{"id":"https://openalex.org/W4392909571","doi":"https://doi.org/10.1109/icassp48485.2024.10447464","title":"SELM: Speech Enhancement using Discrete Tokens and Language Models","display_name":"SELM: Speech Enhancement using Discrete Tokens and Language Models","publication_year":2024,"publication_date":"2024-03-18","ids":{"openalex":"https://openalex.org/W4392909571","doi":"https://doi.org/10.1109/icassp48485.2024.10447464"},"language":"en","primary_location":{"id":"doi:10.1109/icassp48485.2024.10447464","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp48485.2024.10447464","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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/A5100332224","display_name":"Ziqian Wang","orcid":"https://orcid.org/0000-0002-0282-5941"},"institutions":[{"id":"https://openalex.org/I17145004","display_name":"Northwestern Polytechnical University","ror":"https://ror.org/01y0j0j86","country_code":"CN","type":"education","lineage":["https://openalex.org/I17145004"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ziqian Wang","raw_affiliation_strings":["Northwestern Polytechnical University,Audio, Speech and Language Processing Group (ASLP@NPU), School of Computer Science,Xian,China","Audio, Speech and Language Processing Group (ASLP@NPU), School of Computer Science, Northwestern Polytechnical University, Xian, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Northwestern Polytechnical University,Audio, Speech and Language Processing Group (ASLP@NPU), School of Computer Science,Xian,China","institution_ids":["https://openalex.org/I17145004"]},{"raw_affiliation_string":"Audio, Speech and Language Processing Group (ASLP@NPU), School of Computer Science, Northwestern Polytechnical University, Xian, China","institution_ids":["https://openalex.org/I17145004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101883211","display_name":"Xinfa Zhu","orcid":"https://orcid.org/0000-0001-9275-523X"},"institutions":[{"id":"https://openalex.org/I17145004","display_name":"Northwestern Polytechnical University","ror":"https://ror.org/01y0j0j86","country_code":"CN","type":"education","lineage":["https://openalex.org/I17145004"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xinfa Zhu","raw_affiliation_strings":["Northwestern Polytechnical University,Audio, Speech and Language Processing Group (ASLP@NPU), School of Computer Science,Xian,China","Audio, Speech and Language Processing Group (ASLP@NPU), School of Computer Science, Northwestern Polytechnical University, Xian, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Northwestern Polytechnical University,Audio, Speech and Language Processing Group (ASLP@NPU), School of Computer Science,Xian,China","institution_ids":["https://openalex.org/I17145004"]},{"raw_affiliation_string":"Audio, Speech and Language Processing Group (ASLP@NPU), School of Computer Science, Northwestern Polytechnical University, Xian, China","institution_ids":["https://openalex.org/I17145004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100410545","display_name":"Zihan Zhang","orcid":"https://orcid.org/0000-0002-0415-7721"},"institutions":[{"id":"https://openalex.org/I17145004","display_name":"Northwestern Polytechnical University","ror":"https://ror.org/01y0j0j86","country_code":"CN","type":"education","lineage":["https://openalex.org/I17145004"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zihan Zhang","raw_affiliation_strings":["Northwestern Polytechnical University,Audio, Speech and Language Processing Group (ASLP@NPU), School of Computer Science,Xian,China","Audio, Speech and Language Processing Group (ASLP@NPU), School of Computer Science, Northwestern Polytechnical University, Xian, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Northwestern Polytechnical University,Audio, Speech and Language Processing Group (ASLP@NPU), School of Computer Science,Xian,China","institution_ids":["https://openalex.org/I17145004"]},{"raw_affiliation_string":"Audio, Speech and Language Processing Group (ASLP@NPU), School of Computer Science, Northwestern Polytechnical University, Xian, China","institution_ids":["https://openalex.org/I17145004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5111149107","display_name":"YuanJun Lv","orcid":null},"institutions":[{"id":"https://openalex.org/I17145004","display_name":"Northwestern Polytechnical University","ror":"https://ror.org/01y0j0j86","country_code":"CN","type":"education","lineage":["https://openalex.org/I17145004"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"YuanJun Lv","raw_affiliation_strings":["Northwestern Polytechnical University,Audio, Speech and Language Processing Group (ASLP@NPU), School of Computer Science,Xian,China","Audio, Speech and Language Processing Group (ASLP@NPU), School of Computer Science, Northwestern Polytechnical University, Xian, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Northwestern Polytechnical University,Audio, Speech and Language Processing Group (ASLP@NPU), School of Computer Science,Xian,China","institution_ids":["https://openalex.org/I17145004"]},{"raw_affiliation_string":"Audio, Speech and Language Processing Group (ASLP@NPU), School of Computer Science, Northwestern Polytechnical University, Xian, China","institution_ids":["https://openalex.org/I17145004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101759345","display_name":"Ning Jiang","orcid":"https://orcid.org/0000-0003-0794-7996"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ning Jiang","raw_affiliation_strings":["Mashang Consumer Finance Co., Ltd"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Mashang Consumer Finance Co., Ltd","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100628448","display_name":"Guoqing Zhao","orcid":"https://orcid.org/0000-0001-7130-7147"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Guoqing Zhao","raw_affiliation_strings":["Mashang Consumer Finance Co., Ltd"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Mashang Consumer Finance Co., Ltd","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100668966","display_name":"Lei Xie","orcid":"https://orcid.org/0000-0001-8234-0823"},"institutions":[{"id":"https://openalex.org/I17145004","display_name":"Northwestern Polytechnical University","ror":"https://ror.org/01y0j0j86","country_code":"CN","type":"education","lineage":["https://openalex.org/I17145004"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lei