{"id":"https://openalex.org/W4415433170","doi":"https://doi.org/10.21437/interspeech.2025-1668","title":"Lightweight Front-end Enhancement for Robust ASR via Frame Resampling and Sub-Band Pruning","display_name":"Lightweight Front-end Enhancement for Robust ASR via Frame Resampling and Sub-Band Pruning","publication_year":2025,"publication_date":"2025-08-17","ids":{"openalex":"https://openalex.org/W4415433170","doi":"https://doi.org/10.21437/interspeech.2025-1668"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2025-1668","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2025-1668","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2025","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2509.21833","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5004652309","display_name":"Siyi Zhao","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Siyi Zhao","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102017560","display_name":"Wei Wang","orcid":"https://orcid.org/0000-0001-9775-9774"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wei Wang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5100341993","display_name":"Yanmin Qian","orcid":"https://orcid.org/0000-0002-0314-3790"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yanmin Qian","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"3409","last_page":"3413"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11038","display_name":"Advanced SAR Imaging Techniques","score":0.9965999722480774,"subfield":{"id":"https://openalex.org/subfields/2202","display_name":"Aerospace Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T11038","display_name":"Advanced SAR Imaging Techniques","score":0.9965999722480774,"subfield":{"id":"https://openalex.org/subfields/2202","display_name":"Aerospace Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10069","display_name":"Antenna Design and Analysis","score":0.9944000244140625,"subfield":{"id":"https://openalex.org/subfields/2202","display_name":"Aerospace Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11946","display_name":"Antenna Design and Optimization","score":0.9919999837875366,"subfield":{"id":"https://openalex.org/subfields/2202","display_name":"Aerospace Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/resampling","display_name":"Resampling","score":0.8388000130653381},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.7436000108718872},{"id":"https://openalex.org/keywords/preprocessor","display_name":"Preprocessor","score":0.6287000179290771},{"id":"https://openalex.org/keywords/pruning","display_name":"Pruning","score":0.5770999789237976},{"id":"https://openalex.org/keywords/computational-complexity-theory","display_name":"Computational complexity theory","score":0.5591999888420105},{"id":"https://openalex.org/keywords/frame","display_name":"Frame (networking)","score":0.5458999872207642},{"id":"https://openalex.org/keywords/residual","display_name":"Residual","score":0.5159000158309937},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.5072000026702881}],"concepts":[{"id":"https://openalex.org/C150921843","wikidata":"https://www.wikidata.org/wiki/Q1170431","display_name":"Resampling","level":2,"score":0.8388000130653381},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7993999719619751},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.7436000108718872},{"id":"https://openalex.org/C34736171","wikidata":"https://www.wikidata.org/wiki/Q918333","display_name":"Preprocessor","level":2,"score":0.6287000179290771},{"id":"https://openalex.org/C108010975","wikidata":"https://www.wikidata.org/wiki/Q500094","display_name":"Pruning","level":2,"score":0.5770999789237976},{"id":"https://openalex.org/C179799912","wikidata":"https://www.wikidata.org/wiki/Q205084","display_name":"Computational complexity theory","level":2,"score":0.5591999888420105},{"id":"https://openalex.org/C126042441","wikidata":"https://www.wikidata.org/wiki/Q1324888","display_name":"Frame (networking)","level":2,"score":0.5458999872207642},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5246999859809875},{"id":"https://openalex.org/C155512373","wikidata":"https://www.wikidata.org/wiki/Q287450","display_name":"Residual","level":2,"score":0.5159000158309937},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.5072000026702881},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5009999871253967},{"id":"https://openalex.org/C2779960059","wikidata":"https://www.wikidata.org/wiki/Q7113681","display_name":"Overhead (engineering)","level":2,"score":0.40619999170303345},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3634999990463257},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.34220001101493835},{"id":"https://openalex.org/C29265498","wikidata":"https://www.wikidata.org/wiki/Q7047719","display_name":"Noise measurement","level":3,"score":0.32580000162124634},{"id":"https://openalex.org/C2984784707","wikidata":"https://www.wikidata.org/wiki/Q167555","display_name":"Digit recognition","level":3,"score":0.31189998984336853},{"id":"https://openalex.org/C28855332","wikidata":"https://www.wikidata.org/wiki/Q198099","display_name":"Quantization (signal processing)","level":2,"score":0.3050000071525574},{"id":"https://openalex.org/C2781170535","wikidata":"https://www.wikidata.org/wiki/Q30587856","display_name":"Noisy data","level":2,"score":0.2897000014781952},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.2838999927043915},{"id":"https://openalex.org/C66024118","wikidata":"https://www.wikidata.org/wiki/Q1122506","display_name":"Computational model","level":2,"score":0.2761000096797943},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.2732999920845032},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.2720000147819519}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.21437/interspeech.2025-1668","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2025-1668","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2025","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2509.21833","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2509.21833","pdf_url":"https://arxiv.org/pdf/2509.21833","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2509.21833","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2509.21833","pdf_url":"https://arxiv.org/pdf/2509.21833","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Recent":[0],"advancements":[1],"in":[2,13],"automatic":[3],"speech":[4,19],"recognition":[5],"(ASR)":[6],"have":[7],"achieved":[8],"notable":[9],"progress,":[10],"whereas":[11],"robustness":[12],"noisy":[14,96],"environments":[15],"remains":[16],"challenging.":[17],"While":[18],"enhancement":[20],"(SE)":[21],"front-ends":[22],"are":[23],"widely":[24],"used":[25],"to":[26,45,73,109],"mitigate":[27,74],"noise":[28],"as":[29],"a":[30],"preprocessing":[31],"step":[32],"for":[33],"ASR,":[34],"they":[35],"often":[36],"introduce":[37],"computational":[38,48,88,104],"non-negligible":[39],"overhead.":[40],"This":[41],"paper":[42],"proposes":[43],"optimizations":[44],"reduce":[46],"SE":[47,103],"costs":[49],"without":[50],"compromising":[51],"ASR":[52,116],"performance.":[53,117],"Our":[54],"approach":[55],"integrates":[56],"layer-wise":[57],"frame":[58],"resampling":[59,65],"and":[60,94],"progressive":[61],"sub-band":[62,78],"pruning.":[63],"Frame":[64],"downsamples":[66],"inputs":[67],"within":[68],"layers,":[69],"utilizing":[70],"residual":[71],"connections":[72],"information":[75],"loss.":[76],"Simultaneously,":[77],"pruning":[79],"progressively":[80],"excludes":[81],"less":[82],"informative":[83],"frequency":[84],"bands,":[85],"further":[86],"reducing":[87],"demands.":[89],"Extensive":[90],"experiments":[91],"on":[92],"synthetic":[93],"real-world":[95],"datasets":[97],"demonstrate":[98],"that":[99],"our":[100],"system":[101],"reduces":[102],"overhead":[105],"over":[106],"66":[107],"compared":[108],"the":[110],"standard":[111],"BSRNN,":[112],"while":[113],"maintaining":[114],"strong":[115]},"counts_by_year":[{"year":2025,"cited_by_count":2}],"updated_date":"2026-07-28T07:46:37.118299","created_date":"2025-10-23T00:00:00"}