{"id":"https://openalex.org/W4415709749","doi":"https://doi.org/10.1109/icme59968.2025.11209113","title":"SpeechPrune: Context-Aware Token Pruning for Speech Information Retrieval","display_name":"SpeechPrune: Context-Aware Token Pruning for Speech Information Retrieval","publication_year":2025,"publication_date":"2025-06-30","ids":{"openalex":"https://openalex.org/W4415709749","doi":"https://doi.org/10.1109/icme59968.2025.11209113"},"language":null,"primary_location":{"id":"doi:10.1109/icme59968.2025.11209113","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icme59968.2025.11209113","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 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/A5100768194","display_name":"Yueqian Lin","orcid":"https://orcid.org/0000-0003-1473-8981"},"institutions":[{"id":"https://openalex.org/I170897317","display_name":"Duke University","ror":"https://ror.org/00py81415","country_code":"US","type":"education","lineage":["https://openalex.org/I170897317"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Yueqian Lin","raw_affiliation_strings":["Duke University,Durham,USA"],"affiliations":[{"raw_affiliation_string":"Duke University,Durham,USA","institution_ids":["https://openalex.org/I170897317"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5055491561","display_name":"Yuzhe Fu","orcid":"https://orcid.org/0000-0002-1381-0278"},"institutions":[{"id":"https://openalex.org/I170897317","display_name":"Duke University","ror":"https://ror.org/00py81415","country_code":"US","type":"education","lineage":["https://openalex.org/I170897317"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yuzhe Fu","raw_affiliation_strings":["Duke University,Durham,USA"],"affiliations":[{"raw_affiliation_string":"Duke University,Durham,USA","institution_ids":["https://openalex.org/I170897317"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5063092287","display_name":"Jingyang Zhang","orcid":"https://orcid.org/0000-0002-1788-6501"},"institutions":[{"id":"https://openalex.org/I170897317","display_name":"Duke University","ror":"https://ror.org/00py81415","country_code":"US","type":"education","lineage":["https://openalex.org/I170897317"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jingyang Zhang","raw_affiliation_strings":["Duke University,Durham,USA"],"affiliations":[{"raw_affiliation_string":"Duke University,Durham,USA","institution_ids":["https://openalex.org/I170897317"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5079115940","display_name":"Yudong Liu","orcid":"https://orcid.org/0000-0002-5153-3400"},"institutions":[{"id":"https://openalex.org/I170897317","display_name":"Duke University","ror":"https://ror.org/00py81415","country_code":"US","type":"education","lineage":["https://openalex.org/I170897317"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yudong Liu","raw_affiliation_strings":["Duke University,Durham,USA"],"affiliations":[{"raw_affiliation_string":"Duke University,Durham,USA","institution_ids":["https://openalex.org/I170897317"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101609539","display_name":"Jianyi Zhang","orcid":"https://orcid.org/0000-0001-8765-053X"},"institutions":[{"id":"https://openalex.org/I170897317","display_name":"Duke University","ror":"https://ror.org/00py81415","country_code":"US","type":"education","lineage":["https://openalex.org/I170897317"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jianyi Zhang","raw_affiliation_strings":["Duke University,Durham,USA"],"affiliations":[{"raw_affiliation_string":"Duke University,Durham,USA","institution_ids":["https://openalex.org/I170897317"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5024963902","display_name":"Jingwei Sun","orcid":"https://orcid.org/0000-0001-8358-9487"},"institutions":[{"id":"https://openalex.org/I170897317","display_name":"Duke University","ror":"https://ror.org/00py81415","country_code":"US","type":"education","lineage":["https://openalex.org/I170897317"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jingwei Sun","raw_affiliation_strings":["Duke University,Durham,USA"],"affiliations":[{"raw_affiliation_string":"Duke University,Durham,USA","institution_ids":["https://openalex.org/I170897317"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100429403","display_name":"Hai Li","orcid":"https://orcid.org/0000-0003-3228-6544"},"institutions":[{"id":"https://openalex.org/I170897317","display_name":"Duke University","ror":"https://ror.org/00py81415","country_code":"US","type":"education","lineage":["https://openalex.org/I170897317"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Hai Helen Li","raw_affiliation_strings":["Duke University,Durham,USA"],"affiliations":[{"raw_affiliation_string":"Duke University,Durham,USA","institution_ids":["https://openalex.org/I170897317"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5102868511","display_name":"Yiran Chen","orcid":"https://orcid.org/0009-0004-4668-4505"},"institutions":[{"id":"https://openalex.org/I170897317","display_name":"Duke University","ror":"https://ror.org/00py81415","country_code":"US","type":"education","lineage":["https://openalex.org/I170897317"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yiran Chen","raw_affiliation_strings":["Duke University,Durham,USA"],"affiliations":[{"raw_affiliation_string":"Duke