{"id":"https://openalex.org/W7148468665","doi":"https://doi.org/10.1109/asru65441.2025.11434703","title":"Acoustic Phonetic Temporal Speech Representation","display_name":"Acoustic Phonetic Temporal Speech Representation","publication_year":2025,"publication_date":"2025-12-06","ids":{"openalex":"https://openalex.org/W7148468665","doi":"https://doi.org/10.1109/asru65441.2025.11434703"},"language":null,"primary_location":{"id":"doi:10.1109/asru65441.2025.11434703","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asru65441.2025.11434703","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","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/A5040077928","display_name":"Yunbin Deng","orcid":"https://orcid.org/0000-0001-5844-0381"},"institutions":[{"id":"https://openalex.org/I4210122954","display_name":"MIT Lincoln Laboratory","ror":"https://ror.org/022z6jk58","country_code":"US","type":"facility","lineage":["https://openalex.org/I4210122954","https://openalex.org/I63966007"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Yunbin Deng","raw_affiliation_strings":["Lincoln Labortoary MIT,Lexington,MA,USA"],"affiliations":[{"raw_affiliation_string":"Lincoln Labortoary MIT,Lexington,MA,USA","institution_ids":["https://openalex.org/I4210122954"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5040077928"],"corresponding_institution_ids":["https://openalex.org/I4210122954"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.81922064,"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":"7"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10403","display_name":"Phonetics and Phonology Research","score":0.29829999804496765,"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":0.29829999804496765,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.210999995470047,"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":0.09390000253915787,"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/representation","display_name":"Representation (politics)","score":0.6133000254631042},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.5485000014305115},{"id":"https://openalex.org/keywords/tracing","display_name":"Tracing","score":0.5406000018119812},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.42879998683929443},{"id":"https://openalex.org/keywords/feature-learning","display_name":"Feature learning","score":0.4255000054836273},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.3427000045776367}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7559000253677368},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.6133000254631042},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6003999710083008},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.5485000014305115},{"id":"https://openalex.org/C138673069","wikidata":"https://www.wikidata.org/wiki/Q322229","display_name":"Tracing","level":2,"score":0.5406000018119812},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4902999997138977},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.42879998683929443},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.4255000054836273},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.3427000045776367},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.3353999853134155},{"id":"https://openalex.org/C155635449","wikidata":"https://www.wikidata.org/wiki/Q4674699","display_name":"Acoustic model","level":3,"score":0.3345000147819519},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.31690001487731934},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.27239999175071716},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.26930001378059387},{"id":"https://openalex.org/C137584468","wikidata":"https://www.wikidata.org/wiki/Q35395","display_name":"Phonetics","level":2,"score":0.26159998774528503}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/asru65441.2025.11434703","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asru65441.2025.11434703","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/10","score":0.4208037853240967,"display_name":"Reduced inequalities"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":20,"referenced_works":["https://openalex.org/W1494198834","https://openalex.org/W2963609956","https://openalex.org/W2964243274","https://openalex.org/W3095883095","https://openalex.org/W3150572638","https://openalex.org/W3163596559","https://openalex.org/W3203394408","https://openalex.org/W3203575608","https://openalex.org/W3207272747","https://openalex.org/W4225527248","https://openalex.org/W4297841787","https://openalex.org/W4311737082","https://openalex.org/W4322629454","https://openalex.org/W4381708595","https://openalex.org/W4385800847","https://openalex.org/W4399261686","https://openalex.org/W4402111622","https://openalex.org/W4402112414","https://openalex.org/W4408352962","https://openalex.org/W4413456957"],"related_works":[],"abstract_inverted_index":{"We":[0],"propose":[1],"a":[2,28,52,58],"novel":[3,63],"phoneme-aware":[4],"Acoustic":[5],"Phonetic":[6],"Temporal":[7],"(APT)":[8],"speech":[9,39],"representation":[10,64,123],"to":[11,50,92,115,137],"shed":[12],"light":[13],"on":[14,97,129],"explainable":[15,66],"audio":[16],"deepfake":[17,67],"detection":[18,69,106],"and":[19,46,88,118,135],"source":[20,126,143],"tracing.":[21],"It":[22],"captures":[23],"rich":[24,53],"articulatory":[25,111],"features":[26,49,85],"of":[27],"speaker":[29],"or":[30],"TTS":[31],"algorithm":[32],"at":[33],"the":[34,93,116,121,125,130,140],"phoneme":[35,42,44],"level.":[36],"The":[37,76],"APT":[38,77,103,122],"feature":[40,78],"combines":[41],"ID,":[43],"duration,":[45],"phoneme-specific":[47],"acoustic":[48],"form":[51],"representation.":[54],"When":[55],"combined":[56],"with":[57],"transformer":[59],"neural":[60],"network,":[61],"this":[62],"enables":[65],"voice":[68],"that":[70,102],"raw":[71],"data-driven":[72],"approaches":[73],"cannot":[74],"offer.":[75],"provides":[79],"intuitive":[80],"insights":[81],"by":[82,108],"highlighting":[83],"which":[84],"are":[86],"used":[87],"when":[89],"they":[90],"contribute":[91],"classification":[94],"decision.":[95],"Evaluation":[96],"an":[98],"In-the-Wild":[99],"dataset":[100,132],"shows":[101],"achieves":[104],"near-perfect":[105],"accuracy":[107,128],"learning":[109],"speaker-specific":[110],"features.":[112],"Moreover,":[113],"compared":[114],"Wav2Vec2.0/AASIST":[117],"RawNet2":[119],"baselines,":[120],"improves":[124],"tracing":[127,144],"TIMIT-TTS":[131],"from":[133],"29.5%":[134],"67.1%":[136],"80.4%":[138],"for":[139],"challenging":[141],"single-speaker":[142],"problem.":[145]},"counts_by_year":[],"updated_date":"2026-04-03T16:44:17.987007","created_date":"2026-04-03T00:00:00"}