{"id":"https://openalex.org/W4408354049","doi":"https://doi.org/10.1109/icassp49660.2025.10887886","title":"Dynamic Speech Generation to Enhance Intelligibility in Noisy Environments","display_name":"Dynamic Speech Generation to Enhance Intelligibility in Noisy Environments","publication_year":2025,"publication_date":"2025-03-12","ids":{"openalex":"https://openalex.org/W4408354049","doi":"https://doi.org/10.1109/icassp49660.2025.10887886"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49660.2025.10887886","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10887886","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/A5056333052","display_name":"Olympia Simantiraki","orcid":"https://orcid.org/0000-0001-8592-2132"},"institutions":[{"id":"https://openalex.org/I8901234","display_name":"Foundation for Research and Technology Hellas","ror":"https://ror.org/052rphn09","country_code":"GR","type":"facility","lineage":["https://openalex.org/I8901234"]}],"countries":["GR"],"is_corresponding":true,"raw_author_name":"Olympia Simantiraki","raw_affiliation_strings":["Foundation for Research and Technology,Institute of Applied and Computational Mathematics,Greece"],"affiliations":[{"raw_affiliation_string":"Foundation for Research and Technology,Institute of Applied and Computational Mathematics,Greece","institution_ids":["https://openalex.org/I8901234"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5049178759","display_name":"Maria Markaki","orcid":"https://orcid.org/0000-0002-0071-341X"},"institutions":[{"id":"https://openalex.org/I8901234","display_name":"Foundation for Research and Technology Hellas","ror":"https://ror.org/052rphn09","country_code":"GR","type":"facility","lineage":["https://openalex.org/I8901234"]}],"countries":["GR"],"is_corresponding":false,"raw_author_name":"Maria Markaki","raw_affiliation_strings":["Foundation for Research and Technology,Institute of Applied and Computational Mathematics,Greece"],"affiliations":[{"raw_affiliation_string":"Foundation for Research and Technology,Institute of Applied and Computational Mathematics,Greece","institution_ids":["https://openalex.org/I8901234"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5010084334","display_name":"Yannis Pantazis","orcid":"https://orcid.org/0000-0002-2009-7562"},"institutions":[{"id":"https://openalex.org/I8901234","display_name":"Foundation for Research and Technology Hellas","ror":"https://ror.org/052rphn09","country_code":"GR","type":"facility","lineage":["https://openalex.org/I8901234"]}],"countries":["GR"],"is_corresponding":false,"raw_author_name":"Yannis Pantazis","raw_affiliation_strings":["Foundation for Research and Technology,Institute of Applied and Computational Mathematics,Greece"],"affiliations":[{"raw_affiliation_string":"Foundation for Research and Technology,Institute of Applied and Computational Mathematics,Greece","institution_ids":["https://openalex.org/I8901234"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5056333052"],"corresponding_institution_ids":["https://openalex.org/I8901234"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.0556749,"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/T10860","display_name":"Speech and Audio Processing","score":0.9115999937057495,"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":0.9115999937057495,"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":0.732245683670044},{"id":"https://openalex.org/keywords/intelligibility","display_name":"Intelligibility (philosophy)","score":0.7035617828369141},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6273188591003418}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.732245683670044},{"id":"https://openalex.org/C60048801","wikidata":"https://www.wikidata.org/wiki/Q1433889","display_name":"Intelligibility (philosophy)","level":2,"score":0.7035617828369141},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6273188591003418},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49660.2025.10887886","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10887886","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/F4320327859","display_name":"Hellenic Foundation for Research and Innovation","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":33,"referenced_works":["https://openalex.org/W65497148","https://openalex.org/W1716865208","https://openalex.org/W1970405784","https://openalex.org/W2022880580","https://openalex.org/W2068548806","https://openalex.org/W2086745849","https://openalex.org/W2104387086","https://openalex.org/W2118258949","https://openalex.org/W2139913386","https://openalex.org/W2149948223","https://openalex.org/W2163010125","https://openalex.org/W2401725871","https://openalex.org/W2403280443","https://openalex.org/W2404548911","https://openalex.org/W2516196108","https://openalex.org/W2636064478","https://openalex.org/W2749552851","https://openalex.org/W2771877711","https://openalex.org/W2898066540","https://openalex.org/W2903739847","https://openalex.org/W2911412811","https://openalex.org/W2938932039","https://openalex.org/W2963609956","https://openalex.org/W3095545636","https://openalex.org/W3096795913","https://openalex.org/W3097587372","https://openalex.org/W4372260118","https://openalex.org/W4385350068","https://openalex.org/W4385822622","https://openalex.org/W6712845745","https://openalex.org/W6748409065","https://openalex.org/W6779337556","https://openalex.org/W6917585676"],"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/W2127461790","https://openalex.org/W2069324367"],"abstract_inverted_index":{"Synthetic":[0],"speech":[1,42,47,66,80,111,183],"is":[2,81],"occasionally":[3],"required":[4],"to":[5,15,84],"be":[6],"enhanced":[7],"by":[8,61],"a":[9,40,132],"fixed":[10],"amount":[11],"before":[12],"being":[13],"presented":[14],"the":[16,22,51,58,65,70,73,78,85,99,106,138,154,159,170,178],"listener.":[17],"However,":[18],"this":[19],"approach":[20],"neglects":[21],"diverse":[23],"types":[24],"and":[25,88,137,149,151,176],"levels":[26],"of":[27,53,147,162,180],"noise,":[28],"potentially":[29],"resulting":[30],"in":[31,114,127,145,153,186],"either":[32],"unintelligible":[33],"or":[34],"unpleasant":[35],"speech.":[36,172],"This":[37],"paper":[38],"proposes":[39],"dynamic":[41,182],"enhancement":[43,184],"approach,":[44],"which":[45],"generates":[46],"while":[48],"accounting":[49],"for":[50],"presence":[52],"noise.":[54,75],"Our":[55,121,173],"methodology":[56],"extends":[57],"WaveRNN":[59],"vocoder":[60],"conditioning":[62],"not":[63],"only":[64],"mel-spectrograms":[67],"but":[68],"also":[69],"spectrogram":[71],"from":[72],"background":[74],"In":[76],"training,":[77],"target":[79,103],"tilted":[82],"according":[83],"listeners\u2019":[86],"preference":[87,150],"we":[89],"further":[90],"introduce":[91],"an":[92],"objective":[93],"metric":[94],"that":[95,125],"aims":[96],"at":[97,117],"maximizing":[98],"spectro-temporal":[100],"regions":[101],"where":[102,158],"energy":[104],"exceeds":[105],"masker":[107],"energy.":[108],"The":[109],"generated":[110],"was":[112],"tested":[113],"speech-shaped":[115],"noise":[116,119],"various":[118],"levels.":[120],"evaluation":[122],"results":[123],"showed":[124],"(a)":[126],"more":[128],"adverse":[129],"conditions,":[130,157],"both":[131],"fixed-amount":[133],"post-enhanced":[134],"baseline":[135],"system":[136,141],"suggested":[139],"dynamically-enhanced":[140,171],"performed":[142],"equally":[143],"well":[144],"terms":[146],"intelligibility":[148,160],"(b)":[152],"least":[155],"noisy":[156,187],"scores":[161],"all":[163],"models":[164],"were":[165],"nearly":[166],"identical,":[167],"listeners":[168],"preferred":[169],"findings":[174],"demonstrate":[175],"reinforce":[177],"benefits":[179],"using":[181],"techniques":[185],"environments.":[188]},"counts_by_year":[],"updated_date":"2025-12-21T01:58:51.020947","created_date":"2025-10-10T00:00:00"}