{"id":"https://openalex.org/W2972354707","doi":"https://doi.org/10.21437/interspeech.2019-1816","title":"Cascaded Cross-Module Residual Learning Towards Lightweight End-to-End Speech Coding","display_name":"Cascaded Cross-Module Residual Learning Towards Lightweight End-to-End Speech Coding","publication_year":2019,"publication_date":"2019-09-13","ids":{"openalex":"https://openalex.org/W2972354707","doi":"https://doi.org/10.21437/interspeech.2019-1816","mag":"2972354707"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2019-1816","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2019-1816","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2019","raw_type":"proceedings-article"},"type":"conference-paper","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/A5047870570","display_name":"Kai Zhen","orcid":"https://orcid.org/0000-0003-4133-8158"},"institutions":[{"id":"https://openalex.org/I4210119109","display_name":"Indiana University Bloomington","ror":"https://ror.org/02k40bc56","country_code":"US","type":"education","lineage":["https://openalex.org/I4210119109","https://openalex.org/I592451"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Kai Zhen","raw_affiliation_strings":["Indiana University, Cognitive Science Program, Bloomington, IN","Indiana University, School of Informatics, Computing, and Engineering, Bloomington, IN"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Indiana University, Cognitive Science Program, Bloomington, IN","institution_ids":["https://openalex.org/I4210119109"]},{"raw_affiliation_string":"Indiana University, School of Informatics, Computing, and Engineering, Bloomington, IN","institution_ids":["https://openalex.org/I4210119109"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5033055249","display_name":"Jongmo Sung","orcid":"https://orcid.org/0000-0002-3396-1137"},"institutions":[{"id":"https://openalex.org/I142401562","display_name":"Electronics and Telecommunications Research Institute","ror":"https://ror.org/03ysstz10","country_code":"KR","type":"facility","lineage":["https://openalex.org/I142401562","https://openalex.org/I2801339556","https://openalex.org/I4210144908","https://openalex.org/I4387152098"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Jongmo Sung","raw_affiliation_strings":["Electronics and Telecommunications Research Institute, Daejeon, South Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Electronics and Telecommunications Research Institute, Daejeon, South Korea","institution_ids":["https://openalex.org/I142401562"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5005473429","display_name":"Mi Suk Lee","orcid":"https://orcid.org/0000-0001-8951-5032"},"institutions":[{"id":"https://openalex.org/I142401562","display_name":"Electronics and Telecommunications Research Institute","ror":"https://ror.org/03ysstz10","country_code":"KR","type":"facility","lineage":["https://openalex.org/I142401562","https://openalex.org/I2801339556","https://openalex.org/I4210144908","https://openalex.org/I4387152098"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Mi Suk Lee","raw_affiliation_strings":["Electronics and Telecommunications Research Institute, Daejeon, South Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Electronics and Telecommunications Research Institute, Daejeon, South Korea","institution_ids":["https://openalex.org/I142401562"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5071537541","display_name":"Seungkwon Beack","orcid":"https://orcid.org/0000-0002-6254-2062"},"institutions":[{"id":"https://openalex.org/I142401562","display_name":"Electronics and Telecommunications Research Institute","ror":"https://ror.org/03ysstz10","country_code":"KR","type":"facility","lineage":["https://openalex.org/I142401562","https://openalex.org/I2801339556","https://openalex.org/I4210144908","https://openalex.org/I4387152098"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Seungkwon Beack","raw_affiliation_strings":["Electronics and Telecommunications Research Institute, Daejeon, South Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Electronics and Telecommunications Research Institute, Daejeon, South Korea","institution_ids":["https://openalex.org/I142401562"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5064582903","display_name":"Minje