{"id":"https://openalex.org/W4404688015","doi":"https://doi.org/10.1109/lsp.2024.3505794","title":"Controllable Conformer for Speech Enhancement and Recognition","display_name":"Controllable Conformer for Speech Enhancement and Recognition","publication_year":2024,"publication_date":"2024-11-25","ids":{"openalex":"https://openalex.org/W4404688015","doi":"https://doi.org/10.1109/lsp.2024.3505794"},"language":"en","primary_location":{"id":"doi:10.1109/lsp.2024.3505794","is_oa":false,"landing_page_url":"https://doi.org/10.1109/lsp.2024.3505794","pdf_url":null,"source":{"id":"https://openalex.org/S120629676","display_name":"IEEE Signal Processing Letters","issn_l":"1070-9908","issn":["1070-9908","1558-2361"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Signal Processing Letters","raw_type":"journal-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/A5089001438","display_name":"Zilu Guo","orcid":"https://orcid.org/0009-0000-0486-6088"},"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":"Zilu Guo","raw_affiliation_strings":["National Engineering Research Center of Speech and Language Information Processing, University of Science and Technology of China, Hefei, China"],"raw_orcid":"https://orcid.org/0009-0000-0486-6088","affiliations":[{"raw_affiliation_string":"National Engineering Research Center of Speech and Language Information Processing, University of Science and Technology of China, Hefei, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5066595711","display_name":"Jun Du","orcid":"https://orcid.org/0000-0002-2387-0389"},"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":"Jun Du","raw_affiliation_strings":["National Engineering Research Center of Speech and Language Information Processing, University of Science and Technology of China, Hefei, China"],"raw_orcid":"https://orcid.org/0000-0002-2387-0389","affiliations":[{"raw_affiliation_string":"National Engineering Research Center of Speech and Language Information Processing, University of Science and Technology of China, Hefei, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5079659476","display_name":"Sabato Marco Siniscalchi","orcid":"https://orcid.org/0000-0002-0770-0507"},"institutions":[{"id":"https://openalex.org/I900890020","display_name":"University of Palermo","ror":"https://ror.org/044k9ta02","country_code":"IT","type":"education","lineage":["https://openalex.org/I900890020"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Sabato Marco Siniscalchi","raw_affiliation_strings":["Computer Engineering Section, University of Palermo, Palermo, Italy"],"raw_orcid":"https://orcid.org/0000-0002-0770-0507","affiliations":[{"raw_affiliation_string":"Computer Engineering Section, University of Palermo, Palermo, Italy","institution_ids":["https://openalex.org/I900890020"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101924451","display_name":"Jia Pan","orcid":"https://orcid.org/0000-0002-7073-1744"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jia Pan","raw_affiliation_strings":["iFLYTEK Research, Hefei, China"],"raw_orcid":"https://orcid.org/0000-0002-7073-1744","affiliations":[{"raw_affiliation_string":"iFLYTEK Research, Hefei, China","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100349237","display_name":"Qingfeng Liu","orcid":"https://orcid.org/0000-0003-2492-8092"},"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":"Qingfeng Liu","raw_affiliation_strings":["National Engineering Research Center of Speech and Language Information Processing, University of Science and Technology of China, Hefei, 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, China","institution_ids":["https://openalex.org/I126520041"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.8446,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.73170192,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":98},"biblio":{"volume":"32","issue":null,"first_page":"156","last_page":"160"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9927999973297119,"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":0.9927999973297119,"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":0.9587000012397766,"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/speech-recognition","display_name":"Speech recognition","score":0.6524719595909119},{"id":"https://openalex.org/keywords/speech-enhancement","display_name":"Speech