{"id":"https://openalex.org/W4412945669","doi":"https://doi.org/10.18653/v1/2025.acl-long.388","title":"Distilling an End-to-End Voice Assistant Without Instruction Training Data","display_name":"Distilling an End-to-End Voice Assistant Without Instruction Training Data","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4412945669","doi":"https://doi.org/10.18653/v1/2025.acl-long.388"},"language":"en","primary_location":{"id":"doi:10.18653/v1/2025.acl-long.388","doi":"https://doi.org/10.18653/v1/2025.acl-long.388","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.acl-long.388","pdf_url":"https://aclanthology.org/2025.acl-long.388.pdf","source":{"id":"https://openalex.org/S4393915740","display_name":"Proceedings of the conference - Association for Computational Linguistics. Meeting","issn_l":"0736-587X","issn":["0736-587X"],"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":["norway-1"],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":"public-domain","license_id":"https://openalex.org/licenses/public-domain","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"},"volume":null,"type":"conference-paper","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://aclanthology.org/2025.acl-long.388.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"William Held","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I12912129","display_name":"Northeastern University","ror":"https://ror.org/04t5xt781","country_code":"US","type":"education","lineage":["https://openalex.org/I12912129"]},{"id":"https://openalex.org/I130701444","display_name":"Georgia Institute of Technology","ror":"https://ror.org/01zkghx44","country_code":"US","type":"education","lineage":["https://openalex.org/I130701444"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"William Held","raw_affiliation_strings":["Georgia Institute of Technology , \u03f5 Northeastern University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Georgia Institute of Technology , \u03f5 Northeastern University","institution_ids":["https://openalex.org/I12912129","https://openalex.org/I130701444"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5034912720","display_name":"Yanzhe Zhang","orcid":"https://orcid.org/0009-0001-6253-4273","observed_orcids":["https://orcid.org/0009-0001-6253-4273"]},"institutions":[{"id":"https://openalex.org/I12912129","display_name":"Northeastern University","ror":"https://ror.org/04t5xt781","country_code":"US","type":"education","lineage":["https://openalex.org/I12912129"]},{"id":"https://openalex.org/I130701444","display_name":"Georgia Institute of Technology","ror":"https://ror.org/01zkghx44","country_code":"US","type":"education","lineage":["https://openalex.org/I130701444"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yanzhe Zhang","raw_affiliation_strings":["Georgia Institute of Technology , \u03f5 Northeastern University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Georgia Institute of Technology , \u03f5 Northeastern University","institution_ids":["https://openalex.org/I12912129","https://openalex.org/I130701444"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5022683477","display_name":"Minzhi Li","orcid":"https://orcid.org/0000-0002-1013-8930","observed_orcids":["https://orcid.org/0000-0002-1013-8930"]},"institutions":[{"id":"https://openalex.org/I165932596","display_name":"National University of Singapore","ror":"https://ror.org/01tgyzw49","country_code":"SG","type":"education","lineage":["https://openalex.org/I165932596"]},{"id":"https://openalex.org/I97018004","display_name":"Stanford University","ror":"https://ror.org/00f54p054","country_code":"US","type":"education","lineage":["https://openalex.org/I97018004"]}],"countries":["SG","US"],"is_corresponding":false,"raw_author_name":"Minzhi Li","raw_affiliation_strings":["National University of Singapore , \u03c3 Stanford University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National University of Singapore , \u03c3 Stanford University","institution_ids":["https://openalex.org/I165932596","https://openalex.org/I97018004"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Weiyan Shi","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I12912129","display_name":"Northeastern University","ror":"https://ror.org/04t5xt781","country_code":"US","type":"education","lineage":["https://openalex.org/I12912129"]},{"id":"https://openalex.org/I130701444","display_name":"Georgia Institute of Technology","ror":"https://ror.org/01zkghx44","country_code":"US","type":"education","lineage":["https://openalex.org/I130701444"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Weiyan