Kim","orcid":"https://orcid.org/0000-0003-3513-8328"},"institutions":[{"id":"https://openalex.org/I4210119109","display_name":"Indiana University Bloomington","ror":"https://ror.org/02k40bc56","country_code":"US","type":"education","lineage":["https://openalex.org/I4210119109","https://openalex.org/I592451"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Minje Kim","raw_affiliation_strings":["Indiana University, Cognitive Science Program, Bloomington, IN","Indiana University, School of Informatics, Computing, and Engineering, Bloomington, IN"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Indiana University, Cognitive Science Program, Bloomington, IN","institution_ids":["https://openalex.org/I4210119109"]},{"raw_affiliation_string":"Indiana University, School of Informatics, Computing, and Engineering, Bloomington, IN","institution_ids":["https://openalex.org/I4210119109"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":3.2496,"has_fulltext":false,"cited_by_count":36,"citation_normalized_percentile":{"value":0.93400433,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":96,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"3396","last_page":"3400"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9998000264167786,"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":0.9998000264167786,"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":0.9994999766349792,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9994000196456909,"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/codec","display_name":"Codec","score":0.8488872051239014},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8062169551849365},{"id":"https://openalex.org/keywords/speech-coding","display_name":"Speech coding","score":0.7211151123046875},{"id":"https://openalex.org/keywords/residual","display_name":"Residual","score":0.6548867225646973},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6144780516624451},{"id":"https://openalex.org/keywords/code-excited-linear-prediction","display_name":"Code-excited linear prediction","score":0.5120937824249268},{"id":"https://openalex.org/keywords/linear-predictive-coding","display_name":"Linear predictive coding","score":0.4987664222717285},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.46997493505477905},{"id":"https://openalex.org/keywords/end-to-end-principle","display_name":"End-to-end principle","score":0.4302923083305359},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.349337637424469},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.16799703240394592},{"id":"https://openalex.org/keywords/computer-hardware","display_name":"Computer hardware","score":0.1651955544948578}],"concepts":[{"id":"https://openalex.org/C161765866","wikidata":"https://www.wikidata.org/wiki/Q184748","display_name":"Codec","level":2,"score":0.8488872051239014},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8062169551849365},{"id":"https://openalex.org/C13895895","wikidata":"https://www.wikidata.org/wiki/Q3270773","display_name":"Speech coding","level":2,"score":0.7211151123046875},{"id":"https://openalex.org/C155512373","wikidata":"https://www.wikidata.org/wiki/Q287450","display_name":"Residual","level":2,"score":0.6548867225646973},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6144780516624451},{"id":"https://openalex.org/C105964291","wikidata":"https://www.wikidata.org/wiki/Q856184","display_name":"Code-excited linear prediction","level":4,"score":0.5120937824249268},{"id":"https://openalex.org/C59883199","wikidata":"https://www.wikidata.org/wiki/Q1826438","display_name":"Linear predictive coding","level":3,"score":0.4987664222717285},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.46997493505477905},{"id":"https://openalex.org/C74296488","wikidata":"https://www.wikidata.org/wiki/Q2527392","display_name":"End-to-end principle","level":2,"score":0.4302923083305359},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.349337637424469},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.16799703240394592},{"id":"https://openalex.org/C9390403","wikidata":"https://www.wikidata.org/wiki/Q3966","display_name":"Computer