{"id":"https://openalex.org/W4413125390","doi":"https://doi.org/10.1109/lsp.2025.3596826","title":"Token-Prediction-Based Post-Processing for Low-Bitrate Speech Coding","display_name":"Token-Prediction-Based Post-Processing for Low-Bitrate Speech Coding","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4413125390","doi":"https://doi.org/10.1109/lsp.2025.3596826"},"language":"en","primary_location":{"id":"doi:10.1109/lsp.2025.3596826","is_oa":false,"landing_page_url":"https://doi.org/10.1109/lsp.2025.3596826","pdf_url":null,"source":{"id":"https://openalex.org/S120629676","display_name":"IEEE Signal Processing Letters","issn_l":"1070-9908","issn":["1070-9908","1558-2361"],"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 Signal Processing Letters","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/A5115602455","display_name":"Fei Liu","orcid":"https://orcid.org/0000-0002-9814-4226"},"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":"Fei Liu","raw_affiliation_strings":["National Engineering Research Center of Speech and Language Information Processing, University of Science and Technology of China, Hefei, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Engineering Research Center of Speech and Language Information Processing, University of Science and Technology of China, Hefei, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5045907056","display_name":"Yang Ai","orcid":"https://orcid.org/0000-0001-6668-022X"},"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":"Yang Ai","raw_affiliation_strings":["National Engineering Research Center of Speech and Language Information Processing, University of Science and Technology of China, Hefei, China"],"raw_orcid":"https://orcid.org/0000-0001-6668-022X","affiliations":[{"raw_affiliation_string":"National Engineering Research Center of Speech and Language Information Processing, University of Science and Technology of China, Hefei, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5059767940","display_name":"Zhen-Hua Ling","orcid":"https://orcid.org/0000-0001-7853-5273"},"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":"Zhen-Hua Ling","raw_affiliation_strings":["National Engineering Research Center of Speech and Language Information Processing, University of Science and Technology of China, Hefei, China"],"raw_orcid":"https://orcid.org/0000-0001-7853-5273","affiliations":[{"raw_affiliation_string":"National Engineering Research Center of Speech and Language Information Processing, University of Science and Technology of China, Hefei, China","institution_ids":["https://openalex.org/I126520041"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.15817117,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"32","issue":null,"first_page":"3235","last_page":"3239"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10901","display_name":"Advanced Data Compression Techniques","score":0.9984999895095825,"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":0.9984999895095825,"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":0.9879000186920166,"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":0.9729999899864197,"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":0.753719687461853},{"id":"https://openalex.org/keywords/speech-coding","display_name":"Speech coding","score":0.7446996569633484},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6627868413925171},{"id":"https://openalex.org/keywords/linear-predictive-coding","display_name":"Linear predictive coding","score":0.6204718351364136},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.5277584195137024},{"id":"https://openalex.org/keywords/codec2","display_name":"Codec2","score":0.522839367389679},{"id":"https://openalex.org/keywords/voice-activity-detection","display_name":"Voice activity detection","score":0.4805338978767395},{"id":"https://openalex.org/keywords/coding","display_name":"Coding (social sciences)","score":0.46447479724884033},{"id":"https://openalex.org/keywords/transform-coding","display_name":"Transform coding","score":0.4594673812389374},{"id":"https://openalex.org/keywords/sub-band-coding","display_name":"Sub-band coding","score":0.44748127460479736},{"id":"https://openalex.org/keywords/security-token","display_name":"Security token","score":0.4433172941207886},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.28532254695892334},{"id":"https://openalex.org/keywords/discrete-cosine-transform","display_name":"Discrete cosine transform","score":0.24843713641166687},{"id":"https://openalex.org/keywords/computer-network","display_name":"Computer network","score":0.1343614161014557},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.11181333661079407},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.08619734644889832}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.753719687461853},{"id":"https://openalex.org/C13895895","wikidata":"https://www.wikidata.org/wiki/Q3270773","display_name":"Speech coding","level":2,"score":0.7446996569633484},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6627868413925171},{"id":"https://openalex.org/C59883199","wikidata":"https://www.wikidata.org/wiki/Q1826438","display_name":"Linear predictive