{"id":"https://openalex.org/W4415433019","doi":"https://doi.org/10.21437/interspeech.2025-1932","title":"Effective Context in Neural Speech Models","display_name":"Effective Context in Neural Speech Models","publication_year":2025,"publication_date":"2025-08-17","ids":{"openalex":"https://openalex.org/W4415433019","doi":"https://doi.org/10.21437/interspeech.2025-1932"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2025-1932","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2025-1932","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2025","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://www.research.ed.ac.uk/files/532318349/MengEtalInterspeech2025EffectiveContextinNeural.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5062573067","display_name":"Yen Meng","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yen Meng","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5075564798","display_name":"Sharon Goldwater","orcid":"https://orcid.org/0000-0002-7298-0947"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Sharon Goldwater","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5050748634","display_name":"Hao Tang","orcid":"https://orcid.org/0000-0002-2077-1246"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hao Tang","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":null,"has_fulltext":true,"cited_by_count":3,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"246","last_page":"250"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.7208999991416931,"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":0.7208999991416931,"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/context","display_name":"Context (archaeology)","score":0.694599986076355},{"id":"https://openalex.org/keywords/phone","display_name":"Phone","score":0.6517999768257141},{"id":"https://openalex.org/keywords/measure","display_name":"Measure (data warehouse)","score":0.5303000211715698},{"id":"https://openalex.org/keywords/context-model","display_name":"Context model","score":0.4765999913215637},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.4611000120639801},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.460099995136261}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7427999973297119},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.694599986076355},{"id":"https://openalex.org/C2778707766","wikidata":"https://www.wikidata.org/wiki/Q202064","display_name":"Phone","level":2,"score":0.6517999768257141},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5885999798774719},{"id":"https://openalex.org/C2780009758","wikidata":"https://www.wikidata.org/wiki/Q6804172","display_name":"Measure (data warehouse)","level":2,"score":0.5303000211715698},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5099999904632568},{"id":"https://openalex.org/C183322885","wikidata":"https://www.wikidata.org/wiki/Q17007702","display_name":"Context model","level":3,"score":0.4765999913215637},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.4611000120639801},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.460099995136261},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.36070001125335693},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3555999994277954},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.310699999332428},{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.2831999957561493},{"id":"https://openalex.org/C48677424","wikidata":"https://www.wikidata.org/wiki/Q6888088","display_name":"Mode (computer interface)","level":2,"score":0.2741999924182892},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.26919999718666077},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.2554999887943268}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.21437/interspeech.2025-1932","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2025-1932","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2025","raw_type":"proceedings-article"},{"id":"pmh:oai:pure.ed.ac.uk:openaire/67224a98-0fdd-490e-bc22-7b8c7de4ae06","is_oa":true,"landing_page_url":"https://www.research.ed.ac.uk/en/publications/67224a98-0fdd-490e-bc22-7b8c7de4ae06","pdf_url":"https://www.research.ed.ac.uk/files/532318349/MengEtalInterspeech2025EffectiveContextinNeural.pdf","source":{"id":"https://openalex.org/S4306400321","display_name":"Edinburgh Research Explorer (University of Edinburgh)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I98677209","host_organization_name":"University of Edinburgh","host_organization_lineage":["https://openalex.org/I98677209"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Meng, Y, Goldwater, S & Tang, H 2025, Effective context in neural speech models. in Interspeech 2025. Proceedings of the International Conference on Spoken Language Processing, pp. 246-250, 26th Edition of the Interspeech Conference, Rotterdam, Netherlands, 17/08/25. https://doi.org/10.21437/Interspeech.2025-1932","raw_type":"contributionToPeriodical"}],"best_oa_location":{"id":"pmh:oai:pure.ed.ac.uk:openaire/67224a98-0fdd-490e-bc22-7b8c7de4ae06","is_oa":true,"landing_page_url":"https://www.research.ed.ac.uk/en/publications/67224a98-0fdd-490e-bc22-7b8c7de4ae06","pdf_url":"https://www.research.ed.ac.uk/files/532318349/MengEtalInterspeech2025EffectiveContextinNeural.pdf","source":{"id":"https://openalex.org/S4306400321","display_name":"Edinburgh Research Explorer (University of Edinburgh)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I98677209","host_organization_name":"University of Edinburgh","host_organization_lineage":["https://openalex.org/I98677209"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Meng, Y, Goldwater, S & Tang, H 2025, Effective context in neural speech models. in Interspeech 2025. Proceedings of the International Conference on Spoken Language Processing, pp. 246-250, 26th Edition of the Interspeech Conference, Rotterdam, Netherlands, 17/08/25. https://doi.org/10.21437/Interspeech.2025-1932","raw_type":"contributionToPeriodical"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4415433019.pdf","grobid_xml":"https://content.openalex.org/works/W4415433019.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Modern":[0],"neural":[1],"speech":[2,57],"models":[3,34,117],"benefit":[4],"from":[5],"having":[6],"longer":[7],"context,":[8,50],"and":[9,51,82,105,141],"many":[10],"approaches":[11,45],"have":[12,26],"been":[13],"proposed":[14],"to":[15,28,46,54,109,138],"increase":[16],"the":[17,38,48,65,71,74,102,110,139],"maximum":[18],"context":[19,32,67,98,123],"a":[20,121],"model":[21],"can":[22,130],"use.":[23],"However,":[24],"few":[25],"attempted":[27],"measure":[29],"how":[30],"much":[31],"these":[33,116],"actually":[35],"use,":[36],"i.e.,":[37],"effective":[39,49,66,89,97],"context.":[40,90],"Here,":[41],"we":[42,62,94,126],"propose":[43],"two":[44],"measuring":[47],"use":[52,120],"them":[53],"analyze":[55],"different":[56],"Transformers.":[58],"For":[59,91],"supervised":[60,111],"models,":[61,93],"find":[63,95],"that":[64,96,115,128],"correlates":[68],"well":[69],"with":[70,76],"nature":[72],"of":[73,88],"task,":[75],"fundamental":[77],"frequency":[78],"tracking,":[79],"phone":[80,112],"classification,":[81],"word":[83],"classification":[84],"requiring":[85],"increasing":[86],"amounts":[87],"self-supervised":[92],"increases":[99],"mainly":[100],"in":[101,133],"early":[103],"layers,":[104],"remains":[106],"relatively":[107],"short---similar":[108],"model.":[113],"Given":[114],"do":[118],"not":[119],"long":[122],"during":[124],"prediction,":[125],"show":[127],"HuBERT":[129],"be":[131],"run":[132],"streaming":[134],"mode":[135],"without":[136,142],"modification":[137],"architecture":[140],"further":[143],"fine-tuning.<br/><br/>":[144]},"counts_by_year":[{"year":2026,"cited_by_count":3}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-24T00:00:00"}