, Nanyang Technological University (NTU), Singapore","institution_ids":["https://openalex.org/I172675005"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101474723","display_name":"Chen Chen","orcid":"https://orcid.org/0000-0003-4181-9285"},"institutions":[{"id":"https://openalex.org/I172675005","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302","country_code":"SG","type":"education","lineage":["https://openalex.org/I172675005"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Chen Chen","raw_affiliation_strings":["School of Computer Science and Engineering, Nanyang Technological University (NTU), Singapore"],"raw_orcid":"https://orcid.org/0000-0003-4181-9285","affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering, Nanyang Technological University (NTU), Singapore","institution_ids":["https://openalex.org/I172675005"]}]},{"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":["National Engineering Research Center of Speech and Language Information Processing (NERC-SLIP), University of Science and Technology of China (USTC), Hefei, China"],"raw_orcid":"https://orcid.org/0000-0002-1196-7781","affiliations":[{"raw_affiliation_string":"National Engineering Research Center of Speech and Language Information Processing (NERC-SLIP), University of Science and Technology of China (USTC), Hefei, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5070872826","display_name":"Eng Siong Chng","orcid":"https://orcid.org/0000-0001-6257-7399"},"institutions":[{"id":"https://openalex.org/I172675005","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302","country_code":"SG","type":"education","lineage":["https://openalex.org/I172675005"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Eng Siong Chng","raw_affiliation_strings":["School of Computer Science and Engineering, Nanyang Technological University (NTU), Singapore"],"raw_orcid":"https://orcid.org/0000-0001-6257-7399","affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering, Nanyang Technological University (NTU), Singapore","institution_ids":["https://openalex.org/I172675005"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5101619807"],"corresponding_institution_ids":["https://openalex.org/I172675005"],"apc_list":null,"apc_paid":null,"fwci":1.8745,"has_fulltext":false,"cited_by_count":11,"citation_normalized_percentile":{"value":0.88746899,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":"32","issue":null,"first_page":"1145","last_page":"1156"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9998999834060669,"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"}},"topics":[{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9998999834060669,"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/T10860","display_name":"Speech and Audio Processing","score":0.9998999834060669,"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":0.9980999827384949,"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/codebook","display_name":"Codebook","score":0.8468099236488342},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7935773134231567},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.6552194356918335},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6165487766265869},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4863665699958801},{"id":"https://openalex.org/keywords/fidelity","display_name":"Fidelity","score":0.464517742395401},{"id":"https://openalex.org/keywords/distortion","display_name":"Distortion (music)","score":0.45956283807754517},{"id":"https://openalex.org/keywords/high-fidelity","display_name":"High fidelity","score":0.444650262594223},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3694317042827606},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.06978374719619751}],"concepts":[{"id":"https://openalex.org/C127759330","wikidata":"https://www.wikidata.org/wiki/Q637416","display_name":"Codebook","level":2,"score":0.8468099236488342},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7935773134231567},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.6552194356918335},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6165487766265869},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4863665699958801},{"id":"https://openalex.org/C2776459999","wikidata":"https://www.wikidata.org/wiki/Q2119376","display_name":"Fidelity","level":2,"score":0.464517742395401},{"id":"https://openalex.org/C126780896","wikidata":"https://www.wikidata.org/wiki/Q899871","display_name":"Distortion (music)","level":4,"score":0.45956283807754517},{"id":"https://openalex.org/C113364801","wikidata":"https://www.wikidata.org/wiki/Q26674","display_name":"High fidelity","level":2,"score":0.444650262594223},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3694317042827606},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.06978374719619751},{"id":"https://openalex.org/C2776257435","wikidata":"https://www.wikidata.org/wiki/Q1576430","display_name":"Bandwidth (computing)","level":2,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0},{"id":"https://openalex.org/C194257627","wikidata":"https://www.wikidata.org/wiki/Q211554","display_name":"Amplifier","level":3,"score":0.0},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","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},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/taslp.2023.3332545","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taslp.2023.3332545","pdf_url":null,"source":{"id":"https://openalex.org/S4210169297","display_name":"IEEE/ACM Transactions on Audio Speech and Language Processing","issn_l":"2329-9290","issn":["2329-9290","2329-9304"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE/ACM Transactions on Audio, Speech, and Language