{"id":"https://openalex.org/W4408351987","doi":"https://doi.org/10.1109/icassp49660.2025.10889119","title":"SSR-Speech: Towards Stable, Safe and Robust Zero-shot Text-based Speech Editing and Synthesis","display_name":"SSR-Speech: Towards Stable, Safe and Robust Zero-shot Text-based Speech Editing and Synthesis","publication_year":2025,"publication_date":"2025-03-12","ids":{"openalex":"https://openalex.org/W4408351987","doi":"https://doi.org/10.1109/icassp49660.2025.10889119"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49660.2025.10889119","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10889119","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/A5101664824","display_name":"Helin Wang","orcid":"https://orcid.org/0000-0001-6088-0378"},"institutions":[{"id":"https://openalex.org/I145311948","display_name":"Johns Hopkins University","ror":"https://ror.org/00za53h95","country_code":"US","type":"education","lineage":["https://openalex.org/I145311948"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Helin Wang","raw_affiliation_strings":["Johns Hopkins University,Baltimore,USA"],"affiliations":[{"raw_affiliation_string":"Johns Hopkins University,Baltimore,USA","institution_ids":["https://openalex.org/I145311948"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101647742","display_name":"Yu Meng","orcid":"https://orcid.org/0000-0002-7472-1842"},"institutions":[{"id":"https://openalex.org/I4210108985","display_name":"Bellevue Hospital Center","ror":"https://ror.org/01ky34z31","country_code":"US","type":"healthcare","lineage":["https://openalex.org/I1283621791","https://openalex.org/I4210086933","https://openalex.org/I4210108985"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Meng Yu","raw_affiliation_strings":["Tencent AI Lab,Bellevue,USA"],"affiliations":[{"raw_affiliation_string":"Tencent AI Lab,Bellevue,USA","institution_ids":["https://openalex.org/I4210108985"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5048171604","display_name":"Jiarui Hai","orcid":"https://orcid.org/0000-0001-9968-7372"},"institutions":[{"id":"https://openalex.org/I145311948","display_name":"Johns Hopkins University","ror":"https://ror.org/00za53h95","country_code":"US","type":"education","lineage":["https://openalex.org/I145311948"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jiarui Hai","raw_affiliation_strings":["Johns Hopkins University,Baltimore,USA"],"affiliations":[{"raw_affiliation_string":"Johns Hopkins University,Baltimore,USA","institution_ids":["https://openalex.org/I145311948"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5114973667","display_name":"Chen Chen","orcid":"https://orcid.org/0000-0001-7359-8515"},"institutions":[{"id":"https://openalex.org/I172675005","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302","country_code":"SG","type":"education","lineage":["https://openalex.org/I172675005"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Chen Chen","raw_affiliation_strings":["Nanyang Technological University,Singapore"],"affiliations":[{"raw_affiliation_string":"Nanyang Technological University,Singapore","institution_ids":["https://openalex.org/I172675005"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100598749","display_name":"Yuchen Hu","orcid":"https://orcid.org/0009-0002-6789-2093"},"institutions":[{"id":"https://openalex.org/I172675005","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302","country_code":"SG","type":"education","lineage":["https://openalex.org/I172675005"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Yuchen Hu","raw_affiliation_strings":["Nanyang Technological University,Singapore"],"affiliations":[{"raw_affiliation_string":"Nanyang Technological University,Singapore","institution_ids":["https://openalex.org/I172675005"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5073675630","display_name":"Rilin Chen","orcid":null},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Rilin Chen","raw_affiliation_strings":["Tencent AI Lab,Beijing,China"],"affiliations":[{"raw_affiliation_string":"Tencent AI Lab,Beijing,China","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5050632169","display_name":"Najim Dehak","orcid":"https://orcid.org/0000-0002-4489-5753"},"institutions":[{"id":"https://openalex.org/I145311948","display_name":"Johns Hopkins University","ror":"https://ror.org/00za53h95","country_code":"US","type":"education","lineage":["https://openalex.org/I145311948"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Najim Dehak","raw_affiliation_strings":["Johns Hopkins University,Baltimore,USA"],"affiliations":[{"raw_affiliation_string":"Johns Hopkins University,Baltimore,USA","institution_ids":["https://openalex.org/I145311948"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5111337211","display_name":"Yu Dong","orcid":null},"institutions":[{"id":"https://openalex.org/I4210108985","display_name":"Bellevue Hospital Center","ror":"https://ror.org/01ky34z31","country_code":"US","type":"healthcare","lineage":["https://openalex.org/I1283621791","https://openalex.org/I4210086933","https://openalex.org/I4210108985"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Dong Yu","raw_affiliation_strings":["Tencent AI Lab,Bellevue,USA"],"affiliations":[{"raw_affiliation_string":"Tencent AI