Xie","raw_affiliation_strings":["Northwestern Polytechnical University,Audio, Speech and Language Processing Group (ASLP@NPU), School of Computer Science,Xian,China","Audio, Speech and Language Processing Group (ASLP@NPU), School of Computer Science, Northwestern Polytechnical University, Xian, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Northwestern Polytechnical University,Audio, Speech and Language Processing Group (ASLP@NPU), School of Computer Science,Xian,China","institution_ids":["https://openalex.org/I17145004"]},{"raw_affiliation_string":"Audio, Speech and Language Processing Group (ASLP@NPU), School of Computer Science, Northwestern Polytechnical University, Xian, China","institution_ids":["https://openalex.org/I17145004"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":26,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"11561","last_page":"11565"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9973000288009644,"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":0.9973000288009644,"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":0.9943000078201294,"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/T12031","display_name":"Speech and dialogue systems","score":0.954200029373169,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7329177260398865},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.48951733112335205},{"id":"https://openalex.org/keywords/speech-enhancement","display_name":"Speech enhancement","score":0.4789296090602875},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.46529802680015564},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4455384910106659},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.43271923065185547}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7329177260398865},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.48951733112335205},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.4789296090602875},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.46529802680015564},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4455384910106659},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.43271923065185547},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp48485.2024.10447464","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp48485.2024.10447464","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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":48,"referenced_works":["https://openalex.org/W2094721231","https://openalex.org/W2144404214","https://openalex.org/W2299467264","https://openalex.org/W2696967604","https://openalex.org/W2952218014","https://openalex.org/W2963341071","https://openalex.org/W2972541922","https://openalex.org/W2980451698","https://openalex.org/W3011982609","https://openalex.org/W3024869864","https://openalex.org/W3027008958","https://openalex.org/W3093990297","https://openalex.org/W3097777922","https://openalex.org/W3097945073","https://openalex.org/W3099330747","https://openalex.org/W3131332223","https://openalex.org/W3161480375","https://openalex.org/W3174264304","https://openalex.org/W3197042120","https://openalex.org/W3197478142","https://openalex.org/W3197580070","https://openalex.org/W3198694222","https://openalex.org/W3209984917","https://openalex.org/W4221144097","https://openalex.org/W4232282348","https://openalex.org/W4297841790","https://openalex.org/W4313679638","https://openalex.org/W4319862462","https://openalex.org/W4372259751","https://openalex.org/W4379539302","https://openalex.org/W4381786045","https://openalex.org/W4382603054","https://openalex.org/W4384080510","https://openalex.org/W4385245566","https://openalex.org/W4385822255","https://openalex.org/W4387634372","https://openalex.org/W4394671563","https://openalex.org/W4400111385","https://openalex.org/W6678914141","https://openalex.org/W6777776875","https://openalex.org/W6778883912","https://openalex.org/W6783867762","https://openalex.org/W6784457260","https://openalex.org/W6790356757","https://openalex.org/W6848735303","https://openalex.org/W6852859116","https://openalex.org/W6853888607","https://openalex.org/W6857478255"],"related_works":["https://openalex.org/W1630865680","https://openalex.org/W2373767407","https://openalex.org/W2169518243","https://openalex.org/W2516933085","https://openalex.org/W3168109306","https://openalex.org/W3204019825","https://openalex.org/W3096184950","https://openalex.org/W4231424160","https://openalex.org/W2275432853","https://openalex.org/W197907117"],"abstract_inverted_index":{"Language":[0,86],"models":[1,81,87],"(LMs)":[2],"have":[3],"recently":[4],"shown":[5],"superior":[6,118],"performances":[7],"in":[8,114],"various":[9],"speech":[10,26,29,37,49],"generation":[11,27],"tasks,":[12],"demonstrating":[13],"their":[14],"powerful":[15],"ability":[16],"for":[17,36],"semantic":[18,32],"context":[19],"modeling.":[20],"Given":[21],"the":[22],"intrinsic":[23],"similarity":[24],"between":[25],"and":[28,56,66,82,99,117],"enhancement,":[30],"harnessing":[31],"information":[33,92],"is":[34],"advantageous":[35],"enhancement":[38,50],"tasks.":[39],"In":[40],"light":[41],"of":[42],"this,":[43],"we":[44],"propose":[45],"SELM,":[46],"a":[47,83,97],"novel":[48],"paradigm":[51],"that":[52,109],"integrates":[53],"discrete":[54,74],"tokens":[55,75],"leverages":[57],"language":[58],"models.":[59],"SELM":[60,110],"comprises":[61],"three":[62],"stages:":[63],"encoding,":[64],"modeling,":[65],"decoding.":[67],"We":[68],"transform":[69],"continuous":[70],"waveform":[71],"signals":[72],"into":[73,103],"using":[76],"pre-trained":[77],"self-supervised":[78],"learning":[79],"(SSL)":[80],"k-means":[84],"tokenizer.":[85],"then":[88],"capture":[89],"comprehensive":[90],"contextual":[91],"within":[93],"these":[94],"tokens.":[95],"Finally,":[96],"de-tokenizer":[98],"HiFi-GAN":[100],"restore":[101],"them":[102],"enhanced":[104],"speech.":[105],"Experimental":[106],"results":[107],"demonstrate":[108],"achieves":[111],"comparable":[112],"performance":[113],"objective":[115],"metrics":[116],"subjective":[119],"perception":[120],"results.":[121],"Our":[122],"demos":[123],"are":[124],"available":[125],"<sup":[126],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[127],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">1</sup>":[128],".":[129]},"counts_by_year":[{"year":2026,"cited_by_count":13},{"year":2025,"cited_by_count":12},{"year":2024,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}
