{"id":"https://openalex.org/W4408354705","doi":"https://doi.org/10.1109/icassp49660.2025.10890497","title":"Robust and Efficient Text-based Speech Editing using Noise Conditioning and Rectified Flow","display_name":"Robust and Efficient Text-based Speech Editing using Noise Conditioning and Rectified Flow","publication_year":2025,"publication_date":"2025-03-12","ids":{"openalex":"https://openalex.org/W4408354705","doi":"https://doi.org/10.1109/icassp49660.2025.10890497"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49660.2025.10890497","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10890497","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/A5036227113","display_name":"Hui Yin","orcid":"https://orcid.org/0000-0002-6611-2684"},"institutions":[{"id":"https://openalex.org/I96908189","display_name":"Xinjiang University","ror":"https://ror.org/059gw8r13","country_code":"CN","type":"education","lineage":["https://openalex.org/I96908189"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Haowen Yin","raw_affiliation_strings":["Xinjiang University,School of Computer Science and Technology,Urumqi,China"],"affiliations":[{"raw_affiliation_string":"Xinjiang University,School of Computer Science and Technology,Urumqi,China","institution_ids":["https://openalex.org/I96908189"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101575588","display_name":"Kai Wang","orcid":"https://orcid.org/0000-0001-9767-2951"},"institutions":[{"id":"https://openalex.org/I96908189","display_name":"Xinjiang University","ror":"https://ror.org/059gw8r13","country_code":"CN","type":"education","lineage":["https://openalex.org/I96908189"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Kai Wang","raw_affiliation_strings":["Xinjiang University,School of Computer Science and Technology,Urumqi,China"],"affiliations":[{"raw_affiliation_string":"Xinjiang University,School of Computer Science and Technology,Urumqi,China","institution_ids":["https://openalex.org/I96908189"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102793453","display_name":"Hongli Yang","orcid":"https://orcid.org/0009-0008-7605-655X"},"institutions":[{"id":"https://openalex.org/I96908189","display_name":"Xinjiang University","ror":"https://ror.org/059gw8r13","country_code":"CN","type":"education","lineage":["https://openalex.org/I96908189"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hongli Yang","raw_affiliation_strings":["Xinjiang University,School of Computer Science and Technology,Urumqi,China"],"affiliations":[{"raw_affiliation_string":"Xinjiang University,School of Computer Science and Technology,Urumqi,China","institution_ids":["https://openalex.org/I96908189"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5024772368","display_name":"Hao Huang","orcid":"https://orcid.org/0000-0001-6604-0951"},"institutions":[{"id":"https://openalex.org/I96908189","display_name":"Xinjiang University","ror":"https://ror.org/059gw8r13","country_code":"CN","type":"education","lineage":["https://openalex.org/I96908189"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hao Huang","raw_affiliation_strings":["Xinjiang University,School of Computer Science and Technology,Urumqi,China"],"affiliations":[{"raw_affiliation_string":"Xinjiang University,School of Computer Science and Technology,Urumqi,China","institution_ids":["https://openalex.org/I96908189"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5063120015","display_name":"Wushour Silamu","orcid":"https://orcid.org/0000-0003-4592-7806"},"institutions":[{"id":"https://openalex.org/I96908189","display_name":"Xinjiang University","ror":"https://ror.org/059gw8r13","country_code":"CN","type":"education","lineage":["https://openalex.org/I96908189"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wushour Silamu","raw_affiliation_strings":["Xinjiang University,School of Computer Science and Technology,Urumqi,China"],"affiliations":[{"raw_affiliation_string":"Xinjiang University,School of Computer Science and