Shi","raw_affiliation_strings":["Georgia Institute of Technology , \u03f5 Northeastern University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Georgia Institute of Technology , \u03f5 Northeastern University","institution_ids":["https://openalex.org/I12912129","https://openalex.org/I130701444"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5059760181","display_name":"Michael J. Ryan","orcid":"https://orcid.org/0000-0002-6335-3773","observed_orcids":["https://orcid.org/0000-0002-6335-3773","https://orcid.org/0000-0002-6381-9545"]},"institutions":[{"id":"https://openalex.org/I12912129","display_name":"Northeastern University","ror":"https://ror.org/04t5xt781","country_code":"US","type":"education","lineage":["https://openalex.org/I12912129"]},{"id":"https://openalex.org/I130701444","display_name":"Georgia Institute of Technology","ror":"https://ror.org/01zkghx44","country_code":"US","type":"education","lineage":["https://openalex.org/I130701444"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Michael J Ryan","raw_affiliation_strings":["Georgia Institute of Technology , \u03f5 Northeastern University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Georgia Institute of Technology , \u03f5 Northeastern University","institution_ids":["https://openalex.org/I12912129","https://openalex.org/I130701444"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5089413311","display_name":"Diyi Yang","orcid":"https://orcid.org/0000-0003-1220-3983","observed_orcids":["https://orcid.org/0000-0003-1220-3983"]},"institutions":[{"id":"https://openalex.org/I12912129","display_name":"Northeastern University","ror":"https://ror.org/04t5xt781","country_code":"US","type":"education","lineage":["https://openalex.org/I12912129"]},{"id":"https://openalex.org/I130701444","display_name":"Georgia Institute of Technology","ror":"https://ror.org/01zkghx44","country_code":"US","type":"education","lineage":["https://openalex.org/I130701444"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Diyi Yang","raw_affiliation_strings":["Georgia Institute of Technology , \u03f5 Northeastern University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Georgia Institute of Technology , \u03f5 Northeastern University","institution_ids":["https://openalex.org/I12912129","https://openalex.org/I130701444"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":5.6978,"has_fulltext":true,"cited_by_count":6,"citation_normalized_percentile":{"value":0.96560965,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":96,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"7876","last_page":"7891"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.7860999703407288,"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":0.7860999703407288,"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/T12031","display_name":"Speech and dialogue systems","score":0.14810000360012054,"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/T10036","display_name":"Advanced Neural Network Applications","score":0.027699999511241913,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/voice-assistants","display_name":"voice assistants","score":0.6309999823570251},{"id":"https://openalex.org/keywords/end-to-end-speech-recognition","display_name":"end-to-end speech recognition","score":0.7269999980926514},{"id":"https://openalex.org/keywords/knowledge-distillation","display_name":"knowledge distillation","score":0.746999979019165},{"id":"https://openalex.org/keywords/low-resource-training-data","display_name":"low-resource training data","score":0.45899999141693115}],"concepts":[{"id":"https://openalex.org/C74296488","wikidata":"https://www.wikidata.org/wiki/Q2527392","display_name":"End-to-end principle","level":2,"score":0.8986750841140747},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.750947117805481},{"id":"https://openalex.org/C2777211547","wikidata":"https://www.wikidata.org/wiki/Q17141490","display_name":"Training (meteorology)","level":2,"score":0.60225510597229},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.46040260791778564},{"id":"https://openalex.org/C91262260","wikidata":"https://www.wikidata.org/wiki/Q528074","display_name":"End user","level":2,"score":0.4593283534049988},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2603801190853119},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.15741175413131714},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C153294291","wikidata":"https://www.wikidata.org/wiki/Q25261","display_name":"Meteorology","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.18653/v1/2025.acl-long.388","doi":"https://doi.org/10.18653/v1/2025.acl-long.388","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.acl-long.388","pdf_url":"https://aclanthology.org/2025.acl-long.388.pdf","source":{"id":"https://openalex.org/S4393915740","display_name":"Proceedings