{"id":"https://openalex.org/W7106329963","doi":"https://doi.org/10.1007/978-981-95-3343-5_18","title":"Exploring Representation-Efficient Transfer Learning Approaches for\u00a0Speech Recognition and\u00a0Translation Using Pre-trained Speech Models","display_name":"Exploring Representation-Efficient Transfer Learning Approaches for\u00a0Speech Recognition and\u00a0Translation Using Pre-trained Speech Models","publication_year":2025,"publication_date":"2025-11-22","ids":{"openalex":"https://openalex.org/W7106329963","doi":"https://doi.org/10.1007/978-981-95-3343-5_18"},"language":"en","primary_location":{"id":"doi:10.1007/978-981-95-3343-5_18","is_oa":false,"landing_page_url":"https://doi.org/10.1007/978-981-95-3343-5_18","pdf_url":null,"source":{"id":"https://openalex.org/S106296714","display_name":"Lecture notes in computer science","issn_l":"0302-9743","issn":["0302-9743","1611-3349"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"book series"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Lecture Notes in Computer Science","raw_type":"book-chapter"},"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":null,"display_name":"Wenhao Wang","orcid":null},"institutions":[{"id":"https://openalex.org/I2722730","display_name":"Inner Mongolia University","ror":"https://ror.org/0106qb496","country_code":"CN","type":"education","lineage":["https://openalex.org/I2722730"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wenhao Wang","raw_affiliation_strings":["College of Computer Science, Inner Mongolia University, Hohhot, China","Inner Mongolia Key Laboratory of Multilingual Artificial Intelligence Technology, Hohhot, China","National and Local Joint Engineering Research Center of Intelligent Information Processing Technology for Mongolian, Hohhot, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"College of Computer Science, Inner Mongolia University, Hohhot, China","institution_ids":["https://openalex.org/I2722730"]},{"raw_affiliation_string":"Inner Mongolia Key Laboratory of Multilingual Artificial Intelligence Technology, Hohhot, China","institution_ids":[]},{"raw_affiliation_string":"National and Local Joint Engineering Research Center of Intelligent Information Processing Technology for Mongolian, Hohhot, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":null,"display_name":"Yonghe Wang","orcid":null},"institutions":[{"id":"https://openalex.org/I2722730","display_name":"Inner Mongolia University","ror":"https://ror.org/0106qb496","country_code":"CN","type":"education","lineage":["https://openalex.org/I2722730"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Yonghe Wang","raw_affiliation_strings":["College of Computer Science, Inner Mongolia University, Hohhot, China","Inner Mongolia Key Laboratory of Multilingual Artificial Intelligence Technology, Hohhot, China","National and Local Joint Engineering Research Center of Intelligent Information Processing Technology for Mongolian, Hohhot, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"College of Computer Science, Inner Mongolia University, Hohhot, China","institution_ids":["https://openalex.org/I2722730"]},{"raw_affiliation_string":"Inner Mongolia Key Laboratory of Multilingual Artificial Intelligence Technology, Hohhot, China","institution_ids":[]},{"raw_affiliation_string":"National and Local Joint Engineering Research Center of Intelligent Information Processing Technology for Mongolian, Hohhot, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":null,"display_name":"Nan Chen","orcid":null},"institutions":[{"id":"https://openalex.org/I2722730","display_name":"Inner Mongolia University","ror":"https://ror.org/0106qb496","country_code":"CN","type":"education","lineage":["https://openalex.org/I2722730"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Nan Chen","raw_affiliation_strings":["College of Computer Science, Inner Mongolia University, Hohhot, China","Inner Mongolia Key Laboratory of Multilingual Artificial Intelligence Technology, Hohhot, China","National and Local Joint Engineering Research Center of Intelligent Information Processing Technology for Mongolian, Hohhot, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"College of Computer Science, Inner Mongolia University, Hohhot, China","institution_ids":["https://openalex.org/I2722730"]},{"raw_affiliation_string":"Inner Mongolia Key Laboratory of Multilingual Artificial Intelligence Technology, Hohhot, China","institution_ids":[]},{"raw_affiliation_string":"National and Local Joint Engineering Research Center of Intelligent Information Processing Technology for Mongolian, Hohhot, China","institution_ids":[]}]},{"author_position":"last","author":{"id":null,"display_name":"Feilong Bao","orcid":null},"institutions":[{"id":"https://openalex.org/I2722730","display_name":"Inner Mongolia University","ror":"https://ror.org/0106qb496","country_code":"CN","type":"education","lineage":["https://openalex.org/I2722730"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Feilong Bao","raw_affiliation_strings":["College of Computer Science, Inner Mongolia University, Hohhot, China","Inner Mongolia Key Laboratory of Multilingual Artificial Intelligence Technology, Hohhot, China","National and Local Joint Engineering Research Center of Intelligent Information Processing Technology for Mongolian, Hohhot, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"College of Computer Science, Inner Mongolia University, Hohhot, China","institution_ids":["https://openalex.org/I2722730"]},{"raw_affiliation_string":"Inner Mongolia Key Laboratory of Multilingual Artificial Intelligence