{"id":"https://openalex.org/W4402979396","doi":"https://doi.org/10.1109/icme57554.2024.10688073","title":"Efficient Speech-to-Text Translation: Progressive Pruning for Accelerated Speech Pre-trained Model","display_name":"Efficient Speech-to-Text Translation: Progressive Pruning for Accelerated Speech Pre-trained Model","publication_year":2024,"publication_date":"2024-07-15","ids":{"openalex":"https://openalex.org/W4402979396","doi":"https://doi.org/10.1109/icme57554.2024.10688073"},"language":"en","primary_location":{"id":"doi:10.1109/icme57554.2024.10688073","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/icme57554.2024.10688073","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE International Conference on Multimedia and Expo (ICME)","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/A5041092735","display_name":"Nan Chen","orcid":"https://orcid.org/0000-0002-2077-3284"},"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":"Nan Chen","raw_affiliation_strings":["Inner Mongolia University,College of Computer Science,Hohhot,China"],"affiliations":[{"raw_affiliation_string":"Inner Mongolia University,College of Computer Science,Hohhot,China","institution_ids":["https://openalex.org/I2722730"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5008226894","display_name":"Yonghe Wang","orcid":"https://orcid.org/0000-0003-1647-1539"},"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":"Yonghe Wang","raw_affiliation_strings":["Inner Mongolia University,College of Computer Science,Hohhot,China"],"affiliations":[{"raw_affiliation_string":"Inner Mongolia University,College of Computer Science,Hohhot,China","institution_ids":["https://openalex.org/I2722730"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5010464164","display_name":"Xiangdong Su","orcid":"https://orcid.org/0000-0001-8061-1474"},"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":"Xiangdong Su","raw_affiliation_strings":["Inner Mongolia University,College of Computer Science,Hohhot,China"],"affiliations":[{"raw_affiliation_string":"Inner Mongolia University,College of Computer Science,Hohhot,China","institution_ids":["https://openalex.org/I2722730"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5014372166","display_name":"Feilong Bao","orcid":"https://orcid.org/0000-0001-7312-1629"},"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":["Inner Mongolia University,College of Computer Science,Hohhot,China"],"affiliations":[{"raw_affiliation_string":"Inner Mongolia University,College of Computer Science,Hohhot,China","institution_ids":["https://openalex.org/I2722730"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5041092735"],"corresponding_institution_ids":["https://openalex.org/I2722730"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.14118457,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"6"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9977999925613403,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9977999925613403,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9965999722480774,"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/T10028","display_name":"Topic Modeling","score":0.982699990272522,"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/speech-translation","display_name":"Speech translation","score":0.7426024079322815},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7358502149581909},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6778968572616577},{"id":"https://openalex.org/keywords/pruning","display_name":"Pruning","score":0.5592030882835388},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5441736578941345},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5398892760276794},{"id":"https://openalex.org/keywords/translation","display_name":"Translation (biology)","score":0.5109416842460632},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.46456044912338257},{"id":"https://openalex.org/keywords/machine-translation","display_name":"Machine translation","score":0.4448028802871704}],"concepts":[{"id":"https://openalex.org/C2780366754","wikidata":"https://www.wikidata.org/wiki/Q7494857","display_name":"Speech translation","level":3,"score":0.7426024079322815},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7358502149581909},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6778968572616577},{"id":"https://openalex.org/C108010975","wikidata":"https://www.wikidata.org/wiki/Q500094","display_name":"Pruning","level":2,"score":0.5592030882835388},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5441736578941345},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5398892760276794},{"id":"https://openalex.org/C149364088","wikidata":"https://www.wikidata.org/wiki/Q185917","display_name":"Translation (biology)","level":4,"score":0.5109416842460632},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.46456044912338257},{"id":"https://openalex.org/C203005215","wikidata":"https://www.wikidata.org/wiki/Q79798","display_name":"Machine translation","level":2,"score":0.4448028802871704},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C6557445","wikidata":"https://www.wikidata.org/wiki/Q173113","display_name":"Agronomy","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C105580179","wikidata":"https://www.wikidata.org/wiki/Q188928","display_name":"Messenger RNA","level":3,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icme57554.2024.10688073","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/icme57554.2024.10688073","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE International Conference on Multimedia and Expo (ICME)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320322216","display_name":"Inner Mongolia University","ror":"https://ror.org/0106qb496"},{"id":"https://openalex.org/F4320337504","display_name":"Research and Development","ror":"https://ror.org/027s68j25"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W3011059803","https://openalex.org/W2373300491","https://openalex.org/W4301342010","https://openalex.org/W2378744544","https://openalex.org/W2883671469","https://openalex.org/W2728761353","https://openalex.org/W2338806053","https://openalex.org/W4385571610","https://openalex.org/W2293738010","https://openalex.org/W4360995948"],"abstract_inverted_index":{"Recently,":[0],"speech":[1,22,34,108,140],"pre-trained":[2,23,109,141],"models":[3,24],"based":[4],"on":[5],"the":[6,31,38,47,103,107],"Transformer":[7],"architecture":[8],"have":[9],"become":[10],"very":[11],"popular":[12],"for":[13,46,77],"speech-to-text":[14],"translation":[15],"tasks.":[16],"However,":[17],"computing":[18],"representation":[19,63],"outputs":[20],"of":[21,33,106],"is":[25,132],"highly":[26],"time-consuming,":[27],"primarily":[28],"due":[29],"to":[30,42,73,90,126,138],"length":[32,65],"sequences":[35],"far":[36],"exceeding":[37],"corresponding":[39],"texts,":[40],"leading":[41],"quadratic":[43],"computation":[44],"costs":[45],"self-attention":[48],"module.":[49],"To":[50],"address":[51],"this":[52],"issue,":[53],"we":[54,81],"propose":[55],"a":[56,115],"novel":[57],"pruning":[58,87],"method":[59,130],"that":[60,99],"progressively":[61],"reduces":[62,102],"sequence":[64],"layer":[66],"by":[67,111],"layer.":[68],"We":[69,143],"leverage":[70],"attention":[71],"scores":[72,76],"calculate":[74],"importance":[75],"all":[78],"tokens.":[79],"Additionally,":[80],"introduce":[82],"both":[83],"fixed":[84],"and":[85,119,135],"scheduled":[86],"rate":[88],"strategies":[89],"determine":[91],"which":[92],"tokens":[93,105],"should":[94],"be":[95],"retained.":[96],"Experiments":[97],"demonstrate":[98],"our":[100,145],"approach":[101],"output":[104],"model":[110],"55%,":[112],"with":[113],"only":[114],"0.7%":[116],"performance":[117],"decrease,":[118],"improves":[120],"in":[121],"practice":[122],"encoding":[123],"speed":[124],"up":[125],"1.76":[127],"\u00d7.":[128],"Our":[129],"also":[131],"an":[133],"orthogonal":[134],"complementary":[136],"direction":[137],"efficient":[139],"models.":[142],"release":[144],"code":[146],"at":[147],"https://github.com/myaxxxxx/pruning.":[148]},"counts_by_year":[],"updated_date":"2025-12-27T23:08:20.325037","created_date":"2025-10-10T00:00:00"}