enhancement","score":0.6368839144706726},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6094878315925598},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.4362500309944153},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.34407228231430054},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3263586461544037},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.16667446494102478}],"concepts":[{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6524719595909119},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.6368839144706726},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6094878315925598},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.4362500309944153},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.34407228231430054},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3263586461544037},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.16667446494102478}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/lsp.2024.3505794","is_oa":false,"landing_page_url":"https://doi.org/10.1109/lsp.2024.3505794","pdf_url":null,"source":{"id":"https://openalex.org/S120629676","display_name":"IEEE Signal Processing Letters","issn_l":"1070-9908","issn":["1070-9908","1558-2361"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Signal Processing Letters","raw_type":"journal-article"},{"id":"pmh:oai:iris.unipa.it:10447/664606","is_oa":false,"landing_page_url":"https://hdl.handle.net/10447/664606","pdf_url":null,"source":{"id":"https://openalex.org/S4306401065","display_name":"Nova Science Publishers (Nova Science Publishers, Inc.)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"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":"info:eu-repo/semantics/article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1713836045","display_name":null,"funder_award_id":"62171427","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":28,"referenced_works":["https://openalex.org/W1552314771","https://openalex.org/W2044893557","https://openalex.org/W2069681747","https://openalex.org/W2113131123","https://openalex.org/W2516001803","https://openalex.org/W2559260703","https://openalex.org/W2618099328","https://openalex.org/W2962892438","https://openalex.org/W3015312544","https://openalex.org/W3028077980","https://openalex.org/W3142252347","https://openalex.org/W3160085755","https://openalex.org/W3213240302","https://openalex.org/W4221143458","https://openalex.org/W4224920397","https://openalex.org/W4225269836","https://openalex.org/W4226390724","https://openalex.org/W4285119904","https://openalex.org/W4296068829","https://openalex.org/W4297841555","https://openalex.org/W4297841603","https://openalex.org/W4297841651","https://openalex.org/W4380434618","https://openalex.org/W4385807442","https://openalex.org/W4385822788","https://openalex.org/W4399345616","https://openalex.org/W6762114000","https://openalex.org/W6765775151"],"related_works":["https://openalex.org/W2033914206","https://openalex.org/W2042327336","https://openalex.org/W3096184950","https://openalex.org/W4231424160","https://openalex.org/W2120771489","https://openalex.org/W2051376034","https://openalex.org/W2955597484","https://openalex.org/W3110551121","https://openalex.org/W2089240210","https://openalex.org/W2131486661"],"abstract_inverted_index":{"We":[0],"propose":[1],"a":[2,17,22],"novel":[3],"approach":[4],"to":[5,31,72,90],"speech":[6,33,42,54,118],"enhancement,":[7],"termed":[8],"Controllable":[9],"ConforMer":[10],"for":[11,35,122],"Speech":[12],"Enhancement":[13],"(CCMSE),":[14],"which":[15],"leverages":[16],"Conformer-based":[18],"architecture":[19],"integrated":[20],"with":[21,109],"control":[23],"factor":[24],"embedding":[25],"module.":[26],"Our":[27],"method":[28,101],"is":[29,46,120],"designed":[30],"optimize":[32],"quality":[34],"both":[36,123],"human":[37,60,124],"auditory":[38,61],"perception":[39],"and":[40,125],"automatic":[41],"recognition":[43],"(ASR).":[44],"It":[45],"observed":[47],"that":[48,82,119],"while":[49],"mild":[50,107],"denoising":[51,57,98,108],"typically":[52],"preserves":[53],"naturalness,":[55],"stronger":[56,113],"can":[58],"improve":[59],"tasks":[62],"but":[63],"often":[64],"at":[65,94],"the":[66,104,110,131,135],"cost":[67],"of":[68,97,106,112,137],"ASR":[69],"accuracy":[70],"due":[71],"increased":[73],"distortion.":[74],"To":[75],"address":[76],"this,":[77],"we":[78],"introduce":[79],"an":[80],"algorithm":[81],"balances":[83],"these":[84],"trade-offs.":[85],"By":[86],"utilizing":[87],"differential":[88],"equations":[89],"interpolate":[91],"between":[92],"outputs":[93],"varying":[95],"levels":[96],"intensity,":[99],"our":[100,138],"effectively":[102],"combines":[103],"robustness":[105],"clarity":[111],"denoising,":[114],"resulting":[115],"in":[116],"enhanced":[117],"well-suited":[121],"machine":[126],"listeners.":[127],"Experimental":[128],"results":[129],"on":[130],"CHiME-4":[132],"dataset":[133],"validate":[134],"effectiveness":[136],"approach.":[139]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":1}],"updated_date":"2025-12-27T23:08:20.325037","created_date":"2025-10-10T00:00:00"}