{"id":"https://openalex.org/W2944079609","doi":"https://doi.org/10.21437/interspeech.2020-2939","title":"Improving Opus Low Bit Rate Quality with Neural Speech Synthesis","display_name":"Improving Opus Low Bit Rate Quality with Neural Speech Synthesis","publication_year":2020,"publication_date":"2020-10-25","ids":{"openalex":"https://openalex.org/W2944079609","doi":"https://doi.org/10.21437/interspeech.2020-2939","mag":"2944079609"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2020-2939","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2020-2939","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2020","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/1905.04628","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","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"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5021269794","display_name":"Jean-Marc Valin","orcid":"https://orcid.org/0000-0002-9883-6927"},"institutions":[{"id":"https://openalex.org/I4210089985","display_name":"Amazon (Germany)","ror":"https://ror.org/00b9ktm87","country_code":"DE","type":"company","lineage":["https://openalex.org/I1311688040","https://openalex.org/I4210089985"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Jean-Marc Valin","raw_affiliation_strings":["Amazon"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Amazon","institution_ids":["https://openalex.org/I4210089985"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.5416,"has_fulltext":true,"cited_by_count":4,"citation_normalized_percentile":{"value":0.722303,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":96},"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":0.9995999932289124,"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":0.9995999932289124,"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":0.9995999932289124,"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":0.9994999766349792,"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/opus","display_name":"Opus","score":0.832298994064331},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8028782606124878},{"id":"https://openalex.org/keywords/decoding-methods","display_name":"Decoding methods","score":0.6572703719139099},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6391665935516357},{"id":"https://openalex.org/keywords/waveform","display_name":"Waveform","score":0.5971952676773071},{"id":"https://openalex.org/keywords/speech-coding","display_name":"Speech coding","score":0.4753177762031555},{"id":"https://openalex.org/keywords/latency","display_name":"Latency (audio)","score":0.4616052210330963},{"id":"https://openalex.org/keywords/parametric-statistics","display_name":"Parametric statistics","score":0.4433605670928955},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3245982527732849},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.271933376789093},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.11040443181991577},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.10904404520988464}],"concepts":[{"id":"https://openalex.org/C2778950570","wikidata":"https://www.wikidata.org/wiki/Q1466199","display_name":"Opus","level":2,"score":0.832298994064331},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8028782606124878},{"id":"https://openalex.org/C57273362","wikidata":"https://www.wikidata.org/wiki/Q576722","display_name":"Decoding methods","level":2,"score":0.6572703719139099},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6391665935516357},{"id":"https://openalex.org/C197424946","wikidata":"https://www.wikidata.org/wiki/Q1165717","display_name":"Waveform","level":3,"score":0.5971952676773071},{"id":"https://openalex.org/C13895895","wikidata":"https://www.wikidata.org/wiki/Q3270773","display_name":"Speech coding","level":2,"score":0.4753177762031555},{"id":"https://openalex.org/C82876162","wikidata":"https://www.wikidata.org/wiki/Q17096504","display_name":"Latency (audio)","level":2,"score":0.4616052210330963},{"id":"https://openalex.org/C117251300","wikidata":"https://www.wikidata.org/wiki/Q1849855","display_name":"Parametric