{"id":"https://openalex.org/W7213407453","doi":"https://doi.org/10.48550/arxiv.2609.17509","title":"LACE: Layer-Wise Compression for Dynamic Frame Rate Codecs","display_name":"LACE: Layer-Wise Compression for Dynamic Frame Rate Codecs","publication_year":2026,"publication_date":"2026-09-15","ids":{"openalex":"https://openalex.org/W7213407453","doi":"https://doi.org/10.48550/arxiv.2609.17509"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2609.17509","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2609.17509","pdf_url":"https://arxiv.org/pdf/2609.17509","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"volume":null,"type":"preprint","is_traditional":true,"indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2609.17509","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5099096874","display_name":"Thanapat Trachu","orcid":"https://orcid.org/0009-0006-4866-5011","observed_orcids":["https://orcid.org/0009-0006-4866-5011"]},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Trachu, Thanapat","raw_affiliation_strings":["Language Technologies Institute , Carnegie Mellon University , Pittsburgh , USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Language Technologies Institute , Carnegie Mellon University , Pittsburgh , USA","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5047682990","display_name":"Samuele Cornell","orcid":"https://orcid.org/0000-0002-5358-1844","observed_orcids":["https://orcid.org/0000-0002-5358-1844"]},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Cornell, Samuele","raw_affiliation_strings":["Language Technologies Institute , Carnegie Mellon University , Pittsburgh , USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Language Technologies Institute , Carnegie Mellon University , Pittsburgh , USA","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139182584","display_name":"William Chen","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Chen, William","raw_affiliation_strings":["Language Technologies Institute , Carnegie Mellon University , Pittsburgh , USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Language Technologies Institute , Carnegie Mellon University , Pittsburgh , USA","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5151925332","display_name":"Shinji Watanabe","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Watanabe, Shinji","raw_affiliation_strings":["Language Technologies Institute , Carnegie Mellon University , Pittsburgh , USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Language Technologies Institute , Carnegie Mellon University , Pittsburgh , USA","institution_ids":["https://openalex.org/I74973139"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I74973139"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9926999807357788,"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":0.9926999807357788,"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":0.006500000134110451,"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":9.999999747378752e-05,"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/neural-audio-codecs","display_name":"neural audio codecs","score":0.9150000214576721},{"id":"https://openalex.org/keywords/frame-rate-reduction","display_name":"frame rate reduction","score":0.574999988079071},{"id":"https://openalex.org/keywords/text-to-speech","display_name":"text-to-speech","score":0.7409999966621399}],"concepts":[{"id":"https://openalex.org/C161765866","wikidata":"https://www.wikidata.org/wiki/Q184748","display_name":"Codec","level":2,"score":0.7792999744415283},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7590000033378601},{"id":"https://openalex.org/C125864890","wikidata":"https://www.wikidata.org/wiki/Q1262687","display_name":"Intra-frame","level":3,"score":0.5860000252723694},{"id":"https://openalex.org/C28855332","wikidata":"https://www.wikidata.org/wiki/Q198099","display_name":"Quantization (signal processing)","level":2,"score":0.5705999732017517},{"id":"https://openalex.org/C199833920","wikidata":"https://www.wikidata.org/wiki/Q612536","display_name":"Vector quantization","level":2,"score":0.47290000319480896},{"id":"https://openalex.org/C78548338","wikidata":"https://www.wikidata.org/wiki/Q2493","display_name":"Data compression","level":2,"score":0.46399998664855957},{"id":"https://openalex.org/C177067256","wikidata":"https://www.wikidata.org/wiki/Q4676210","display_name":"Adaptive Multi-Rate audio codec","level":4,"score":0.44780001044273376},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4302000105381012},{"id":"https://openalex.org/C94835093","wikidata":"https://www.wikidata.org/wiki/Q3113333","display_name":"Data compression ratio","level":5,"score":0.41440001130104065},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3935999870300293},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.3749000132083893},{"id":"https://openalex.org/C13895895","wikidata":"https://www.wikidata.org/wiki/Q3270773","display_name":"Speech coding","level":2,"score":0.36980000138282776},{"id":"https://openalex.org/C197129107","wikidata":"https://www.wikidata.org/wiki/Q1921621","display_name":"Merge (version control)","level":2,"score":0.3682999908924103},{"id":"https://openalex.org/C150178126","wikidata":"https://www.wikidata.org/wiki/Q18433212","display_name":"Dynamic range compression","level":2,"score":0.35690000653266907},{"id":"https://openalex.org/C204641915","wikidata":"https://www.wikidata.org/wiki/Q7315509","display_name":"Residual