{"id":"https://openalex.org/W4416799050","doi":"https://doi.org/10.1109/apsipaasc65261.2025.11249254","title":"Normalization Through Fine-Tuning: Understanding Wav2vec2.0 Embeddings for Phonetic Analysis","display_name":"Normalization Through Fine-Tuning: Understanding Wav2vec2.0 Embeddings for Phonetic Analysis","publication_year":2025,"publication_date":"2025-10-22","ids":{"openalex":"https://openalex.org/W4416799050","doi":"https://doi.org/10.1109/apsipaasc65261.2025.11249254"},"language":null,"primary_location":{"id":"doi:10.1109/apsipaasc65261.2025.11249254","is_oa":false,"landing_page_url":"https://doi.org/10.1109/apsipaasc65261.2025.11249254","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 Asia Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5100377965","display_name":"Yiming Wang","orcid":"https://orcid.org/0009-0007-0436-5209"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yiming Wang","raw_affiliation_strings":["University of Science and Technology of China,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Science and Technology of China,China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5043406907","display_name":"Jiahong Yuan","orcid":"https://orcid.org/0009-0008-2162-7167"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiahong Yuan","raw_affiliation_strings":["University of Science and Technology of China,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Science and Technology of China,China","institution_ids":["https://openalex.org/I126520041"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I126520041"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"2587","last_page":"2591"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.7754999995231628,"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":0.7754999995231628,"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/T10667","display_name":"Emotion and Mood Recognition","score":0.04820000007748604,"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/T10403","display_name":"Phonetics and Phonology Research","score":0.035100001841783524,"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/normalization","display_name":"Normalization (sociology)","score":0.8496000170707703},{"id":"https://openalex.org/keywords/preprocessor","display_name":"Preprocessor","score":0.6603999733924866},{"id":"https://openalex.org/keywords/comparability","display_name":"Comparability","score":0.4535999894142151},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.40389999747276306},{"id":"https://openalex.org/keywords/parallels","display_name":"Parallels","score":0.3262999951839447}],"concepts":[{"id":"https://openalex.org/C136886441","wikidata":"https://www.wikidata.org/wiki/Q926129","display_name":"Normalization (sociology)","level":2,"score":0.8496000170707703},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.754800021648407},{"id":"https://openalex.org/C34736171","wikidata":"https://www.wikidata.org/wiki/Q918333","display_name":"Preprocessor","level":2,"score":0.6603999733924866},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.635200023651123},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4878999888896942},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4551999866962433},{"id":"https://openalex.org/C197947376","wikidata":"https://www.wikidata.org/wiki/Q5155608","display_name":"Comparability","level":2,"score":0.4535999894142151},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.40389999747276306},{"id":"https://openalex.org/C2775922551","wikidata":"https://www.wikidata.org/wiki/Q7135033","display_name":"Parallels","level":2,"score":0.3262999951839447},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.31940001249313354},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.3109000027179718},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.30000001192092896}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/apsipaasc65261.2025.11249254","is_oa":false,"landing_page_url":"https://doi.org/10.1109/apsipaasc65261.2025.11249254","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 Asia Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":13,"referenced_works":["https://openalex.org/W2003483021","https://openalex.org/W2035853491","https://openalex.org/W2041086022","https://openalex.org/W2059596129","https://openalex.org/W2069826235","https://openalex.org/W2749756027","https://openalex.org/W2963242190","https://openalex.org/W2994325518","https://openalex.org/W3156786336","https://openalex.org/W3163596720","https://openalex.org/W3206440620","https://openalex.org/W4308206564","https://openalex.org/W4385823077"],"related_works":[],"abstract_inverted_index":{"Phonetic":[0],"normalization":[1,53,91,144],"is":[2,31,41,67,132],"essential":[3],"in":[4,55,149,157],"speech":[5,57,80,150,159],"recognition":[6],"and":[7,108],"analysis,":[8],"ensuring":[9],"the":[10,20,46,114],"comparability":[11],"of":[12,23,116],"features":[13,78],"extracted":[14],"from":[15],"raw":[16],"audio":[17],"data.":[18],"In":[19,110],"current":[21],"paradigm":[22],"fine-tuning":[24,86],"pretrained":[25],"large":[26],"transformer":[27],"models,":[28,58,151],"however,":[29,113],"it":[30,40],"not":[32,133],"treated":[33],"as":[34,76,98,106],"a":[35,60,68],"necessary":[36],"preprocessing":[37],"step;":[38],"rather,":[39],"implicitly":[42],"carried":[43],"out":[44],"within":[45],"models":[47,118],"themselves.":[48],"This":[49],"study":[50],"examines":[51],"how":[52],"emerges":[54],"transformer-based":[56],"with":[59],"focus":[61],"on":[62],"Wav2vec2.0.":[63],"Understanding":[64],"this":[65],"process":[66],"crucial":[69],"step":[70],"toward":[71],"effectively":[72],"leveraging":[73],"model":[74],"embeddings":[75,115],"phonetic":[77,90,143],"for":[79,121,136],"analysis.":[81],"Our":[82],"results":[83,140],"show":[84],"that":[85,128,142],"Wav2vec2.0":[87],"can":[88,145],"achieve":[89],"by":[92],"selectively":[93],"suppressing":[94,129],"irrelevant":[95],"information,":[96,104],"such":[97,105],"speaker":[99],"sex,":[100],"while":[101],"enhancing":[102],"task-relevant":[103],"tones":[107],"finals.":[109],"multi-task":[111],"learning,":[112],"fine-tuned":[117],"retain":[119],"information":[120,131],"each":[122],"task":[123],"without":[124],"compromising":[125],"performance,":[126],"suggesting":[127],"task-irrelevant":[130],"strictly":[134],"required":[135],"effective":[137],"classification.":[138],"These":[139],"demonstrate":[141],"be":[146],"flexibly":[147],"achieved":[148],"providing":[152],"insights":[153],"into":[154],"potential":[155],"parallels":[156],"human":[158],"perception.":[160]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-11-28T00:00:00"}