{"id":"https://openalex.org/W4319862683","doi":"https://doi.org/10.1109/slt54892.2023.10022818","title":"Monotonic Segmental Attention for Automatic Speech Recognition","display_name":"Monotonic Segmental Attention for Automatic Speech Recognition","publication_year":2023,"publication_date":"2023-01-09","ids":{"openalex":"https://openalex.org/W4319862683","doi":"https://doi.org/10.1109/slt54892.2023.10022818"},"language":"en","primary_location":{"id":"doi:10.1109/slt54892.2023.10022818","is_oa":false,"landing_page_url":"https://doi.org/10.1109/slt54892.2023.10022818","pdf_url":null,"source":{"id":"https://openalex.org/S4363605953","display_name":"2022 IEEE Spoken Language Technology Workshop (SLT)","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":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 IEEE Spoken Language Technology Workshop (SLT)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5059521407","display_name":"Albert Zeyer","orcid":"https://orcid.org/0000-0002-6655-671X"},"institutions":[{"id":"https://openalex.org/I887968799","display_name":"RWTH Aachen University","ror":"https://ror.org/04xfq0f34","country_code":"DE","type":"education","lineage":["https://openalex.org/I887968799"]},{"id":"https://openalex.org/I99977706","display_name":"FH Aachen","ror":"https://ror.org/04tqgg260","country_code":"DE","type":"education","lineage":["https://openalex.org/I99977706"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Albert Zeyer","raw_affiliation_strings":["RWTH Aachen University,Human Language Technology and Pattern Recognition,Computer Science Department,Aachen,Germany,52062","AppTek GmbH, Aachen, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"RWTH Aachen University,Human Language Technology and Pattern Recognition,Computer Science Department,Aachen,Germany,52062","institution_ids":["https://openalex.org/I887968799"]},{"raw_affiliation_string":"AppTek GmbH, Aachen, Germany","institution_ids":["https://openalex.org/I99977706"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5032650967","display_name":"Robin Schmitt","orcid":null},"institutions":[{"id":"https://openalex.org/I887968799","display_name":"RWTH Aachen University","ror":"https://ror.org/04xfq0f34","country_code":"DE","type":"education","lineage":["https://openalex.org/I887968799"]},{"id":"https://openalex.org/I99977706","display_name":"FH Aachen","ror":"https://ror.org/04tqgg260","country_code":"DE","type":"education","lineage":["https://openalex.org/I99977706"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Robin Schmitt","raw_affiliation_strings":["RWTH Aachen University,Human Language Technology and Pattern Recognition,Computer Science Department,Aachen,Germany,52062","AppTek GmbH, Aachen, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"RWTH Aachen University,Human Language Technology and Pattern Recognition,Computer Science Department,Aachen,Germany,52062","institution_ids":["https://openalex.org/I887968799"]},{"raw_affiliation_string":"AppTek GmbH, Aachen, Germany","institution_ids":["https://openalex.org/I99977706"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100636970","display_name":"Wei Zhou","orcid":"https://orcid.org/0009-0006-3754-8872"},"institutions":[{"id":"https://openalex.org/I887968799","display_name":"RWTH Aachen University","ror":"https://ror.org/04xfq0f34","country_code":"DE","type":"education","lineage":["https://openalex.org/I887968799"]},{"id":"https://openalex.org/I99977706","display_name":"FH Aachen","ror":"https://ror.org/04tqgg260","country_code":"DE","type":"education","lineage":["https://openalex.org/I99977706"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Wei Zhou","raw_affiliation_strings":["RWTH Aachen University,Human Language Technology and Pattern Recognition,Computer Science Department,Aachen,Germany,52062","AppTek GmbH, Aachen, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"RWTH Aachen University,Human Language Technology and Pattern Recognition,Computer Science Department,Aachen,Germany,52062","institution_ids":["https://openalex.org/I887968799"]},{"raw_affiliation_string":"AppTek GmbH, Aachen, Germany","institution_ids":["https://openalex.org/I99977706"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5088968292","display_name":"Ralf Schl\u00fcter","orcid":"https://orcid.org/0000-0003-2839-9247"},"institutions":[{"id":"https://openalex.org/I887968799","display_name":"RWTH Aachen University","ror":"https://ror.org/04xfq0f34","country_code":"DE","type":"education","lineage":["https://openalex.org/I887968799"]},{"id":"https://openalex.org/I99977706","display_name":"FH Aachen","ror":"https://ror.org/04tqgg260","country_code":"DE","type":"education","lineage":["https://openalex.org/I99977706"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Ralf Schluter","raw_affiliation_strings":["RWTH Aachen University,Human Language Technology and Pattern Recognition,Computer Science Department,Aachen,Germany,52062","AppTek GmbH, Aachen, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"RWTH Aachen University,Human Language Technology and Pattern Recognition,Computer Science Department,Aachen,Germany,52062","institution_ids":["https://openalex.org/I887968799"]},{"raw_affiliation_string":"AppTek GmbH, Aachen, Germany","institution_ids":["https://openalex.org/I99977706"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5112501010","display_name":"Hermann Ney","orcid":null},"institutions":[{"id":"https://openalex.org/I887968799","display_name":"RWTH Aachen University","ror":"https://ror.org/04xfq0f34","country_code":"DE","type":"education","lineage":["https://openalex.org/I887968799"]},{"id":"https://openalex.org/I99977706","display_name":"FH Aachen","ror":"https://ror.org/04tqgg260","country_code":"DE","type":"education","lineage":["https://openalex.org/I99977706"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Hermann Ney","raw_affiliation_strings":["RWTH Aachen University,Human Language Technology and