{"id":"https://openalex.org/W2963208781","doi":"https://doi.org/10.1109/icassp.2019.8682435","title":"High-quality Speech Coding with Sample RNN","display_name":"High-quality Speech Coding with Sample RNN","publication_year":2019,"publication_date":"2019-04-16","ids":{"openalex":"https://openalex.org/W2963208781","doi":"https://doi.org/10.1109/icassp.2019.8682435","mag":"2963208781"},"language":"en","primary_location":{"is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2019.8682435","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_indexed_in_scopus":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":null,"is_accepted":false,"is_published":false},"type":"article","type_crossref":"proceedings-article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/1811.03021","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5085752833","display_name":"Janusz Klejsa","orcid":null},"institutions":[{"id":"https://openalex.org/I4210093833","display_name":"Dolby (Sweden)","ror":"https://ror.org/00gqs6306","country_code":"SE","type":"company","lineage":["https://openalex.org/I4210093833","https://openalex.org/I4210093996"]}],"countries":["SE"],"is_corresponding":false,"raw_author_name":"Janusz Klejsa","raw_affiliation_strings":["Dolby Sweden AB, Stockholm, Sweden"],"affiliations":[{"raw_affiliation_string":"Dolby Sweden AB, Stockholm, Sweden","institution_ids":["https://openalex.org/I4210093833"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5057102869","display_name":"P. Hedelin","orcid":null},"institutions":[{"id":"https://openalex.org/I4210093833","display_name":"Dolby (Sweden)","ror":"https://ror.org/00gqs6306","country_code":"SE","type":"company","lineage":["https://openalex.org/I4210093833","https://openalex.org/I4210093996"]}],"countries":["SE"],"is_corresponding":false,"raw_author_name":"Per Hedelin","raw_affiliation_strings":["Dolby Sweden AB, Stockholm, Sweden"],"affiliations":[{"raw_affiliation_string":"Dolby Sweden AB, Stockholm, Sweden","institution_ids":["https://openalex.org/I4210093833"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102733043","display_name":"Cong Zhou","orcid":"https://orcid.org/0000-0002-4379-0298"},"institutions":[{"id":"https://openalex.org/I4210093996","display_name":"Dolby (United States)","ror":"https://ror.org/01eyenr26","country_code":"US","type":"company","lineage":["https://openalex.org/I4210093996"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Cong Zhou","raw_affiliation_strings":["Dolby Laboratories, San Francisco, CA, USA"],"affiliations":[{"raw_affiliation_string":"Dolby Laboratories, San Francisco, CA, USA","institution_ids":["https://openalex.org/I4210093996"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5054924576","display_name":"Roy Fejgin","orcid":null},"institutions":[{"id":"https://openalex.org/I4210093996","display_name":"Dolby (United States)","ror":"https://ror.org/01eyenr26","country_code":"US","type":"company","lineage":["https://openalex.org/I4210093996"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Roy Fejgin","raw_affiliation_strings":["Dolby Laboratories, San Francisco, CA, USA"],"affiliations":[{"raw_affiliation_string":"Dolby Laboratories, San Francisco, CA, USA","institution_ids":["https://openalex.org/I4210093996"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5030554103","display_name":"Lars Villemoes","orcid":"https://orcid.org/0009-0006-3011-5476"},"institutions":[{"id":"https://openalex.org/I4210093833","display_name":"Dolby (Sweden)","ror":"https://ror.org/00gqs6306","country_code":"SE","type":"company","lineage":["https://openalex.org/I4210093833","https://openalex.org/I4210093996"]}],"countries":["SE"],"is_corresponding":false,"raw_author_name":"Lars Villemoes","raw_affiliation_strings":["Dolby Sweden AB, Stockholm, Sweden"],"affiliations":[{"raw_affiliation_string":"Dolby Sweden AB, Stockholm, Sweden","institution_ids":["https://openalex.org/I4210093833"]}]}],"institution_assertions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":4.467,"has_fulltext":true,"fulltext_origin":"ngrams","cited_by_count":46,"citation_normalized_percentile":{"value":0.999609,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":96,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"7155","last_page":"7159"},"is_retracted":false,"is_paratext":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9999,"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":0.9999,"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":0.9997,"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":0.9996,"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/codec","display_name":"Codec","score":0.6200243},{"id":"https://openalex.org/keywords/psqm","display_name":"PSQM","score":0.5116749},{"id":"https://openalex.org/keywords/intelligibility","display_name":"Intelligibility (philosophy)","score":0.42106354},{"id":"https://openalex.org/keywords/distortion","display_name":"Distortion (music)","score":0.42105192}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7847445},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6891563},{"id":"https://openalex.org/C161765866","wikidata":"https://www.wikidata.org/wiki/Q184748","display_name":"Codec","level":2,"score":0.6200243},{"id":"https://openalex.org/C13895895","wikidata":"https://www.wikidata.org/wiki/Q3270773","display_name":"Speech coding","level":2,"score":0.6166831},{"id":"https://openalex.org/C179518139","wikidata":"https://www.wikidata.org/wiki/Q5140297","display_name":"Coding (social sciences)","level":2,"score":0.57145786},{"id":"https://openalex.org/C108699837","wikidata":"https://www.wikidata.org/wiki/Q7120750","display_name":"PSQM","level":4,"score":0.5116749},{"id":"https://openalex.org/C177291462","wikidata":"https://www.wikidata.org/wiki/Q423038","display_name":"Active listening","level":2,"score":0.5071199},{"id":"https://openalex.org/C77618280","wikidata":"https://www.wikidata.org/wiki/Q1155772","display_name":"Scheme (mathematics)","level":2,"score":0.45894256},{"id":"https://openalex.org/C60048801","wikidata":"https://www.wikidata.org/wiki/Q1433889","display_name":"Intelligibility (philosophy)","level":2,"score":0.42106354},{"id":"https://openalex.org/C126780896","wikidata":"https://www.wikidata.org/wiki/Q899871","display_name":"Distortion (music)","level":4,"score":0.42105192},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.37433428},{"id":"https://openalex.org/C59883199","wikidata":"https://www.wikidata.org/wiki/Q1826438","display_name":"Linear predictive coding","level":3,"score":0.23334703},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.10762301},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.09109652},{"id":"https://openalex.org/C2776257435","wikidata":"https://www.wikidata.org/wiki/Q1576430","display_name":"Bandwidth (computing)","level":2,"score":0.08488625},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.061603338},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.06093198},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","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/C194257627","wikidata":"https://www.wikidata.org/wiki/Q211554","display_name":"Amplifier","level":3,"score":0.0},{"id":"https://openalex.org/C46312422","wikidata":"https://www.wikidata.org/wiki/Q11024","display_name":"Communication","level":1,"score":0.0},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2019.8682435","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_indexed_in_scopus":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":null,"is_accepted":false,"is_published":false},{"is_oa":true,"landing_page_url":"https://arxiv.org/abs/1811.03021","pdf_url":"https://arxiv.org/pdf/1811.03021","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_indexed_in_scopus":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":["Cornell University"],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false}],"best_oa_location":{"is_oa":true,"landing_page_url":"https://arxiv.org/abs/1811.03021","pdf_url":"https://arxiv.org/pdf/1811.03021","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_indexed_in_scopus":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":["Cornell University"],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","display_name":"Peace, justice, and strong institutions","score":0.59}],"grants":[],"datasets":[],"versions":[],"referenced_works_count":26,"referenced_works":["https://openalex.org/W1500246642","https://openalex.org/W1522301498","https://openalex.org/W1634005169","https://openalex.org/W190385572","https://openalex.org/W2057653135","https://openalex.org/W2074137884","https://openalex.org/W2136103566","https://openalex.org/W2141459228","https://openalex.org/W2157331557","https://openalex.org/W2165291881","https://openalex.org/W2252143850","https://openalex.org/W2519091744","https://openalex.org/W2520116514","https://openalex.org/W2584032004","https://openalex.org/W2591927543","https://openalex.org/W2757519008","https://openalex.org/W2775336875","https://openalex.org/W2803595463","https://openalex.org/W2888470020","https://openalex.org/W2889347065","https://openalex.org/W2901997113","https://openalex.org/W2963782041","https://openalex.org/W2964121744","https://openalex.org/W2964122153","https://openalex.org/W34242971","https://openalex.org/W4294619240"],"related_works":["https://openalex.org/W3095556352","https://openalex.org/W2899318368","https://openalex.org/W2787189739","https://openalex.org/W2374470469","https://openalex.org/W2352448339","https://openalex.org/W2159899134","https://openalex.org/W2129913000","https://openalex.org/W2085637247","https://openalex.org/W2069597661","https://openalex.org/W1947419639"],"abstract_inverted_index":{"We":[0,47],"provide":[1,40],"a":[2,7,41,53],"speech":[3],"coding":[4],"scheme":[5,38,51],"employing":[6],"generative":[8],"model":[9],"based":[10],"on":[11],"SampleRNN":[12],"that,":[13],"while":[14],"operating":[15],"at":[16],"significantly":[17],"lower":[18],"bitrates,":[19],"matches":[20],"or":[21],"surpasses":[22],"the":[23,36,49,62],"perceptual":[24],"quality":[25],"of":[26,55,61],"state-of-the-art":[27],"classic":[28],"wide-band":[29],"codecs.":[30],"Moreover,":[31],"it":[32],"is":[33],"demonstrated":[34],"that":[35],"proposed":[37,50],"can":[39],"meaningful":[42],"rate-distortion":[43],"trade-off":[44],"without":[45],"retraining.":[46],"evaluate":[48],"in":[52],"series":[54],"listening":[56],"tests":[57],"and":[58],"discuss":[59],"limitations":[60],"approach.":[63]},"abstract_inverted_index_v3":null,"cited_by_api_url":"https://api.openalex.org/works?filter=cites:W2963208781","counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":4},{"year":2023,"cited_by_count":8},{"year":2022,"cited_by_count":6},{"year":2021,"cited_by_count":11},{"year":2020,"cited_by_count":11},{"year":2019,"cited_by_count":5}],"updated_date":"2025-02-23T07:11:26.906847","created_date":"2019-07-30"}