{"id":"https://openalex.org/W4284888249","doi":"https://doi.org/10.21437/interspeech.2022-10988","title":"Ultra-Low-Bitrate Speech Coding with Pretrained Transformers","display_name":"Ultra-Low-Bitrate Speech Coding with Pretrained Transformers","publication_year":2022,"publication_date":"2022-09-16","ids":{"openalex":"https://openalex.org/W4284888249","doi":"https://doi.org/10.21437/interspeech.2022-10988"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2022-10988","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2022-10988","pdf_url":null,"source":{"id":"https://openalex.org/S4363604309","display_name":"Interspeech 2022","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2022","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/A5044553315","display_name":"Ali Siahkoohi","orcid":"https://orcid.org/0000-0001-8779-2247"},"institutions":[{"id":"https://openalex.org/I130701444","display_name":"Georgia Institute of Technology","ror":"https://ror.org/01zkghx44","country_code":"US","type":"education","lineage":["https://openalex.org/I130701444"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Ali Siahkoohi","raw_affiliation_strings":["School of Computational Science and Engineering, Georgia Institute of Technology"],"affiliations":[{"raw_affiliation_string":"School of Computational Science and Engineering, Georgia Institute of Technology","institution_ids":["https://openalex.org/I130701444"]}]},{"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":["Chrome Media, Google"],"affiliations":[{"raw_affiliation_string":"Chrome Media, Google","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5012782228","display_name":"Tom Denton","orcid":null},"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":"Tom Denton","raw_affiliation_strings":["Chrome Media, Google"],"affiliations":[{"raw_affiliation_string":"Chrome Media, 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/I41156924","display_name":"Victoria University of Wellington","ror":"https://ror.org/0040r6f76","country_code":"NZ","type":"education","lineage":["https://openalex.org/I41156924"]},{"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":["NZ","US"],"is_corresponding":false,"raw_author_name":"W. Bastiaan Kleijn","raw_affiliation_strings":["Chrome Media, Google","School of Engineering and Computer Science, Victoria University of Wellington"],"affiliations":[{"raw_affiliation_string":"Chrome Media, 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":"last","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":["Chrome Media, Google"],"affiliations":[{"raw_affiliation_string":"Chrome Media, Google","institution_ids":["https://openalex.org/I1291425158"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5044553315"],"corresponding_institution_ids":["https://openalex.org/I130701444"],"apc_list":null,"apc_paid":null,"fwci":0.735,"has_fulltext":false,"cited_by_count":8,"citation_normalized_percentile":{"value":0.70707017,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"4421","last_page":"4425"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9983999729156494,"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":0.9983999729156494,"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":0.998199999332428,"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/T11609","display_name":"Geophysical Methods and Applications","score":0.9837999939918518,"subfield":{"id":"https://openalex.org/subfields/2212","display_name":"Ocean Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6887872219085693},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.5883942246437073},{"id":"https://openalex.org/keywords/speech-coding","display_name":"Speech coding","score":0.5587502717971802},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5467560887336731},{"id":"https://openalex.org/keywords/coding","display_name":"Coding (social sciences)","score":0.516955554485321},{"id":"https://openalex.org/keywords/electrical-engineering","display_name":"Electrical engineering","score":0.19047316908836365},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.1422290802001953},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.061543554067611694},{"id":"https://openalex.org/keywords/voltage","display_name":"Voltage","score":0.061301469802856445}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6887872219085693},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.5883942246437073},{"id":"https://openalex.org/C13895895","wikidata":"https://www.wikidata.org/wiki/Q3270773","display_name":"Speech