{"id":"https://openalex.org/W3016098186","doi":"https://doi.org/10.1109/icassp40776.2020.9053657","title":"Robust Low Rate Speech Coding Based on Cloned Networks and Wavenet","display_name":"Robust Low Rate Speech Coding Based on Cloned Networks and Wavenet","publication_year":2020,"publication_date":"2020-04-09","ids":{"openalex":"https://openalex.org/W3016098186","doi":"https://doi.org/10.1109/icassp40776.2020.9053657","mag":"3016098186"},"language":"en","primary_location":{"id":"doi:10.1109/icassp40776.2020.9053657","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp40776.2020.9053657","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/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":true,"raw_author_name":"Felicia S. C. Lim","raw_affiliation_strings":["Google LLC, San Francisco, CA"],"affiliations":[{"raw_affiliation_string":"Google LLC, San Francisco, CA","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","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 LLC, San Francisco, CA"],"affiliations":[{"raw_affiliation_string":"Google LLC, San Francisco, CA","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5016309279","display_name":"Michael Chinen","orcid":"https://orcid.org/0000-0003-4154-2132"},"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":"Michael Chinen","raw_affiliation_strings":["Google LLC, San Francisco, CA"],"affiliations":[{"raw_affiliation_string":"Google LLC, San Francisco, CA","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"last","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 LLC, San Francisco, CA"],"affiliations":[{"raw_affiliation_string":"Google LLC, San Francisco, CA","institution_ids":["https://openalex.org/I1291425158"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5008147916"],"corresponding_institution_ids":["https://openalex.org/I1291425158"],"apc_list":null,"apc_paid":null,"fwci":1.5153,"has_fulltext":false,"cited_by_count":10,"citation_normalized_percentile":{"value":0.82692561,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":"70","issue":null,"first_page":"6769","last_page":"6773"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9997000098228455,"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":0.9997000098228455,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9993000030517578,"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/T11309","display_name":"Music and Audio Processing","score":0.9993000030517578,"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":0.7072020769119263},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7004860043525696},{"id":"https://openalex.org/keywords/speech-coding","display_name":"Speech coding","score":0.645237147808075},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.5190796852111816},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.5039657950401306},{"id":"https://openalex.org/keywords/quantization","display_name":"Quantization (signal processing)","score":0.48750564455986023},{"id":"https://openalex.org/keywords/vector-quantization","display_name":"Vector quantization","score":0.45306190848350525},{"id":"https://openalex.org/keywords/speech-enhancement","display_name":"Speech enhancement","score":0.4299886226654053},{"id":"https://openalex.org/keywords/coding","display_name":"Coding (social sciences)","score":0.424262672662735},{"id":"https://openalex.org/keywords/voice-activity-detection","display_name":"Voice activity detection","score":0.41171106696128845},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3775585889816284},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.368127703666687},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.33317917585372925},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.1965429186820984},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.18521064519882202},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.1301741600036621}],"concepts":[{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7072020769119263},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7004860043525696},{"id":"https://openalex.org/C13895895","wikidata":"https://www.wikidata.org/wiki/Q3270773","display_name":"Speech coding","level":2,"score":0.645237147808075},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.5190796852111816},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.5039657950401306},{"id":"https://openalex.org/C28855332","wikidata":"https://www.wikidata.org/wiki/Q198099","display_name":"Quantization (signal processing)","level":2,"score":0.48750564455986023},{"id":"https://openalex.org/C199833920","wikidata":"https://www.wikidata.org/wiki/Q612536","display_name":"Vector