{"id":"https://openalex.org/W4408354098","doi":"https://doi.org/10.1109/icassp49660.2025.10887658","title":"Advanced Zero-Shot Text-to-Speech for Background Removal and Preservation with Controllable Masked Speech Prediction","display_name":"Advanced Zero-Shot Text-to-Speech for Background Removal and Preservation with Controllable Masked Speech Prediction","publication_year":2025,"publication_date":"2025-03-12","ids":{"openalex":"https://openalex.org/W4408354098","doi":"https://doi.org/10.1109/icassp49660.2025.10887658"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49660.2025.10887658","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10887658","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/A5040622610","display_name":"Leying Zhang","orcid":"https://orcid.org/0000-0003-3356-6660"},"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":"Leying Zhang","raw_affiliation_strings":["Shanghai Jiao Tong University,Auditory Cognition and Computational Acoustics Lab, MoE Key Lab of Artificial Intelligence,AI Institute Department of Computer Science and Engineering,Shanghai,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University,Auditory Cognition and Computational Acoustics Lab, MoE Key Lab of Artificial Intelligence,AI Institute Department of Computer Science and Engineering,Shanghai,China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5071937621","display_name":"Wangyou Zhang","orcid":"https://orcid.org/0000-0003-4500-3515"},"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":"Wangyou Zhang","raw_affiliation_strings":["Shanghai Jiao Tong University,Auditory Cognition and Computational Acoustics Lab, MoE Key Lab of Artificial Intelligence,AI Institute Department of Computer Science and Engineering,Shanghai,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University,Auditory Cognition and Computational Acoustics Lab, MoE Key Lab of Artificial Intelligence,AI Institute Department of Computer Science and Engineering,Shanghai,China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101416769","display_name":"Zhengyang Chen","orcid":"https://orcid.org/0000-0003-1293-8146"},"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":"Zhengyang Chen","raw_affiliation_strings":["Shanghai Jiao Tong University,Auditory Cognition and Computational Acoustics Lab, MoE Key Lab of Artificial Intelligence,AI Institute Department of Computer Science and Engineering,Shanghai,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University,Auditory Cognition and Computational Acoustics Lab, MoE Key Lab of Artificial Intelligence,AI Institute Department of Computer Science and Engineering,Shanghai,China","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 Acoustics Lab, MoE Key Lab of Artificial Intelligence,AI Institute Department of Computer Science and Engineering,Shanghai,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University,Auditory Cognition and Computational Acoustics Lab, MoE Key Lab of Artificial Intelligence,AI Institute Department of Computer Science and Engineering,Shanghai,China","institution_ids":["https://openalex.org/I183067930"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I183067930"],"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":0.9930999875068665,"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":0.9930999875068665,"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":0.9491000175476074,"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":0.6867786049842834},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6503273844718933},{"id":"https://openalex.org/keywords/zero","display_name":"Zero (linguistics)","score":0.6078200340270996},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.49936842918395996},{"id":"https://openalex.org/keywords/shot","display_name":"Shot (pellet)","score":0.4494304060935974},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.4245205521583557},{"id":"https://openalex.org/keywords/speech-coding","display_name":"Speech coding","score":0.41450047492980957},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.1116340160369873}],"concepts":[{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6867786049842834},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6503273844718933},{"id":"https://openalex.org/C2780813799","wikidata":"https://www.wikidata.org/wiki/Q3274237","display_name":"Zero (linguistics)","level":2,"score":0.6078200340270996},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.49936842918395996},{"id":"https://openalex.org/C2778344882","wikidata":"https://www.wikidata.org/wiki/Q278938","display_name":"Shot (pellet)","level":2,"score":0.4494304060935974},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.4245205521583557},{"id":"https://openalex.org/C13895895","wikidata":"https://www.wikidata.org/wiki/Q3270773","display_name":"Speech coding","level":2,"score":0.41450047492980957},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.1116340160369873},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"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/C178790620","wikidata":"https://www.wikidata.org/wiki/Q11351","display_name":"Organic chemistry","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49660.2025.10887658","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10887658","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","score":0.49000000953674316,"display_name":"Reduced inequalities"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":34,"referenced_works":["https://openalex.org/W2566935005","https://openalex.org/W2696967604","https://openalex.org/W2801554275","https://openalex.org/W2972359262","https://openalex.org/W2972541922","https://openalex.org/W3163906773","https://openalex.org/W3205925339","https://openalex.org/W3206189675","https://openalex.org/W3209984917","https://openalex.org/W4221146604","https://openalex.org/W4226075807","https://openalex.org/W4252812408","https://openalex.org/W4297841603","https://openalex.org/W4372260214","https://openalex.org/W4375928773","https://openalex.org/W4386902717","https://openalex.org/W4391021752","https://openalex.org/W4392902843","https://openalex.org/W4392904355","https://openalex.org/W4392910802","https://openalex.org/W4400111385","https://openalex.org/W4402111215","https://openalex.org/W4406462048","https://openalex.org/W6752307458","https://openalex.org/W6783867762","https://openalex.org/W6795986329","https://openalex.org/W6840815571","https://openalex.org/W6846539466","https://openalex.org/W6848735303","https://openalex.org/W6851724922","https://openalex.org/W6859583170","https://openalex.org/W6862144568","https://openalex.org/W6864493879","https://openalex.org/W6936113694"],"related_works":["https://openalex.org/W1546240199","https://openalex.org/W193702574","https://openalex.org/W2063862874","https://openalex.org/W2164147372","https://openalex.org/W2053531689","https://openalex.org/W2154415461","https://openalex.org/W2550171623","https://openalex.org/W1842536210","https://openalex.org/W4253660971","https://openalex.org/W1923241916"],"abstract_inverted_index":{"The":[0,32],"acoustic":[1,133],"background":[2,22,47,54,110,130],"plays":[3],"a":[4,20,88,96,100],"crucial":[5,57],"role":[6],"in":[7,69,140],"natural":[8],"conversation.":[9],"It":[10],"provides":[11],"context":[12],"and":[13,112,135],"helps":[14],"listeners":[15,27],"understand":[16,29],"the":[17,53,60,64,106,125],"environment,":[18],"but":[19],"strong":[21,137],"makes":[23],"it":[24,41],"difficult":[25],"for":[26],"to":[28,45,48,58,104],"spoken":[30],"words.":[31],"appropriate":[33],"handling":[34],"of":[35,63,108,129],"these":[36,84],"backgrounds":[37],"is":[38,55],"situation-dependent:":[39],"Although":[40],"may":[42],"be":[43],"necessary":[44],"remove":[46],"ensure":[49],"speech":[50,78],"clarity,":[51],"preserving":[52],"sometimes":[56],"maintaining":[59],"contextual":[61],"integrity":[62],"speech.":[65],"Despite":[66],"recent":[67],"advancements":[68],"zero-shot":[70],"Text-to-Speech":[71],"technologies,":[72],"current":[73],"systems":[74],"often":[75],"struggle":[76],"with":[77,95],"prompts":[79],"containing":[80],"backgrounds.":[81],"To":[82],"address":[83],"challenges,":[85],"we":[86],"propose":[87],"Controllable":[89],"Masked":[90],"Speech":[91],"Prediction":[92],"strategy":[93],"coupled":[94],"dual-speaker":[97],"encoder,":[98],"utilizing":[99],"task-related":[101],"control":[102,123],"signal":[103],"guide":[105],"prediction":[107],"dual":[109],"removal":[111,126],"preservation":[113,128],"targets.":[114],"Experimental":[115],"results":[116],"demonstrate":[117],"that":[118],"our":[119],"approach":[120],"enables":[121],"precise":[122],"over":[124],"or":[127],"across":[131],"various":[132],"conditions":[134],"exhibits":[136],"generalization":[138],"capabilities":[139],"unseen":[141],"scenarios.":[142]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}