{"id":"https://openalex.org/W4408352176","doi":"https://doi.org/10.1109/icassp49660.2025.10889081","title":"Evaluating the Impact of Discriminative and Generative E2E Speech Enhancement Models on Syllable Stress Preservation","display_name":"Evaluating the Impact of Discriminative and Generative E2E Speech Enhancement Models on Syllable Stress Preservation","publication_year":2025,"publication_date":"2025-03-12","ids":{"openalex":"https://openalex.org/W4408352176","doi":"https://doi.org/10.1109/icassp49660.2025.10889081"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49660.2025.10889081","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10889081","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/A5115405394","display_name":"Rangavajjala Sankara Bharadwaj","orcid":null},"institutions":[{"id":"https://openalex.org/I64189192","display_name":"International Institute of Information Technology, Hyderabad","ror":"https://ror.org/05f11g639","country_code":"IN","type":"education","lineage":["https://openalex.org/I64189192"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Rangavajjala Sankara Bharadwaj","raw_affiliation_strings":["International Institute of Information Technology,Language Technology Research Centre,Hyderabad,India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"International Institute of Information Technology,Language Technology Research Centre,Hyderabad,India","institution_ids":["https://openalex.org/I64189192"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5008931819","display_name":"Jhansi Mallela","orcid":null},"institutions":[{"id":"https://openalex.org/I64189192","display_name":"International Institute of Information Technology, Hyderabad","ror":"https://ror.org/05f11g639","country_code":"IN","type":"education","lineage":["https://openalex.org/I64189192"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Jhansi Mallela","raw_affiliation_strings":["International Institute of Information Technology,Language Technology Research Centre,Hyderabad,India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"International Institute of Information Technology,Language Technology Research Centre,Hyderabad,India","institution_ids":["https://openalex.org/I64189192"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5092596607","display_name":"Sai Harshitha Aluru","orcid":null},"institutions":[{"id":"https://openalex.org/I64189192","display_name":"International Institute of Information Technology, Hyderabad","ror":"https://ror.org/05f11g639","country_code":"IN","type":"education","lineage":["https://openalex.org/I64189192"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Sai Harshitha Aluru","raw_affiliation_strings":["International Institute of Information Technology,Language Technology Research Centre,Hyderabad,India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"International Institute of Information Technology,Language Technology Research Centre,Hyderabad,India","institution_ids":["https://openalex.org/I64189192"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5064062192","display_name":"Chiranjeevi Yarra","orcid":"https://orcid.org/0000-0002-0574-8777"},"institutions":[{"id":"https://openalex.org/I64189192","display_name":"International Institute of Information Technology, Hyderabad","ror":"https://ror.org/05f11g639","country_code":"IN","type":"education","lineage":["https://openalex.org/I64189192"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Chiranjeevi Yarra","raw_affiliation_strings":["International Institute of Information Technology,Language Technology Research Centre,Hyderabad,India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"International Institute of Information Technology,Language Technology Research Centre,Hyderabad,India","institution_ids":["https://openalex.org/I64189192"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I64189192"],"apc_list":null,"apc_paid":null,"fwci":2.8096,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.88514327,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":97},"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/T10403","display_name":"Phonetics and Phonology Research","score":0.9068999886512756,"subfield":{"id":"https://openalex.org/subfields/3205","display_name":"Experimental and Cognitive Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},"topics":[{"id":"https://openalex.org/T10403","display_name":"Phonetics and Phonology Research","score":0.9068999886512756,"subfield":{"id":"https://openalex.org/subfields/3205","display_name":"Experimental and Cognitive Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/discriminative-model","display_name":"Discriminative model","score":0.8689976930618286},{"id":"https://openalex.org/keywords/syllable","display_name":"Syllable","score":0.7662920951843262},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6836411952972412},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6605778932571411},{"id":"https://openalex.org/keywords/generative-grammar","display_name":"Generative grammar","score":0.6232450008392334},{"id":"https://openalex.org/keywords/stress","display_name":"Stress (linguistics)","score":0.6159605979919434},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.40205276012420654},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.32383477687835693},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.12619149684906006}],"concepts":[{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.8689976930618286},{"id":"https://openalex.org/C109089402","wikidata":"https://www.wikidata.org/wiki/Q8188","display_name":"Syllable","level":2,"score":0.7662920951843262},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6836411952972412},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6605778932571411},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.6232450008392334},{"id":"https://openalex.org/C21036866","wikidata":"https://www.wikidata.org/wiki/Q181767","display_name":"Stress (linguistics)","level":2,"score":0.6159605979919434},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.40205276012420654},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.32383477687835693},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.12619149684906006},{"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/icassp49660.2025.10889081","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10889081","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":[{"score":0.8199999928474426,"id":"https://metadata.un.org/sdg/10","display_name":"Reduced inequalities"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":35,"referenced_works":["https://openalex.org/W135108420","https://openalex.org/W1494198834","https://openalex.org/W1897240248","https://openalex.org/W1901129140","https://openalex.org/W1973657629","https://openalex.org/W2094721231","https://openalex.org/W2167642311","https://openalex.org/W2221705832","https://openalex.org/W2593116425","https://openalex.org/W2603567530","https://openalex.org/W2608319664","https://openalex.org/W2746457594","https://openalex.org/W2889540509","https://openalex.org/W2952218014","https://openalex.org/W2962935966","https://openalex.org/W2972852081","https://openalex.org/W2973325419","https://openalex.org/W2990594533","https://openalex.org/W3003326990","https://openalex.org/W3095057960","https://openalex.org/W3097906045","https://openalex.org/W3097945073","https://openalex.org/W3209059054","https://openalex.org/W4221144097","https://openalex.org/W4224918181","https://openalex.org/W4232282348","https://openalex.org/W4388119635","https://openalex.org/W4388878660","https://openalex.org/W4393973357","https://openalex.org/W6637714784","https://openalex.org/W6679045638","https://openalex.org/W6744762798","https://openalex.org/W6770509160","https://openalex.org/W6780218876","https://openalex.org/W6803378298"],"related_works":["https://openalex.org/W4396941953","https://openalex.org/W2987280934","https://openalex.org/W3211091934","https://openalex.org/W2148825993","https://openalex.org/W1547743883","https://openalex.org/W2514064218","https://openalex.org/W2181821413","https://openalex.org/W2094188777","https://openalex.org/W2065604758","https://openalex.org/W2132658536"],"abstract_inverted_index":{"Automatic":[0],"syllable":[1,62,83,172],"stress":[2,18,63,84,115,132,154,173,198,224],"detection":[3,19,85,199,225],"is":[4,38,65,148,201],"a":[5,144],"crucial":[6],"component":[7],"in":[8,32,113,156,161],"Computer-Assisted":[9],"Language":[10],"Learning":[11],"(CALL)":[12],"systems":[13],"for":[14,130],"language":[15],"learners.":[16],"Current":[17],"models":[20,92,170,207],"are":[21,127,179,211,220],"typically":[22],"trained":[23],"on":[24,60,181],"clean":[25,162],"speech,":[26,163],"which":[27,125],"may":[28],"not":[29,66],"be":[30,55],"robust":[31,202],"real-world":[33],"scenarios":[34],"where":[35],"background":[36],"noise":[37],"prevalent.":[39],"To":[40,136],"address":[41],"this,":[42],"speech":[43,50,97,158,183],"enhancement":[44],"(SE)":[45],"models,":[46,75,143],"designed":[47],"to":[48,96,106,123,150],"enhance":[49],"by":[51,93,176],"removing":[52],"noise,":[53],"might":[54],"employed,":[56],"but":[57],"their":[58,111],"impact":[59,140],"preserving":[61],"patterns":[64,133,155],"well":[67,168],"studied.":[68],"This":[69],"study":[70,147,219],"examines":[71],"how":[72,167],"different":[73,120],"SE":[74,142,206,229],"representing":[76],"discriminative":[77],"and":[78,109,190],"generative":[79,205],"modeling":[80],"approaches,":[81],"affect":[82],"under":[86,227],"noisy":[87],"conditions.":[88],"We":[89],"assess":[90],"these":[91,169],"applying":[94],"them":[95],"data":[98,184],"with":[99,159,203,222],"varying":[100],"signal-to-noise":[101],"ratios":[102],"(SNRs)":[103],"from":[104,185,216],"0":[105],"20":[107],"dB,":[108],"evaluating":[110],"effectiveness":[112],"maintaining":[114],"patterns.":[116],"Additionally,":[117],"we":[118],"explore":[119],"feature":[121],"sets":[122],"determine":[124],"ones":[126],"most":[128],"effective":[129],"capturing":[131],"amidst":[134],"noise.":[135],"further":[137],"understand":[138],"the":[139,152,193,197,204,214,217,223],"of":[141,188],"human-based":[145],"perceptual":[146,218],"conducted":[149],"compare":[151],"perceived":[153,175],"SE-enhanced":[157],"those":[160],"providing":[164],"insights":[165],"into":[166],"preserve":[171],"as":[174],"listeners.":[177],"Experiments":[178],"performed":[180],"English":[182],"non-native":[186],"speakers":[187],"German":[189],"Italian.":[191],"And":[192],"results":[194],"reveal":[195],"that":[196],"performance":[200],"when":[208],"heuristic":[209],"features":[210],"used.":[212],"Also,":[213],"observations":[215],"consistent":[221],"outcomes":[226],"all":[228],"models.":[230]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1}],"updated_date":"2026-06-26T08:34:08.712188","created_date":"2025-10-10T00:00:00"}