{"id":"https://openalex.org/W4405710117","doi":"https://doi.org/10.1109/iscslp63861.2024.10800235","title":"Band-Wise Front-End Distortion Suppression for Robust Speech Recognition","display_name":"Band-Wise Front-End Distortion Suppression for Robust Speech Recognition","publication_year":2024,"publication_date":"2024-11-07","ids":{"openalex":"https://openalex.org/W4405710117","doi":"https://doi.org/10.1109/iscslp63861.2024.10800235"},"language":"en","primary_location":{"id":"doi:10.1109/iscslp63861.2024.10800235","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iscslp63861.2024.10800235","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE 14th International Symposium on Chinese Spoken Language Processing (ISCSLP)","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/A5004652309","display_name":"Siyi Zhao","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":true,"raw_author_name":"Siyi Zhao","raw_affiliation_strings":["Shanghai Jiao Tong University,Auditory Cognition and Computational Acoustic Lab MoE Key Lab of Aritificial Intelligence, AI Institute,Department of Computer Science and Engineering,Shanghai"],"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University,Auditory Cognition and Computational Acoustic Lab MoE Key Lab of Aritificial Intelligence, AI Institute,Department of Computer Science and Engineering,Shanghai","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100391971","display_name":"Wei Wang","orcid":"https://orcid.org/0000-0002-4392-1884"},"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":"Wei Wang","raw_affiliation_strings":["Shanghai Jiao Tong University,Auditory Cognition and Computational Acoustic Lab MoE Key Lab of Aritificial Intelligence, AI Institute,Department of Computer Science and Engineering,Shanghai"],"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University,Auditory Cognition and Computational Acoustic Lab MoE Key Lab of Aritificial Intelligence, AI Institute,Department of Computer Science and Engineering,Shanghai","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100341993","display_name":"Yanmin Qian","orcid":"https://orcid.org/0000-0002-0314-3790"},"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":"Yanmin Qian","raw_affiliation_strings":["Shanghai Jiao Tong University,Auditory Cognition and Computational Acoustic Lab MoE Key Lab of Aritificial Intelligence, AI Institute,Department of Computer Science and Engineering,Shanghai"],"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University,Auditory Cognition and Computational Acoustic Lab MoE Key Lab of Aritificial Intelligence, AI Institute,Department of Computer Science and Engineering,Shanghai","institution_ids":["https://openalex.org/I183067930"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5004652309"],"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":0.27192419,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"681","last_page":"685"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9975000023841858,"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":0.9975000023841858,"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":0.9940000176429749,"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":0.9836999773979187,"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/front-and-back-ends","display_name":"Front and back ends","score":0.7148568630218506},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7062240839004517},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6251876354217529},{"id":"https://openalex.org/keywords/distortion","display_name":"Distortion (music)","score":0.5852136611938477},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.41706883907318115},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.36160823702812195},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.13813263177871704},{"id":"https://openalex.org/keywords/bandwidth","display_name":"Bandwidth (computing)","score":0.08226519823074341}],"concepts":[{"id":"https://openalex.org/C53016008","wikidata":"https://www.wikidata.org/wiki/Q620167","display_name":"Front and back ends","level":2,"score":0.7148568630218506},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7062240839004517},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6251876354217529},{"id":"https://openalex.org/C126780896","wikidata":"https://www.wikidata.org/wiki/Q899871","display_name":"Distortion (music)","level":4,"score":0.5852136611938477},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.41706883907318115},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.36160823702812195},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.13813263177871704},{"id":"https://openalex.org/C2776257435","wikidata":"https://www.wikidata.org/wiki/Q1576430","display_name":"Bandwidth (computing)","level":2,"score":0.08226519823074341},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C194257627","wikidata":"https://www.wikidata.org/wiki/Q211554","display_name":"Amplifier","level":3,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/iscslp63861.2024.10800235","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iscslp63861.2024.10800235","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE 14th International Symposium on Chinese Spoken Language Processing (ISCSLP)","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":22,"referenced_works":["https://openalex.org/W1494198834","https://openalex.org/W1989034586","https://openalex.org/W2296167893","https://openalex.org/W2559260703","https://openalex.org/W2618099328","https://openalex.org/W2962780374","https://openalex.org/W2972320711","https://openalex.org/W2972436155","https://openalex.org/W2972541922","https://openalex.org/W3015213852","https://openalex.org/W3160085755","https://openalex.org/W3206531472","https://openalex.org/W4225310539","https://openalex.org/W4297841603","https://openalex.org/W4372259751","https://openalex.org/W4372260292","https://openalex.org/W4372260557","https://openalex.org/W4391021774","https://openalex.org/W4400877621","https://openalex.org/W6631190155","https://openalex.org/W6847363464","https://openalex.org/W6847544085"],"related_works":["https://openalex.org/W2770593030","https://openalex.org/W3154990682","https://openalex.org/W2560201613","https://openalex.org/W2171975302","https://openalex.org/W2022352247","https://openalex.org/W2488129135","https://openalex.org/W4312219546","https://openalex.org/W2377538627","https://openalex.org/W2107220315","https://openalex.org/W1589637664"],"abstract_inverted_index":{"Advancements":[0],"in":[1,30],"deep":[2],"learning":[3],"techniques":[4],"have":[5],"significantly":[6],"improved":[7,141],"automatic":[8],"speech":[9,28,34,105],"recognition":[10,29],"(ASR).":[11],"However,":[12],"improving":[13],"robustness":[14],"to":[15,44,51,135,140],"acoustic":[16],"interferences,":[17],"such":[18],"as":[19,39],"background":[20],"noise":[21],"and":[22,65,93,103,116],"reverberation,":[23],"remains":[24],"crucial":[25],"for":[26,83,107],"accurate":[27],"noisy":[31,102,109],"environments.":[32],"Traditional":[33],"enhancement":[35],"(SE)":[36],"modules":[37],"used":[38],"pre-processing":[40],"front-ends":[41],"often":[42],"fail":[43],"integrate":[45],"well":[46],"with":[47],"ASR":[48,142],"models":[49],"due":[50],"intelligibility":[52],"distortions":[53],"introduced":[54],"by":[55,60],"the":[56,61,99,122],"SE":[57,71],"module.":[58],"Inspired":[59],"observation":[62,79],"adding":[63,80],"technique":[64],"band-wise":[66,78],"network":[67,90],"design":[68],"of":[69,101],"recent":[70],"models,":[72],"we":[73],"propose":[74],"a":[75],"novel":[76],"adaptive":[77],"(BOA)":[81],"module":[82,124],"front-end":[84],"distortion":[85],"suppression.":[86],"The":[87],"lightweight":[88],"BOA":[89,123],"learns":[91],"time-":[92],"frequencyvariant":[94],"OA":[95,129,137],"factors,":[96,138],"adaptively":[97],"balancing":[98],"contributions":[100],"enhanced":[104],"signals":[106],"diverse":[108],"conditions.":[110],"Experiments":[111],"conducted":[112],"on":[113],"both":[114],"simulated":[115],"real-world":[117],"test":[118],"sets":[119],"demonstrate":[120],"that":[121],"produces":[125],"more":[126],"effective":[127],"dynamic":[128],"factors":[130],"under":[131],"various":[132],"conditions":[133],"compared":[134],"fixed":[136],"leading":[139],"performance.":[143]},"counts_by_year":[],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}