{"id":"https://openalex.org/W4402112540","doi":"https://doi.org/10.21437/interspeech.2024-1330","title":"Dynamic Data Pruning for Automatic Speech Recognition","display_name":"Dynamic Data Pruning for Automatic Speech Recognition","publication_year":2024,"publication_date":"2024-09-01","ids":{"openalex":"https://openalex.org/W4402112540","doi":"https://doi.org/10.21437/interspeech.2024-1330"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2024-1330","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2024-1330","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2024","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://research.tue.nl/en/publications/7a3b87d7-6fa9-45d6-bb75-a49104eec34a","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Qiao Xiao","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Qiao Xiao","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101728918","display_name":"Pingchuan Ma","orcid":"https://orcid.org/0000-0001-7680-2817"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Pingchuan Ma","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5079540599","display_name":"Adriana Fernandez-Lopez","orcid":"https://orcid.org/0000-0001-8839-6537"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Adriana Fernandez-Lopez","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5111921306","display_name":"Boqian Wu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Boqian Wu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101707919","display_name":"Lu Yin","orcid":"https://orcid.org/0009-0008-3327-9788"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Lu Yin","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5009475700","display_name":"Stavros Petridis","orcid":"https://orcid.org/0000-0001-7478-9479"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Stavros Petridis","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5022601535","display_name":"Mykola Pechenizkiy","orcid":"https://orcid.org/0000-0003-4955-0743"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Mykola Pechenizkiy","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5016033078","display_name":"Maja Panti\u0107","orcid":"https://orcid.org/0000-0002-3620-5986"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Maja Pantic","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5011045254","display_name":"Decebal Constantin Mocanu","orcid":"https://orcid.org/0000-0002-5636-7683"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Decebal Constantin Mocanu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5100415810","display_name":"Shiwei Liu","orcid":"https://orcid.org/0000-0002-5389-1930"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Shiwei Liu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.3556,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":{"value":0.53756346,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"4488","last_page":"4492"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9437000155448914,"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":0.9437000155448914,"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/computer-science","display_name":"Computer science","score":0.8199490904808044},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6964079141616821},{"id":"https://openalex.org/keywords/pruning","display_name":"Pruning","score":0.6754964590072632},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5131007432937622},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.38635116815567017},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.36741191148757935}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8199490904808044},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6964079141616821},{"id":"https://openalex.org/C108010975","wikidata":"https://www.wikidata.org/wiki/Q500094","display_name":"Pruning","level":2,"score":0.6754964590072632},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5131007432937622},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.38635116815567017},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.36741191148757935},{"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}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.21437/interspeech.2024-1330","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2024-1330","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2024","raw_type":"proceedings-article"},{"id":"pmh:oai:pure.tue.nl:openaire/7a3b87d7-6fa9-45d6-bb75-a49104eec34a","is_oa":true,"landing_page_url":"https://research.tue.nl/en/publications/7a3b87d7-6fa9-45d6-bb75-a49104eec34a","pdf_url":null,"source":{"id":"https://openalex.org/S4406922641","display_name":"TU/e Research Portal","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Xiao, Q, Ma, P, Fernandez-Lopez, A, Wu, B, Yin, L, Petridis, S, Pechenizkiy, M, Pantic, M, Mocanu, D C & Liu, S 2024, Dynamic Data Pruning for Automatic Speech Recognition. in Interspeech 2024 : Kos, Greece 1-5 September 2024. ISCA, pp. 4488-4492, 25th Interspeech Conference, Interspeech 2024, Kos, Greece, 