University,Durham,USA","institution_ids":["https://openalex.org/I170897317"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":8,"corresponding_author_ids":["https://openalex.org/A5100768194"],"corresponding_institution_ids":["https://openalex.org/I170897317"],"apc_list":null,"apc_paid":null,"fwci":2.4121,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.91795839,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":91,"max":95},"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.8787000179290771,"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":0.8787000179290771,"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":0.04439999908208847,"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"}},{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.01209999993443489,"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/pruning","display_name":"Pruning","score":0.8091999888420105},{"id":"https://openalex.org/keywords/security-token","display_name":"Security token","score":0.6710000038146973},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.5795000195503235},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.5698999762535095},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.5544999837875366},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.525600016117096},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.46369999647140503},{"id":"https://openalex.org/keywords/question-answering","display_name":"Question answering","score":0.42340001463890076}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8158000111579895},{"id":"https://openalex.org/C108010975","wikidata":"https://www.wikidata.org/wiki/Q500094","display_name":"Pruning","level":2,"score":0.8091999888420105},{"id":"https://openalex.org/C48145219","wikidata":"https://www.wikidata.org/wiki/Q1335365","display_name":"Security token","level":2,"score":0.6710000038146973},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6331999897956848},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.5795000195503235},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.5698999762535095},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.5544999837875366},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5404000282287598},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.525600016117096},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.46369999647140503},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.436599999666214},{"id":"https://openalex.org/C44291984","wikidata":"https://www.wikidata.org/wiki/Q1074173","display_name":"Question answering","level":2,"score":0.42340001463890076},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.39649999141693115},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3946000039577484},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.3481000065803528},{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.33889999985694885},{"id":"https://openalex.org/C13895895","wikidata":"https://www.wikidata.org/wiki/Q3270773","display_name":"Speech coding","level":2,"score":0.3057999908924103},{"id":"https://openalex.org/C31170391","wikidata":"https://www.wikidata.org/wiki/Q188619","display_name":"Hierarchy","level":2,"score":0.30559998750686646},{"id":"https://openalex.org/C2776230583","wikidata":"https://www.wikidata.org/wiki/Q1322198","display_name":"Spoken language","level":2,"score":0.30140000581741333},{"id":"https://openalex.org/C45273575","wikidata":"https://www.wikidata.org/wiki/Q578970","display_name":"Spectrogram","level":2,"score":0.2865000069141388},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.27489998936653137}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icme59968.2025.11209113","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icme59968.2025.11209113","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE International Conference on Multimedia and Expo (ICME)","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":10,"referenced_works":["https://openalex.org/W2056486423","https://openalex.org/W2912904516","https://openalex.org/W2972359262","https://openalex.org/W3180037928","https://openalex.org/W4225956675","https://openalex.org/W4389524500","https://openalex.org/W4402672034","https://openalex.org/W4404781855","https://openalex.org/W4411119642","https://openalex.org/W4412945669"],"related_works":[],"abstract_inverted_index":{"While":[0],"current":[1],"Speech":[2,34,42],"Large":[3],"Language":[4],"Models":[5],"(Speech":[6],"LLMs)":[7],"excel":[8],"at":[9,112,125],"short-form":[10],"tasks,":[11],"they":[12],"struggle":[13],"with":[14,29],"the":[15,26,63,104,108,133],"computational":[16],"and":[17,44,82,99,107,140],"representational":[18],"demands":[19],"of":[20,65,97,116,129,135],"longer":[21],"audio":[22],"clips.":[23],"To":[24,61],"advance":[25],"model\u2019s":[27],"capabilities":[28],"long-form":[30,142],"speech,":[31],"we":[32,70],"introduce":[33],"Information":[35],"Retrieval":[36],"(SIR),":[37],"a":[38,47,73,113,126],"long-context":[39],"task":[40],"for":[41,138],"LLMs,":[43],"present":[45],"SPIRAL,":[46,92],"1,012-sample":[48],"benchmark":[49],"testing":[50],"models\u2019":[51],"ability":[52],"to":[53,86,101],"extract":[54],"critical":[55],"details":[56],"from":[57],"long":[58,67],"spoken":[59],"inputs.":[60],"overcome":[62],"challenges":[64],"processing":[66],"speech":[68,143],"sequences,":[69],"propose":[71],"SpeechPrune,":[72],"training-free":[74],"token":[75],"pruning":[76,110,114,127,137],"strategy":[77],"that":[78],"uses":[79],"speech-text":[80],"similarity":[81],"approximated":[83],"attention":[84],"scores":[85],"efficiently":[87],"discard":[88],"irrelevant":[89],"tokens.":[90],"In":[91],"SpeechPrune":[93,119],"achieves":[94],"accuracy":[95],"improvements":[96],"29%":[98],"up":[100],"47%":[102],"over":[103],"original":[105],"model":[106,111],"random":[109],"rate":[115],"20%,":[117],"respectively.":[118],"can":[120],"maintain":[121],"network":[122],"performance":[123],"even":[124],"level":[128],"80%.":[130],"This":[131],"highlights":[132],"potential":[134],"token-level":[136],"efficient":[139],"scalable":[141],"understanding.":[144]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-04-03T22:45:19.894376","created_date":"2025-10-30T00:00:00"}