{"id":"https://openalex.org/W4225290925","doi":"https://doi.org/10.1109/icassp43922.2022.9746103","title":"Neural Speech Synthesis on a Shoestring: Improving the Efficiency of Lpcnet","display_name":"Neural Speech Synthesis on a Shoestring: Improving the Efficiency of Lpcnet","publication_year":2022,"publication_date":"2022-04-27","ids":{"openalex":"https://openalex.org/W4225290925","doi":"https://doi.org/10.1109/icassp43922.2022.9746103"},"language":"en","primary_location":{"id":"doi:10.1109/icassp43922.2022.9746103","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp43922.2022.9746103","pdf_url":null,"source":{"id":"https://openalex.org/S4363607702","display_name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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":"ICASSP 2022 - 2022 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/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 Web Services,Palo Alto,CA,USA","Amazon Web Services, Palo Alto, CA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Amazon Web Services,Palo Alto,CA,USA","institution_ids":["https://openalex.org/I1311688040"]},{"raw_affiliation_string":"Amazon Web Services, Palo Alto, CA, USA","institution_ids":["https://openalex.org/I1311688040"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5036092393","display_name":"Umut Isik","orcid":null},"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":"Umut Isik","raw_affiliation_strings":["Amazon Web Services,Palo Alto,CA,USA","Amazon Web Services, Palo Alto, CA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Amazon Web Services,Palo Alto,CA,USA","institution_ids":["https://openalex.org/I1311688040"]},{"raw_affiliation_string":"Amazon Web Services, Palo Alto, CA, USA","institution_ids":["https://openalex.org/I1311688040"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5038903729","display_name":"Paris Smaragdis","orcid":null},"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":"Paris Smaragdis","raw_affiliation_strings":["Amazon Web Services,Palo Alto,CA,USA","Amazon Web Services, Palo Alto, CA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Amazon Web Services,Palo Alto,CA,USA","institution_ids":["https://openalex.org/I1311688040"]},{"raw_affiliation_string":"Amazon Web Services, Palo Alto, CA, USA","institution_ids":["https://openalex.org/I1311688040"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5112751528","display_name":"Arvindh Krishnaswamy","orcid":null},"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":"Arvindh Krishnaswamy","raw_affiliation_strings":["Amazon Web Services,Palo Alto,CA,USA","Amazon Web Services, Palo Alto, CA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Amazon Web Services,Palo Alto,CA,USA","institution_ids":["https://openalex.org/I1311688040"]},{"raw_affiliation_string":"Amazon Web Services, Palo Alto, CA, USA","institution_ids":["https://openalex.org/I1311688040"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.6229,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":{"value":0.66207262,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"8437","last_page":"8441"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9988999962806702,"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/T12031","display_name":"Speech and dialogue systems","score":0.9965000152587891,"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/usable","display_name":"USable","score":0.8593482971191406},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7461485862731934},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.5946211218833923},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.5906057953834534},{"id":"https://openalex.org/keywords/variety","display_name":"Variety (cybernetics)","score":0.5305987596511841},{"id":"https://openalex.org/keywords/computational-complexity-theory","display_name":"Computational complexity theory","score":0.5141535401344299},{"id":"https://openalex.org/keywords/quality","display_name":"Quality (philosophy)","score":0.4508315622806549},{"id":"https://openalex.org/keywords/computer-engineering","display_name":"Computer engineering","score":0.38867831230163574},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3601887822151184},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3543580174446106},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.33895909786224365},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.287550151348114}],"concepts":[{"id":"https://openalex.org/C2780615836","wikidata":"https://www.wikidata.org/wiki/Q2471869","display_name":"USable","level":2,"score":0.8593482971191406},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7461485862731934},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5946211218833923},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.5906057953834534},{"id":"https://openalex.org/C136197465","wikidata":"https://www.wikidata.org/wiki/Q1729295","display_name":"Variety (cybernetics)","level":2,"score":0.5305987596511841},{"id":"https://openalex.org/C179799912","wikidata":"https://www.wikidata.org/wiki/Q205084","display_name":"Computational complexity theory","level":2,"score":0.5141535401344299},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.4508315622806549},{"id":"https://openalex.org/C113775141","wikidata":"https://www.wikidata.org/wiki/Q428691","display_name":"Computer engineering","level":1,"score":0.38867831230163574},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3601887822151184},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3543580174446106},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.33895909786224365},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.287550151348114},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp43922.2022.9746103","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp43922.2022.9746103","pdf_url":null,"source":{"id":"https://openalex.org/S4363607702","display_name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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":"ICASSP 2022 - 2022 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","display_name":"Quality Education","score":0.6399999856948853}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":41,"referenced_works":["https://openalex.org/W648786980","https://openalex.org/W1522301498","https://openalex.org/W2016589492","https://openalex.org/W2029147192","https://openalex.org/W2150658333","https://openalex.org/W2154920538","https://openalex.org/W2176263492","https://openalex.org/W2403891086","https://openalex.org/W2519091744","https://openalex.org/W2584032004","https://openalex.org/W2750167318","https://openalex.org/W2775336875","https://openalex.org/W2890983311","https://openalex.org/W2895654193","https://openalex.org/W2963091184","https://openalex.org/W2963300588","https://openalex.org/W2963868408","https://openalex.org/W2964243274","https://openalex.org/W2972519044","https://openalex.org/W3028785944","https://openalex.org/W3028954259","https://openalex.org/W3030374183","https://openalex.org/W3032479101","https://openalex.org/W3032558098","https://openalex.org/W3092791109","https://openalex.org/W3095459301","https://openalex.org/W3095851005","https://openalex.org/W3198020407","https://openalex.org/W4297817572","https://openalex.org/W4298580827","https://openalex.org/W6621543089","https://openalex.org/W6631190155","https://openalex.org/W6685322675","https://openalex.org/W6732429163","https://openalex.org/W6748409065","https://openalex.org/W6755257315","https://openalex.org/W6760712927","https://openalex.org/W6777781272","https://openalex.org/W6778625279","https://openalex.org/W6778672582","https://openalex.org/W6779192484"],"related_works":["https://openalex.org/W2982321410","https://openalex.org/W95465806","https://openalex.org/W2392004567","https://openalex.org/W2046296964","https://openalex.org/W2940029036","https://openalex.org/W2756595502","https://openalex.org/W2010789764","https://openalex.org/W2187233292","https://openalex.org/W2219281195","https://openalex.org/W4389422031"],"abstract_inverted_index":{"Neural":[0],"speech":[1,8],"synthesis":[2,70,88],"models":[3],"can":[4,84],"synthesize":[5],"high":[6,13],"quality":[7,71],"but":[9],"typically":[10],"require":[11],"a":[12,60],"computational":[14,52],"complexity":[15,33],"to":[16,29,55],"do":[17],"so.":[18],"In":[19,37],"previous":[20],"work,":[21,39],"we":[22,40],"introduced":[23],"LPCNet,":[24],"which":[25],"uses":[26],"linear":[27],"prediction":[28],"significantly":[30],"reduce":[31],"the":[32,43],"of":[34,45,63],"neural":[35,87],"synthesis.":[36],"this":[38],"further":[41],"improve":[42],"efficiency":[44],"LPCNet":[46,82],"\u2013":[47,54],"targeting":[48],"both":[49],"algorithmic":[50],"and":[51,93],"improvements":[53],"make":[56],"it":[57],"usable":[58,96],"on":[59,89],"wide":[61],"variety":[62],"devices.":[64,100],"We":[65],"demonstrate":[66],"an":[67],"improvement":[68],"in":[69,97],"while":[72],"operating":[73],"2.5x":[74],"faster.":[75],"The":[76],"resulting":[77],"open-source":[78],"<sup":[79],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[80],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">1</sup>":[81],"algorithm":[83],"perform":[85],"real-time":[86],"most":[90],"existing":[91],"phones":[92],"is":[94],"even":[95],"some":[98],"embedded":[99]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}