{"id":"https://openalex.org/W4375869380","doi":"https://doi.org/10.1109/icassp49357.2023.10095442","title":"LMCodec: A Low Bitrate Speech Codec with Causal Transformer Models","display_name":"LMCodec: A Low Bitrate Speech Codec with Causal Transformer Models","publication_year":2023,"publication_date":"2023-05-05","ids":{"openalex":"https://openalex.org/W4375869380","doi":"https://doi.org/10.1109/icassp49357.2023.10095442"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49357.2023.10095442","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49357.2023.10095442","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2023 - 2023 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/A5024402879","display_name":"Teerapat Jenrungrot","orcid":"https://orcid.org/0000-0002-8562-7210"},"institutions":[{"id":"https://openalex.org/I201448701","display_name":"University of Washington","ror":"https://ror.org/00cvxb145","country_code":"US","type":"education","lineage":["https://openalex.org/I201448701"]},{"id":"https://openalex.org/I58610484","display_name":"Seattle University","ror":"https://ror.org/02jqc0m91","country_code":"US","type":"education","lineage":["https://openalex.org/I58610484"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Teerapat Jenrungrot","raw_affiliation_strings":["University of Washington,Seattle","University of Washington, Seattle"],"affiliations":[{"raw_affiliation_string":"University of Washington,Seattle","institution_ids":["https://openalex.org/I58610484","https://openalex.org/I201448701"]},{"raw_affiliation_string":"University of Washington, Seattle","institution_ids":["https://openalex.org/I58610484","https://openalex.org/I201448701"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5016309279","display_name":"Michael Chinen","orcid":"https://orcid.org/0000-0003-4154-2132"},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Michael Chinen","raw_affiliation_strings":["Google"],"affiliations":[{"raw_affiliation_string":"Google","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5087492771","display_name":"W. Bastiaan Kleijn","orcid":"https://orcid.org/0000-0002-1973-3920"},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]},{"id":"https://openalex.org/I41156924","display_name":"Victoria University of Wellington","ror":"https://ror.org/0040r6f76","country_code":"NZ","type":"education","lineage":["https://openalex.org/I41156924"]}],"countries":["NZ","US"],"is_corresponding":false,"raw_author_name":"W. Bastiaan Kleijn","raw_affiliation_strings":["Google","School of Engineering and Computer Science, Victoria University of Wellington"],"affiliations":[{"raw_affiliation_string":"Google","institution_ids":["https://openalex.org/I1291425158"]},{"raw_affiliation_string":"School of Engineering and Computer Science, Victoria University of Wellington","institution_ids":["https://openalex.org/I41156924"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5070792118","display_name":"Jan Skoglund","orcid":"https://orcid.org/0009-0008-0167-4628"},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jan Skoglund","raw_affiliation_strings":["Google"],"affiliations":[{"raw_affiliation_string":"Google","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5026110001","display_name":"Zal\u00e1n Borsos","orcid":"https://orcid.org/0000-0003-0007-829X"},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Zal\u00e1n Borsos","raw_affiliation_strings":["Google"],"affiliations":[{"raw_affiliation_string":"Google","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5047639590","display_name":"Neil Zeghidour","orcid":"https://orcid.org/0000-0001-6896-3987"},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Neil Zeghidour","raw_affiliation_strings":["Google"],"affiliations":[{"raw_affiliation_string":"Google","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5033341878","display_name":"Marco Tagliasacchi","orcid":"https://orcid.org/0000-0002-7682-6795"},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Marco Tagliasacchi","raw_affiliation_strings":["Google"],"affiliations":[{"raw_affiliation_string":"Google","institution_ids":["https://openalex.org/I1291425158"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5024402879"],"corresponding_institution_ids":["https://openalex.org/I201448701","https://openalex.org/I58610484"],"apc_list":null,"apc_paid":null,"fwci":5.0622,"has_fulltext":false,"cited_by_count":25,"citation_normalized_percentile":{"value":0.96393382,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":99},"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/T10860","display_name":"Speech and Audio Processing","score":0.9998000264167786,"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":0.9998000264167786,"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":0.9997000098228455,"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":0.9947999715805054,"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":0.8027557134628296},{"id":"https://openalex.org/keywords/codec","display_name":"Codec","score":0.7260469794273376},{"id":"https://openalex.org/keywords/speech-coding","display_name":"Speech