{"id":"https://openalex.org/W4408352440","doi":"https://doi.org/10.1109/icassp49660.2025.10888202","title":"Low Frame-rate Speech Codec: a Codec Designed for Fast High-quality Speech LLM Training and Inference","display_name":"Low Frame-rate Speech Codec: a Codec Designed for Fast High-quality Speech LLM Training and Inference","publication_year":2025,"publication_date":"2025-03-12","ids":{"openalex":"https://openalex.org/W4408352440","doi":"https://doi.org/10.1109/icassp49660.2025.10888202"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49660.2025.10888202","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10888202","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":"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/A5025318789","display_name":"Edresson Casanova","orcid":"https://orcid.org/0000-0003-0160-7173"},"institutions":[{"id":"https://openalex.org/I4210127875","display_name":"Nvidia (United States)","ror":"https://ror.org/03jdj4y14","country_code":"US","type":"company","lineage":["https://openalex.org/I4210127875"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Edresson Casanova","raw_affiliation_strings":["NVIDIA Corporation"],"affiliations":[{"raw_affiliation_string":"NVIDIA Corporation","institution_ids":["https://openalex.org/I4210127875"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5040023052","display_name":"Ryan Langman","orcid":null},"institutions":[{"id":"https://openalex.org/I4210127875","display_name":"Nvidia (United States)","ror":"https://ror.org/03jdj4y14","country_code":"US","type":"company","lineage":["https://openalex.org/I4210127875"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ryan Langman","raw_affiliation_strings":["NVIDIA Corporation"],"affiliations":[{"raw_affiliation_string":"NVIDIA Corporation","institution_ids":["https://openalex.org/I4210127875"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5030710635","display_name":"Paarth Neekhara","orcid":"https://orcid.org/0009-0002-8598-0353"},"institutions":[{"id":"https://openalex.org/I4210127875","display_name":"Nvidia (United States)","ror":"https://ror.org/03jdj4y14","country_code":"US","type":"company","lineage":["https://openalex.org/I4210127875"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Paarth Neekhara","raw_affiliation_strings":["NVIDIA Corporation"],"affiliations":[{"raw_affiliation_string":"NVIDIA Corporation","institution_ids":["https://openalex.org/I4210127875"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5015232966","display_name":"Shehzeen Hussain","orcid":"https://orcid.org/0000-0003-4693-2113"},"institutions":[{"id":"https://openalex.org/I4210127875","display_name":"Nvidia (United States)","ror":"https://ror.org/03jdj4y14","country_code":"US","type":"company","lineage":["https://openalex.org/I4210127875"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Shehzeen Hussain","raw_affiliation_strings":["NVIDIA Corporation"],"affiliations":[{"raw_affiliation_string":"NVIDIA Corporation","institution_ids":["https://openalex.org/I4210127875"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100762970","display_name":"Jason Li","orcid":"https://orcid.org/0000-0002-1150-3549"},"institutions":[{"id":"https://openalex.org/I4210127875","display_name":"Nvidia (United States)","ror":"https://ror.org/03jdj4y14","country_code":"US","type":"company","lineage":["https://openalex.org/I4210127875"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jason Li","raw_affiliation_strings":["NVIDIA Corporation"],"affiliations":[{"raw_affiliation_string":"NVIDIA Corporation","institution_ids":["https://openalex.org/I4210127875"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101935896","display_name":"Subhankar Ghosh","orcid":"https://orcid.org/0000-0001-9191-5684"},"institutions":[{"id":"https://openalex.org/I4210127875","display_name":"Nvidia (United States)","ror":"https://ror.org/03jdj4y14","country_code":"US","type":"company","lineage":["https://openalex.org/I4210127875"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Subhankar Ghosh","raw_affiliation_strings":["NVIDIA Corporation"],"affiliations":[{"raw_affiliation_string":"NVIDIA Corporation","institution_ids":["https://openalex.org/I4210127875"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5063860258","display_name":"Ante Juki\u0107","orcid":"https://orcid.org/0000-0003-2202-2203"},"institutions":[{"id":"https://openalex.org/I4210127875","display_name":"Nvidia (United States)","ror":"https://ror.org/03jdj4y14","country_code":"US","type":"company","lineage":["https://openalex.org/I4210127875"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ante Juki\u0107","raw_affiliation_strings":["NVIDIA Corporation"],"affiliations":[{"raw_affiliation_string":"NVIDIA Corporation","institution_ids":["https://openalex.org/I4210127875"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5114608942","display_name":"Sang\u2010Gil