{"id":"https://openalex.org/W4226403810","doi":"https://doi.org/10.21437/interspeech.2022-10002","title":"Boosting Self-Supervised Embeddings for Speech Enhancement","display_name":"Boosting Self-Supervised Embeddings for Speech Enhancement","publication_year":2022,"publication_date":"2022-09-16","ids":{"openalex":"https://openalex.org/W4226403810","doi":"https://doi.org/10.21437/interspeech.2022-10002"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2022-10002","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2022-10002","pdf_url":null,"source":{"id":"https://openalex.org/S4363604309","display_name":"Interspeech 2022","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":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2022","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/A5064333828","display_name":"Kuo-Hsuan Hung","orcid":"https://orcid.org/0000-0002-6298-5269"},"institutions":[{"id":"https://openalex.org/I16733864","display_name":"National Taiwan University","ror":"https://ror.org/05bqach95","country_code":"TW","type":"education","lineage":["https://openalex.org/I16733864"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Kuo-Hsuan Hung","raw_affiliation_strings":["National Taiwan University,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Taiwan University,","institution_ids":["https://openalex.org/I16733864"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5071471469","display_name":"Szu\u2010Wei Fu","orcid":"https://orcid.org/0000-0002-3487-8212"},"institutions":[{"id":"https://openalex.org/I4210105678","display_name":"Microsoft (Finland)","ror":"https://ror.org/01nehjf29","country_code":"FI","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210105678"]}],"countries":["FI"],"is_corresponding":false,"raw_author_name":"Szu-wei Fu","raw_affiliation_strings":["Microsoft Corporation,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft Corporation,","institution_ids":["https://openalex.org/I4210105678"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5034788095","display_name":"H. Eric Tseng","orcid":"https://orcid.org/0000-0001-9544-4226"},"institutions":[{"id":"https://openalex.org/I84653119","display_name":"Academia Sinica","ror":"https://ror.org/05bxb3784","country_code":"TW","type":"facility","lineage":["https://openalex.org/I84653119"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Huan-Hsin Tseng","raw_affiliation_strings":["Academia Sinica"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Academia Sinica","institution_ids":["https://openalex.org/I84653119"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5041130078","display_name":"Hsin-Tien Chiang","orcid":"https://orcid.org/0009-0009-4697-4357"},"institutions":[{"id":"https://openalex.org/I84653119","display_name":"Academia Sinica","ror":"https://ror.org/05bxb3784","country_code":"TW","type":"facility","lineage":["https://openalex.org/I84653119"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Hsin-Tien Chiang","raw_affiliation_strings":["Academia Sinica"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Academia Sinica","institution_ids":["https://openalex.org/I84653119"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5044008055","display_name":"Yu Tsao","orcid":"https://orcid.org/0000-0001-6956-0418"},"institutions":[{"id":"https://openalex.org/I84653119","display_name":"Academia Sinica","ror":"https://ror.org/05bxb3784","country_code":"TW","type":"facility","lineage":["https://openalex.org/I84653119"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Yu Tsao","raw_affiliation_strings":["Academia Sinica"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Academia Sinica","institution_ids":["https://openalex.org/I84653119"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5066973702","display_name":"Chii\u2010Wann Lin","orcid":"https://orcid.org/0000-0002-8721-3441"},"institutions":[{"id":"https://openalex.org/I16733864","display_name":"National Taiwan University","ror":"https://ror.org/05bqach95","country_code":"TW","type":"education","lineage":["https://openalex.org/I16733864"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Chii-Wann Lin","raw_affiliation_strings":["National Taiwan University,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Taiwan University,","institution_ids":["https://openalex.org/I16733864"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":6,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":4.2364,"has_fulltext":false,"cited_by_count":38,"citation_normalized_percentile":{"value":0.95876613,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"186","last_page":"190"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9991999864578247,"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":0.9991999864578247,"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":0.9923999905586243,"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/T11398","display_name":"Hand Gesture Recognition Systems","score":0.9550999999046326,"subfield":{"id":"https://openalex.org/subfields/1709","display_name":"Human-Computer Interaction"},"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/boosting","display_name":"Boosting (machine learning)","score":0.8833557367324829},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6478689312934875},{"id":"https://openalex.org/keywords/speech-enhancement","display_name":"Speech