hardware","level":1,"score":0.1651955544948578}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21437/interspeech.2019-1816","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2019-1816","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2019","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16","score":0.49000000953674316}],"awards":[],"funders":[{"id":"https://openalex.org/F4320324891","display_name":"Iran Telecommunication Research Center","ror":"https://ror.org/01a3g2z22"},{"id":"https://openalex.org/F4320328359","display_name":"Ministry of Science and ICT, South Korea","ror":"https://ror.org/01wpjm123"},{"id":"https://openalex.org/F4320335489","display_name":"Institute for Information and Communications Technology Promotion","ror":"https://ror.org/01g0hqq23"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":30,"referenced_works":["https://openalex.org/W1512294521","https://openalex.org/W1522301498","https://openalex.org/W1552314771","https://openalex.org/W1553834069","https://openalex.org/W1556611829","https://openalex.org/W1703292843","https://openalex.org/W2002182716","https://openalex.org/W2013078344","https://openalex.org/W2020883660","https://openalex.org/W2037034710","https://openalex.org/W2060108852","https://openalex.org/W2129652681","https://openalex.org/W2151626637","https://openalex.org/W2165291881","https://openalex.org/W2168013545","https://openalex.org/W2194775991","https://openalex.org/W2266701264","https://openalex.org/W2309400744","https://openalex.org/W2476548250","https://openalex.org/W2584032004","https://openalex.org/W2597747080","https://openalex.org/W2732044853","https://openalex.org/W2775336875","https://openalex.org/W2889329491","https://openalex.org/W2891355459","https://openalex.org/W2935711438","https://openalex.org/W2963182577","https://openalex.org/W2963208781","https://openalex.org/W3127686677","https://openalex.org/W4297752165"],"related_works":["https://openalex.org/W1570840316","https://openalex.org/W2899318368","https://openalex.org/W1551277881","https://openalex.org/W2051489660","https://openalex.org/W2155796184","https://openalex.org/W2402025388","https://openalex.org/W2014919663","https://openalex.org/W2129876624","https://openalex.org/W1042315724","https://openalex.org/W2370596938"],"abstract_inverted_index":{"Speech":[0],"codecs":[1,20,156],"learn":[2],"compact":[3],"representations":[4],"of":[5,31,79],"speech":[6,19,59,66,99],"signals":[7,113],"to":[8],"facilitate":[9],"data":[10],"transmission.Many":[11],"recent":[12],"deep":[13],"neural":[14,73],"network":[15,104],"(DNN)":[16],"based":[17],"end-to-end":[18,107],"achieve":[21],"low":[22],"bitrates":[23,132],"and":[24,95,135],"high":[25,131],"perceptual":[26],"quality":[27,129],"at":[28,130],"the":[29,49,96,153,158],"cost":[30],"model":[32],"complexity.We":[33],"propose":[34],"a":[35,42,70,77,83,102,147],"cross-module":[36],"residual":[37,50],"learning":[38],"(CMRL)":[39],"pipeline":[40],"as":[41,114],"module":[43,47],"carrier":[44],"with":[45,101,121],"each":[46],"reconstructing":[48],"from":[51,56],"its":[52],"preceding":[53],"modules.CMRL":[54],"differs":[55],"other":[57,154],"DNN-based":[58,155],"codecs,":[60],"in":[61,69,82,157],"that":[62],"rather":[63],"than":[64,93,133,152],"modeling":[65],"compression":[67],"problem":[68],"single":[71],"large":[72],"network,":[74],"it":[75,109],"optimizes":[76],"series":[78],"less-complicated":[80],"modules":[81],"two-phase":[84],"training":[85],"scheme.The":[86],"proposed":[87],"method":[88],"shows":[89],"better":[90,127],"objective":[91],"performance":[92],"AMR-WB":[94,134],"state-of-the-art":[97],"DNNbased":[98],"codec":[100],"similar":[103],"architecture.As":[105],"an":[106,115],"model,":[108],"takes":[110],"raw":[111],"PCM":[112],"input,":[116],"but":[117],"is":[118,138],"also":[119],"compatible":[120],"linear":[122],"predictive":[123],"coding":[124],"(LPC),":[125],"showing":[126],"subjective":[128],"OPUS.The":[136],"gain":[137],"achieved":[139],"by":[140],"using":[141],"only":[142],"0.9":[143],"million":[144],"trainable":[145],"parameters,":[146],"significantly":[148],"less":[149],"complex":[150],"architecture":[151],"literature.":[159]},"counts_by_year":[{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":6},{"year":2023,"cited_by_count":10},{"year":2022,"cited_by_count":8},{"year":2021,"cited_by_count":5},{"year":2020,"cited_by_count":4}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}