{"id":"https://openalex.org/W2936706905","doi":"https://doi.org/10.1109/icassp.2019.8682224","title":"Windowed Attention Mechanisms for Speech Recognition","display_name":"Windowed Attention Mechanisms for Speech Recognition","publication_year":2019,"publication_date":"2019-04-17","ids":{"openalex":"https://openalex.org/W2936706905","doi":"https://doi.org/10.1109/icassp.2019.8682224","mag":"2936706905"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2019.8682224","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2019.8682224","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2019 - 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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/en/publications/2b10ed5c-7440-4e1e-a7aa-0d7b34be1638","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5003030422","display_name":"Shucong Zhang","orcid":null},"institutions":[{"id":"https://openalex.org/I98677209","display_name":"University of Edinburgh","ror":"https://ror.org/01nrxwf90","country_code":"GB","type":"education","lineage":["https://openalex.org/I98677209"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Shucong Zhang","raw_affiliation_strings":["Centre for Speech Technology Research, University of Edinburgh, Edinburgh, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Centre for Speech Technology Research, University of Edinburgh, Edinburgh, UK","institution_ids":["https://openalex.org/I98677209"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5042184515","display_name":"Erfan Loweimi","orcid":"https://orcid.org/0000-0002-8761-021X"},"institutions":[{"id":"https://openalex.org/I98677209","display_name":"University of Edinburgh","ror":"https://ror.org/01nrxwf90","country_code":"GB","type":"education","lineage":["https://openalex.org/I98677209"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Erfan Loweimi","raw_affiliation_strings":["Centre for Speech Technology Research, University of Edinburgh, Edinburgh, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Centre for Speech Technology Research, University of Edinburgh, Edinburgh, UK","institution_ids":["https://openalex.org/I98677209"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102911387","display_name":"Peter Bell","orcid":"https://orcid.org/0000-0002-9597-9615"},"institutions":[{"id":"https://openalex.org/I98677209","display_name":"University of Edinburgh","ror":"https://ror.org/01nrxwf90","country_code":"GB","type":"education","lineage":["https://openalex.org/I98677209"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Peter Bell","raw_affiliation_strings":["Centre for Speech Technology Research, University of Edinburgh, Edinburgh, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Centre for Speech Technology Research, University of Edinburgh, Edinburgh, UK","institution_ids":["https://openalex.org/I98677209"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5027442277","display_name":"Steve Renals","orcid":"https://orcid.org/0000-0002-8790-3389"},"institutions":[{"id":"https://openalex.org/I98677209","display_name":"University of Edinburgh","ror":"https://ror.org/01nrxwf90","country_code":"GB","type":"education","lineage":["https://openalex.org/I98677209"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Steve Renals","raw_affiliation_strings":["Centre for Speech Technology Research, University of Edinburgh, Edinburgh, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Centre for Speech Technology Research, University of Edinburgh, Edinburgh, UK","institution_ids":["https://openalex.org/I98677209"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I98677209"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":23,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"7100","last_page":"7104"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9998999834060669,"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":0.9998999834060669,"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/T11309","display_name":"Music and Audio Processing","score":0.9995999932289124,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9984999895095825,"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":0.7879207134246826},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6259692311286926},{"id":"https://openalex.org/keywords/timit","display_name":"TIMIT","score":0.6156927347183228},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.582223117351532},{"id":"https://openalex.org/keywords/window","display_name":"Window (computing)","score":0.5744653940200806},{"id":"https://openalex.org/keywords/joint","display_name":"Joint (building)","score":0.5023722648620605},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.45199328660964966},{"id":"https://openalex.org/keywords/mechanism","display_name":"Mechanism (biology)","score":0.4406328499317169},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.35204559564590454},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.2359764277935028}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7879207134246826},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6259692311286926},{"id":"https://openalex.org/C2778724510","wikidata":"https://www.wikidata.org/wiki/Q7670405","display_name":"TIMIT","level":3,"score":0.6156927347183228},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.582223117351532},{"id":"https://openalex.org/C2778751112","wikidata":"https://www.wikidata.org/wiki/Q835016","display_name":"Window (computing)","level":2,"score":0.5744653940200806},{"id":"https://openalex.org/C18555067","wikidata":"https://www.wikidata.org/wiki/Q8375051","display_name":"Joint (building)","level":2,"score":0.5023722648620605},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.45199328660964966},{"id":"https://openalex.org/C89611455","wikidata":"https://www.wikidata.org/wiki/Q6804646","display_name":"Mechanism (biology)","level":2,"score":0.4406328499317169},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.35204559564590454},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.2359764277935028},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.0},{"id":"https://openalex.org/C170154142","wikidata":"https://www.wikidata.org/wiki/Q150737","display_name":"Architectural engineering","level":1,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1109/icassp.2019.8682224","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2019.8682224","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2019 - 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},{"id":"pmh:oai:pure.ed.ac.uk:openaire/2b10ed5c-7440-4e1e-a7aa-0d7b34be1638","is_oa":true,"landing_page_url":"https://www.research.ed.ac.uk/en/publications/2b10ed5c-7440-4e1e-a7aa-0d7b34be1638","pdf_url":null,"source":{"id":"https://openalex.org/S4406922455","display_name":"Edinburgh Research Explorer","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":"Zhang, S, Loweimi, E, Bell, P & Renals, S 2019, Windowed Attention Mechanisms for Speech Recognition. in ICASSP 2019 - 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). Institute of Electrical and Electronics Engineers, Brighton, United Kingdom, pp. 7100-7104, 44th International Conference on Acoustics, Speech, and Signal Processing, Brighton , United Kingdom, 12/05/19. https://doi.org/10.1109/ICASSP.2019.8682224","raw_type":"contributionToPeriodical"},{"id":"pmh:oai:pure.ed.ac.uk:publications/2b10ed5c-7440-4e1e-a7aa-0d7b34be1638","is_oa":false,"landing_page_url":"https://ieeexplore.ieee.org/document/8682224","pdf_url":null,"source":{"id":"https://openalex.org/S4406922455","display_name":"Edinburgh Research Explorer","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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":""},{"id":"pmh:oai:repository@napier.ac.uk:3585909","is_oa":false,"landing_page_url":"http://researchrepository.napier.ac.uk/Output/3585909","pdf_url":null,"source":{"id":"https://openalex.org/S4306402591","display_name":"Edinburgh Napier Research Repository (Edinburgh Napier University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I251738","host_organization_name":"Edinburgh Napier University","host_organization_lineage":["https://openalex.org/I251738"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Presentation / Conference Contribution"}],"best_oa_location":{"id":"pmh:oai:pure.ed.ac.uk:openaire/2b10ed5c-7440-4e1e-a7aa-0d7b34be1638","is_oa":true,"landing_page_url":"https://www.research.ed.ac.uk/en/publications/2b10ed5c-7440-4e1e-a7aa-0d7b34be1638","pdf_url":null,"source":{"id":"https://openalex.org/S4406922455","display_name":"Edinburgh Research Explorer","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":"Zhang, S, Loweimi, E, Bell, P & Renals, S 2019, Windowed Attention Mechanisms for Speech Recognition. in ICASSP 2019 - 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). Institute of Electrical and Electronics Engineers, Brighton, United Kingdom, pp. 7100-7104, 44th International Conference on Acoustics, Speech, and Signal Processing, Brighton , United Kingdom, 12/05/19. https://doi.org/10.1109/ICASSP.2019.8682224","raw_type":"contributionToPeriodical"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/1","score":0.5400000214576721,"display_name":"No poverty"}],"awards":[{"id":"https://openalex.org/G3297227137","display_name":null,"funder_award_id":"EP/R012180/1","funder_id":"https://openalex.org/F4320334627","funder_display_name":"Engineering and Physical Sciences Research Council"}],"funders":[{"id":"https://openalex.org/F4320334627","display_name":"Engineering and Physical Sciences Research Council","ror":"https://ror.org/0439y7842"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":32,"referenced_works":["https://openalex.org/W6908809","https://openalex.org/W854541894","https://openalex.org/W1514535095","https://openalex.org/W1524333225","https://openalex.org/W1635512741","https://openalex.org/W1855892484","https://openalex.org/W1902237438","https://openalex.org/W2125496931","https://openalex.org/W2133564696","https://openalex.org/W2178654303","https://openalex.org/W2519091744","https://openalex.org/W2526425061","https://openalex.org/W2577366047","https://openalex.org/W2627092829","https://openalex.org/W2749514303","https://openalex.org/W2750499125","https://openalex.org/W2767601419","https://openalex.org/W2799800213","https://openalex.org/W2949382160","https://openalex.org/W2962742956","https://openalex.org/W2962780374","https://openalex.org/W2962826786","https://openalex.org/W2964308564","https://openalex.org/W6600284362","https://openalex.org/W6623517193","https://openalex.org/W6630875275","https://openalex.org/W6631362777","https://openalex.org/W6639156005","https://openalex.org/W6679434410","https://openalex.org/W6685711979","https://openalex.org/W6745543685","https://openalex.org/W6746345256"],"related_works":["https://openalex.org/W2071828724","https://openalex.org/W1994694193","https://openalex.org/W170831052","https://openalex.org/W4247725880","https://openalex.org/W1006721676","https://openalex.org/W2100854157","https://openalex.org/W1771058801","https://openalex.org/W2978471304","https://openalex.org/W4285346358","https://openalex.org/W14769199"],"abstract_inverted_index":{"The":[0,49],"usual":[1],"attention":[2,27,31,42,70,86,124],"mechanisms":[3,28],"used":[4],"for":[5],"encoder-decoder":[6],"models":[7],"do":[8],"not":[9],"constrain":[10],"the":[11,57,77,81,90,94,102,108,122,133,138],"relationship":[12],"between":[13],"input":[14],"and":[15,71],"output":[16],"sequences":[17],"to":[18,32,43,89,132],"be":[19],"monotonic.":[20],"To":[21],"address":[22],"this":[23,63,111],"we":[24,65],"explore":[25],"windowed":[26,69],"which":[29,79],"restrict":[30],"a":[33,44,67,73,116],"block":[34],"of":[35,51,83],"source":[36],"hidden":[37],"states.":[38],"Rule-based":[39],"windowing":[40],"restricts":[41],"(typically":[45],"large)":[46],"fixed-length":[47],"window.":[48],"performance":[50,82,104,119],"such":[52,84],"methods":[53],"is":[54,60,98,105],"poor":[55],"if":[56],"window":[58,92,96],"size":[59,97],"small.":[61],"In":[62],"paper,":[64],"propose":[66],"fully-trainable":[68],"provide":[72],"detailed":[74],"analysis":[75],"on":[76,137],"factors":[78],"affect":[80],"an":[85],"mechanism.":[87],"Compared":[88],"rule-based":[91],"methods,":[93],"learned":[95],"significantly":[99],"smaller":[100],"yet":[101],"model's":[103],"competitive.":[106],"On":[107],"TIMIT":[109],"corpus":[110],"approach":[112],"has":[113],"resulted":[114],"in":[115],"17%":[117],"(relative)":[118],"improvement":[120],"over":[121],"traditional":[123],"model.":[125],"Our":[126],"model":[127,136],"also":[128],"yields":[129],"comparable":[130],"accuracies":[131],"joint":[134],"CTC-attention":[135],"Wall":[139],"Street":[140],"Journal":[141],"corpus.":[142]},"counts_by_year":[{"year":2023,"cited_by_count":4},{"year":2022,"cited_by_count":4},{"year":2021,"cited_by_count":7},{"year":2020,"cited_by_count":4},{"year":2019,"cited_by_count":4}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}