Lab,Bellevue,USA","institution_ids":["https://openalex.org/I4210108985"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":8,"corresponding_author_ids":["https://openalex.org/A5101664824"],"corresponding_institution_ids":["https://openalex.org/I145311948"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.01997159,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"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":0.9919999837875366,"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":0.9919999837875366,"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":0.9162999987602234,"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":0.7107877135276794},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6298555135726929},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.6156187653541565},{"id":"https://openalex.org/keywords/zero","display_name":"Zero (linguistics)","score":0.5327404141426086},{"id":"https://openalex.org/keywords/shot","display_name":"Shot (pellet)","score":0.4619344472885132},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3733968734741211},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3392106294631958},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.12438645958900452}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7107877135276794},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6298555135726929},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.6156187653541565},{"id":"https://openalex.org/C2780813799","wikidata":"https://www.wikidata.org/wiki/Q3274237","display_name":"Zero (linguistics)","level":2,"score":0.5327404141426086},{"id":"https://openalex.org/C2778344882","wikidata":"https://www.wikidata.org/wiki/Q278938","display_name":"Shot (pellet)","level":2,"score":0.4619344472885132},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3733968734741211},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3392106294631958},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.12438645958900452},{"id":"https://openalex.org/C178790620","wikidata":"https://www.wikidata.org/wiki/Q11351","display_name":"Organic chemistry","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/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49660.2025.10889119","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10889119","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":33,"referenced_works":["https://openalex.org/W1901129140","https://openalex.org/W2972359262","https://openalex.org/W3015826515","https://openalex.org/W3160438760","https://openalex.org/W3198694222","https://openalex.org/W3202278141","https://openalex.org/W3209984917","https://openalex.org/W4200300291","https://openalex.org/W4221142789","https://openalex.org/W4225420087","https://openalex.org/W4225596771","https://openalex.org/W4307323391","https://openalex.org/W4385245566","https://openalex.org/W4385571941","https://openalex.org/W4387865047","https://openalex.org/W4392903621","https://openalex.org/W4392904805","https://openalex.org/W4402111456","https://openalex.org/W4402112250","https://openalex.org/W4402672020","https://openalex.org/W4409362648","https://openalex.org/W6761551260","https://openalex.org/W6805710207","https://openalex.org/W6840815571","https://openalex.org/W6845479124","https://openalex.org/W6847363464","https://openalex.org/W6848735303","https://openalex.org/W6853188576","https://openalex.org/W6853888607","https://openalex.org/W6859934604","https://openalex.org/W6862144568","https://openalex.org/W6869189190","https://openalex.org/W6910888796"],"related_works":["https://openalex.org/W2074502265","https://openalex.org/W4214877189","https://openalex.org/W2773965352","https://openalex.org/W2381179799","https://openalex.org/W2980279061","https://openalex.org/W2334685461","https://openalex.org/W2366718574","https://openalex.org/W2359774528","https://openalex.org/W4298312966","https://openalex.org/W2325697621"],"abstract_inverted_index":{"In":[0,68],"this":[1],"paper,":[2],"we":[3],"introduce":[4],"SSR-Speech,":[5],"a":[6,28],"neural":[7],"codec":[8],"autoregressive":[9],"model":[10],"designed":[11],"for":[12],"stable,":[13],"safe,":[14],"and":[15,21,31,98,113,126],"robust":[16],"zero-shot":[17],"text-based":[18],"speech":[19,58,77,95,111],"editing":[20,96,112],"text-to-speech":[22,101],"synthesis.":[23],"SSR-Speech":[24,107],"is":[25,46],"built":[26],"on":[27],"Transformer":[29],"decoder":[30],"incorporates":[32],"classifier-free":[33],"guidance":[34],"to":[35,48,83,118],"enhance":[36],"the":[37,40,53,57,70,74,84,93,99],"stability":[38],"of":[39,56],"generation":[41],"process.":[42],"A":[43],"watermark":[44],"Encodec":[45,85],"proposed":[47],"embed":[49],"frame-level":[50],"watermarks":[51],"into":[52],"edited":[54,64],"regions":[55],"so":[59],"that":[60],"which":[61],"parts":[62],"were":[63],"can":[65],"be":[66],"detected.":[67],"addition,":[69],"waveform":[71],"reconstruction":[72],"leverages":[73],"original":[75],"unedited":[76],"segments,":[78],"providing":[79],"superior":[80],"recovery":[81],"compared":[82],"model.":[86],"Our":[87],"approach":[88],"achieves":[89],"state-of-the-art":[90],"performance":[91],"in":[92,109],"RealEdit":[94],"task":[97],"LibriTTS":[100],"task,":[102],"surpassing":[103],"previous":[104],"methods.":[105],"Furthermore,":[106],"excels":[108],"multi-span":[110],"also":[114],"demonstrates":[115],"remarkable":[116],"robustness":[117],"background":[119],"sounds.":[120],"The":[121],"source":[122],"code<sup":[123],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[124,128],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">1</sup>":[125],"demos<sup":[127],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">2</sup>":[129],"are":[130],"released.":[131]},"counts_by_year":[],"updated_date":"2025-12-28T23:10:05.387466","created_date":"2025-10-10T00:00:00"}