{"id":"https://openalex.org/W7126455409","doi":"https://doi.org/10.18653/v1/2024.findings-eacl.23","title":"Towards efficient self-supervised representation learning in speech processing","display_name":"Towards efficient self-supervised representation learning in speech processing","publication_year":2024,"publication_date":"2024-01-01","ids":{"openalex":"https://openalex.org/W7126455409","doi":"https://doi.org/10.18653/v1/2024.findings-eacl.23"},"language":null,"primary_location":{"id":"doi:10.18653/v1/2024.findings-eacl.23","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2024.findings-eacl.23","pdf_url":"https://aclanthology.org/2024.findings-eacl.23.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Findings of the Association for Computational Linguistics: EACL 2024","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/2024.findings-eacl.23.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5031248134","display_name":"Luis Lugo","orcid":null},"institutions":[{"id":"https://openalex.org/I19370010","display_name":"Orange (France)","ror":"https://ror.org/035j0tq82","country_code":"FR","type":"company","lineage":["https://openalex.org/I19370010"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Luis Lugo","raw_affiliation_strings":["Orange , Cesson-Svign , France Orange , Cesson-Svign , France"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Orange , Cesson-Svign , France Orange , Cesson-Svign , France","institution_ids":["https://openalex.org/I19370010"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5124547919","display_name":"Valentin Vielzeuf","orcid":null},"institutions":[{"id":"https://openalex.org/I19370010","display_name":"Orange (France)","ror":"https://ror.org/035j0tq82","country_code":"FR","type":"company","lineage":["https://openalex.org/I19370010"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Valentin Vielzeuf","raw_affiliation_strings":["Orange , Cesson-Svign , France Orange , Cesson-Svign , France"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Orange , Cesson-Svign , France Orange , Cesson-Svign , France","institution_ids":["https://openalex.org/I19370010"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I19370010"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.57020585,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"340","last_page":"346"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.5601999759674072,"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":0.5601999759674072,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.03869999945163727,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.028599999845027924,"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/representation","display_name":"Representation (politics)","score":0.4708000123500824},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.4047999978065491},{"id":"https://openalex.org/keywords/signal-processing","display_name":"Signal processing","score":0.35760000348091125},{"id":"https://openalex.org/keywords/feature-learning","display_name":"Feature learning","score":0.34049999713897705},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.31150001287460327}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6933000087738037},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5248000025749207},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5123000144958496},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.478300005197525},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.4708000123500824},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.4047999978065491},{"id":"https://openalex.org/C104267543","wikidata":"https://www.wikidata.org/wiki/Q208163","display_name":"Signal processing","level":3,"score":0.35760000348091125},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.34049999713897705},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.31150001287460327},{"id":"https://openalex.org/C504749915","wikidata":"https://www.wikidata.org/wiki/Q9010971","display_name":"Speech technology","level":3,"score":0.2824999988079071},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.26919999718666077}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2024.findings-eacl.23","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2024.findings-eacl.23","pdf_url":"https://aclanthology.org/2024.findings-eacl.23.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Findings of the Association for Computational Linguistics: EACL 2024","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/2024.findings-eacl.23","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2024.findings-eacl.23","pdf_url":"https://aclanthology.org/2024.findings-eacl.23.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Findings of the Association for Computational Linguistics: EACL 2024","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7126455409.pdf","grobid_xml":"https://content.openalex.org/works/W7126455409.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Self-supervised":[0],"learning":[1],"has":[2],"achieved":[3],"impressive":[4],"results":[5],"in":[6,87],"speech":[7,92],"processing,":[8],"but":[9],"current":[10],"models":[11],"are":[12],"computationally":[13],"expensive,":[14],"generating":[15],"environmental":[16],"concerns":[17],"because":[18],"of":[19,44,84],"their":[20],"high":[21,32],"energy":[22],"consumption.Therefore,":[23],"we":[24],"propose":[25],"an":[26],"efficient":[27],"self-supervised":[28],"approach":[29,47],"to":[30,41,81],"address":[31],"computational":[33,88],"costs,":[34],"using":[35],"a":[36],"single":[37],"GPU":[38],"during":[39],"24":[40],"48":[42],"hours":[43],"pretraining.The":[45],"proposed":[46,77],"combines":[48],"linear,":[49],"convolutional,":[50],"and":[51,66],"self-attention":[52],"layers":[53],"with":[54,70],"several":[55],"optimizations,":[56],"including":[57],"dynamic":[58],"batching,":[59],"flash":[60],"attention,":[61],"mixed-precision":[62],"training,":[63],"gradient":[64],"accumulation,":[65],"acoustic":[67],"feature":[68],"extraction":[69],"input":[71],"preprocessing.Computational":[72],"cost":[73],"estimations":[74],"for":[75],"our":[76],"model":[78],"represent":[79],"up":[80],"two":[82],"orders":[83],"magnitude":[85],"improvements":[86],"efficiency":[89],"against":[90],"existing":[91],"models.":[93]},"counts_by_year":[],"updated_date":"2026-06-26T08:34:08.712188","created_date":"2026-02-02T00:00:00"}