{"id":"https://openalex.org/W7148498175","doi":"https://doi.org/10.1109/asru65441.2025.11434796","title":"Towards General Discrete Speech Codec for Complex Acoustic Environments: A Study of Reconstruction and Downstream Task Consistency","display_name":"Towards General Discrete Speech Codec for Complex Acoustic Environments: A Study of Reconstruction and Downstream Task Consistency","publication_year":2025,"publication_date":"2025-12-06","ids":{"openalex":"https://openalex.org/W7148498175","doi":"https://doi.org/10.1109/asru65441.2025.11434796"},"language":null,"primary_location":{"id":"doi:10.1109/asru65441.2025.11434796","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asru65441.2025.11434796","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","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/A5100446035","display_name":"Hao Wang","orcid":"https://orcid.org/0000-0001-6881-9977"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Haoran Wang","raw_affiliation_strings":["Shanghai Jiao Tong University,MoE Key Lab of Artificial Intelligence, Jiangsu Key Lab of Language Computing, X-LANCE Lab, School of Computer Science,China"],"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University,MoE Key Lab of Artificial Intelligence, Jiangsu Key Lab of Language Computing, X-LANCE Lab, School of Computer Science,China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Guanyu Chen","orcid":null},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Guanyu Chen","raw_affiliation_strings":["Shanghai Jiao Tong University,MoE Key Lab of Artificial Intelligence, Jiangsu Key Lab of Language Computing, X-LANCE Lab, School of Computer Science,China"],"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University,MoE Key Lab of Artificial Intelligence, Jiangsu Key Lab of Language Computing, X-LANCE Lab, School of Computer Science,China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5132824332","display_name":"Bohan Li","orcid":null},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Bohan Li","raw_affiliation_strings":["Shanghai Jiao Tong University,MoE Key Lab of Artificial Intelligence, Jiangsu Key Lab of Language Computing, X-LANCE Lab, School of Computer Science,China"],"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University,MoE Key Lab of Artificial Intelligence, Jiangsu Key Lab of Language Computing, X-LANCE Lab, School of Computer Science,China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103183873","display_name":"Hankun Wang","orcid":"https://orcid.org/0000-0003-0338-1809"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hankun Wang","raw_affiliation_strings":["Shanghai Jiao Tong University,MoE Key Lab of Artificial Intelligence, Jiangsu Key Lab of Language Computing, X-LANCE Lab, School of Computer Science,China"],"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University,MoE Key Lab of Artificial Intelligence, Jiangsu Key Lab of Language Computing, X-LANCE Lab, School of Computer Science,China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Yiwei Guo","orcid":null},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yiwei Guo","raw_affiliation_strings":["Shanghai Jiao Tong University,MoE Key Lab of Artificial Intelligence, Jiangsu Key Lab of Language Computing, X-LANCE Lab, School of Computer Science,China"],"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University,MoE Key Lab of Artificial Intelligence, Jiangsu Key Lab of Language Computing, X-LANCE Lab, School of Computer Science,China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102930758","display_name":"Zhihan Li","orcid":"https://orcid.org/0000-0001-5242-9990"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhihan Li","raw_affiliation_strings":["Shanghai Jiao Tong University,MoE Key Lab of Artificial Intelligence, Jiangsu Key Lab of Language Computing, X-LANCE Lab, School of Computer Science,China"],"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University,MoE Key Lab of Artificial Intelligence, Jiangsu Key Lab of Language Computing, X-LANCE Lab, School of Computer Science,China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5132816935","display_name":"Xie Chen","orcid":null},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xie Chen","raw_affiliation_strings":["Shanghai Jiao Tong University,MoE Key Lab of Artificial Intelligence, Jiangsu Key Lab of Language Computing, X-LANCE Lab, School of Computer Science,China"],"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University,MoE Key Lab of Artificial Intelligence, Jiangsu Key Lab of Language Computing, X-LANCE Lab, School of Computer Science,China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5132801590","display_name":"Kai Yu","orcid":null},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Kai Yu","raw_affiliation_strings":["Shanghai Jiao Tong University,MoE Key Lab of Artificial Intelligence, Jiangsu Key Lab of Language Computing, X-LANCE Lab, School of Computer Science,China"],"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University,MoE Key Lab of Artificial Intelligence, Jiangsu Key Lab of Language Computing, X-LANCE Lab, School of Computer Science,China","institution_ids":["https://openalex.org/I183067930"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":8,"corresponding_author_ids":["https://openalex.org/A5100446035"],"corresponding_institution_ids":["https://openalex.org/I183067930"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.86702962,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"6"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.6804999709129333,"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":0.6804999709129333,"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/T10860","display_name":"Speech and Audio