{"id":"https://openalex.org/W4408352927","doi":"https://doi.org/10.1109/icassp49660.2025.10889792","title":"Aligning Noisy-Clean Speech Pairs at Feature and Embedding Levels for Learning Noise-Invariant Speaker Representations","display_name":"Aligning Noisy-Clean Speech Pairs at Feature and Embedding Levels for Learning Noise-Invariant Speaker Representations","publication_year":2025,"publication_date":"2025-03-12","ids":{"openalex":"https://openalex.org/W4408352927","doi":"https://doi.org/10.1109/icassp49660.2025.10889792"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49660.2025.10889792","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10889792","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5107955159","display_name":"Zuoliang Li","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":"Zuoliang Li","raw_affiliation_strings":["University of Science and Technology of China (USTC),The National Engineering Research Center for Speech and Language Information Processing (NERC-SLIP),Hefei,China,230027"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Science and Technology of China (USTC),The National Engineering Research Center for Speech and Language Information Processing (NERC-SLIP),Hefei,China,230027","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":["University of Science and Technology of China (USTC),The National Engineering Research Center for Speech and Language Information Processing (NERC-SLIP),Hefei,China,230027"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Science and Technology of China (USTC),The National Engineering Research Center for Speech and Language Information Processing (NERC-SLIP),Hefei,China,230027","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100436740","display_name":"Jie Zhang","orcid":"https://orcid.org/0000-0002-4230-1077"},"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":"Jie Zhang","raw_affiliation_strings":["University of Science and Technology of China (USTC),The National Engineering Research Center for Speech and Language Information Processing (NERC-SLIP),Hefei,China,230027"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Science and Technology of China (USTC),The National Engineering Research Center for Speech and Language Information Processing (NERC-SLIP),Hefei,China,230027","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5113361556","display_name":"Shengyu Peng","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":"Shengyu Peng","raw_affiliation_strings":["University of Science and Technology of China (USTC),The National Engineering Research Center for Speech and Language Information Processing (NERC-SLIP),Hefei,China,230027"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Science and Technology of China (USTC),The National Engineering Research Center for Speech and Language Information Processing (NERC-SLIP),Hefei,China,230027","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5084397928","display_name":"Yu Guan","orcid":"https://orcid.org/0000-0002-7833-9755"},"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":"Yu Guan","raw_affiliation_strings":["University of Science and Technology of China (USTC),The National Engineering Research Center for Speech and Language Information Processing (NERC-SLIP),Hefei,China,230027"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Science and Technology of China (USTC),The National Engineering Research Center for Speech and Language Information Processing (NERC-SLIP),Hefei,China,230027","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101875578","display_name":"Bin Gu","orcid":"https://orcid.org/0000-0003-1621-7311"},"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":"Bin Gu","raw_affiliation_strings":["University of Science and Technology of China (USTC),The National Engineering Research Center for Speech and Language Information Processing (NERC-SLIP),Hefei,China,230027"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Science and Technology of China (USTC),The National Engineering Research Center for Speech and Language Information Processing (NERC-SLIP),Hefei,China,230027","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5038369085","display_name":"Wu Guo","orcid":"https://orcid.org/0000-0002-3779-7944"},"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":"Wu Guo","raw_affiliation_strings":["University of Science and Technology of China (USTC),The National Engineering Research Center for Speech and Language Information Processing (NERC-SLIP),Hefei,China,230027"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Science and Technology of China (USTC),The National Engineering Research Center for Speech and Language Information Processing (NERC-SLIP),Hefei,China,230027","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":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"5"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9958999752998352,"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":0.9958999752998352,"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":0.9945999979972839,"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/T11309","display_name":"Music and Audio Processing","score":0.960099995136261,"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-recognition","display_name":"Speech