{"id":"https://openalex.org/W7155056250","doi":"https://doi.org/10.1109/ncc68160.2026.11478864","title":"Autoencoder Based Optimized SSL Representations: Complexity Minimization and Improved Dysarthric ASR","display_name":"Autoencoder Based Optimized SSL Representations: Complexity Minimization and Improved Dysarthric ASR","publication_year":2026,"publication_date":"2026-02-26","ids":{"openalex":"https://openalex.org/W7155056250","doi":"https://doi.org/10.1109/ncc68160.2026.11478864"},"language":null,"primary_location":{"id":"doi:10.1109/ncc68160.2026.11478864","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ncc68160.2026.11478864","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2026 National Conference on Communications (NCC)","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/A5106638699","display_name":"Paban Sapkota","orcid":null},"institutions":[{"id":"https://openalex.org/I101326570","display_name":"National Institute of Technology Sikkim","ror":"https://ror.org/04pam3b03","country_code":"IN","type":"education","lineage":["https://openalex.org/I101326570"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Paban Sapkota","raw_affiliation_strings":["National Institute of Technology Sikkim,Department of Electronics and Communication Engineering,India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Institute of Technology Sikkim,Department of Electronics and Communication Engineering,India","institution_ids":["https://openalex.org/I101326570"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5003438160","display_name":"Hemant Kumar Kathania","orcid":"https://orcid.org/0000-0002-6367-5203"},"institutions":[{"id":"https://openalex.org/I101326570","display_name":"National Institute of Technology Sikkim","ror":"https://ror.org/04pam3b03","country_code":"IN","type":"education","lineage":["https://openalex.org/I101326570"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Hemant Kumar Kathania","raw_affiliation_strings":["National Institute of Technology Sikkim,Department of Electronics and Communication Engineering,India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Institute of Technology Sikkim,Department of Electronics and Communication Engineering,India","institution_ids":["https://openalex.org/I101326570"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5043424064","display_name":"Mikko Kurimo","orcid":"https://orcid.org/0000-0001-5278-7974"},"institutions":[{"id":"https://openalex.org/I9927081","display_name":"Aalto University","ror":"https://ror.org/020hwjq30","country_code":"FI","type":"education","lineage":["https://openalex.org/I9927081"]}],"countries":["FI"],"is_corresponding":false,"raw_author_name":"Mikko Kurimo","raw_affiliation_strings":["Aalto University,Department of Information and Communications Engineering,Finland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Aalto University,Department of Information and Communications Engineering,Finland","institution_ids":["https://openalex.org/I9927081"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5134151362","display_name":"Shrikanth Narayanan","orcid":null},"institutions":[{"id":"https://openalex.org/I1174212","display_name":"University of Southern California","ror":"https://ror.org/03taz7m60","country_code":"US","type":"education","lineage":["https://openalex.org/I1174212"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Shrikanth Narayanan","raw_affiliation_strings":["University of Southern California,Signal Analysis and Interpretation Laboratory (SAIL),Los Angeles,USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Southern California,Signal Analysis and Interpretation Laboratory (SAIL),Los Angeles,USA","institution_ids":["https://openalex.org/I1174212"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5080870546","display_name":"Sudarsana Reddy Kadiri","orcid":"https://orcid.org/0000-0001-5806-3053"},"institutions":[{"id":"https://openalex.org/I1174212","display_name":"University of Southern California","ror":"https://ror.org/03taz7m60","country_code":"US","type":"education","lineage":["https://openalex.org/I1174212"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Sudarsana Reddy Kadiri","raw_affiliation_strings":["University of Southern California,Signal Analysis and Interpretation Laboratory (SAIL),Los Angeles,USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Southern California,Signal Analysis and Interpretation Laboratory (SAIL),Los Angeles,USA","institution_ids":["https://openalex.org/I1174212"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.4670418,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"590","last_page":"595"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10863","display_name":"Voice and Speech Disorders","score":0.776199996471405,"subfield":{"id":"https://openalex.org/subfields/2737","display_name":"Physiology"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}},"topics":[{"id":"https://openalex.org/T10863","display_name":"Voice and Speech