{"id":"https://openalex.org/W4416798550","doi":"https://doi.org/10.1109/apsipaasc65261.2025.11249345","title":"A High-Quality and Low-Complexity Streamable Neural Speech Codec with Knowledge Distillation","display_name":"A High-Quality and Low-Complexity Streamable Neural Speech Codec with Knowledge Distillation","publication_year":2025,"publication_date":"2025-10-22","ids":{"openalex":"https://openalex.org/W4416798550","doi":"https://doi.org/10.1109/apsipaasc65261.2025.11249345"},"language":null,"primary_location":{"id":"doi:10.1109/apsipaasc65261.2025.11249345","is_oa":false,"landing_page_url":"https://doi.org/10.1109/apsipaasc65261.2025.11249345","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 Asia Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)","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":null,"display_name":"En-Wei Zhang","orcid":null},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"En-Wei Zhang","raw_affiliation_strings":["National Engineering Research Center of Speech and Language Information Processing, University of Science and Technology of China,Hefei,P. R. China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Engineering Research Center of Speech and Language Information Processing, University of Science and Technology of China,Hefei,P. R. China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5067982618","display_name":"Hui-Peng Du","orcid":null},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hui-Peng Du","raw_affiliation_strings":["National Engineering Research Center of Speech and Language Information Processing, University of Science and Technology of China,Hefei,P. R. China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Engineering Research Center of Speech and Language Information Processing, University of Science and Technology of China,Hefei,P. R. China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5031429152","display_name":"Xiao-Hang Jiang","orcid":null},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiao-Hang Jiang","raw_affiliation_strings":["National Engineering Research Center of Speech and Language Information Processing, University of Science and Technology of China,Hefei,P. R. China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Engineering Research Center of Speech and Language Information Processing, University of Science and Technology of China,Hefei,P. R. China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5045907056","display_name":"Yang Ai","orcid":"https://orcid.org/0000-0001-6668-022X"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yang Ai","raw_affiliation_strings":["National Engineering Research Center of Speech and Language Information Processing, University of Science and Technology of China,Hefei,P. R. China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Engineering Research Center of Speech and Language Information Processing, University of Science and Technology of China,Hefei,P. R. China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5059767940","display_name":"Zhen-Hua Ling","orcid":"https://orcid.org/0000-0001-7853-5273"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhen-Hua Ling","raw_affiliation_strings":["National Engineering Research Center of Speech and Language Information Processing, University of Science and Technology of China,Hefei,P. R. China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Engineering Research Center of Speech and Language Information Processing, University of Science and Technology of China,Hefei,P. R. China","institution_ids":["https://openalex.org/I126520041"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I126520041"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.17274791,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"676","last_page":"681"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.40380001068115234,"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"}},"topics":[{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.40380001068115234,"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/T10901","display_name":"Advanced Data Compression Techniques","score":0.2126999944448471,"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":0.12720000743865967,"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-coding","display_name":"Speech coding","score":0.580299973487854},{"id":"https://openalex.org/keywords/codec","display_name":"Codec","score":0.579800009727478},{"id":"https://openalex.org/keywords/codec2","display_name":"Codec2","score":0.4984000027179718},{"id":"https://openalex.org/keywords/voice-activity-detection","display_name":"Voice activity detection","score":0.47699999809265137},{"id":"https://openalex.org/keywords/psqm","display_name":"PSQM","score":0.4447000026702881},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.40299999713897705},{"id":"https://openalex.org/keywords/coding","display_name":"Coding (social sciences)","score":0.4009000062942505},{"id":"https://openalex.org/keywords/latency","display_name":"Latency (audio)","score":0.39959999918937683},{"id":"https://openalex.org/keywords/quantization","display_name":"Quantization (signal processing)","score":0.3910999894142151}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8220999836921692},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6521999835968018},{"id":"https://openalex.org/C13895895","wikidata":"https://www.wikidata.org/wiki/Q3270773","display_name":"Speech coding","level":2,"score":0.580299973487854},{"id":"https://openalex.org/C161765866","wikidata":"https://www.wikidata.org/wiki/Q184748","display_name":"Codec","level":2,"score":0.579800009727478},{"id":"https://openalex.org/C75217168","wikidata":"https://www.wikidata.org/wiki/Q1105653","display_name":"Codec2","level":4,"score":0.4984000027179718},{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.47699999809265137},{"id":"https://openalex.org/C108699837","wikidata":"https://www.wikidata.org/wiki/Q7120750","display_name":"PSQM","level":4,"score":0.4447000026702881},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.40299999713897705},{"id":"https://openalex.org/C179518139","wikidata":"https://www.wikidata.org/wiki/Q5140297","display_name":"Coding (social sciences)","level":2,"score":0.4009000062942505},{"id":"https://openalex.org/C82876162","wikidata":"https://www.wikidata.org/wiki/Q17096504","display_name":"Latency (audio)","level":2,"score":0.39959999918937683},{"id":"https://openalex.org/C28855332","wikidata":"https://www.wikidata.org/wiki/Q198099","display_name":"Quantization (signal processing)","level":2,"score":0.3910999894142151},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.38609999418258667},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.3684000074863434},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3555000126361847},{"id":"https://openalex.org/C179799912","wikidata":"https://www.wikidata.org/wiki/Q205084","display_name":"Computational complexity theory","level":2,"score":0.3353999853134155},{"id":"https://openalex.org/C59883199","wikidata":"https://www.wikidata.org/wiki/Q1826438","display_name":"Linear predictive coding","level":3,"score":0.3190000057220459},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.3138999938964844},{"id":"https://openalex.org/C179717631","wikidata":"https://www.wikidata.org/wiki/Q2991667","display_name":"Multilayer perceptron","level":3,"score":0.30219998955726624},{"id":"https://openalex.org/C57273362","wikidata":"https://www.wikidata.org/wiki/Q576722","display_name":"Decoding methods","level":2,"score":0.3000999987125397},{"id":"https://openalex.org/C60048801","wikidata":"https://www.wikidata.org/wiki/Q1433889","display_name":"Intelligibility (philosophy)","level":2,"score":0.28540000319480896},{"id":"https://openalex.org/C188198153","wikidata":"https://www.wikidata.org/wiki/Q1613840","display_name":"Limiting","level":2,"score":0.28529998660087585},{"id":"https://openalex.org/C77637269","wikidata":"https://www.wikidata.org/wiki/Q7002051","display_name":"Neural coding","level":2,"score":0.28279998898506165},{"id":"https://openalex.org/C504749915","wikidata":"https://www.wikidata.org/wiki/Q9010971","display_name":"Speech technology","level":3,"score":0.2824000120162964},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.2793999910354614},{"id":"https://openalex.org/C103734657","wikidata":"https://www.wikidata.org/wiki/Q2739975","display_name":"PESQ","level":4,"score":0.2754000127315521},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.2694000005722046},{"id":"https://openalex.org/C46637626","wikidata":"https://www.wikidata.org/wiki/Q6693015","display_name":"Low latency (capital markets)","level":2,"score":0.2687999904155731},{"id":"https://openalex.org/C177067256","wikidata":"https://www.wikidata.org/wiki/Q4676210","display_name":"Adaptive Multi-Rate audio codec","level":4,"score":0.267300009727478}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/apsipaasc65261.2025.11249345","is_oa":false,"landing_page_url":"https://doi.org/10.1109/apsipaasc65261.2025.11249345","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 Asia Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":15,"referenced_works":["https://openalex.org/W1481955708","https://openalex.org/W2067295501","https://openalex.org/W2168098717","https://openalex.org/W2407386500","https://openalex.org/W2972359262","https://openalex.org/W3037038648","https://openalex.org/W3215615641","https://openalex.org/W4297841491","https://openalex.org/W4381786045","https://openalex.org/W4392902611","https://openalex.org/W4399875170","https://openalex.org/W4405709614","https://openalex.org/W4406461725","https://openalex.org/W4409355993","https://openalex.org/W4411232650"],"related_works":[],"abstract_inverted_index":{"While":[0],"many":[1],"current":[2],"neural":[3],"speech":[4,9,28,32,44,83,100,141],"codecs":[5],"achieve":[6,139],"impressive":[7],"reconstructed":[8,57],"quality,":[10],"they":[11],"often":[12],"neglect":[13],"latency":[14,146],"and":[15,30,50,59,81,91,107,156],"complexity":[16,60,152,159],"considerations,":[17],"limiting":[18],"their":[19],"practical":[20],"deployment":[21],"in":[22],"downstream":[23],"tasks":[24],"such":[25],"as":[26],"real-time":[27],"communication":[29],"efficient":[31],"compression.":[33],"In":[34],"our":[35,129],"previous":[36],"work,":[37],"we":[38,109],"proposed":[39,130],"StreamCodec,":[40,74],"which":[41],"enables":[42],"streamable":[43,80],"coding":[45,84],"by":[46,85,104],"leveraging":[47],"model":[48,105,158],"causalization":[49,106],"a":[51,87,111],"scalar-vectorcombined":[52],"quantization":[53],"strategy,":[54,137],"but":[55],"its":[56],"quality":[58,101],"still":[61],"have":[62],"room":[63],"for":[64,98],"improvement.":[65],"Therefore,":[66],"this":[67],"paper":[68],"proposes":[69],"an":[70],"improved":[71],"iteration":[72],"of":[73,120],"named":[75],"StreamCodec2.":[76],"The":[77],"StreamCodec2":[78,121],"supports":[79],"lightweight":[82],"adopting":[86],"fully":[88],"causal":[89],"architecture":[90],"reducing":[92],"the":[93,99,118,134],"convolutional":[94],"channels.":[95],"To":[96],"compensate":[97],"degradation":[102],"caused":[103],"pruning,":[108],"introduce":[110],"non-causal,":[112],"high-complexity":[113],"teacher":[114],"codec":[115],"to":[116],"guide":[117],"training":[119],"through":[122],"knowledge":[123,135],"distillation.":[124],"Experimental":[125],"results":[126],"demonstrate":[127],"that":[128],"StreamCodec2,":[131],"trained":[132],"with":[133],"distillation":[136],"can":[138],"high-quality":[140],"reconstruction":[142],"while":[143],"maintaining":[144],"low":[145,150,157],"(only":[147,153,160],"20":[148],"ms),":[149],"computational":[151],"910":[154],"MFLOPs),":[155],"5.4":[161],"M":[162],"parameters).":[163]},"counts_by_year":[],"updated_date":"2026-06-26T08:34:08.712188","created_date":"2025-11-28T00:00:00"}