1/09/24. https://doi.org/10.21437/Interspeech.2024-1330","raw_type":"info:eu-repo/semantics/conferenceObject"},{"id":"pmh:oai:orbilu.uni.lu:10993/67610","is_oa":true,"landing_page_url":"https://orbilu.uni.lu/handle/10993/67610","pdf_url":null,"source":{"id":"https://openalex.org/S4306401815","display_name":"Open Repository and Bibliography (University of Luxembourg)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I186903577","host_organization_name":"University of Luxembourg","host_organization_lineage":["https://openalex.org/I186903577"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":"Proceedings of the Annual Conference of the International Speech Communication Association, INTERSPEECH, 4488 - 4492 (2024-09-01); Interspeech 2024, Kos Island, Greece [GR], 01-09-2024 => 05-09-2024","raw_type":"http://purl.org/coar/resource_type/c_5794"},{"id":"pmh:oai:pure.tue.nl:openaire_cris_publications/7a3b87d7-6fa9-45d6-bb75-a49104eec34a","is_oa":true,"landing_page_url":"https://research.tue.nl/files/349703686/xiao24b_interspeech.pdf","pdf_url":"https://pure.tue.nl/ws/files/349703686/xiao24b_interspeech.pdf","source":{"id":"https://openalex.org/S4406922641","display_name":"TU/e Research Portal","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Xiao, Q, Ma, P, Fernandez-Lopez, A, Wu, B, Yin, L, Petridis, S, Pechenizkiy, M, Pantic, M, Mocanu, D C & Liu, S 2024, Dynamic Data Pruning for Automatic Speech Recognition. in Interspeech 2024 : Kos, Greece 1-5 September 2024. ISCA, pp. 4488-4492, 25th Interspeech Conference, Interspeech 2024, Kos, Greece, 1/09/24. https://doi.org/10.21437/Interspeech.2024-1330","raw_type":"info:eu-repo/semantics/conferenceObject"}],"best_oa_location":{"id":"pmh:oai:pure.tue.nl:openaire/7a3b87d7-6fa9-45d6-bb75-a49104eec34a","is_oa":true,"landing_page_url":"https://research.tue.nl/en/publications/7a3b87d7-6fa9-45d6-bb75-a49104eec34a","pdf_url":null,"source":{"id":"https://openalex.org/S4406922641","display_name":"TU/e Research Portal","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Xiao, Q, Ma, P, Fernandez-Lopez, A, Wu, B, Yin, L, Petridis, S, Pechenizkiy, M, Pantic, M, Mocanu, D C & Liu, S 2024, Dynamic Data Pruning for Automatic Speech Recognition. in Interspeech 2024 : Kos, Greece 1-5 September 2024. ISCA, pp. 4488-4492, 25th Interspeech Conference, Interspeech 2024, Kos, Greece, 1/09/24. https://doi.org/10.21437/Interspeech.2024-1330","raw_type":"info:eu-repo/semantics/conferenceObject"},"sustainable_development_goals":[{"score":0.6000000238418579,"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16"}],"awards":[{"id":"https://openalex.org/G2803124007","display_name":"MEGAMIND \u2013 Measuring, Gathering, Mining and Integrating Data for Self-management in the Edge of the Electricity System","funder_award_id":"P19-25","funder_id":"https://openalex.org/F4320321800","funder_display_name":"Nederlandse Organisatie voor Wetenschappelijk Onderzoek"}],"funders":[{"id":"https://openalex.org/F4320321800","display_name":"Nederlandse Organisatie voor Wetenschappelijk Onderzoek","ror":"https://ror.org/04jsz6e67"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W2373300491","https://openalex.org/W2378744544","https://openalex.org/W2594301978","https://openalex.org/W2379704676","https://openalex.org/W1998810860","https://openalex.org/W4206442282","https://openalex.org/W2384505857","https://openalex.org/W2033914206","https://openalex.org/W2042327336","https://openalex.org/W3204019825"],"abstract_inverted_index":{"The":[0],"recent":[1],"success":[2],"of":[3,15,46,78,96,123],"Automatic":[4],"Speech":[5],"Recognition":[6],"(ASR)":[7],"is":[8],"largely":[9],"attributed":[10],"to":[11,37,64,136],"the":[12,75,89,120],"ever-growing":[13],"amount":[14],"training":[16,24,138],"data.":[17,97],"However,":[18],"this":[19,39,70,72],"trend":[20],"has":[21,34,53],"made":[22],"model":[23],"prohibitively":[25],"costly":[26],"and":[27,57],"imposed":[28],"computational":[29],"demands.":[30],"While":[31],"data":[32,80],"pruning":[33,81,111,122],"been":[35,54],"proposed":[36],"mitigate":[38],"issue":[40],"by":[41,92],"identifying":[42],"a":[43],"small":[44],"subset":[45],"relevant":[47],"data,":[48],"its":[49],"application":[50],"in":[51],"ASR":[52,105],"barely":[55],"explored,":[56],"existing":[58],"works":[59],"often":[60],"entail":[61],"significant":[62],"overhead":[63],"achieve":[65],"meaningful":[66],"results.":[67],"To":[68],"fill":[69],"gap,":[71],"paper":[73],"presents":[74],"first":[76],"investigation":[77],"dynamic":[79],"for":[82,104,115],"ASR,":[83],"finding":[84],"that":[85,131],"we":[86,99],"can":[87,133],"reach":[88],"full-data":[90],"performance":[91,142],"dynamically":[93],"selecting":[94],"70%":[95],"Furthermore,":[98],"introduce":[100],"Dynamic":[101],"Data":[102],"Pruning":[103],"(DDP-ASR),":[106],"which":[107],"offers":[108],"several":[109],"fine-grained":[110],"granularities":[112],"specifically":[113],"tailored":[114],"speech-related":[116],"datasets,":[117],"going":[118],"beyond":[119],"conventional":[121],"entire":[124],"time":[125,139],"sequences.":[126],"Our":[127],"intensive":[128],"experiments":[129],"show":[130],"DDP-ASR":[132],"save":[134],"up":[135],"1.6x":[137],"with":[140],"negligible":[141],"loss.":[143]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}