Disorders","score":0.776199996471405,"subfield":{"id":"https://openalex.org/subfields/2737","display_name":"Physiology"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}},{"id":"https://openalex.org/T12419","display_name":"Phonocardiography and Auscultation Techniques","score":0.07429999858140945,"subfield":{"id":"https://openalex.org/subfields/2740","display_name":"Pulmonary and Respiratory Medicine"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}},{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.03539999946951866,"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/autoencoder","display_name":"Autoencoder","score":0.6654000282287598},{"id":"https://openalex.org/keywords/minification","display_name":"Minification","score":0.5507000088691711},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.423799991607666},{"id":"https://openalex.org/keywords/computational-complexity-theory","display_name":"Computational complexity theory","score":0.3181999921798706},{"id":"https://openalex.org/keywords/frame","display_name":"Frame (networking)","score":0.3133000135421753}],"concepts":[{"id":"https://openalex.org/C101738243","wikidata":"https://www.wikidata.org/wiki/Q786435","display_name":"Autoencoder","level":3,"score":0.6654000282287598},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6175000071525574},{"id":"https://openalex.org/C147764199","wikidata":"https://www.wikidata.org/wiki/Q6865248","display_name":"Minification","level":2,"score":0.5507000088691711},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5447999835014343},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4731999933719635},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.423799991607666},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3276999890804291},{"id":"https://openalex.org/C179799912","wikidata":"https://www.wikidata.org/wiki/Q205084","display_name":"Computational complexity theory","level":2,"score":0.3181999921798706},{"id":"https://openalex.org/C126042441","wikidata":"https://www.wikidata.org/wiki/Q1324888","display_name":"Frame (networking)","level":2,"score":0.3133000135421753},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.2874999940395355},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.28519999980926514},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.25440001487731934}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/ncc68160.2026.11478864","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ncc68160.2026.11478864","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2026 National Conference on Communications (NCC)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":22,"referenced_works":["https://openalex.org/W1631260214","https://openalex.org/W1988536708","https://openalex.org/W2045644151","https://openalex.org/W2749128330","https://openalex.org/W2936861580","https://openalex.org/W2938757327","https://openalex.org/W3015210890","https://openalex.org/W3015611303","https://openalex.org/W3094861110","https://openalex.org/W3163599377","https://openalex.org/W3209059054","https://openalex.org/W4224315877","https://openalex.org/W4297030419","https://openalex.org/W4297841798","https://openalex.org/W4323315382","https://openalex.org/W4386025707","https://openalex.org/W4387672817","https://openalex.org/W4392909075","https://openalex.org/W4401752236","https://openalex.org/W4409156476","https://openalex.org/W4409156561","https://openalex.org/W4410342580"],"related_works":[],"abstract_inverted_index":{"Self-supervised":[0],"learning":[1],"(SSL)":[2],"models":[3],"extract":[4],"rich":[5],"speech":[6,61],"representations":[7],"but":[8],"often":[9],"come":[10],"with":[11],"high-dimensional":[12,44],"features,":[13],"increasing":[14],"computational":[15,72],"complexity.":[16],"This":[17],"work":[18],"explores":[19],"an":[20,40,98],"SSL-AutoEncoder":[21],"(SSL-AE)":[22],"bottlenecking":[23,77],"approach":[24],"to":[25,83],"efficiently":[26],"reduce":[27],"feature":[28,103],"dimensions":[29],"while":[30,69],"maintaining":[31],"dysarthric":[32],"Automatic":[33],"Speech":[34],"Recognition":[35],"(ASR)":[36],"performance.":[37,92],"By":[38],"leveraging":[39],"autoencoder,":[41],"we":[42],"transform":[43],"SSL":[45,85,102],"features":[46],"into":[47],"a":[48],"compact":[49],"space,":[50],"reducing":[51],"model":[52],"complexity":[53],"and":[54],"training":[55,79],"time.":[56],"Our":[57],"method":[58],"preserves":[59],"essential":[60],"information,":[62],"achieving":[63],"reduced":[64],"Word":[65],"Error":[66],"Rates":[67],"(WER)":[68],"significantly":[70],"lowering":[71],"costs.":[73],"Experiments":[74],"show":[75],"SSL-AE":[76],"reduces":[78],"time":[80],"by$8":[81],"\\times$compared":[82],"the":[84],"baseline,":[86],"demonstrating":[87],"efficiency":[88],"without":[89],"sacrificing":[90],"recognition":[91],"These":[93],"results":[94],"highlight":[95],"AE":[96],"as":[97],"effective":[99],"solution":[100],"for":[101],"compression":[104],"in":[105],"resource-constrained":[106],"environments.":[107]},"counts_by_year":[],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2026-04-22T00:00:00"}