Processing","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":80,"referenced_works":["https://openalex.org/W1494198834","https://openalex.org/W1522301498","https://openalex.org/W1598508708","https://openalex.org/W1965154800","https://openalex.org/W1992475611","https://openalex.org/W2016430046","https://openalex.org/W2024490156","https://openalex.org/W2042141988","https://openalex.org/W2069681747","https://openalex.org/W2080921589","https://openalex.org/W2124509324","https://openalex.org/W2127141656","https://openalex.org/W2141411743","https://openalex.org/W2144499799","https://openalex.org/W2148575186","https://openalex.org/W2160815625","https://openalex.org/W2279516409","https://openalex.org/W2290318471","https://openalex.org/W2296167893","https://openalex.org/W2327501763","https://openalex.org/W2398972335","https://openalex.org/W2516310076","https://openalex.org/W2752796333","https://openalex.org/W2889517470","https://openalex.org/W2892009249","https://openalex.org/W2896457183","https://openalex.org/W2920377649","https://openalex.org/W2936774411","https://openalex.org/W2937484199","https://openalex.org/W2962935966","https://openalex.org/W2972320711","https://openalex.org/W2972412503","https://openalex.org/W2972436155","https://openalex.org/W2981991061","https://openalex.org/W2998161426","https://openalex.org/W3032514799","https://openalex.org/W3041561163","https://openalex.org/W3095311338","https://openalex.org/W3097945073","https://openalex.org/W3097973766","https://openalex.org/W3134695619","https://openalex.org/W3158779859","https://openalex.org/W3163142165","https://openalex.org/W3180355996","https://openalex.org/W3205533980","https://openalex.org/W3206531472","https://openalex.org/W3209059054","https://openalex.org/W3209376089","https://openalex.org/W3209984917","https://openalex.org/W3215615641","https://openalex.org/W4200635400","https://openalex.org/W4205292837","https://openalex.org/W4221140371","https://openalex.org/W4221144097","https://openalex.org/W4225699246","https://openalex.org/W4226390724","https://openalex.org/W4284957875","https://openalex.org/W4297841603","https://openalex.org/W4307323391","https://openalex.org/W4375869189","https://openalex.org/W4376456759","https://openalex.org/W4385822727","https://openalex.org/W6623517193","https://openalex.org/W6631190155","https://openalex.org/W6675365184","https://openalex.org/W6687566353","https://openalex.org/W6729448088","https://openalex.org/W6733814495","https://openalex.org/W6739901393","https://openalex.org/W6766224279","https://openalex.org/W6769238691","https://openalex.org/W6780218876","https://openalex.org/W6780226713","https://openalex.org/W6799474351","https://openalex.org/W6805530253","https://openalex.org/W6810007534","https://openalex.org/W6810673746","https://openalex.org/W6811201773","https://openalex.org/W6839082156","https://openalex.org/W6847363464"],"related_works":["https://openalex.org/W4313443006","https://openalex.org/W2945374968","https://openalex.org/W4385452045","https://openalex.org/W4293777179","https://openalex.org/W2164070813","https://openalex.org/W2135608140","https://openalex.org/W2895525995","https://openalex.org/W2319626700","https://openalex.org/W4319589573","https://openalex.org/W1997070615"],"abstract_inverted_index":{"Automatic":[0],"speech":[1,27,34,50,77,115,235],"recognition":[2],"(ASR)":[3],"has":[4],"gained":[5],"remarkable":[6],"successes":[7],"thanks":[8],"to":[9,32,49,66,98,122,138,146,162,197,206],"recent":[10],"advances":[11],"of":[12,173,182],"deep":[13],"learning,":[14],"but":[15,40],"it":[16],"usually":[17],"degrades":[18],"significantly":[19],"under":[20,241],"real-world":[21],"noisy":[22,175,200,227,243],"conditions.":[23],"Recent":[24],"works":[25,57],"introduce":[26],"enhancement":[28],"(SE)":[29],"as":[30,151],"front-end":[31],"improve":[33,70,238],"quality,":[35,211],"which":[36,177],"is":[37],"proved":[38],"effective":[39],"may":[41],"not":[42],"be":[43,85],"optimal":[44],"for":[45,106,217],"downstream":[46,218],"ASR":[47,239],"due":[48],"distortion":[51,68,78,236],"problem.":[52],"Based":[53],"on":[54,222],"that,":[55],"latest":[56],"combine":[58,198],"SE":[59,82,102],"and":[60,69,170,180,201,210,225,237],"currently":[61],"popular":[62],"self-supervised":[63,94],"learning":[64],"(SSL)":[65],"alleviate":[67],"noise":[71],"robustness.":[72,248],"Despite":[73],"the":[74,76,113,131,140,202,234],"effectiveness,":[75],"caused":[79],"by":[80,167],"conventional":[81],"still":[83],"cannot":[84],"cleared":[86],"out.":[87],"In":[88],"this":[89],"paper,":[90],"we":[91,156,190],"propose":[92,157,191],"a":[93,100,124,158],"framework":[95],"named":[96],"Wav2code":[97,231],"implement":[99],"feature-level":[101],"with":[103,186],"reduced":[104,187],"distortions":[105],"noise-robust":[107],"ASR.":[108,219],"First,":[109],"in":[110,144,149,213,246],"pre-training":[111],"stage":[112],"clean":[114,142,165,184,204],"representations":[116,185,205],"from":[117],"SSL":[118],"model":[119],"are":[120,135],"sent":[121],"lookup":[123],"discrete":[125],"codebook":[126,150],"via":[127],"nearest-neighbor":[128],"feature":[129,194],"matching,":[130],"resulted":[132],"code":[133,160],"sequence":[134],"then":[136],"exploited":[137],"reconstruct":[139],"original":[141,199],"representations,":[143,176],"order":[145],"store":[147],"them":[148],"prior.":[152],"Second,":[153],"during":[154],"finetuning":[155],"Transformer-based":[159],"predictor":[161],"accurately":[163],"predict":[164],"codes":[166],"modeling":[168],"global":[169],"local":[171],"dependency":[172],"input":[174],"enables":[178],"discovery":[179],"restoration":[181],"high-quality":[183],"distortions.":[188],"Furthermore,":[189],"an":[192],"interactive":[193],"fusion":[195],"network":[196],"restored":[203],"consider":[207],"both":[208,223],"fidelity":[209],"resulting":[212,245],"more":[214],"informative":[215],"features":[216],"Finally,":[220],"experiments":[221],"synthetic":[224],"real":[226],"datasets":[228],"demonstrate":[229],"that":[230],"can":[232],"solve":[233],"performance":[240],"various":[242],"conditions,":[244],"stronger":[247]},"counts_by_year":[{"year":2025,"cited_by_count":6},{"year":2024,"cited_by_count":4},{"year":2023,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}