{"id":"https://openalex.org/W3210440118","doi":"https://doi.org/10.1109/icspcc52875.2021.9564779","title":"A New Four-Channel Speech Coding Method Based on Recurrent Neural Network","display_name":"A New Four-Channel Speech Coding Method Based on Recurrent Neural Network","publication_year":2021,"publication_date":"2021-08-17","ids":{"openalex":"https://openalex.org/W3210440118","doi":"https://doi.org/10.1109/icspcc52875.2021.9564779","mag":"3210440118"},"language":"en","primary_location":{"id":"doi:10.1109/icspcc52875.2021.9564779","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icspcc52875.2021.9564779","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 IEEE International Conference on Signal Processing, Communications and Computing (ICSPCC)","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/A5064549045","display_name":"Xue Yang","orcid":"https://orcid.org/0000-0001-5846-5319"},"institutions":[{"id":"https://openalex.org/I37796252","display_name":"Beijing University of Technology","ror":"https://ror.org/037b1pp87","country_code":"CN","type":"education","lineage":["https://openalex.org/I37796252"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xue Yang","raw_affiliation_strings":["Speech and Audio Signal Processing Laboratory, Faculty of Information Technology, Beijing University of Technology, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Speech and Audio Signal Processing Laboratory, Faculty of Information Technology, Beijing University of Technology, Beijing, China","institution_ids":["https://openalex.org/I37796252"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5070475244","display_name":"Changchun Bao","orcid":"https://orcid.org/0000-0002-5606-5343"},"institutions":[{"id":"https://openalex.org/I37796252","display_name":"Beijing University of Technology","ror":"https://ror.org/037b1pp87","country_code":"CN","type":"education","lineage":["https://openalex.org/I37796252"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Changchun Bao","raw_affiliation_strings":["Speech and Audio Signal Processing Laboratory, Faculty of Information Technology, Beijing University of Technology, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Speech and Audio Signal Processing Laboratory, Faculty of Information Technology, Beijing University of Technology, Beijing, China","institution_ids":["https://openalex.org/I37796252"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I37796252"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.13804528,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"10","issue":null,"first_page":"1","last_page":"5"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":1.0,"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":1.0,"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/T11309","display_name":"Music and Audio Processing","score":0.9991000294685364,"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":0.9980999827384949,"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/computer-science","display_name":"Computer science","score":0.7705249786376953},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7659797668457031},{"id":"https://openalex.org/keywords/speech-coding","display_name":"Speech coding","score":0.7381008863449097},{"id":"https://openalex.org/keywords/residual","display_name":"Residual","score":0.7266514897346497},{"id":"https://openalex.org/keywords/codec","display_name":"Codec","score":0.6820205450057983},{"id":"https://openalex.org/keywords/recurrent-neural-network","display_name":"Recurrent neural network","score":0.6534388065338135},{"id":"https://openalex.org/keywords/linear-predictive-coding","display_name":"Linear predictive coding","score":0.5841307640075684},{"id":"https://openalex.org/keywords/vector-sum-excited-linear-prediction","display_name":"Vector sum excited linear prediction","score":0.5786486268043518},{"id":"https://openalex.org/keywords/decoding-methods","display_name":"Decoding methods","score":0.5152040123939514},{"id":"https://openalex.org/keywords/coding","display_name":"Coding (social sciences)","score":0.5133609175682068},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.5039612650871277},{"id":"https://openalex.org/keywords/channel","display_name":"Channel (broadcasting)","score":0.49363791942596436},{"id":"https://openalex.org/keywords/microphone","display_name":"Microphone","score":0.430919885635376},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.42970559000968933},{"id":"https://openalex.org/keywords/linear-prediction","display_name":"Linear prediction","score":0.4296990633010864},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4122334122657776},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.36991703510284424},{"id":"https://openalex.org/keywords/code-excited-linear-prediction","display_name":"Code-excited linear prediction","score":0.3528672456741333},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.283555269241333},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.10278564691543579},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.09611672163009644}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7705249786376953},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7659797668457031},{"id":"https://openalex.org/C13895895","wikidata":"https://www.wikidata.org/wiki/Q3270773","display_name":"Speech coding","level":2,"score":0.7381008863449097},{"id":"https://openalex.org/C155512373","wikidata":"https://www.wikidata.org/wiki/Q287450","display_name":"Residual","level":2,"score":0.7266514897346497},{"id":"https://openalex.org/C161765866","wikidata":"https://www.wikidata.org/wiki/Q184748","display_name":"Codec","level":2,"score":0.6820205450057983},{"id":"https://openalex.org/C147168706","wikidata":"https://www.wikidata.org/wiki/Q1457734","display_name":"Recurrent neural network","level":3,"score":0.6534388065338135},{"id":"https://openalex.org/C59883199","wikidata":"https://www.wikidata.org/wiki/Q1826438","display_name":"Linear