Lee","orcid":"https://orcid.org/0000-0002-1981-056X"},"institutions":[{"id":"https://openalex.org/I4210127875","display_name":"Nvidia (United States)","ror":"https://ror.org/03jdj4y14","country_code":"US","type":"company","lineage":["https://openalex.org/I4210127875"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Sang-Gil Lee","raw_affiliation_strings":["NVIDIA Corporation"],"affiliations":[{"raw_affiliation_string":"NVIDIA Corporation","institution_ids":["https://openalex.org/I4210127875"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":8,"corresponding_author_ids":["https://openalex.org/A5025318789"],"corresponding_institution_ids":["https://openalex.org/I4210127875"],"apc_list":null,"apc_paid":null,"fwci":6.5456,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.957799,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":95,"max":98},"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9811000227928162,"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":0.9811000227928162,"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/T10901","display_name":"Advanced Data Compression Techniques","score":0.95169997215271,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/codec","display_name":"Codec","score":0.901165246963501},{"id":"https://openalex.org/keywords/adaptive-multi-rate-audio-codec","display_name":"Adaptive Multi-Rate audio codec","score":0.8846442699432373},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8209570646286011},{"id":"https://openalex.org/keywords/codec2","display_name":"Codec2","score":0.7837722897529602},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6824185252189636},{"id":"https://openalex.org/keywords/speech-coding","display_name":"Speech coding","score":0.6582825779914856},{"id":"https://openalex.org/keywords/psqm","display_name":"PSQM","score":0.6563190817832947},{"id":"https://openalex.org/keywords/voice-activity-detection","display_name":"Voice activity detection","score":0.5537570118904114},{"id":"https://openalex.org/keywords/full-rate","display_name":"Full Rate","score":0.5301355123519897},{"id":"https://openalex.org/keywords/speech-enhancement","display_name":"Speech enhancement","score":0.5153552889823914},{"id":"https://openalex.org/keywords/training","display_name":"Training (meteorology)","score":0.4992668628692627},{"id":"https://openalex.org/keywords/frame","display_name":"Frame (networking)","score":0.4876478910446167},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.4796105623245239},{"id":"https://openalex.org/keywords/intra-frame","display_name":"Intra-frame","score":0.4716740548610687},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.384324848651886},{"id":"https://openalex.org/keywords/linear-predictive-coding","display_name":"Linear predictive coding","score":0.3530231714248657},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.2674410939216614},{"id":"https://openalex.org/keywords/computer-hardware","display_name":"Computer hardware","score":0.15102168917655945},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.11794576048851013},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.11050716042518616}],"concepts":[{"id":"https://openalex.org/C161765866","wikidata":"https://www.wikidata.org/wiki/Q184748","display_name":"Codec","level":2,"score":0.901165246963501},{"id":"https://openalex.org/C177067256","wikidata":"https://www.wikidata.org/wiki/Q4676210","display_name":"Adaptive Multi-Rate audio codec","level":4,"score":0.8846442699432373},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8209570646286011},{"id":"https://openalex.org/C75217168","wikidata":"https://www.wikidata.org/wiki/Q1105653","display_name":"Codec2","level":4,"score":0.7837722897529602},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6824185252189636},{"id":"https://openalex.org/C13895895","wikidata":"https://www.wikidata.org/wiki/Q3270773","display_name":"Speech coding","level":2,"score":0.6582825779914856},{"id":"https://openalex.org/C108699837","wikidata":"https://www.wikidata.org/wiki/Q7120750","display_name":"PSQM","level":4,"score":0.6563190817832947},{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.5537570118904114},{"id":"https://openalex.org/C197477341","wikidata":"https://www.wikidata.org/wiki/Q2532845","display_name":"Full Rate","level":3,"score":0.5301355123519897},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.5153552889823914},{"id":"https://openalex.org/C2777211547","wikidata":"https://www.wikidata.org/wiki/Q17141490","display_name":"Training (meteorology)","level":2,"score":0.4992668628692627},{"id":"https://openalex.org/C126042441","wikidata":"https://www.wikidata.org/wiki/Q1324888","display_name":"Frame (networking)","level":2,"score":0.4876478910446167},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.4796105623245239},{"id":"https://openalex.org/C125864890","wikidata":"https://www.wikidata.org/wiki/Q1262687","display_name":"Intra-frame","level":3,"score":0.4716740548610687},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.384324848651886},{"id":"https://openalex.org/C59883199","wikidata":"https://www.wikidata.org/wiki/Q1826438","display_name":"Linear predictive coding","level":3,"score":0.3530231714248657},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2674410939216614},{"id":"https://openalex.org/C9390403","wikidata":"https://www.wikidata.org/wiki/Q3966","display_name":"Computer hardware","level":1,"score":0.15102168917655945},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.11794576048851013},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.11050716042518616},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C160633673","wikidata":"https://www.wikidata.org/wiki/Q355198","display_name":"Pixel","level":2,"score":0.0},{"id":"https://openalex.org/C153294291","wikidata":"https://www.wikidata.org/wiki/Q25261","display_name":"Meteorology","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49660.2025.10888202","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10888202","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":[{"id":"https://metadata.un.org/sdg/4","score":0.49000000953674316,"display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":40,"referenced_works":["https://openalex.org/W2131738223","https://openalex.org/W2752796333","https://openalex.org/W2935711438","https://openalex.org/W2963182577","https://openalex.org/W2964058413","https://openalex.org/W2972359262","https://openalex.org/W2998572311","https://openalex.org/W3095410713","https://openalex.org/W3198020407","https://openalex.org/W3209984917","https://openalex.org/W3215615641","https://openalex.org/W4307323391","https://openalex.org/W4372191700","https://openalex.org/W4372260337","https://openalex.org/W4372349107","https://openalex.org/W4381786045","https://openalex.org/W4385823076","https://openalex.org/W4385823460","https://openalex.org/W4392902628","https://openalex.org/W4392903006","https://openalex.org/W4399875170","https://openalex.org/W4402112155","https://openalex.org/W4402112436","https://openalex.org/W4402112533","https://openalex.org/W4405521053","https://openalex.org/W6631190155","https://openalex.org/W6771467084","https://openalex.org/W6783867762","https://openalex.org/W6847363464","https://openalex.org/W6848735303","https://openalex.org/W6852581948","https://openalex.org/W6853096648","https://openalex.org/W6853515095","https://openalex.org/W6853937136","https://openalex.org/W6855650468","https://openalex.org/W6855885476","https://openalex.org/W6861935630","https://openalex.org/W6863923569","https://openalex.org/W6868809805","https://openalex.org/W6871686990"],"related_works":["https://openalex.org/W1601770773","https://openalex.org/W2159307410","https://openalex.org/W2363660481","https://openalex.org/W137020845","https://openalex.org/W2092228680","https://openalex.org/W2382399415","https://openalex.org/W2374470469","https://openalex.org/W890199843","https://openalex.org/W2395467354","https://openalex.org/W2163834050"],"abstract_inverted_index":{"Large":[0],"language":[1,22,74],"models":[2,75,104],"(LLMs)":[3],"have":[4],"significantly":[5],"advanced":[6],"audio":[7,10,14,26,29,61,79],"processing":[8],"through":[9],"codecs":[11,30],"that":[12,63,93],"convert":[13],"into":[15],"discrete":[16],"tokens,":[17],"enabling":[18],"the":[19,53,99],"application":[20],"of":[21,101],"modeling":[23],"techniques":[24],"to":[25,76,116],"data.":[27],"However,":[28],"often":[31],"operate":[32],"at":[33],"high":[34],"frame":[35],"rates,":[36],"resulting":[37],"in":[38],"slow":[39],"training":[40,70],"and":[41,68,86,112],"inference,":[42],"especially":[43],"for":[44],"autoregressive":[45],"models.":[46,118],"To":[47],"address":[48],"this":[49],"challenge,":[50],"we":[51],"present":[52],"Low":[54],"Frame-rate":[55],"Speech":[56],"Codec":[57],"(LFSC):":[58],"a":[59,82],"neural":[60],"codec":[62,96],"leverages":[64],"finite":[65],"scalar":[66],"quantization":[67],"adversarial":[69],"with":[71,81],"large":[72],"speech":[73],"achieve":[77],"high-quality":[78],"compression":[80],"1.89":[83],"kbps":[84],"bitrate":[85],"21.5":[87],"frames":[88],"per":[89],"second.":[90],"We":[91],"demonstrate":[92],"our":[94],"novel":[95],"can":[97],"make":[98],"inference":[100],"LLM-based":[102],"text-to-speech":[103],"around":[105],"three":[106],"times":[107],"faster":[108],"while":[109],"improving":[110],"intelligibility":[111],"producing":[113],"quality":[114],"comparable":[115],"previous":[117]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":2}],"updated_date":"2026-04-23T09:07:50.710637","created_date":"2025-10-10T00:00:00"}