coding","score":0.629928469657898},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.627670407295227},{"id":"https://openalex.org/keywords/adaptive-multi-rate-audio-codec","display_name":"Adaptive Multi-Rate audio codec","score":0.5070712566375732},{"id":"https://openalex.org/keywords/vector-quantization","display_name":"Vector quantization","score":0.41085439920425415},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.3097546696662903},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3007791042327881},{"id":"https://openalex.org/keywords/voice-activity-detection","display_name":"Voice activity detection","score":0.17713969945907593},{"id":"https://openalex.org/keywords/computer-hardware","display_name":"Computer hardware","score":0.14566847681999207}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8027557134628296},{"id":"https://openalex.org/C161765866","wikidata":"https://www.wikidata.org/wiki/Q184748","display_name":"Codec","level":2,"score":0.7260469794273376},{"id":"https://openalex.org/C13895895","wikidata":"https://www.wikidata.org/wiki/Q3270773","display_name":"Speech coding","level":2,"score":0.629928469657898},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.627670407295227},{"id":"https://openalex.org/C177067256","wikidata":"https://www.wikidata.org/wiki/Q4676210","display_name":"Adaptive Multi-Rate audio codec","level":4,"score":0.5070712566375732},{"id":"https://openalex.org/C199833920","wikidata":"https://www.wikidata.org/wiki/Q612536","display_name":"Vector quantization","level":2,"score":0.41085439920425415},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.3097546696662903},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3007791042327881},{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.17713969945907593},{"id":"https://openalex.org/C9390403","wikidata":"https://www.wikidata.org/wiki/Q3966","display_name":"Computer hardware","level":1,"score":0.14566847681999207}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49357.2023.10095442","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49357.2023.10095442","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2023 - 2023 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":0.550000011920929,"display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":27,"referenced_works":["https://openalex.org/W1481955708","https://openalex.org/W1494198834","https://openalex.org/W1597121597","https://openalex.org/W2129913307","https://openalex.org/W2935711438","https://openalex.org/W2963091184","https://openalex.org/W2963182577","https://openalex.org/W2963868408","https://openalex.org/W2972354707","https://openalex.org/W2995181338","https://openalex.org/W2998572311","https://openalex.org/W3037038648","https://openalex.org/W3097777922","https://openalex.org/W3140429000","https://openalex.org/W3160077247","https://openalex.org/W3186609711","https://openalex.org/W3202278141","https://openalex.org/W3215615641","https://openalex.org/W4205788663","https://openalex.org/W4284888249","https://openalex.org/W4293569541","https://openalex.org/W4385245566","https://openalex.org/W6629717138","https://openalex.org/W6639363673","https://openalex.org/W6739901393","https://openalex.org/W6751104502","https://openalex.org/W6772349387"],"related_works":["https://openalex.org/W4252424250","https://openalex.org/W2374470469","https://openalex.org/W2110375858","https://openalex.org/W2363660481","https://openalex.org/W2352448339","https://openalex.org/W2159899134","https://openalex.org/W2787189739","https://openalex.org/W2089575384","https://openalex.org/W1968563888","https://openalex.org/W1999835922"],"abstract_inverted_index":{"We":[0],"introduce":[1],"LMCodec,":[2],"a":[3,23,31,42,56],"causal":[4,24],"neural":[5],"speech":[6],"codec":[7,26],"that":[8,27,97],"provides":[9],"high":[10],"quality":[11,99],"audio":[12,29,109],"at":[13,105,112],"very":[14],"low":[15],"bitrates.":[16,107],"The":[17],"backbone":[18],"of":[19,33,63,72],"the":[20,48,52,61,70,73,77,98],"system":[21],"is":[22,82,100,110],"convolutional":[25],"encodes":[28],"into":[30],"hierarchy":[32],"coarse-to-fine":[34],"tokens":[35,50],"using":[36],"residual":[37],"vector":[38],"quantization.":[39],"LMCodec":[40],"trains":[41],"Transformer":[43,68],"language":[44],"model":[45],"to":[46,84,102],"predict":[47],"fine":[49],"from":[51],"coarse":[53],"ones":[54],"in":[55],"generative":[57],"fashion,":[58],"allowing":[59],"for":[60],"transmission":[62],"fewer":[64],"codes.":[65],"A":[66,89],"second":[67],"predicts":[69],"uncertainty":[71],"next":[74],"codes":[75],"given":[76],"past":[78],"transmitted":[79],"codes,":[80],"and":[81,95],"used":[83],"perform":[85],"conditional":[86],"entropy":[87],"coding.":[88],"MUSHRA":[90],"subjective":[91],"test":[92],"was":[93],"conducted":[94],"shows":[96],"comparable":[101],"reference":[103],"codecs":[104],"higher":[106],"Example":[108],"available":[111],"https://mjenrungrot.github.io/chrome-media-audio-papers/publications/lmcodec.":[113]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":10},{"year":2024,"cited_by_count":13},{"year":2023,"cited_by_count":1}],"updated_date":"2026-03-09T08:58:05.943551","created_date":"2025-10-10T00:00:00"}