of the conference - Association for Computational Linguistics. Meeting","issn_l":"0736-587X","issn":["0736-587X"],"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":["norway-1"],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":"public-domain","license_id":"https://openalex.org/licenses/public-domain","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2410.02678","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2410.02678","pdf_url":"https://arxiv.org/pdf/2410.02678","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"public-domain","license_id":"https://openalex.org/licenses/public-domain","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2410.02678","doi":"https://doi.org/10.48550/arxiv.2410.02678","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2410.02678","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"doi:10.18653/v1/2025.acl-long.388","doi":"https://doi.org/10.18653/v1/2025.acl-long.388","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.acl-long.388","pdf_url":"https://aclanthology.org/2025.acl-long.388.pdf","source":{"id":"https://openalex.org/S4393915740","display_name":"Proceedings of the conference - Association for Computational Linguistics. Meeting","issn_l":"0736-587X","issn":["0736-587X"],"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":["norway-1"],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":"public-domain","license_id":"https://openalex.org/licenses/public-domain","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"},"sustainable_development_goals":[],"sustainable_development_goals_aurora":[],"study_designs":[],"awards":[{"id":"https://openalex.org/G2749129067","display_name":"CAREER: Socially-Aware Language Technologies To Support People in Supporting Others for Better Online Communities","funder_award_id":"2247357","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320337345","display_name":"Office of Naval Research","ror":"https://ror.org/00rk2pe57"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4412945669.pdf","grobid_xml":"https://content.openalex.org/works/W4412945669.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4417115565","https://openalex.org/W7123605778","https://openalex.org/W4415433242","https://openalex.org/W4412888284","https://openalex.org/W4388684946","https://openalex.org/W7134847634","https://openalex.org/W4408354168","https://openalex.org/W4386876109","https://openalex.org/W7220894988","https://openalex.org/W4412944935"],"abstract_inverted_index":{"Voice":[0,83],"assistants,":[1],"such":[2],"as":[3,69],"Siri":[4],"and":[5,11,19,92],"Google":[6],"Assistant,":[7],"typically":[8],"model":[9],"audio":[10],"text":[12],"separately,":[13],"resulting":[14],"in":[15],"lost":[16],"speech":[17],"information":[18],"increased":[20],"complexity.Recent":[21],"efforts":[22],"to":[23,41,67,87],"address":[24],"this":[25,71],"with":[26,35,105],"end-to-end":[27],"Speech":[28,55],"Large":[29],"Language":[30],"Models":[31],"(speech-in,":[32],"text-out)":[33],"trained":[34],"supervised":[36],"finetuning":[37],"(SFT)":[38],"have":[39],"led":[40],"models":[42,107],"\"forgetting\"":[43],"capabilities":[44],"from":[45],"text-only":[46,65],"LLMs.Our":[47],"work":[48],"proposes":[49],"an":[50],"alternative":[51],"paradigm":[52],"for":[53],"training":[54,116],"LLMs":[56],"without":[57,76],"instruction":[58],"data,":[59],"using":[60,113],"the":[61],"response":[62],"of":[63],"a":[64,100],"LLM":[66],"transcripts":[68],"self-supervision.Importantly,":[70],"process":[72],"can":[73],"be":[74],"performed":[75],"annotated":[77],"responses.We":[78],"show":[79],"that":[80],"our":[81],"Distilled":[82],"Assistant":[84],"(DiVA)":[85],"generalizes":[86],"Spoken":[88],"Question":[89],"Answering,":[90],"Classification,":[91],"Translation.Furthermore,":[93],"DiVA":[94],"better":[95],"matches":[96],"user":[97],"preferences,":[98],"achieving":[99],"72%":[101],"win":[102],"rate":[103],"compared":[104],"state-of-the-art":[106],"like":[108],"Qwen":[109],"2":[110],"Audio,":[111],"despite":[112],">100x":[114],"less":[115],"compute.":[117]},"counts_by_year":[{"year":2026,"cited_by_count":3},{"year":2025,"cited_by_count":3}],"updated_date":"2026-10-29T09:56:32.521200","created_date":"2025-10-10T00:00:00"}