quantization","level":2,"score":0.45306190848350525},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.4299886226654053},{"id":"https://openalex.org/C179518139","wikidata":"https://www.wikidata.org/wiki/Q5140297","display_name":"Coding (social sciences)","level":2,"score":0.424262672662735},{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.41171106696128845},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3775585889816284},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.368127703666687},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.33317917585372925},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.1965429186820984},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.18521064519882202},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.1301741600036621},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"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/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp40776.2020.9053657","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp40776.2020.9053657","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":[{"score":0.7400000095367432,"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":37,"referenced_works":["https://openalex.org/W160896187","https://openalex.org/W1591492847","https://openalex.org/W1594680456","https://openalex.org/W2033875152","https://openalex.org/W2037034710","https://openalex.org/W2098717508","https://openalex.org/W2108532241","https://openalex.org/W2127589108","https://openalex.org/W2130158387","https://openalex.org/W2158554386","https://openalex.org/W2164764235","https://openalex.org/W2164943005","https://openalex.org/W2165291881","https://openalex.org/W2519091744","https://openalex.org/W2584032004","https://openalex.org/W2591927543","https://openalex.org/W2752796333","https://openalex.org/W2775336875","https://openalex.org/W2911317657","https://openalex.org/W2911940095","https://openalex.org/W2935711438","https://openalex.org/W2938418853","https://openalex.org/W2949382160","https://openalex.org/W2950237361","https://openalex.org/W2963208781","https://openalex.org/W2963799213","https://openalex.org/W2964307104","https://openalex.org/W2972354707","https://openalex.org/W2972359262","https://openalex.org/W2972519044","https://openalex.org/W2972827473","https://openalex.org/W2996286887","https://openalex.org/W4298580827","https://openalex.org/W6732429163","https://openalex.org/W6748409065","https://openalex.org/W6761768988","https://openalex.org/W6768435317"],"related_works":["https://openalex.org/W2115984063","https://openalex.org/W2160220319","https://openalex.org/W2138799587","https://openalex.org/W2377001183","https://openalex.org/W2072046374","https://openalex.org/W2167107465","https://openalex.org/W2373451165","https://openalex.org/W2120771489","https://openalex.org/W642007152","https://openalex.org/W2056066842"],"abstract_inverted_index":{"Rapid":[0],"advances":[1],"in":[2,12,33,54],"machine-learning":[3],"based":[4,44],"generative":[5],"modeling":[6],"of":[7,20,28,74,77,115],"speech":[8,13],"make":[9],"its":[10],"use":[11,32],"coding":[14],"attractive.":[15],"However,":[16],"the":[17,29,51,63,68,116],"current":[18],"performance":[19,121],"such":[21],"models":[22],"drops":[23],"rapidly":[24],"with":[25],"noise":[26],"contamination":[27],"input,":[30],"preventing":[31],"practical":[34],"applications.":[35],"We":[36],"present":[37],"a":[38,75,87,101,111],"new":[39],"speech-coding":[40],"scheme":[41],"that":[42,47,110],"is":[43,126],"on":[45],"features":[46,71],"are":[48,98],"robust":[49,128],"to":[50,66,86,95,129],"distortions":[52],"occurring":[53],"speech-coder":[55],"input":[56],"signals.":[57],"To":[58],"this":[59],"purpose,":[60],"we":[61],"encourage":[62],"feature":[64],"encoder":[65],"provide":[67],"same":[69],"independent":[70,92],"for":[72,105,122],"each":[73],"set":[76],"linguistically":[78],"equivalent":[79],"signals,":[80,124],"obtained":[81],"by":[82],"adding":[83],"various":[84],"noises":[85],"common":[88],"clean":[89,123],"signal.":[90],"The":[91],"features,":[93],"subjected":[94],"scalar":[96],"quantization,":[97],"used":[99],"as":[100],"conditioning":[102],"vector":[103],"sequence":[104],"WaveNet.":[106],"Our":[107],"experiments":[108],"show":[109],"1.8":[112],"kb/s":[113],"implementation":[114],"resulting":[117],"coder":[118],"provides":[119],"state-of-the-art":[120],"and":[125],"additionally":[127],"noisy":[130],"input.":[131]},"counts_by_year":[{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":7},{"year":2020,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}