{"id":"https://openalex.org/W2775336875","doi":"https://doi.org/10.1109/icassp.2018.8462529","title":"Wavenet Based Low Rate Speech Coding","display_name":"Wavenet Based Low Rate Speech Coding","publication_year":2018,"publication_date":"2018-04-01","ids":{"openalex":"https://openalex.org/W2775336875","doi":"https://doi.org/10.1109/icassp.2018.8462529","mag":"2775336875"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2018.8462529","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2018.8462529","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 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/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"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"W. Bastiaan Kleijn","raw_affiliation_strings":["Google Inc., San Francisco, CA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google Inc., San Francisco, CA","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5008147916","display_name":"Felicia S. C. Lim","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":"Felicia S. C. Lim","raw_affiliation_strings":["Google Inc., San Francisco, CA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google Inc., San Francisco, CA","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5030815835","display_name":"Alejandro Luebs","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":"Alejandro Luebs","raw_affiliation_strings":["Google Inc., San Francisco, CA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google Inc., San Francisco, CA","institution_ids":["https://openalex.org/I1291425158"]}]},{"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 Inc., San Francisco, CA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google Inc., San Francisco, CA","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5061287315","display_name":"Florian Stimberg","orcid":null},"institutions":[{"id":"https://openalex.org/I4210090411","display_name":"Google DeepMind (United Kingdom)","ror":"https://ror.org/00971b260","country_code":"GB","type":"company","lineage":["https://openalex.org/I4210090411","https://openalex.org/I4210128969"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Florian Stimberg","raw_affiliation_strings":["DeepMind, London, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"DeepMind, London, UK","institution_ids":["https://openalex.org/I4210090411"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100418248","display_name":"Quan Wang","orcid":"https://orcid.org/0000-0001-6943-4569"},"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":"Quan Wang","raw_affiliation_strings":["Google Inc., San Francisco, CA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google Inc., San Francisco, CA","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5003608440","display_name":"Thomas C. Walters","orcid":"https://orcid.org/0000-0003-1623-9238"},"institutions":[{"id":"https://openalex.org/I4210090411","display_name":"Google DeepMind (United Kingdom)","ror":"https://ror.org/00971b260","country_code":"GB","type":"company","lineage":["https://openalex.org/I4210090411","https://openalex.org/I4210128969"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Thomas C. Walters","raw_affiliation_strings":["DeepMind, London, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"DeepMind, London, UK","institution_ids":["https://openalex.org/I4210090411"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":7,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":12.6366,"has_fulltext":false,"cited_by_count":154,"citation_normalized_percentile":{"value":0.99159226,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":98,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"676","last_page":"680"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"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"}},"topics":[{"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/T10901","display_name":"Advanced Data Compression Techniques","score":0.9993000030517578,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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":0.9990000128746033,"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/speech-recognition","display_name":"Speech recognition","score":0.7667800188064575},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7585095167160034},{"id":"https://openalex.org/keywords/waveform","display_name":"Waveform","score":0.6368407011032104},{"id":"https://openalex.org/keywords/speech-coding","display_name":"Speech coding","score":0.6290149092674255},{"id":"https://openalex.org/keywords/parametric-statistics","display_name":"Parametric statistics","score":0.5930963754653931},{"id":"https://openalex.org/keywords/bit-rate","display_name":"Bit rate","score":0.5581931471824646},{"id":"https://openalex.org/keywords/generative-grammar","display_name":"Generative grammar","score":0.49724987149238586},{"id":"https://openalex.org/keywords/generative-model","display_name":"Generative model","score":0.47137391567230225},{"id":"https://openalex.org/keywords/codec2","display_name":"Codec2","score":0.45934611558914185},{"id":"https://openalex.org/keywords/coding","display_name":"Coding (social sciences)","score":0.44738179445266724},{"id":"https://openalex.org/keywords/linear-predictive-coding","display_name":"Linear predictive coding","score":0.43577277660369873},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.4146013855934143},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.34780555963516235},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.11092835664749146},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.06130906939506531},{"id":"https://openalex.org/keywords/real-time-computing","display_name":"Real-time