{"id":"https://openalex.org/W4408352063","doi":"https://doi.org/10.1109/icassp49660.2025.10888726","title":"Post-Net2.0: An adaptive weighted loss function driven by linguistic constraint for automatic syllable stress detection","display_name":"Post-Net2.0: An adaptive weighted loss function driven by linguistic constraint for automatic syllable stress detection","publication_year":2025,"publication_date":"2025-03-12","ids":{"openalex":"https://openalex.org/W4408352063","doi":"https://doi.org/10.1109/icassp49660.2025.10888726"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49660.2025.10888726","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10888726","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/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":["LTRC IIITH,Speech Processing Lab,Hyderabad,India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"LTRC IIITH,Speech Processing Lab,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":["LTRC IIITH,Speech Processing Lab,Hyderabad,India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"LTRC IIITH,Speech Processing Lab,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":["LTRC IIITH,Speech Processing Lab,Hyderabad,India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"LTRC IIITH,Speech Processing Lab,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":1.4048,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.78982101,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":95,"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":0.8967999815940857,"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":0.8967999815940857,"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"}},{"id":"https://openalex.org/T12031","display_name":"Speech and dialogue systems","score":0.8456000089645386,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.8149999976158142,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/syllable","display_name":"Syllable","score":0.8537561297416687},{"id":"https://openalex.org/keywords/constraint","display_name":"Constraint (computer-aided design)","score":0.7593186497688293},{"id":"https://openalex.org/keywords/stress","display_name":"Stress (linguistics)","score":0.6840565204620361},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6007145643234253},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5790292024612427},{"id":"https://openalex.org/keywords/function","display_name":"Function (biology)","score":0.5433964133262634},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4488084316253662},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4366072714328766},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.351095974445343},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.21874761581420898}],"concepts":[{"id":"https://openalex.org/C109089402","wikidata":"https://www.wikidata.org/wiki/Q8188","display_name":"Syllable","level":2,"score":0.8537561297416687},{"id":"https://openalex.org/C2776036281","wikidata":"https://www.wikidata.org/wiki/Q48769818","display_name":"Constraint (computer-aided design)","level":2,"score":0.7593186497688293},{"id":"https://openalex.org/C21036866","wikidata":"https://www.wikidata.org/wiki/Q181767","display_name":"Stress (linguistics)","level":2,"score":0.6840565204620361},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6007145643234253},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5790292024612427},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.5433964133262634},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4488084316253662},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4366072714328766},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.351095974445343},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.21874761581420898},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C78458016","wikidata":"https://www.wikidata.org/wiki/Q840400","display_name":"Evolutionary biology","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/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49660.2025.10888726","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10888726","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":0.4399999976158142,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":21,"referenced_works":["https://openalex.org/W135108420","https://openalex.org/W1498436455","https://openalex.org/W1973657629","https://openalex.org/W2038428558","https://openalex.org/W2064675550","https://openalex.org/W2167642311","https://openalex.org/W2221705832","https://openalex.org/W2402146185","https://openalex.org/W2517980096","https://openalex.org/W2608319664","https://openalex.org/W2973325419","https://openalex.org/W4233243299","https://openalex.org/W4388878660","https://openalex.org/W4393973357","https://openalex.org/W4402112166","https://openalex.org/W6631190155","https://openalex.org/W6637714784","https://openalex.org/W6682889407","https://openalex.org/W6683017116","https://openalex.org/W6770509160","https://openalex.org/W6780218876"],"related_works":["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","https://openalex.org/W3156241633","https://openalex.org/W2112609279"],"abstract_inverted_index":{"Automatic":[0],"syllable":[1,58,73,136],"stress":[2,59,91],"detection":[3,60],"is":[4,74,86,125,158,168,221,234],"an":[5,64,100],"essential":[6],"component":[7],"in":[8,42,114,223,236],"Computer":[9],"assisted":[10],"language":[11,18],"learning":[12],"(CALL)":[13],"systems":[14],"to":[15,68,127,243,247],"guide":[16],"nonnative":[17],"learners.":[19],"In":[20,205],"English,":[21],"each":[22],"word":[23],"typically":[24],"contains":[25],"only":[26,71,191],"one":[27,72],"primary":[28,134],"stressed":[29,49,75,135],"syllable.":[30],"However,":[31],"standard":[32,176],"loss":[33,103,123,144,194,217,260],"functions,":[34],"such":[35],"as":[36],"Binary":[37],"Cross-Entropy":[38],"(BCE),":[39],"often":[40],"result":[41],"predictions":[43],"where":[44],"multiple":[45],"syllables":[46],"may":[47],"be":[48],"or":[50],"none":[51],"at":[52],"all.":[53],"As":[54],"a":[55,132,154,159,196,239],"result,":[56],"automatic":[57],"models":[61,173,189,209],"frequently":[62],"require":[63],"additional":[65],"post-processing":[66,81],"step":[67],"ensure":[69],"that":[70,83,105,186,256],"per":[76],"word.":[77],"This":[78,120,254],"reliance":[79],"on":[80,153,181,212],"suggests":[82],"the":[84,90,108,129,147,171,182,188,213,219,225,228,231,257,264,270],"model":[85,139],"not":[87],"fully":[88],"capturing":[89],"patterns":[92],"accurately.":[93],"To":[94],"address":[95],"this":[96,143],"issue,":[97],"we":[98],"propose":[99],"adaptive":[101,121,215,258],"weighted":[102,122,216,259],"function":[104,124,145,261],"builds":[106],"upon":[107],"Stress":[109],"Intensity":[110],"Modulation":[111],"Loss":[112],"proposed":[113,149,214],"our":[115],"recent":[116],"work":[117],"of":[118,131,161],"Post-Net.":[119],"designed":[126],"enforce":[128],"constraint":[130,266],"single":[133],"directly":[137],"during":[138,267],"training.":[140],"We":[141],"integrate":[142],"into":[146],"previously":[148],"Post-Net":[150,162],"(PN_DNN)":[151],"and":[152,163,202],"new":[155],"architecture":[156],"which":[157],"hybrid":[160],"LSTM":[164],"(PN_DLSTM).":[165],"Their":[166],"performance":[167],"compared":[169],"against":[170],"state-of-the-art":[172],"trained":[174,190,211],"with":[175,192,201,238],"BCE":[177,193],"loss.":[178],"Experiments":[179],"conducted":[180],"ISLE":[183],"corpus":[184],"reveal":[185],"both":[187,224],"show":[195],"significant":[197],"accuracy":[198],"gap":[199,220],"between":[200],"without":[203],"post-processing.":[204,273],"contrast,":[206],"when":[207],"these":[208],"are":[210],"function,":[218],"narrowed":[222],"models.":[226],"Between":[227],"two":[229],"models,":[230],"highest":[232],"reduction":[233],"observed":[235],"PN_DNN":[237],"decrease":[240],"from":[241],"3.87%":[242],"2.45%":[244],"&":[245,251],"4.6%":[246],"3.75%":[248],"for":[249,272],"GER":[250],"ITA":[252],"respectively.":[253],"indicates":[255],"effectively":[262],"captures":[263],"linguistic":[265],"training,":[268],"reducing":[269],"need":[271]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-06-26T08:34:08.712188","created_date":"2025-10-10T00:00:00"}