coding","level":2,"score":0.5587502717971802},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5467560887336731},{"id":"https://openalex.org/C179518139","wikidata":"https://www.wikidata.org/wiki/Q5140297","display_name":"Coding (social sciences)","level":2,"score":0.516955554485321},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.19047316908836365},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.1422290802001953},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.061543554067611694},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.061301469802856445},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21437/interspeech.2022-10988","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2022-10988","pdf_url":null,"source":{"id":"https://openalex.org/S4363604309","display_name":"Interspeech 2022","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2022","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions","score":0.7300000190734863}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":35,"referenced_works":["https://openalex.org/W1481955708","https://openalex.org/W1567186732","https://openalex.org/W1996957914","https://openalex.org/W2108532241","https://openalex.org/W2114925438","https://openalex.org/W2115098197","https://openalex.org/W2129438793","https://openalex.org/W2131738223","https://openalex.org/W2292235217","https://openalex.org/W2519091744","https://openalex.org/W2775336875","https://openalex.org/W2935711438","https://openalex.org/W2963091184","https://openalex.org/W2963208781","https://openalex.org/W2963799213","https://openalex.org/W2970006822","https://openalex.org/W2998572311","https://openalex.org/W3007965881","https://openalex.org/W3016098186","https://openalex.org/W3036601975","https://openalex.org/W3037038648","https://openalex.org/W3092028330","https://openalex.org/W3093579165","https://openalex.org/W3097777922","https://openalex.org/W3140429000","https://openalex.org/W3160077247","https://openalex.org/W3206495532","https://openalex.org/W3215615641","https://openalex.org/W4205788663","https://openalex.org/W4226033575","https://openalex.org/W4226380987","https://openalex.org/W4297808394","https://openalex.org/W4320013936","https://openalex.org/W4385245566","https://openalex.org/W4394668580"],"related_works":["https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W2358668433","https://openalex.org/W2376932109","https://openalex.org/W2382290278","https://openalex.org/W1911859126","https://openalex.org/W2120730869","https://openalex.org/W2118508889","https://openalex.org/W2166699153"],"abstract_inverted_index":{"Speech":[0],"coding":[1],"facilitates":[2],"the":[3,61,68,79,117,141,153,160,163,181],"transmission":[4],"of":[5,29,33,39,63,70,74,120,136,162,172],"speech":[6,14,55,65,123,127,131,144,148],"over":[7,23],"lowbandwidth":[8],"networks":[9],"with":[10,95,103,125,133],"minimal":[11],"distortion.Neural-network":[12],"based":[13],"codecs":[15,30,66,174],"have":[16],"recently":[17],"demonstrated":[18],"significant":[19],"improvements":[20],"in":[21,78,93,146],"quality":[22,149,161],"traditional":[24],"approaches.While":[25],"this":[26],"new":[27],"generation":[28],"is":[31,100,166],"capable":[32,73],"synthesizing":[34],"highfidelity":[35],"speech,":[36],"their":[37,46,84],"use":[38,69,89],"recurrent":[40],"or":[41,168],"convolutional":[42,97,118],"layers":[43],"often":[44],"restricts":[45],"effective":[47],"receptive":[48],"fields,":[49],"which":[50,99],"prevents":[51],"them":[52],"from":[53],"compressing":[54],"efficiently.We":[56],"propose":[57],"to":[58,83,178],"further":[59],"reduce":[60],"bitrate":[62,135],"neural":[64,122,143],"through":[67],"pretrained":[71,91],"Transformers,":[72],"exploiting":[75],"long-range":[76],"dependencies":[77],"input":[80],"signal":[81],"due":[82],"inductive":[85],"bias.As":[86],"such,":[87],"we":[88],"a":[90,96,104,107,121,130,134],"Transformer":[92,126],"tandem":[94],"encoder,":[98],"trained":[101,151],"end-to-end":[102],"quantizer":[105],"and":[106],"generative":[108],"adversarial":[109],"net":[110],"decoder.Our":[111],"numerical":[112],"experiments":[113],"show":[114],"that":[115,139,159,171],"supplementing":[116],"encoder":[119],"codec":[124,132,145,165],"embeddings":[128],"yields":[129],"600":[137],"bps":[138],"outperforms":[140],"original":[142],"synthesized":[147],"when":[150],"at":[152,176],"same":[154],"bitrate.Subjective":[155],"human":[156],"evaluations":[157],"suggest":[158],"resulting":[164],"comparable":[167],"better":[169],"than":[170],"conventional":[173],"operating":[175],"three":[177],"four":[179],"times":[180],"rate.":[182]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":2}],"updated_date":"2026-03-09T08:58:05.943551","created_date":"2025-10-10T00:00:00"}