{"id":"https://openalex.org/W2924551963","doi":"https://doi.org/10.21437/interspeech.2019-1255","title":"A Real-Time Wideband Neural Vocoder at 1.6kb/s Using LPCNet","display_name":"A Real-Time Wideband Neural Vocoder at 1.6kb/s Using LPCNet","publication_year":2019,"publication_date":"2019-09-13","ids":{"openalex":"https://openalex.org/W2924551963","doi":"https://doi.org/10.21437/interspeech.2019-1255","mag":"2924551963"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2019-1255","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2019-1255","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2019","raw_type":"proceedings-article"},"type":"preprint","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/1903.12087","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5021269794","display_name":"Jean-Marc Valin","orcid":"https://orcid.org/0000-0002-9883-6927"},"institutions":[{"id":"https://openalex.org/I1311688040","display_name":"Amazon (United States)","ror":"https://ror.org/04mv4n011","country_code":"US","type":"company","lineage":["https://openalex.org/I1311688040"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jean-Marc Valin","raw_affiliation_strings":["Amazon (United States), Seattle, United States"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Amazon (United States), Seattle, United States","institution_ids":["https://openalex.org/I1311688040"]}]},{"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":["Google,,,,,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google,,,,,","institution_ids":["https://openalex.org/I1291425158"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.723,"has_fulltext":true,"cited_by_count":6,"citation_normalized_percentile":{"value":0.7793254,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"3406","last_page":"3410"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9984999895095825,"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":0.9984999895095825,"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/T10320","display_name":"Neural Networks and Applications","score":0.983299970626831,"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/wideband-audio","display_name":"Wideband audio","score":0.8437525629997253},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8080573081970215},{"id":"https://openalex.org/keywords/codec","display_name":"Codec","score":0.793427050113678},{"id":"https://openalex.org/keywords/speech-coding","display_name":"Speech coding","score":0.6587134003639221},{"id":"https://openalex.org/keywords/uncompressed-video","display_name":"Uncompressed video","score":0.6464235782623291},{"id":"https://openalex.org/keywords/waveform","display_name":"Waveform","score":0.597771406173706},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5520272850990295},{"id":"https://openalex.org/keywords/linear-predictive-coding","display_name":"Linear predictive coding","score":0.5224522352218628},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.5119515657424927},{"id":"https://openalex.org/keywords/codec2","display_name":"Codec2","score":0.4949430823326111},{"id":"https://openalex.org/keywords/linear-prediction","display_name":"Linear prediction","score":0.49424365162849426},{"id":"https://openalex.org/keywords/wideband","display_name":"Wideband","score":0.49276331067085266},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.45722901821136475},{"id":"https://openalex.org/keywords/full-rate","display_name":"Full Rate","score":0.44992199540138245},{"id":"https://openalex.org/keywords/coding","display_name":"Coding (social sciences)","score":0.42578476667404175},{"id":"https://openalex.org/keywords/code-excited-linear-prediction","display_name":"Code-excited linear prediction","score":0.4175565242767334},{"id":"https://openalex.org/keywords/computer-hardware","display_name":"Computer hardware","score":0.2125493884086609},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.20880022644996643},{"id":"https://openalex.org/keywords/digital-audio","display_name":"Digital audio","score":0.16622725129127502},{"id":"https://openalex.org/keywords/electronic-engineering","display_name":"Electronic engineering","score":0.13778993487358093},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.11114448308944702},{"id":"https://openalex.org/keywords/audio-signal","display_name":"Audio signal","score":0.09430119395256042},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.07362028956413269}],"concepts":[{"id":"https://openalex.org/C173391809","wikidata":"https://www.wikidata.org/wiki/Q2740189","display_name":"Wideband audio","level":5,"score":0.8437525629997253},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8080573081970215},{"id":"https://openalex.org/C161765866","wikidata":"https://www.wikidata.org/wiki/Q184748","display_name":"Codec","level":2,"score":0.793427050113678},{"id":"https://openalex.org/C13895895","wikidata":"https://www.wikidata.org/wiki/Q3270773","display_name":"Speech coding","level":2,"score":0.6587134003639221},{"id":"https://openalex.org/C162478608","wikidata":"https://www.wikidata.org/wiki/Q4011369","display_name":"Uncompressed video","level":4,"score":0.6464235782623291},{"id":"https://openalex.org/C197424946","wikidata":"https://www.wikidata.org/wiki/Q1165717","display_name":"Waveform","level":3,"score":0.597771406173706},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5520272850990295},{"id":"https://openalex.org/C59883199","wikidata":"https://www.wikidata.org/wiki/Q1826438","display_name":"Linear predictive coding","level":3,"score":0.5224522352218628},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5119515657424927},{"id":"https://openalex.org/C75217168","wikidata":"https://www.wikidata.org/wiki/Q1105653","display_name":"Codec2","level":4,"score":0.4949430823326111},{"id":"https://openalex.org/C131109320","wikidata":"https://www.wikidata.org/wiki/Q581012","display_name":"Linear prediction","level":2,"score":0.49424365162849426},{"id":"https://openalex.org/C2780202535","wikidata":"https://www.wikidata.org/wiki/Q4524457","display_name":"Wideband","level":2,"score":0.49276331067085266},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.45722901821136475},{"id":"https://openalex.org/C197477341","wikidata":"https://www.wikidata.org/wiki/Q2532845","display_name":"Full