enhancement","score":0.601486086845398},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5735641121864319},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.49088460206985474},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.34544700384140015},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.34362518787384033},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.1016155481338501}],"concepts":[{"id":"https://openalex.org/C46686674","wikidata":"https://www.wikidata.org/wiki/Q466303","display_name":"Boosting (machine learning)","level":2,"score":0.8833557367324829},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6478689312934875},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.601486086845398},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5735641121864319},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.49088460206985474},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.34544700384140015},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.34362518787384033},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.1016155481338501}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21437/interspeech.2022-10002","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2022-10002","pdf_url":null,"source":{"id":"https://openalex.org/S4363604309","display_name":"Interspeech 2022","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":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2022","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","score":0.6000000238418579,"id":"https://metadata.un.org/sdg/16"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":38,"referenced_works":["https://openalex.org/W2044893557","https://openalex.org/W2405774341","https://openalex.org/W2603567530","https://openalex.org/W2935693977","https://openalex.org/W2949756029","https://openalex.org/W2962866211","https://openalex.org/W2962946126","https://openalex.org/W2972943112","https://openalex.org/W2973049979","https://openalex.org/W2982223350","https://openalex.org/W3015213852","https://openalex.org/W3015337486","https://openalex.org/W3015949486","https://openalex.org/W3016132433","https://openalex.org/W3035837245","https://openalex.org/W3049256661","https://openalex.org/W3095248373","https://openalex.org/W3112034174","https://openalex.org/W3132954452","https://openalex.org/W3163827866","https://openalex.org/W3169320628","https://openalex.org/W3193271183","https://openalex.org/W3196614065","https://openalex.org/W3197227964","https://openalex.org/W3197284240","https://openalex.org/W3197580070","https://openalex.org/W3202278141","https://openalex.org/W3209984917","https://openalex.org/W3211224152","https://openalex.org/W4210484003","https://openalex.org/W4221162932","https://openalex.org/W4224933800","https://openalex.org/W4226380987","https://openalex.org/W4244026860","https://openalex.org/W4285250921","https://openalex.org/W4297808394","https://openalex.org/W4311137818","https://openalex.org/W4311167834"],"related_works":["https://openalex.org/W2125652721","https://openalex.org/W1540371141","https://openalex.org/W4231274751","https://openalex.org/W2154063878","https://openalex.org/W2556012038","https://openalex.org/W3082059448","https://openalex.org/W4313640622","https://openalex.org/W3096184950","https://openalex.org/W2770665941","https://openalex.org/W2782782444"],"abstract_inverted_index":{"Self-supervised":[0],"learning":[1],"(SSL)":[2],"representation":[3,50,69,104],"for":[4,18,79],"speech":[5,21,45],"has":[6],"achieved":[7],"state-of-the-art":[8],"(SOTA)":[9],"performance":[10],"on":[11,95],"several":[12],"downstream":[13],"tasks.However,":[14],"there":[15],"remains":[16],"room":[17],"improvement":[19],"in":[20,116,131,151],"enhancement":[22],"(SE)":[23],"tasks.In":[24],"this":[25],"study,":[26],"we":[27,81],"used":[28],"a":[29],"crossdomain":[30],"feature":[31],"to":[32,43,136],"solve":[33],"the":[34,48,53,61,64,76,96,111,128,152],"problem":[35],"that":[36,83,100],"SSL":[37,49,68,84,103,132,149],"embeddings":[38,133],"may":[39,145],"lack":[40],"fine-grained":[41],"information":[42],"regenerate":[44],"signals.By":[46],"integrating":[47],"and":[51,75,119,144],"spectrogram,":[52],"result":[54],"can":[55,109],"be":[56],"significantly":[57],"boosted.We":[58],"further":[59],"study":[60],"relationship":[62],"between":[63],"noise":[65,88],"robustness":[66,89],"of":[67],"via":[70],"clean-noisy":[71],"distance":[72,130],"(CN":[73],"distance)":[74],"layer":[77],"importance":[78],"SE.Consequently,":[80],"found":[82],"representations":[85],"with":[86,105],"lower":[87],"are":[90],"more":[91],"important.Furthermore,":[92],"our":[93,142],"experiments":[94],"VCTK-DEMAND":[97],"dataset":[98],"demonstrated":[99],"fine-tuning":[101],"an":[102,106],"SE":[107,114],"model":[108],"outperform":[110],"SOTA":[112],"SSL-based":[113],"methods":[115],"PESQ,":[117],"CSIG":[118],"COVL":[120],"without":[121],"invoking":[122],"complicated":[123],"network":[124],"architectures.In":[125],"later":[126],"experiments,":[127],"CN":[129],"was":[134],"observed":[135],"increase":[137],"after":[138],"fine-tuning.These":[139],"results":[140],"verify":[141],"expectations":[143],"help":[146],"design":[147],"SE-related":[148],"training":[150],"future.":[153]},"counts_by_year":[{"year":2026,"cited_by_count":3},{"year":2025,"cited_by_count":10},{"year":2024,"cited_by_count":13},{"year":2023,"cited_by_count":11},{"year":2022,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}