predictive coding","level":3,"score":0.5841307640075684},{"id":"https://openalex.org/C138807605","wikidata":"https://www.wikidata.org/wiki/Q7917845","display_name":"Vector sum excited linear prediction","level":5,"score":0.5786486268043518},{"id":"https://openalex.org/C57273362","wikidata":"https://www.wikidata.org/wiki/Q576722","display_name":"Decoding methods","level":2,"score":0.5152040123939514},{"id":"https://openalex.org/C179518139","wikidata":"https://www.wikidata.org/wiki/Q5140297","display_name":"Coding (social sciences)","level":2,"score":0.5133609175682068},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5039612650871277},{"id":"https://openalex.org/C127162648","wikidata":"https://www.wikidata.org/wiki/Q16858953","display_name":"Channel (broadcasting)","level":2,"score":0.49363791942596436},{"id":"https://openalex.org/C2778263558","wikidata":"https://www.wikidata.org/wiki/Q46384","display_name":"Microphone","level":3,"score":0.430919885635376},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.42970559000968933},{"id":"https://openalex.org/C131109320","wikidata":"https://www.wikidata.org/wiki/Q581012","display_name":"Linear prediction","level":2,"score":0.4296990633010864},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4122334122657776},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.36991703510284424},{"id":"https://openalex.org/C105964291","wikidata":"https://www.wikidata.org/wiki/Q856184","display_name":"Code-excited linear prediction","level":4,"score":0.3528672456741333},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.283555269241333},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.10278564691543579},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.09611672163009644},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0},{"id":"https://openalex.org/C68115822","wikidata":"https://www.wikidata.org/wiki/Q1068172","display_name":"Sound pressure","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icspcc52875.2021.9564779","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icspcc52875.2021.9564779","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 IEEE International Conference on Signal Processing, Communications and Computing (ICSPCC)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.4399999976158142,"display_name":"Quality Education"}],"awards":[{"id":"https://openalex.org/G3909335432","display_name":"\u590d\u6742\u573a\u666f\u58f0\u4fe1\u53f7\u83b7\u53d6\u548c\u8bc6\u522b\u57fa\u7840\u7406\u8bba\u4e0e\u65b9\u6cd5\u7814\u7a76: \u591a\u901a\u9053\u58f0\u4fe1\u53f7\u83b7\u53d6\u3001\u4f20\u8f93\u4e0e\u91cd\u6784","funder_award_id":"61831019","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":32,"referenced_works":["https://openalex.org/W1552314771","https://openalex.org/W1597752450","https://openalex.org/W1974387177","https://openalex.org/W2024205924","https://openalex.org/W2046317813","https://openalex.org/W2061074721","https://openalex.org/W2094099446","https://openalex.org/W2113744809","https://openalex.org/W2135817141","https://openalex.org/W2138406058","https://openalex.org/W2141532435","https://openalex.org/W2141998673","https://openalex.org/W2152961470","https://openalex.org/W2155889651","https://openalex.org/W2157331557","https://openalex.org/W2157363431","https://openalex.org/W2158688802","https://openalex.org/W2166223512","https://openalex.org/W2403555780","https://openalex.org/W2568308529","https://openalex.org/W2799789537","https://openalex.org/W3007541473","https://openalex.org/W3094114204","https://openalex.org/W3127686677","https://openalex.org/W4296927107","https://openalex.org/W6635825563","https://openalex.org/W6662135573","https://openalex.org/W6665565033","https://openalex.org/W6682822620","https://openalex.org/W6683258052","https://openalex.org/W6713425292","https://openalex.org/W6917638038"],"related_works":["https://openalex.org/W1570840316","https://openalex.org/W1982751076","https://openalex.org/W2051489660","https://openalex.org/W2119342582","https://openalex.org/W2794974041","https://openalex.org/W2350749055","https://openalex.org/W1042315724","https://openalex.org/W2111369522","https://openalex.org/W2402025388","https://openalex.org/W2114934544"],"abstract_inverted_index":{"With":[0],"the":[1,19,69,80,84,88,93,101,108,116,122,125,131,136],"increase":[2],"of":[3,23,44,96,107,124],"microphone":[4],"array":[5],"applications,":[6],"multi-channel":[7],"speech":[8,30,105,146],"coding":[9,31],"has":[10],"become":[11],"an":[12],"important":[13],"technology.":[14],"In":[15],"this":[16],"paper,":[17],"using":[18,52,68,115],"powerful":[20],"learning":[21],"ability":[22],"deep":[24],"neural":[25,36],"network,":[26],"a":[27,53,141],"new":[28],"four-channel":[29,145],"method":[32,127,138],"based":[33],"on":[34],"recurrent":[35],"network":[37],"(RNN)":[38],"is":[39,76],"proposed.":[40],"Only":[41],"two":[42,57,98,110],"signals":[43,59,66,86,95,106],"four":[45],"channels":[46,99,111],"are":[47,60],"encoded":[48],"and":[49,91,130],"decoded":[50,58],"separately":[51],"standard":[54],"codec.":[55],"These":[56],"processed":[61],"to":[62,78],"obtain":[63,140],"their":[64],"residual":[65,85,94],"by":[67],"well-known":[70],"linear":[71],"prediction":[72],"analysis.":[73],"The":[74],"RNN":[75],"used":[77],"learn":[79],"differences":[81],"lied":[82],"in":[83,87,100],"training":[89],"stage":[90],"predict":[92],"other":[97,109],"testing":[102],"stage.":[103],"Finally,":[104],"can":[112],"be":[113],"recovered":[114],"synthesis":[117],"process.":[118],"Through":[119],"objective":[120],"measurements,":[121],"performance":[123],"proposed":[126,137],"was":[128],"assessed":[129],"experimental":[132],"results":[133],"indicated":[134],"that":[135],"could":[139],"higher":[142],"efficiency":[143],"for":[144],"coding.":[147]},"counts_by_year":[],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}