Technology,Urumqi,China","institution_ids":["https://openalex.org/I96908189"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5036227113"],"corresponding_institution_ids":["https://openalex.org/I96908189"],"apc_list":null,"apc_paid":null,"fwci":2.8599,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.89849575,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":95},"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":0.9927999973297119,"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":0.9927999973297119,"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":0.9337999820709229,"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":0.6871967911720276},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6758097410202026},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.6107677221298218},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.33402788639068604}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6871967911720276},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6758097410202026},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.6107677221298218},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.33402788639068604},{"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/icassp49660.2025.10890497","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10890497","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":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":29,"referenced_works":["https://openalex.org/W1552314771","https://openalex.org/W1836465849","https://openalex.org/W1901129140","https://openalex.org/W2107860279","https://openalex.org/W2194775991","https://openalex.org/W2519091744","https://openalex.org/W2737697117","https://openalex.org/W2747874407","https://openalex.org/W2964243274","https://openalex.org/W3097945073","https://openalex.org/W3163906773","https://openalex.org/W4221142789","https://openalex.org/W4221146604","https://openalex.org/W4225596771","https://openalex.org/W4226075807","https://openalex.org/W4297841480","https://openalex.org/W4385245566","https://openalex.org/W4385571941","https://openalex.org/W4386902717","https://openalex.org/W4392904491","https://openalex.org/W4392931781","https://openalex.org/W4402112176","https://openalex.org/W6688816777","https://openalex.org/W6778823374","https://openalex.org/W6779823529","https://openalex.org/W6783867762","https://openalex.org/W6843731886","https://openalex.org/W6847363464","https://openalex.org/W6849790239"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W4391913857","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W4396696052"],"abstract_inverted_index":{"Significant":[0],"advancements":[1],"have":[2],"been":[3],"made":[4],"in":[5,144],"text-based":[6],"speech":[7,18,32,54,112,139],"editing":[8,15,120],"(TSE)":[9],"for":[10,52,149],"clear":[11],"speech,":[12,29,151],"but":[13],"effectively":[14],"the":[16,25,72,107],"noise-contaminated":[17],"remains":[19],"a":[20,46,62,141],"challenge.":[21],"Background":[22],"noise":[23,37,57,63,69,87],"degrades":[24],"quality":[26],"of":[27,133],"generated":[28],"and":[30,48,75,93,114],"edited":[31],"that":[33,84,128],"fails":[34],"to":[35,66,98,117],"maintain":[36],"context":[38,113],"consistency":[39],"often":[40],"sounds":[41],"unnatural.":[42],"We":[43],"propose":[44],"Reflow-TSE,":[45],"robust":[47],"efficient":[49],"TSE":[50,146],"model":[51],"noise-consistent":[53],"editing.":[55],"For":[56,101],"robustness,":[58],"1)":[59],"we":[60,77,105],"design":[61],"condition":[64],"module":[65,83],"extract":[67],"frame-level":[68],"sequences":[70,88],"as":[71],"conditioning":[73],"information,":[74],"2)":[76],"introduce":[78,106],"an":[79],"enhanced":[80],"context-conditioned":[81],"prediction":[82],"predicts":[85],"masked":[86],"along":[89],"with":[90,121,129],"conventional":[91],"duration":[92],"pitch,":[94],"using":[95],"these":[96],"conditions":[97,116],"guide":[99],"generation.":[100],"boosting":[102],"efficiency,":[103],"3)":[104],"rectified":[108],"flow":[109],"model,":[110],"leveraging":[111],"predicted":[115],"achieve":[118],"high-quality":[119],"limited":[122],"sampling":[123],"steps.":[124],"Experimental":[125],"results":[126],"show":[127],"just":[130],"two":[131],"steps":[132],"sampling,":[134],"Reflow-TSE":[135,152],"achieves":[136],"context-consistent":[137],"noisy":[138],"editing,":[140],"capability":[142],"absent":[143],"other":[145],"models.":[147,158],"Additionally,":[148],"clean":[150],"also":[153],"matches":[154],"or":[155],"surpasses":[156],"baseline":[157],"Audio":[159],"samples":[160],"are":[161],"available":[162],"at":[163],"https://hw-su.github.io.":[164]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2025-12-28T23:10:05.387466","created_date":"2025-10-10T00:00:00"}