coding","level":3,"score":0.6204718351364136},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.5277584195137024},{"id":"https://openalex.org/C75217168","wikidata":"https://www.wikidata.org/wiki/Q1105653","display_name":"Codec2","level":4,"score":0.522839367389679},{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.4805338978767395},{"id":"https://openalex.org/C179518139","wikidata":"https://www.wikidata.org/wiki/Q5140297","display_name":"Coding (social sciences)","level":2,"score":0.46447479724884033},{"id":"https://openalex.org/C169805256","wikidata":"https://www.wikidata.org/wiki/Q1361381","display_name":"Transform coding","level":4,"score":0.4594673812389374},{"id":"https://openalex.org/C98526533","wikidata":"https://www.wikidata.org/wiki/Q1691938","display_name":"Sub-band coding","level":3,"score":0.44748127460479736},{"id":"https://openalex.org/C48145219","wikidata":"https://www.wikidata.org/wiki/Q1335365","display_name":"Security token","level":2,"score":0.4433172941207886},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.28532254695892334},{"id":"https://openalex.org/C2221639","wikidata":"https://www.wikidata.org/wiki/Q2877","display_name":"Discrete cosine transform","level":3,"score":0.24843713641166687},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.1343614161014557},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.11181333661079407},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.08619734644889832},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/lsp.2025.3596826","is_oa":false,"landing_page_url":"https://doi.org/10.1109/lsp.2025.3596826","pdf_url":null,"source":{"id":"https://openalex.org/S120629676","display_name":"IEEE Signal Processing Letters","issn_l":"1070-9908","issn":["1070-9908","1558-2361"],"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 Signal Processing Letters","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G2545034164","display_name":null,"funder_award_id":"2308085QF200","funder_id":"https://openalex.org/F4320334897","funder_display_name":"Natural Science Foundation of Anhui Province"},{"id":"https://openalex.org/G5861301885","display_name":null,"funder_award_id":"62301521","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320334897","display_name":"Natural Science Foundation of Anhui Province","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":20,"referenced_works":["https://openalex.org/W2126441393","https://openalex.org/W2131094339","https://openalex.org/W2809824582","https://openalex.org/W2972359262","https://openalex.org/W3015780049","https://openalex.org/W3016057201","https://openalex.org/W3097945073","https://openalex.org/W3188073270","https://openalex.org/W3196475561","https://openalex.org/W4225302959","https://openalex.org/W4225860133","https://openalex.org/W4225956675","https://openalex.org/W4252812408","https://openalex.org/W4375869380","https://openalex.org/W4395447416","https://openalex.org/W4399875170","https://openalex.org/W4403918744","https://openalex.org/W4406461725","https://openalex.org/W4408353418","https://openalex.org/W4410314146"],"related_works":["https://openalex.org/W137020845","https://openalex.org/W1542588102","https://openalex.org/W2151333624","https://openalex.org/W4319347033","https://openalex.org/W1572861854","https://openalex.org/W2910493550","https://openalex.org/W2539491809","https://openalex.org/W1976952689","https://openalex.org/W2496295964","https://openalex.org/W2336887028"],"abstract_inverted_index":{"Low-bitrate":[0],"speech":[1,8,13,64,113,137],"coding":[2,22],"plays":[3],"an":[4],"essential":[5],"role":[6],"in":[7],"transmission":[9],"and":[10,55,74,105,115],"storage.":[11],"However,":[12],"quality":[14,37,114],"degrades":[15],"noticeably":[16],"at":[17,123],"low":[18],"bitrates":[19],"with":[20],"current":[21],"methods.":[23],"Therefore,":[24],"this":[25],"letter":[26],"proposes":[27],"a":[28,48,71,82,109],"novel":[29],"Token-Prediction-based":[30],"Post-Processing":[31],"(T3P)":[32],"model":[33],"to":[34,94],"improve":[35],"the":[36,53,77,96],"of":[38,57],"low-bitrate":[39,62],"coded":[40,63],"speech.":[41,98],"Unlike":[42],"existing":[43],"post-processing":[44],"methods,":[45],"T3P":[46,68,102],"is":[47,91],"discrete-domain":[49],"method":[50],"centered":[51],"on":[52],"prediction":[54],"classification":[56],"discrete":[58],"tokens.":[59],"Specifically,":[60],"given":[61],"features":[65],"as":[66],"condition,":[67],"initiates":[69],"from":[70],"random":[72],"token":[73,78],"sequentially":[75],"predicts":[76],"sequences":[79],"produced":[80],"by":[81,118],"residual":[83],"vector":[84],"quantization":[85],"(RVQ)":[86],"based":[87],"neural":[88],"codec,":[89],"which":[90],"subsequently":[92],"decoded":[93],"reconstruct":[95],"raw":[97],"Experiments":[99],"confirm":[100],"that":[101,127],"surpasses":[103],"flow-matching-based":[104],"speech-enhancement-based":[106],"baselines,":[107],"achieving":[108],"better":[110],"trade-off":[111],"between":[112],"efficiency.":[116],"Empowered":[117],"T3P,":[119],"Encodec":[120],"achieves":[121],"performance":[122],"just":[124],"0.5":[125],"kbps":[126,132],"exceeds":[128],"its":[129],"original":[130],"4":[131],"results":[133],"for":[134],"16":[135],"kHz":[136],"coding.":[138]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}