{"id":"https://openalex.org/W4408355663","doi":"https://doi.org/10.1109/icassp49660.2025.10887678","title":"Causal Speech Enhancement with Predicting Semantics based on Quantized Self-supervised Learning Features","display_name":"Causal Speech Enhancement with Predicting Semantics based on Quantized Self-supervised Learning Features","publication_year":2025,"publication_date":"2025-03-12","ids":{"openalex":"https://openalex.org/W4408355663","doi":"https://doi.org/10.1109/icassp49660.2025.10887678"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49660.2025.10887678","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10887678","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":"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/A5011937407","display_name":"Emiru Tsunoo","orcid":null},"institutions":[{"id":"https://openalex.org/I74801974","display_name":"The University of Tokyo","ror":"https://ror.org/057zh3y96","country_code":"JP","type":"education","lineage":["https://openalex.org/I74801974"]}],"countries":["JP"],"is_corresponding":true,"raw_author_name":"Emiru Tsunoo","raw_affiliation_strings":["The University of Tokyo,Japan"],"affiliations":[{"raw_affiliation_string":"The University of Tokyo,Japan","institution_ids":["https://openalex.org/I74801974"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5042731264","display_name":"Yuki Saito","orcid":"https://orcid.org/0000-0002-4825-7783"},"institutions":[{"id":"https://openalex.org/I74801974","display_name":"The University of Tokyo","ror":"https://ror.org/057zh3y96","country_code":"JP","type":"education","lineage":["https://openalex.org/I74801974"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Yuki Saito","raw_affiliation_strings":["The University of Tokyo,Japan"],"affiliations":[{"raw_affiliation_string":"The University of Tokyo,Japan","institution_ids":["https://openalex.org/I74801974"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5068962900","display_name":"Wataru Nakata","orcid":"https://orcid.org/0000-0003-3953-6534"},"institutions":[{"id":"https://openalex.org/I74801974","display_name":"The University of Tokyo","ror":"https://ror.org/057zh3y96","country_code":"JP","type":"education","lineage":["https://openalex.org/I74801974"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Wataru Nakata","raw_affiliation_strings":["The University of Tokyo,Japan"],"affiliations":[{"raw_affiliation_string":"The University of Tokyo,Japan","institution_ids":["https://openalex.org/I74801974"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5003814223","display_name":"Hiroshi Saruwatari","orcid":"https://orcid.org/0000-0003-0876-5617"},"institutions":[{"id":"https://openalex.org/I74801974","display_name":"The University of Tokyo","ror":"https://ror.org/057zh3y96","country_code":"JP","type":"education","lineage":["https://openalex.org/I74801974"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Hiroshi Saruwatari","raw_affiliation_strings":["The University of Tokyo,Japan"],"affiliations":[{"raw_affiliation_string":"The University of Tokyo,Japan","institution_ids":["https://openalex.org/I74801974"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5011937407"],"corresponding_institution_ids":["https://openalex.org/I74801974"],"apc_list":null,"apc_paid":null,"fwci":5.6828,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.94880749,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":95,"max":96},"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":0.9922999739646912,"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":0.9922999739646912,"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":0.9848999977111816,"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/computer-science","display_name":"Computer science","score":0.7559484243392944},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.6313448548316956},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5789297223091125},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5627106428146362},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.524213433265686},{"id":"https://openalex.org/keywords/supervised-learning","display_name":"Supervised