{"id":"https://openalex.org/W4416799383","doi":"https://doi.org/10.1109/apsipaasc65261.2025.11249033","title":"Dimension 414 and Minimal Embedding Dimensions for Phonetic Feature Encoding in WavLM","display_name":"Dimension 414 and Minimal Embedding Dimensions for Phonetic Feature Encoding in WavLM","publication_year":2025,"publication_date":"2025-10-22","ids":{"openalex":"https://openalex.org/W4416799383","doi":"https://doi.org/10.1109/apsipaasc65261.2025.11249033"},"language":null,"primary_location":{"id":"doi:10.1109/apsipaasc65261.2025.11249033","is_oa":false,"landing_page_url":"https://doi.org/10.1109/apsipaasc65261.2025.11249033","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":"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/A5120670616","display_name":"Narthana Sivalingam","orcid":null},"institutions":[{"id":"https://openalex.org/I195740183","display_name":"University of Moratuwa","ror":"https://ror.org/0491f5305","country_code":"LK","type":"education","lineage":["https://openalex.org/I195740183"]}],"countries":["LK"],"is_corresponding":false,"raw_author_name":"Narthana Sivalingam","raw_affiliation_strings":["University of Moratuwa,Department of Computer Science and Engineering,Sri Lanka"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Moratuwa,Department of Computer Science and Engineering,Sri Lanka","institution_ids":["https://openalex.org/I195740183"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5049911731","display_name":"Uthayasanker Thayasivam","orcid":"https://orcid.org/0000-0002-3936-8174"},"institutions":[{"id":"https://openalex.org/I195740183","display_name":"University of Moratuwa","ror":"https://ror.org/0491f5305","country_code":"LK","type":"education","lineage":["https://openalex.org/I195740183"]}],"countries":["LK"],"is_corresponding":false,"raw_author_name":"Uthayasanker Thayasivam","raw_affiliation_strings":["University of Moratuwa,Department of Computer Science and Engineering,Sri Lanka"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Moratuwa,Department of Computer Science and Engineering,Sri Lanka","institution_ids":["https://openalex.org/I195740183"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I195740183"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.17295699,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"879","last_page":"884"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.819100022315979,"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":0.819100022315979,"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/T10403","display_name":"Phonetics and Phonology Research","score":0.08349999785423279,"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/T11448","display_name":"Face recognition and analysis","score":0.017000000923871994,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/embedding","display_name":"Embedding","score":0.8023999929428101},{"id":"https://openalex.org/keywords/dimension","display_name":"Dimension (graph theory)","score":0.6945000290870667},{"id":"https://openalex.org/keywords/nasality","display_name":"Nasality","score":0.593500018119812},{"id":"https://openalex.org/keywords/encode","display_name":"ENCODE","score":0.5464000105857849},{"id":"https://openalex.org/keywords/encoding","display_name":"Encoding (memory)","score":0.4643999934196472},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.42820000648498535},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.4043000042438507},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.4016999900341034}],"concepts":[{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.8023999929428101},{"id":"https://openalex.org/C33676613","wikidata":"https://www.wikidata.org/wiki/Q13415176","display_name":"Dimension (graph