{"id":"https://openalex.org/W3016003977","doi":"https://doi.org/10.1109/icassp40776.2020.9053220","title":"Source Coding of Audio Signals with a Generative Model","display_name":"Source Coding of Audio Signals with a Generative Model","publication_year":2020,"publication_date":"2020-04-09","ids":{"openalex":"https://openalex.org/W3016003977","doi":"https://doi.org/10.1109/icassp40776.2020.9053220","mag":"3016003977"},"language":"en","primary_location":{"id":"doi:10.1109/icassp40776.2020.9053220","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp40776.2020.9053220","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2020 - 2020 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/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":true,"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":"middle","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/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"]}]},{"author_position":"last","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"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5054924576"],"corresponding_institution_ids":["https://openalex.org/I4210093996"],"apc_list":null,"apc_paid":null,"fwci":1.2123,"has_fulltext":false,"cited_by_count":12,"citation_normalized_percentile":{"value":0.78630678,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"341","last_page":"345"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"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"}},"topics":[{"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"}},{"id":"https://openalex.org/T11349","display_name":"Music Technology and Sound Studies","score":0.9965999722480774,"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/T10860","display_name":"Speech and Audio Processing","score":0.9873999953269958,"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/waveform","display_name":"Waveform","score":0.7172670364379883},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6774938106536865},{"id":"https://openalex.org/keywords/coding","display_name":"Coding (social sciences)","score":0.6527017951011658},{"id":"https://openalex.org/keywords/speech-coding","display_name":"Speech coding","score":0.6418497562408447},{"id":"https://openalex.org/keywords/generative-grammar","display_name":"Generative grammar","score":0.5889290571212769},{"id":"https://openalex.org/keywords/generative-model","display_name":"Generative model","score":0.5867487788200378},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5667263269424438},{"id":"https://openalex.org/keywords/sub-band-coding","display_name":"Sub-band coding","score":0.477340966463089},{"id":"https://openalex.org/keywords/audio-signal","display_name":"Audio signal","score":0.4621181786060333},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.34618979692459106},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.17705422639846802},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.12249448895454407},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.06947401165962219}],"concepts":[{"id":"https://openalex.org/C197424946","wikidata":"https://www.wikidata.org/wiki/Q1165717","display_name":"Waveform","level":3,"score":0.7172670364379883},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6774938106536865},{"id":"https://openalex.org/C179518139","wikidata":"https://www.wikidata.org/wiki/Q5140297","display_name":"Coding (social sciences)","level":2,"score":0.6527017951011658},{"id":"https://openalex.org/C13895895","wikidata":"https://www.wikidata.org/wiki/Q3270773","display_name":"Speech coding","level":2,"score":0.6418497562408447},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.5889290571212769},{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.5867487788200378},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5667263269424438},{"id":"https://openalex.org/C98526533","wikidata":"https://www.wikidata.org/wiki/Q1691938","display_name":"Sub-band coding","level":3,"score":0.477340966463089},{"id":"https://openalex.org/C64922751","wikidata":"https://www.wikidata.org/wiki/Q4650799","display_name":"Audio signal","level":3,"score":0.4621181786060333},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.34618979692459106},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.17705422639846802},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.12249448895454407},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.06947401165962219},{"id":"https://openalex.org/C554190296","wikidata":"https://www.wikidata.org/wiki/Q47528","display_name":"Radar","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp40776.2020.9053220","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp40776.2020.9053220","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2020 - 2020 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":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":39,"referenced_works":["https://openalex.org/W1486361899","https://openalex.org/W1522301498","https://openalex.org/W1885680957","https://openalex.org/W1963699091","https://openalex.org/W2115942321","https://openalex.org/W2140593795","https://openalex.org/W2165291881","https://openalex.org/W2519091744","https://openalex.org/W2584032004","https://openalex.org/W2768814045","https://openalex.org/W2769810959","https://openalex.org/W2775336875","https://openalex.org/W2896030002","https://openalex.org/W2898148140","https://openalex.org/W2910577860","https://openalex.org/W2913277358","https://openalex.org/W2935711438","https://openalex.org/W2936557804","https://openalex.org/W2944209089","https://openalex.org/W2949382160","https://openalex.org/W2950547518","https://openalex.org/W2963208781","https://openalex.org/W2963782041","https://openalex.org/W2964121744","https://openalex.org/W2972519044","https://openalex.org/W3096468295","https://openalex.org/W3098418424","https://openalex.org/W4205788663","https://openalex.org/W4288624536","https://openalex.org/W4294619240","https://openalex.org/W6629042192","https://openalex.org/W6631190155","https://openalex.org/W6639363673","https://openalex.org/W6732429163","https://openalex.org/W6755182157","https://openalex.org/W6755446875","https://openalex.org/W6758675244","https://openalex.org/W6758867260","https://openalex.org/W6762390287"],"related_works":["https://openalex.org/W4365211920","https://openalex.org/W3014948380","https://openalex.org/W4380551139","https://openalex.org/W4317695495","https://openalex.org/W4287117424","https://openalex.org/W4387506531","https://openalex.org/W4238433571","https://openalex.org/W2967848559","https://openalex.org/W2109142991","https://openalex.org/W2350061705"],"abstract_inverted_index":{"We":[0,14],"consider":[1],"source":[2,70],"coding":[3,47,63,71],"of":[4,10,76],"audio":[5,77],"signals":[6],"with":[7,68],"the":[8,42,55,61],"help":[9],"a":[11,16,19,25,38],"generative":[12,56],"model.":[13],"use":[15],"construction":[17],"where":[18],"waveform":[20,30],"is":[21,31,49],"first":[22],"quantized,":[23],"yielding":[24],"finite":[26],"bitrate":[27],"representation.":[28],"The":[29,45],"then":[32],"reconstructed":[33],"by":[34],"random":[35],"sampling":[36],"from":[37],"model":[39],"conditioned":[40],"on":[41],"quantized":[43],"waveform.":[44],"proposed":[46,62],"scheme":[48],"theoretically":[50],"analyzed.":[51],"Using":[52],"SampleRNN":[53],"as":[54],"model,":[57],"we":[58],"demonstrate":[59],"that":[60],"structure":[64],"provides":[65],"performance":[66],"competitive":[67],"state-of-the-art":[69],"tools":[72],"for":[73],"specific":[74],"categories":[75],"signals.":[78]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":3},{"year":2021,"cited_by_count":3}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}