{"id":"https://openalex.org/W4408354918","doi":"https://doi.org/10.1109/icassp49660.2025.10889180","title":"Vector Quantized Diffusion Model Based Speech Bandwidth Extension","display_name":"Vector Quantized Diffusion Model Based Speech Bandwidth Extension","publication_year":2025,"publication_date":"2025-03-12","ids":{"openalex":"https://openalex.org/W4408354918","doi":"https://doi.org/10.1109/icassp49660.2025.10889180"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49660.2025.10889180","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10889180","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2025 - 2025 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/A5108978349","display_name":"Yuan Fang","orcid":null},"institutions":[{"id":"https://openalex.org/I2722730","display_name":"Inner Mongolia University","ror":"https://ror.org/0106qb496","country_code":"CN","type":"education","lineage":["https://openalex.org/I2722730"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuan Fang","raw_affiliation_strings":["Inner Mongolia University,College of Computer Science,Hohhot,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Inner Mongolia University,College of Computer Science,Hohhot,China","institution_ids":["https://openalex.org/I2722730"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5000853510","display_name":"Jing Bai","orcid":"https://orcid.org/0009-0006-4970-1002"},"institutions":[{"id":"https://openalex.org/I2722730","display_name":"Inner Mongolia University","ror":"https://ror.org/0106qb496","country_code":"CN","type":"education","lineage":["https://openalex.org/I2722730"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jinglin Bai","raw_affiliation_strings":["Inner Mongolia University,College of Computer Science,Hohhot,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Inner Mongolia University,College of Computer Science,Hohhot,China","institution_ids":["https://openalex.org/I2722730"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100731831","display_name":"Jiajie Wang","orcid":"https://orcid.org/0000-0003-4054-7898"},"institutions":[{"id":"https://openalex.org/I4210128910","display_name":"Group Sense (China)","ror":"https://ror.org/036wd5777","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210128910"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiajie Wang","raw_affiliation_strings":["SenseTime,SenseAuto Intelligent Connection,Beijing,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"SenseTime,SenseAuto Intelligent Connection,Beijing,China","institution_ids":["https://openalex.org/I4210128910"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100693230","display_name":"Xueliang Zhang","orcid":"https://orcid.org/0000-0002-0406-1105"},"institutions":[{"id":"https://openalex.org/I2722730","display_name":"Inner Mongolia University","ror":"https://ror.org/0106qb496","country_code":"CN","type":"education","lineage":["https://openalex.org/I2722730"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xueliang Zhang","raw_affiliation_strings":["Inner Mongolia University,College of Computer Science,Hohhot,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Inner Mongolia University,College of Computer Science,Hohhot,China","institution_ids":["https://openalex.org/I2722730"]}]}],"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":2,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"5"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10901","display_name":"Advanced Data Compression Techniques","score":0.9902999997138977,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/T10901","display_name":"Advanced Data Compression Techniques","score":0.9902999997138977,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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":0.9549999833106995,"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/bandwidth-extension","display_name":"Bandwidth extension","score":0.8480192422866821},{"id":"https://openalex.org/keywords/extension","display_name":"Extension (predicate logic)","score":0.6540150046348572},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.614485502243042},{"id":"https://openalex.org/keywords/bandwidth","display_name":"Bandwidth (computing)","score":0.5798625946044922},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4834524095058441},{"id":"https://openalex.org/keywords/diffusion","display_name":"Diffusion","score":0.4295497238636017},{"id":"https://openalex.org/keywords/speech-coding","display_name":"Speech