theory)","level":2,"score":0.6945000290870667},{"id":"https://openalex.org/C2780256294","wikidata":"https://www.wikidata.org/wiki/Q15946863","display_name":"Nasality","level":3,"score":0.593500018119812},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.555400013923645},{"id":"https://openalex.org/C66746571","wikidata":"https://www.wikidata.org/wiki/Q1134833","display_name":"ENCODE","level":3,"score":0.5464000105857849},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5432000160217285},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.4643999934196472},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.42820000648498535},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.4043000042438507},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.4016999900341034},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3950999975204468},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3758000135421753},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3553999960422516},{"id":"https://openalex.org/C137584468","wikidata":"https://www.wikidata.org/wiki/Q35395","display_name":"Phonetics","level":2,"score":0.3547999858856201},{"id":"https://openalex.org/C117220453","wikidata":"https://www.wikidata.org/wiki/Q5172842","display_name":"Correlation","level":2,"score":0.34439998865127563},{"id":"https://openalex.org/C70518039","wikidata":"https://www.wikidata.org/wiki/Q16000077","display_name":"Dimensionality reduction","level":2,"score":0.31200000643730164},{"id":"https://openalex.org/C30732413","wikidata":"https://www.wikidata.org/wiki/Q17092636","display_name":"Intrinsic dimension","level":3,"score":0.302700012922287},{"id":"https://openalex.org/C83665646","wikidata":"https://www.wikidata.org/wiki/Q42139305","display_name":"Feature vector","level":2,"score":0.2849000096321106},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.27799999713897705},{"id":"https://openalex.org/C3019722297","wikidata":"https://www.wikidata.org/wiki/Q4440864","display_name":"High dimensional","level":2,"score":0.2766000032424927},{"id":"https://openalex.org/C2779227376","wikidata":"https://www.wikidata.org/wiki/Q6505497","display_name":"Layer (electronics)","level":2,"score":0.27300000190734863},{"id":"https://openalex.org/C104267543","wikidata":"https://www.wikidata.org/wiki/Q208163","display_name":"Signal processing","level":3,"score":0.25380000472068787}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/apsipaasc65261.2025.11249033","is_oa":false,"landing_page_url":"https://doi.org/10.1109/apsipaasc65261.2025.11249033","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/W1996881001","https://openalex.org/W2027586365","https://openalex.org/W2097749765","https://openalex.org/W2239141610","https://openalex.org/W3173970713","https://openalex.org/W3209059054","https://openalex.org/W3209984917","https://openalex.org/W4226380987","https://openalex.org/W4281492411","https://openalex.org/W4294559022","https://openalex.org/W4299627282","https://openalex.org/W4385822832","https://openalex.org/W4389520189"],"related_works":[],"abstract_inverted_index":{"Self-supervised":[0],"speech":[1,7,104,129],"models":[2],"like":[3],"WavLM":[4,79,110],"have":[5],"advanced":[6],"processing":[8],"tasks,":[9],"but":[10],"the":[11,70],"role":[12],"of":[13,52],"individual":[14],"embedding":[15,53],"dimensions":[16,54],"from":[17],"each":[18],"transformer":[19],"layer":[20],"remains":[21],"unclear.":[22],"This":[23],"work":[24],"investigates":[25],"how":[26],"phonetic":[27,81,113],"features,":[28,76],"voicing,":[29],"fricative,":[30],"and":[31,75,85,119,127],"nasality":[32],"are":[33,56],"encoded":[34],"withinWavLM":[35],"representations":[36],"across":[37,73],"layers.":[38],"By":[39],"combining":[40],"Integrated":[41],"Gradients":[42],"with":[43,92,102],"a":[44,116],"hybrid":[45],"elbow-point":[46],"method,":[47],"we":[48],"identify":[49],"sparse":[50],"subsets":[51],"that":[55,78,97,109],"sufficient":[57],"to":[58],"retain":[59],"classification":[60],"performance.":[61],"Interestingly,":[62],"one":[63],"dimension":[64,100],"Dimension":[65],"414":[66],"consistently":[67],"emerges":[68],"as":[69],"most":[71],"influential":[72],"layers":[74],"suggesting":[77],"concentrates":[80],"information":[82],"into":[83],"compact":[84],"functionally":[86],"distinct":[87],"dimensions.":[88],"Supporting":[89],"correlation":[90],"analysis":[91],"handcrafted":[93],"acoustic":[94],"descriptors":[95],"reveals":[96],"this":[98],"dominant":[99],"aligns":[101],"interpretable":[103],"properties.":[105],"Our":[106],"findings":[107],"demonstrate":[108],"embeddings":[111],"encode":[112],"features":[114],"in":[115],"sparse,":[117],"structured,":[118],"explainable":[120],"manner,":[121],"offering":[122],"new":[123],"pathways":[124],"for":[125],"transparent":[126],"efficient":[128],"model":[130],"analysis.":[131]},"counts_by_year":[],"updated_date":"2026-06-26T08:34:08.712188","created_date":"2025-11-28T00:00:00"}