Processing","score":0.056699998676776886,"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/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.026399999856948853,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/codec","display_name":"Codec","score":0.7044000029563904},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.6464999914169312},{"id":"https://openalex.org/keywords/downstream","display_name":"Downstream (manufacturing)","score":0.6413000226020813},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.6358000040054321},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.45719999074935913},{"id":"https://openalex.org/keywords/consistency","display_name":"Consistency (knowledge bases)","score":0.45329999923706055},{"id":"https://openalex.org/keywords/speech-coding","display_name":"Speech coding","score":0.4163999855518341},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.40560001134872437}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7698000073432922},{"id":"https://openalex.org/C161765866","wikidata":"https://www.wikidata.org/wiki/Q184748","display_name":"Codec","level":2,"score":0.7044000029563904},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.6464999914169312},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.644599974155426},{"id":"https://openalex.org/C2776207758","wikidata":"https://www.wikidata.org/wiki/Q5303302","display_name":"Downstream (manufacturing)","level":2,"score":0.6413000226020813},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.6358000040054321},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.45719999074935913},{"id":"https://openalex.org/C2776436953","wikidata":"https://www.wikidata.org/wiki/Q5163215","display_name":"Consistency (knowledge bases)","level":2,"score":0.45329999923706055},{"id":"https://openalex.org/C13895895","wikidata":"https://www.wikidata.org/wiki/Q3270773","display_name":"Speech coding","level":2,"score":0.4163999855518341},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.40560001134872437},{"id":"https://openalex.org/C2779843651","wikidata":"https://www.wikidata.org/wiki/Q7390335","display_name":"SIGNAL (programming language)","level":2,"score":0.4020000100135803},{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.40130001306533813},{"id":"https://openalex.org/C104267543","wikidata":"https://www.wikidata.org/wiki/Q208163","display_name":"Signal processing","level":3,"score":0.3919999897480011},{"id":"https://openalex.org/C75217168","wikidata":"https://www.wikidata.org/wiki/Q1105653","display_name":"Codec2","level":4,"score":0.39079999923706055},{"id":"https://openalex.org/C155635449","wikidata":"https://www.wikidata.org/wiki/Q4674699","display_name":"Acoustic model","level":3,"score":0.35670000314712524},{"id":"https://openalex.org/C70958404","wikidata":"https://www.wikidata.org/wiki/Q7512728","display_name":"Signal reconstruction","level":4,"score":0.32170000672340393},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.3100000023841858},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3100000023841858},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.30379998683929443},{"id":"https://openalex.org/C59883199","wikidata":"https://www.wikidata.org/wiki/Q1826438","display_name":"Linear predictive coding","level":3,"score":0.3037000000476837},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.287200003862381},{"id":"https://openalex.org/C108699837","wikidata":"https://www.wikidata.org/wiki/Q7120750","display_name":"PSQM","level":4,"score":0.26510000228881836},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.2612000107765198}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/asru65441.2025.11434796","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asru65441.2025.11434796","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320337504","display_name":"Research and Development","ror":"https://ror.org/027s68j25"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":14,"referenced_works":["https://openalex.org/W2070707809","https://openalex.org/W2972541922","https://openalex.org/W3097906045","https://openalex.org/W3163652268","https://openalex.org/W3209059054","https://openalex.org/W4225905067","https://openalex.org/W4372260337","https://openalex.org/W4401070302","https://openalex.org/W4404740148","https://openalex.org/W4406417959","https://openalex.org/W4409362462","https://openalex.org/W4411119792","https://openalex.org/W4417305271","https://openalex.org/W7133219565"],"related_works":[],"abstract_inverted_index":{"Neural":[0],"speech":[1,7,42,61,83,111],"codecs":[2,43,112],"excel":[3],"in":[4,12,75],"reconstructing":[5],"clean":[6],"signals;":[8],"however,":[9],"their":[10],"efficacy":[11],"complex":[13,93],"acoustic":[14,64,94],"environments":[15,95],"and":[16,62,66,100,113],"downstream":[17,68,76,101],"signal":[18,77,98],"processing":[19,78],"tasks":[20,79],"remains":[21],"underexplored.":[22],"In":[23],"this":[24],"study,":[25],"we":[26,47],"introduce":[27],"a":[28,115],"novel":[29],"benchmark":[30],"named":[31],"Environment-Resilient":[32],"Speech":[33],"Codec":[34],"Benchmark":[35],"(ERSB)":[36],"to":[37],"systematically":[38],"evaluate":[39],"whether":[40],"neural":[41],"are":[44],"environment-resilient.":[45],"Specifically,":[46],"assess":[48],"two":[49],"key":[50],"capabilities:":[51],"(1)":[52],"robust":[53],"reconstruction,":[54],"which":[55,71],"measures":[56],"the":[57,86,107],"preservation":[58],"of":[59,85,109],"both":[60],"non-speech":[63],"details,":[65],"(2)":[67],"task":[69,102],"consistency,":[70],"ensures":[72],"minimal":[73],"deviation":[74],"when":[80],"using":[81],"reconstructed":[82],"instead":[84],"original.":[87],"Our":[88],"comprehensive":[89],"experiments":[90],"reveal":[91],"that":[92,118],"significantly":[96],"degrade":[97],"reconstruction":[99],"consistency.":[103],"This":[104],"work":[105],"highlights":[106],"limitations":[108],"current":[110],"raises":[114],"future":[116],"direction":[117],"improves":[119],"them":[120],"for":[121],"greater":[122],"environmental":[123],"resilience.":[124]},"counts_by_year":[],"updated_date":"2026-04-21T08:09:41.155169","created_date":"2026-04-03T00:00:00"}