Rate","level":3,"score":0.44992199540138245},{"id":"https://openalex.org/C179518139","wikidata":"https://www.wikidata.org/wiki/Q5140297","display_name":"Coding (social sciences)","level":2,"score":0.42578476667404175},{"id":"https://openalex.org/C105964291","wikidata":"https://www.wikidata.org/wiki/Q856184","display_name":"Code-excited linear prediction","level":4,"score":0.4175565242767334},{"id":"https://openalex.org/C9390403","wikidata":"https://www.wikidata.org/wiki/Q3966","display_name":"Computer hardware","level":1,"score":0.2125493884086609},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.20880022644996643},{"id":"https://openalex.org/C87687168","wikidata":"https://www.wikidata.org/wiki/Q173114","display_name":"Digital audio","level":4,"score":0.16622725129127502},{"id":"https://openalex.org/C24326235","wikidata":"https://www.wikidata.org/wiki/Q126095","display_name":"Electronic engineering","level":1,"score":0.13778993487358093},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.11114448308944702},{"id":"https://openalex.org/C64922751","wikidata":"https://www.wikidata.org/wiki/Q4650799","display_name":"Audio signal","level":3,"score":0.09430119395256042},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.07362028956413269},{"id":"https://openalex.org/C202474056","wikidata":"https://www.wikidata.org/wiki/Q1931635","display_name":"Video tracking","level":3,"score":0.0},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.0},{"id":"https://openalex.org/C65483669","wikidata":"https://www.wikidata.org/wiki/Q3536669","display_name":"Video processing","level":2,"score":0.0},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0},{"id":"https://openalex.org/C554190296","wikidata":"https://www.wikidata.org/wiki/Q47528","display_name":"Radar","level":2,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.21437/interspeech.2019-1255","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2019-1255","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2019","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:1903.12087","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1903.12087","pdf_url":"https://arxiv.org/pdf/1903.12087","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"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":"","raw_type":"text"},{"id":"mag:2924551963","is_oa":true,"landing_page_url":"https://arxiv.org/pdf/1903.12087.pdf","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"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":"arXiv (Cornell University)","raw_type":null},{"id":"doi:10.48550/arxiv.1903.12087","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.1903.12087","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"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":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:1903.12087","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1903.12087","pdf_url":"https://arxiv.org/pdf/1903.12087","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"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":"","raw_type":"text"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2924551963.pdf","grobid_xml":"https://content.openalex.org/works/W2924551963.grobid-xml"},"referenced_works_count":20,"referenced_works":["https://openalex.org/W91030945","https://openalex.org/W1498609987","https://openalex.org/W1575718033","https://openalex.org/W1885680957","https://openalex.org/W2097645910","https://openalex.org/W2151409182","https://openalex.org/W2172140247","https://openalex.org/W2775336875","https://openalex.org/W2785523195","https://openalex.org/W2788851830","https://openalex.org/W2890983311","https://openalex.org/W2899725768","https://openalex.org/W2935711438","https://openalex.org/W2949382160","https://openalex.org/W2953331651","https://openalex.org/W2963091184","https://openalex.org/W2963175743","https://openalex.org/W2963589210","https://openalex.org/W2963868408","https://openalex.org/W2964281804"],"related_works":["https://openalex.org/W3096702751","https://openalex.org/W2072158058","https://openalex.org/W2845512037","https://openalex.org/W2890218728","https://openalex.org/W2160372360","https://openalex.org/W2080137303","https://openalex.org/W2284745461","https://openalex.org/W3110277971","https://openalex.org/W2973045486","https://openalex.org/W2113761470","https://openalex.org/W2775623145","https://openalex.org/W2794974041","https://openalex.org/W2388887940","https://openalex.org/W51374719","https://openalex.org/W3015268401","https://openalex.org/W2059442641","https://openalex.org/W2060409740","https://openalex.org/W3174773535","https://openalex.org/W2801903454","https://openalex.org/W48279821"],"abstract_inverted_index":{"Neural":[0],"speech":[1,11],"synthesis":[2,108],"algorithms":[3],"are":[4],"a":[5,39,90],"promising":[6],"new":[7,102],"approach":[8],"for":[9,101],"coding":[10],"at":[12,27,72,94],"very":[13,31],"low":[14,95],"bitrate.":[15,96],"They":[16],"have":[17],"so":[18],"far":[19,23],"demonstrated":[20],"quality":[21,78,88],"that":[22,69,82],"exceeds":[24],"traditional":[25],"vocoders,":[26],"the":[28,45,87,99],"cost":[29],"of":[30,50,89],"high":[32],"complexity.":[33],"In":[34],"this":[35],"work,":[36],"we":[37],"present":[38],"low-bitrate":[40],"neural":[41,107],"vocoder":[42],"based":[43,105],"on":[44,64,106],"LPCNet":[46,70,84],"model.":[47],"The":[48],"use":[49],"linear":[51],"prediction":[52],"and":[53,81],"sparse":[54],"recurrent":[55],"networks":[56],"makes":[57],"it":[58],"possible":[59],"to":[60],"achieve":[61],"real-time":[62],"operation":[63],"general-purpose":[65],"hardware.":[66],"We":[67],"demonstrate":[68],"operating":[71,93],"1.6":[73],"kb/s":[74],"achieves":[75],"significantly":[76],"higher":[77],"than":[79],"MELP":[80],"uncompressed":[83],"can":[85],"exceed":[86],"waveform":[91],"codec":[92,103],"This":[97],"opens":[98],"way":[100],"designs":[104],"models.":[109]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2021,"cited_by_count":3},{"year":2020,"cited_by_count":2}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}