coding","score":0.35951608419418335},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.19973784685134888},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.08687686920166016},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.07995188236236572}],"concepts":[{"id":"https://openalex.org/C9387945","wikidata":"https://www.wikidata.org/wiki/Q4854770","display_name":"Bandwidth extension","level":4,"score":0.8480192422866821},{"id":"https://openalex.org/C2778029271","wikidata":"https://www.wikidata.org/wiki/Q5421931","display_name":"Extension (predicate logic)","level":2,"score":0.6540150046348572},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.614485502243042},{"id":"https://openalex.org/C2776257435","wikidata":"https://www.wikidata.org/wiki/Q1576430","display_name":"Bandwidth (computing)","level":2,"score":0.5798625946044922},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4834524095058441},{"id":"https://openalex.org/C69357855","wikidata":"https://www.wikidata.org/wiki/Q163214","display_name":"Diffusion","level":2,"score":0.4295497238636017},{"id":"https://openalex.org/C13895895","wikidata":"https://www.wikidata.org/wiki/Q3270773","display_name":"Speech coding","level":2,"score":0.35951608419418335},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.19973784685134888},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.08687686920166016},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.07995188236236572},{"id":"https://openalex.org/C97355855","wikidata":"https://www.wikidata.org/wiki/Q11473","display_name":"Thermodynamics","level":1,"score":0.0},{"id":"https://openalex.org/C64922751","wikidata":"https://www.wikidata.org/wiki/Q4650799","display_name":"Audio signal","level":3,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49660.2025.10889180","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10889180","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320330944","display_name":"Nature","ror":null}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":21,"referenced_works":["https://openalex.org/W1728888090","https://openalex.org/W3197334236","https://openalex.org/W4221155904","https://openalex.org/W4224133928","https://openalex.org/W4283215837","https://openalex.org/W4293363567","https://openalex.org/W4312388283","https://openalex.org/W4372260387","https://openalex.org/W4392903177","https://openalex.org/W4392903243","https://openalex.org/W4402112499","https://openalex.org/W4408352482","https://openalex.org/W4410087476","https://openalex.org/W6739901393","https://openalex.org/W6772349387","https://openalex.org/W6779823529","https://openalex.org/W6783867762","https://openalex.org/W6798447524","https://openalex.org/W6803444062","https://openalex.org/W6853515095","https://openalex.org/W6868789466"],"related_works":["https://openalex.org/W2059847929","https://openalex.org/W4319862422","https://openalex.org/W1971598839","https://openalex.org/W2011561032","https://openalex.org/W2091360050","https://openalex.org/W1559703345","https://openalex.org/W2133828239","https://openalex.org/W3207737697","https://openalex.org/W2017964352","https://openalex.org/W3144767625"],"abstract_inverted_index":{"Recent":[0],"advancements":[1],"in":[2,10],"neural":[3],"audio":[4,11],"codec":[5],"(NAC)":[6],"unlock":[7],"new":[8],"potential":[9],"signal":[12,27],"processing.":[13],"Studies":[14],"have":[15],"increasingly":[16],"explored":[17],"leveraging":[18],"the":[19,33,43,70,74],"latent":[20],"features":[21,45],"of":[22,76],"NAC":[23],"for":[24],"various":[25],"speech":[26,37,61,86,105],"processing":[28],"tasks.":[29],"This":[30],"paper":[31],"introduces":[32],"first":[34],"approach":[35,59],"to":[36,83],"bandwidth":[38],"extension":[39],"(BWE)":[40],"that":[41,91],"utilizes":[42],"discrete":[44,56],"obtained":[46],"from":[47],"NAC.":[48],"By":[49],"restoring":[50],"high-frequency":[51,85],"details":[52],"within":[53],"highly":[54],"compressed":[55],"tokens,":[57],"this":[58,92],"enhances":[60],"intelligibility":[62],"and":[63,81,101],"naturalness.":[64],"Based":[65],"on":[66],"Vector":[67],"Quantized":[68],"Diffusion,":[69],"proposed":[71],"framework":[72],"combines":[73],"strengths":[75],"advanced":[77],"NAC,":[78],"diffusion":[79],"models,":[80],"Mamba-2":[82],"reconstruct":[84],"components.":[87],"Extensive":[88],"experiments":[89],"demonstrate":[90],"method":[93],"exhibits":[94],"superior":[95],"performance":[96],"across":[97],"both":[98],"log-spectral":[99],"distance":[100],"ViSQOL,":[102],"significantly":[103],"improving":[104],"quality.":[106]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}