computing","score":0.05611094832420349}],"concepts":[{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7667800188064575},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7585095167160034},{"id":"https://openalex.org/C197424946","wikidata":"https://www.wikidata.org/wiki/Q1165717","display_name":"Waveform","level":3,"score":0.6368407011032104},{"id":"https://openalex.org/C13895895","wikidata":"https://www.wikidata.org/wiki/Q3270773","display_name":"Speech coding","level":2,"score":0.6290149092674255},{"id":"https://openalex.org/C117251300","wikidata":"https://www.wikidata.org/wiki/Q1849855","display_name":"Parametric statistics","level":2,"score":0.5930963754653931},{"id":"https://openalex.org/C2987812609","wikidata":"https://www.wikidata.org/wiki/Q194158","display_name":"Bit rate","level":2,"score":0.5581931471824646},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.49724987149238586},{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.47137391567230225},{"id":"https://openalex.org/C75217168","wikidata":"https://www.wikidata.org/wiki/Q1105653","display_name":"Codec2","level":4,"score":0.45934611558914185},{"id":"https://openalex.org/C179518139","wikidata":"https://www.wikidata.org/wiki/Q5140297","display_name":"Coding (social sciences)","level":2,"score":0.44738179445266724},{"id":"https://openalex.org/C59883199","wikidata":"https://www.wikidata.org/wiki/Q1826438","display_name":"Linear predictive coding","level":3,"score":0.43577277660369873},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.4146013855934143},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.34780555963516235},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.11092835664749146},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.06130906939506531},{"id":"https://openalex.org/C79403827","wikidata":"https://www.wikidata.org/wiki/Q3988","display_name":"Real-time computing","level":1,"score":0.05611094832420349},{"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":1,"locations":[{"id":"doi:10.1109/icassp.2018.8462529","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2018.8462529","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":32,"referenced_works":["https://openalex.org/W204144752","https://openalex.org/W1496971974","https://openalex.org/W1519253855","https://openalex.org/W1594680456","https://openalex.org/W2009674825","https://openalex.org/W2012269826","https://openalex.org/W2020053595","https://openalex.org/W2022554507","https://openalex.org/W2023414836","https://openalex.org/W2037034710","https://openalex.org/W2097035595","https://openalex.org/W2097645910","https://openalex.org/W2099856211","https://openalex.org/W2108532241","https://openalex.org/W2130158387","https://openalex.org/W2140679070","https://openalex.org/W2149288684","https://openalex.org/W2154920538","https://openalex.org/W2155098255","https://openalex.org/W2159644785","https://openalex.org/W2164764235","https://openalex.org/W2168098717","https://openalex.org/W2168510624","https://openalex.org/W2168876247","https://openalex.org/W2519091744","https://openalex.org/W2632564668","https://openalex.org/W2749651610","https://openalex.org/W2911940095","https://openalex.org/W2962788625","https://openalex.org/W6676390839","https://openalex.org/W6681957806","https://openalex.org/W6745415975"],"related_works":["https://openalex.org/W2509918616","https://openalex.org/W2060409740","https://openalex.org/W2010376816","https://openalex.org/W1542588102","https://openalex.org/W1000239413","https://openalex.org/W1570840316","https://openalex.org/W2139283974","https://openalex.org/W2156505556","https://openalex.org/W1842536210","https://openalex.org/W2116865536"],"abstract_inverted_index":{"Traditional":[0],"parametric":[1,44,53],"coding":[2],"of":[3,14,17,41,83,111,130],"speech":[4,27,36,92],"facilitates":[5],"low":[6],"rate":[7,75],"but":[8],"provides":[9],"poor":[10],"reconstruction":[11],"quality":[12,35],"because":[13],"the":[15,18,38,61,69,80,84,91,95,112,116,128,131],"inadequacy":[16],"model":[19,28,64],"used.":[20],"We":[21,50],"describe":[22],"how":[23],"a":[24,42,56,73],"WaveNet":[25,85],"generative":[26,63,132],"can":[29],"be":[30],"used":[31,126],"to":[32,99],"generate":[33],"high":[34,81],"from":[37],"bit":[39],"stream":[40],"standard":[43],"coder":[45,54,58,87],"operating":[46],"at":[47],"2.4":[48],"kb/s.":[49],"compare":[51],"this":[52],"with":[55],"waveform":[57,71],"based":[59,86],"on":[60],"same":[62],"and":[65,88,105],"show":[66,89],"that":[67,90,121],"approximating":[68],"signal":[70],"incurs":[72],"large":[74],"penalty.":[76],"Our":[77],"experiments":[78],"confirm":[79],"performance":[82],"produced":[93],"by":[94],"system":[96],"is":[97],"able":[98],"additionally":[100],"perform":[101],"implicit":[102],"bandwidth":[103],"extension":[104],"does":[106],"not":[107,124],"significantly":[108],"impair":[109],"recognition":[110],"original":[113],"speaker":[114,122],"for":[115],"human":[117],"listener,":[118],"even":[119],"when":[120],"has":[123],"been":[125],"during":[127],"training":[129],"model.":[133]},"counts_by_year":[{"year":2026,"cited_by_count":5},{"year":2025,"cited_by_count":9},{"year":2024,"cited_by_count":26},{"year":2023,"cited_by_count":21},{"year":2022,"cited_by_count":17},{"year":2021,"cited_by_count":25},{"year":2020,"cited_by_count":23},{"year":2019,"cited_by_count":23},{"year":2018,"cited_by_count":5}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}