Technology, Hohhot, China","institution_ids":[]},{"raw_affiliation_string":"National and Local Joint Engineering Research Center of Intelligent Information Processing Technology for Mongolian, Hohhot, China","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I2722730"],"apc_list":{"value":5000,"currency":"EUR","value_usd":5392},"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":"225","last_page":"237"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.7764000296592712,"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":0.7764000296592712,"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":0.04520000144839287,"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":0.030400000512599945,"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/speech-translation","display_name":"Speech translation","score":0.6177999973297119},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.6136000156402588},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5679000020027161},{"id":"https://openalex.org/keywords/transfer-of-learning","display_name":"Transfer of learning","score":0.5453000068664551},{"id":"https://openalex.org/keywords/translation","display_name":"Translation (biology)","score":0.532800018787384},{"id":"https://openalex.org/keywords/machine-translation","display_name":"Machine translation","score":0.506600022315979},{"id":"https://openalex.org/keywords/voice-activity-detection","display_name":"Voice activity detection","score":0.4812999963760376},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.46470001339912415},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.45350000262260437}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.9171000123023987},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6636999845504761},{"id":"https://openalex.org/C2780366754","wikidata":"https://www.wikidata.org/wiki/Q7494857","display_name":"Speech translation","level":3,"score":0.6177999973297119},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.6136000156402588},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5679000020027161},{"id":"https://openalex.org/C150899416","wikidata":"https://www.wikidata.org/wiki/Q1820378","display_name":"Transfer of learning","level":2,"score":0.5453000068664551},{"id":"https://openalex.org/C149364088","wikidata":"https://www.wikidata.org/wiki/Q185917","display_name":"Translation (biology)","level":4,"score":0.532800018787384},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5151000022888184},{"id":"https://openalex.org/C203005215","wikidata":"https://www.wikidata.org/wiki/Q79798","display_name":"Machine translation","level":2,"score":0.506600022315979},{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.4812999963760376},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4691999852657318},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.46470001339912415},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.45350000262260437},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.43700000643730164},{"id":"https://openalex.org/C2776175482","wikidata":"https://www.wikidata.org/wiki/Q1195816","display_name":"Transfer (computing)","level":2,"score":0.3767000138759613},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.3327000141143799},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.31779998540878296},{"id":"https://openalex.org/C13895895","wikidata":"https://www.wikidata.org/wiki/Q3270773","display_name":"Speech coding","level":2,"score":0.3050000071525574},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.29679998755455017},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.29030001163482666},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.28299999237060547},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.27059999108314514},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.2662000060081482},{"id":"https://openalex.org/C2779757391","wikidata":"https://www.wikidata.org/wiki/Q6002292","display_name":"Image translation","level":3,"score":0.265500009059906},{"id":"https://openalex.org/C504749915","wikidata":"https://www.wikidata.org/wiki/Q9010971","display_name":"Speech technology","level":3,"score":0.260699987411499},{"id":"https://openalex.org/C155635449","wikidata":"https://www.wikidata.org/wiki/Q4674699","display_name":"Acoustic model","level":3,"score":0.2590000033378601}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1007/978-981-95-3343-5_18","is_oa":false,"landing_page_url":"https://doi.org/10.1007/978-981-95-3343-5_18","pdf_url":null,"source":{"id":"https://openalex.org/S106296714","display_name":"Lecture notes in computer science","issn_l":"0302-9743","issn":["0302-9743","1611-3349"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"book series"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Lecture Notes in Computer Science","raw_type":"book-chapter"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":17,"referenced_works":["https://openalex.org/W2963341956","https://openalex.org/W3119308075","https://openalex.org/W3209059054","https://openalex.org/W4296070387","https://openalex.org/W4319862635","https://openalex.org/W4392902886","https://openalex.org/W4392903650","https://openalex.org/W4392904112","https://openalex.org/W4392909818","https://openalex.org/W4393147971","https://openalex.org/W4402112402","https://openalex.org/W4402727885","https://openalex.org/W4402753927","https://openalex.org/W4404783482","https://openalex.org/W4406857473","https://openalex.org/W4407613039","https://openalex.org/W4408352487"],"related_works":[],"abstract_inverted_index":null,"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-11-23T00:00:00"}