recognition","score":0.7452389001846313},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6967675685882568},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.6940904855728149},{"id":"https://openalex.org/keywords/invariant","display_name":"Invariant (physics)","score":0.5649555921554565},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.5137661695480347},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4500291347503662},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.4425080418586731},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3753848671913147},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.15169617533683777},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.07506051659584045}],"concepts":[{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7452389001846313},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6967675685882568},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.6940904855728149},{"id":"https://openalex.org/C190470478","wikidata":"https://www.wikidata.org/wiki/Q2370229","display_name":"Invariant (physics)","level":2,"score":0.5649555921554565},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.5137661695480347},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4500291347503662},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.4425080418586731},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3753848671913147},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.15169617533683777},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.07506051659584045},{"id":"https://openalex.org/C37914503","wikidata":"https://www.wikidata.org/wiki/Q156495","display_name":"Mathematical physics","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49660.2025.10889792","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10889792","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/10","display_name":"Reduced inequalities","score":0.41999998688697815}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":34,"referenced_works":["https://openalex.org/W1936725236","https://openalex.org/W2159202424","https://openalex.org/W2726515241","https://openalex.org/W2752782242","https://openalex.org/W2784163702","https://openalex.org/W2890964092","https://openalex.org/W2969985801","https://openalex.org/W2972425344","https://openalex.org/W2972697221","https://openalex.org/W2982037672","https://openalex.org/W3015231328","https://openalex.org/W3024869864","https://openalex.org/W3095079700","https://openalex.org/W3097777922","https://openalex.org/W3110405100","https://openalex.org/W3137249133","https://openalex.org/W3196650842","https://openalex.org/W4206285316","https://openalex.org/W4283703262","https://openalex.org/W4283762346","https://openalex.org/W4313590886","https://openalex.org/W4321608474","https://openalex.org/W4372267288","https://openalex.org/W4372340947","https://openalex.org/W4382536354","https://openalex.org/W4385756536","https://openalex.org/W4385822451","https://openalex.org/W4386702814","https://openalex.org/W4392909885","https://openalex.org/W4402112094","https://openalex.org/W4402116008","https://openalex.org/W6637242042","https://openalex.org/W6776700526","https://openalex.org/W6791742336"],"related_works":["https://openalex.org/W2081900870","https://openalex.org/W2037549926","https://openalex.org/W2345479200","https://openalex.org/W2183306018","https://openalex.org/W2849310602","https://openalex.org/W3006008237","https://openalex.org/W2419146053","https://openalex.org/W4388890789","https://openalex.org/W2088247287","https://openalex.org/W2963903416"],"abstract_inverted_index":{"In":[0],"this":[1],"paper,":[2],"we":[3,28,71],"propose":[4],"a":[5,45,73],"noise-invariant":[6],"speaker":[7],"representation":[8],"learning":[9,76],"(SRL)":[10],"approach":[11],"by":[12,44,54],"aligning":[13],"noisy-clean":[14,31,108],"speech":[15],"pairs":[16,32,110],"at":[17],"both":[18],"the":[19,56,61,68,84,88,100,107,116,131,146,149],"feature":[20],"and":[21,63,87,91,111],"embedding":[22,69,117],"levels":[23],"for":[24],"model":[25],"training.":[26,37],"Specifically,":[27],"first":[29],"construct":[30],"using":[33],"data":[34,109],"augmentation":[35],"during":[36],"The":[38,49],"noisy":[39],"features":[40],"are":[41,123],"then":[42],"processed":[43],"Conformer-based":[46],"enhancement":[47],"module.":[48],"feature-level":[50],"alignment":[51],"is":[52],"achieved":[53],"minimizing":[55],"mean":[57],"squared":[58],"error":[59],"between":[60],"enhanced":[62],"original":[64],"clean":[65],"data.":[66],"At":[67],"level,":[70],"introduce":[72],"supervised":[74],"contrastive":[75],"loss":[77,104,121,128],"with":[78,99,125,142],"noise-adaptive":[79],"margin":[80],"to":[81,105,129],"simultaneously":[82],"enhance":[83],"intra-speaker":[85],"compactness":[86],"inter-speaker":[89],"separability":[90],"better":[92],"adapt":[93],"different":[94],"noise":[95,113,143],"levels,":[96],"in":[97,115],"combination":[98],"Barlow":[101],"Twins":[102],"self-supervised":[103],"align":[106],"reduce":[112],"redundancy":[114],"space.":[118],"Finally,":[119],"these":[120],"components":[122],"integrated":[124],"conventional":[126],"classification":[127],"train":[130],"SRL":[132],"network.":[133],"Experimental":[134],"results":[135],"on":[136],"various":[137],"VoxCeleb1":[138],"test":[139],"sets":[140],"synthesized":[141],"sources":[144],"demonstrate":[145],"effectiveness":[147],"of":[148],"proposed":[150],"method.":[151]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}