frame","level":4,"score":0.33239999413490295},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.32589998841285706},{"id":"https://openalex.org/C155512373","wikidata":"https://www.wikidata.org/wiki/Q287450","display_name":"Residual","level":2,"score":0.32339999079704285},{"id":"https://openalex.org/C126042441","wikidata":"https://www.wikidata.org/wiki/Q1324888","display_name":"Frame (networking)","level":2,"score":0.31299999356269836},{"id":"https://openalex.org/C39394851","wikidata":"https://www.wikidata.org/wiki/Q921594","display_name":"Inter frame","level":4,"score":0.3052999973297119},{"id":"https://openalex.org/C179518139","wikidata":"https://www.wikidata.org/wiki/Q5140297","display_name":"Coding (social sciences)","level":2,"score":0.29010000824928284},{"id":"https://openalex.org/C79403827","wikidata":"https://www.wikidata.org/wiki/Q3988","display_name":"Real-time computing","level":1,"score":0.28189998865127563},{"id":"https://openalex.org/C105964291","wikidata":"https://www.wikidata.org/wiki/Q856184","display_name":"Code-excited linear prediction","level":4,"score":0.27410000562667847},{"id":"https://openalex.org/C172849965","wikidata":"https://www.wikidata.org/wiki/Q3148875","display_name":"Reference frame","level":3,"score":0.27379998564720154},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.2736999988555908},{"id":"https://openalex.org/C180016635","wikidata":"https://www.wikidata.org/wiki/Q2712821","display_name":"Compression (physics)","level":2,"score":0.2651999890804291},{"id":"https://openalex.org/C3261483","wikidata":"https://www.wikidata.org/wiki/Q119565","display_name":"Frame rate","level":2,"score":0.25940001010894775},{"id":"https://openalex.org/C160987145","wikidata":"https://www.wikidata.org/wiki/Q13043846","display_name":"Pulse-code modulation","level":3,"score":0.25450000166893005}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2609.17509","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2609.17509","pdf_url":"https://arxiv.org/pdf/2609.17509","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2609.17509","doi":"https://doi.org/10.48550/arxiv.2609.17509","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2609.17509","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2609.17509","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2609.17509","pdf_url":"https://arxiv.org/pdf/2609.17509","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7213407453.pdf","grobid_xml":"https://content.openalex.org/works/W7213407453.grobid-xml"},"referenced_works_count":2,"referenced_works":["https://openalex.org/W2964121744","https://openalex.org/W4200300291"],"related_works":["https://openalex.org/W7084408266","https://openalex.org/W7166058210","https://openalex.org/W7160282565","https://openalex.org/W4415182342","https://openalex.org/W7127195585","https://openalex.org/W7155053259","https://openalex.org/W4415433232","https://openalex.org/W4408352440","https://openalex.org/W6966311379","https://openalex.org/W7166676062"],"abstract_inverted_index":{"Neural":[0],"audio":[1],"codecs":[2,27,53],"are":[3],"a":[4,37,56,95,148],"key":[5],"component":[6],"in":[7,118],"speech":[8],"language":[9],"modeling.":[10],"However,":[11,45],"their":[12],"high":[13],"frame":[14,25,34,97,155],"rates":[15,84],"lead":[16],"to":[17,40,68,131],"long":[18],"sequence":[19],"lengths,":[20],"increasing":[21],"computational":[22],"costs.":[23],"Dynamic":[24],"rate":[26,35,98,156],"mitigate":[28],"this":[29],"by":[30],"reducing":[31],"the":[32,70,75,159,179],"effective":[33],"using":[36],"compression":[38,58,104,139],"step":[39,59,105],"merge":[41],"multiple":[42],"frames":[43],"together.":[44],"most":[46],"prior":[47,153],"methods":[48,157],"either":[49],"operate":[50],"on":[51,142,158],"single-codebook":[52],"or":[54],"apply":[55],"single":[57],"before":[60],"multi-layer":[61],"quantization.":[62],"This":[63],"forces":[64],"all":[65],"quantization":[66,80,108],"layers":[67,81,136],"share":[69],"same":[71],"segmentation":[72,112],"boundaries,":[73],"despite":[74],"residual":[76],"embeddings":[77],"at":[78,106],"different":[79,83],"exhibiting":[82],"of":[85,178],"change":[86],"over":[87],"time.":[88],"We":[89],"propose":[90],"LACE":[91,116,146],"(Layer-Adaptive":[92],"Codec":[93],"Encoding),":[94],"dynamic":[96,154],"codec":[99,181],"that":[100,145],"applies":[101],"an":[102],"independent":[103],"each":[107],"layer,":[109],"enabling":[110],"layer-specific":[111],"boundaries.":[113],"To":[114],"use":[115],"tokens":[117],"downstream":[119],"text-to-speech":[120],"(TTS),":[121],"we":[122],"further":[123],"introduce":[124],"union":[125],"alignment":[126],"and":[127,162],"boundary":[128],"anchor":[129],"mechanisms":[130],"make":[132],"durations":[133],"consistent":[134],"across":[135],"while":[137,167],"preserving":[138],"benefits.":[140],"Experiments":[141],"LibriTTS":[143],"show":[144],"offers":[147],"better":[149],"rate-quality":[150],"tradeoff":[151],"than":[152],"reconstruction":[160],"task":[161],"improves":[163],"TTS":[164],"inference":[165],"efficiency":[166],"maintaining":[168],"competitive":[169],"synthesis":[170],"quality.":[171],"Our":[172],"code":[173],"is":[174],"released":[175],"as":[176],"part":[177],"ESPnet3":[180],"recipe.":[182]},"counts_by_year":[],"updated_date":"2026-11-07T11:25:07.637180","created_date":"2026-09-17T00:00:00"}