learning","score":0.47892388701438904},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3558085560798645},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.14628735184669495}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7559484243392944},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.6313448548316956},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5789297223091125},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5627106428146362},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.524213433265686},{"id":"https://openalex.org/C136389625","wikidata":"https://www.wikidata.org/wiki/Q334384","display_name":"Supervised learning","level":3,"score":0.47892388701438904},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3558085560798645},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.14628735184669495},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49660.2025.10887678","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10887678","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":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":38,"referenced_works":["https://openalex.org/W1901129140","https://openalex.org/W2078528584","https://openalex.org/W2094721231","https://openalex.org/W2144404214","https://openalex.org/W2405774341","https://openalex.org/W2603567530","https://openalex.org/W2605589342","https://openalex.org/W2760103357","https://openalex.org/W2889442120","https://openalex.org/W2952218014","https://openalex.org/W3015337486","https://openalex.org/W3088775906","https://openalex.org/W3095248373","https://openalex.org/W3096408984","https://openalex.org/W3097906045","https://openalex.org/W3198680319","https://openalex.org/W3209984917","https://openalex.org/W3211944253","https://openalex.org/W4224917166","https://openalex.org/W4226021270","https://openalex.org/W4226403810","https://openalex.org/W4232282348","https://openalex.org/W4296068619","https://openalex.org/W4375868953","https://openalex.org/W4385807442","https://openalex.org/W4392909571","https://openalex.org/W4400111385","https://openalex.org/W4402111617","https://openalex.org/W4402672068","https://openalex.org/W6739901393","https://openalex.org/W6757632829","https://openalex.org/W6762931180","https://openalex.org/W6777701575","https://openalex.org/W6779216093","https://openalex.org/W6790356757","https://openalex.org/W6790758941","https://openalex.org/W6856434366","https://openalex.org/W6869968026"],"related_works":["https://openalex.org/W2961085424","https://openalex.org/W4224009465","https://openalex.org/W4306674287","https://openalex.org/W4286629047","https://openalex.org/W2518241345","https://openalex.org/W4390062853","https://openalex.org/W4389256085","https://openalex.org/W4399290976","https://openalex.org/W4285328440","https://openalex.org/W4313644201"],"abstract_inverted_index":{"Real-time":[0],"speech":[1,8],"enhancement":[2],"(SE)":[3],"is":[4,34,48],"essential":[5],"to":[6,51,76,96],"online":[7],"communication.":[9],"Causal":[10],"SE":[11,59],"models":[12],"use":[13],"only":[14,106],"the":[15,49,82,89,113,148],"previous":[16],"context":[17],"while":[18],"predicting":[19],"future":[20,114],"information,":[21],"such":[22],"as":[23,100],"phoneme":[24],"continuation,":[25],"may":[26],"help":[27],"performing":[28],"causal":[29,62,90,156],"SE.":[30,157],"The":[31,61,103,121],"phonetic":[32,98],"information":[33],"often":[35],"represented":[36],"by":[37],"quantizing":[38],"latent":[39],"features":[40,54,64,71,92,109],"of":[41],"self-supervised":[42],"learning":[43,119],"(SSL)":[44],"models.":[45],"This":[46],"work":[47],"first":[50],"incorporate":[52],"SSL":[53,63,91,108],"with":[55,69,139],"causality":[56],"into":[57],"an":[58,152],"model.":[60],"are":[65],"encoded":[66],"and":[67],"combined":[68],"spectrogram":[70],"using":[72,93,124],"feature-wise":[73],"linear":[74],"modulation":[75],"estimate":[77],"a":[78],"mask":[79],"for":[80],"enhancing":[81],"noisy":[83],"input":[84],"speech.":[85],"Simultaneously,":[86],"we":[87,145],"quantize":[88],"vector":[94],"quantization":[95],"represent":[97],"characteristics":[99],"semantic":[101,115,140,149],"tokens.":[102],"model":[104],"not":[105],"encodes":[107],"but":[110],"also":[111],"predicts":[112],"tokens":[116],"in":[117,136,143,155],"multi-task":[118],"(MTL).":[120],"experimental":[122],"results":[123],"VoiceBank":[125],"+":[126],"DEMAND":[127],"dataset":[128],"show":[129],"that":[130,147],"our":[131],"proposed":[132],"method":[133],"achieves":[134],"2.88":[135],"PESQ,":[137],"especially":[138],"prediction":[141,150],"MTL,":[142],"which":[144],"confirm":[146],"played":[151],"important":[153],"role":[154]},"counts_by_year":[{"year":2025,"cited_by_count":2}],"updated_date":"2025-12-21T23:12:01.093139","created_date":"2025-10-10T00:00:00"}