statistics","level":2,"score":0.4433605670928955},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3245982527732849},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.271933376789093},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.11040443181991577},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.10904404520988464},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","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},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.21437/interspeech.2020-2939","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2020-2939","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2020","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:1905.04628","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1905.04628","pdf_url":"https://arxiv.org/pdf/1905.04628","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:2944079609","is_oa":true,"landing_page_url":"https://arxiv.org/abs/1905.04628","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.1905.04628","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.1905.04628","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:1905.04628","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1905.04628","pdf_url":"https://arxiv.org/pdf/1905.04628","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":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2944079609.pdf","grobid_xml":"https://content.openalex.org/works/W2944079609.grobid-xml"},"referenced_works_count":26,"referenced_works":["https://openalex.org/W1575718033","https://openalex.org/W1594680456","https://openalex.org/W1885680957","https://openalex.org/W2009674825","https://openalex.org/W2093228350","https://openalex.org/W2097645910","https://openalex.org/W2108532241","https://openalex.org/W2130158387","https://openalex.org/W2151626637","https://openalex.org/W2164764235","https://openalex.org/W2165291881","https://openalex.org/W2172140247","https://openalex.org/W2286601668","https://openalex.org/W2508766026","https://openalex.org/W2775336875","https://openalex.org/W2788851830","https://openalex.org/W2890983311","https://openalex.org/W2899725768","https://openalex.org/W2935711438","https://openalex.org/W2949382160","https://openalex.org/W2953318193","https://openalex.org/W2953331651","https://openalex.org/W2963091184","https://openalex.org/W2963868408","https://openalex.org/W2964122153","https://openalex.org/W2972519044"],"related_works":["https://openalex.org/W3096468295","https://openalex.org/W2972519044","https://openalex.org/W51259709","https://openalex.org/W1485475391","https://openalex.org/W2788940629","https://openalex.org/W1508913136","https://openalex.org/W2109124341","https://openalex.org/W2845558680","https://openalex.org/W2948407562","https://openalex.org/W2106757650","https://openalex.org/W2972354707","https://openalex.org/W1650036995","https://openalex.org/W3178321840","https://openalex.org/W2164990219","https://openalex.org/W2910493550","https://openalex.org/W3142112452","https://openalex.org/W1780275742","https://openalex.org/W3015780049","https://openalex.org/W2156542523","https://openalex.org/W1954114910"],"abstract_inverted_index":{"The":[0],"voice":[1],"mode":[2],"of":[3,66,170,184],"the":[4,34,44,77,146,155,168,171,181],"Opus":[5,23,71,137,159,173],"audio":[6,188],"coder":[7],"can":[8],"compress":[9],"wideband":[10],"speech":[11,75,163,186],"at":[12,25,139],"bit":[13,69,160],"rates":[14],"ranging":[15],"from":[16,76,136],"6":[17,140,157],"kb/s":[18,141,158],"to":[19,52,179],"40":[20],"kb/s.":[21],"However,":[22],"is":[24,91,99,117],"its":[26],"core":[27],"a":[28,63,92,103,108,118],"waveform":[29,56,189],"matching":[30],"coder,":[31],"and":[32,88,95,124,187],"as":[33,142],"rate":[35,45,70],"drops":[36],"below":[37],"10":[38],"kb/s,":[39],"quality":[40,72,112,183],"degrades":[41],"quickly.":[42],"As":[43],"reduces":[46],"even":[47],"further,":[48],"parametric":[49],"coders":[50,190],"tend":[51],"perform":[53],"better":[54],"than":[55],"coders.":[57],"In":[58],"this":[59],"paper":[60],"we":[61],"propose":[62],"backward-compatible":[64],"way":[65],"improving":[67],"low":[68],"by":[73],"re-synthesizing":[74],"decoded":[78],"parameters.":[79],"We":[80,130],"compare":[81],"two":[82],"different":[83],"neural":[84],"generative":[85,114,122,147],"models,":[86],"WaveNet":[87,90],"LPCNet.":[89],"powerful,":[93],"high-complexity,":[94],"high-latency":[96],"architecture":[97],"that":[98,153],"not":[100],"feasible":[101],"for":[102,145,154],"practical":[104],"system,":[105],"yet":[106],"provides":[107],"best":[109],"known":[110],"achievable":[111],"with":[113,134],"models.":[115,148],"LPCNet":[116,165],"low-complexity,":[119],"low-latency":[120],"RNN-based":[121],"model,":[123],"practically":[125],"implementable":[126],"on":[127],"mobile":[128],"phones.":[129],"apply":[131],"these":[132],"systems":[133],"parameters":[135],"coded":[138],"conditioning":[143],"features":[144],"A":[149],"listening":[150],"test":[151],"shows":[152],"same":[156],"stream,":[161],"synthesized":[162],"using":[164],"clearly":[166],"outperforms":[167],"output":[169],"standard":[172],"decoder.":[174],"This":[175],"opens":[176],"up":[177],"ways":[178],"improve":[180],"decoding":[182],"existing":[185],"without":[191],"breaking":[192],"compatibility.":[193]},"counts_by_year":[{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":2}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}