Pattern Recognition,Computer Science Department,Aachen,Germany,52062","AppTek GmbH, Aachen, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"RWTH Aachen University,Human Language Technology and Pattern Recognition,Computer Science Department,Aachen,Germany,52062","institution_ids":["https://openalex.org/I887968799"]},{"raw_affiliation_string":"AppTek GmbH, Aachen, Germany","institution_ids":["https://openalex.org/I99977706"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.9601,"has_fulltext":false,"cited_by_count":9,"citation_normalized_percentile":{"value":0.8804754,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"229","last_page":"236"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":1.0,"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":1.0,"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":0.9997000098228455,"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/T10860","display_name":"Speech and Audio Processing","score":0.9993000030517578,"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/computer-science","display_name":"Computer science","score":0.7910037040710449},{"id":"https://openalex.org/keywords/decoding-methods","display_name":"Decoding methods","score":0.7503763437271118},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6575274467468262},{"id":"https://openalex.org/keywords/monotonic-function","display_name":"Monotonic function","score":0.5992169380187988},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4491269588470459},{"id":"https://openalex.org/keywords/quadratic-equation","display_name":"Quadratic equation","score":0.4334753155708313},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.332938551902771},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.28576576709747314},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.07038342952728271}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7910037040710449},{"id":"https://openalex.org/C57273362","wikidata":"https://www.wikidata.org/wiki/Q576722","display_name":"Decoding methods","level":2,"score":0.7503763437271118},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6575274467468262},{"id":"https://openalex.org/C72169020","wikidata":"https://www.wikidata.org/wiki/Q194404","display_name":"Monotonic function","level":2,"score":0.5992169380187988},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4491269588470459},{"id":"https://openalex.org/C129844170","wikidata":"https://www.wikidata.org/wiki/Q41299","display_name":"Quadratic equation","level":2,"score":0.4334753155708313},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.332938551902771},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.28576576709747314},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.07038342952728271},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/slt54892.2023.10022818","is_oa":false,"landing_page_url":"https://doi.org/10.1109/slt54892.2023.10022818","pdf_url":null,"source":{"id":"https://openalex.org/S4363605953","display_name":"2022 IEEE Spoken Language Technology Workshop (SLT)","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":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 IEEE Spoken Language Technology Workshop (SLT)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16","score":0.49000000953674316}],"awards":[{"id":"https://openalex.org/G2418428810","display_name":null,"funder_award_id":"03ZUll06DA","funder_id":"https://openalex.org/F4320321114","funder_display_name":"Bundesministerium f\u00fcr Bildung und Forschung"}],"funders":[{"id":"https://openalex.org/F4320321114","display_name":"Bundesministerium f\u00fcr Bildung und Forschung","ror":"https://ror.org/04pz7b180"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":76,"referenced_works":["https://openalex.org/W854541894","https://openalex.org/W1586532344","https://openalex.org/W1810943226","https://openalex.org/W1828163288","https://openalex.org/W1902237438","https://openalex.org/W2064675550","https://openalex.org/W2083393647","https://openalex.org/W2105482032","https://openalex.org/W2127141656","https://openalex.org/W2133564696","https://openalex.org/W2166637769","https://openalex.org/W2178654303","https://openalex.org/W2287914047","https://openalex.org/W2327501763","https://openalex.org/W2516649778","https://openalex.org/W2526425061","https://openalex.org/W2605141709","https://openalex.org/W2739883972","https://openalex.org/W2740240682","https://openalex.org/W2745439869","https://openalex.org/W2746192915","https://openalex.org/W2754219472","https://openalex.org/W2766219058","https://openalex.org/W2767601419","https://openalex.org/W2798474427","https://openalex.org/W2799800213","https://openalex.org/W2799923439","https://openalex.org/W2889187401","https://openalex.org/W2905489173","https://openalex.org/W2915977493","https://openalex.org/W2936123380","https://openalex.org/W2936706905","https://openalex.org/W2936774411","https://openalex.org/W2952992734","https://openalex.org/W2962784628","https://openalex.org/W2962826786","https://openalex.org/W2963382396","https://openalex.org/W2963795358","https://openalex.org/W2964260331","https://openalex.org/W2972439411","https://openalex.org/W2972977747","https://openalex.org/W2972995428","https://openalex.org/W2973122799","https://openalex.org/W3007073761","https://openalex.org/W3007776460","https://openalex.org/W3008181812","https://openalex.org/W3008191852","https://openalex.org/W3008898571","https://openalex.org/W3013642574","https://openalex.org/W3015194534","https://openalex.org/W3028545098","https://openalex.org/W3048407879","https://openalex.org/W3094957294","https://openalex.org/W3097747488","https://openalex.org/W3105532142","https://openalex.org/W3151269043","https://openalex.org/W3160551958","https://openalex.org/W3197991202","https://openalex.org/W3198439131","https://openalex.org/W3198654230","https://openalex.org/W3210914950","https://openalex.org/W4294619417","https://openalex.org/W6623517193","https://openalex.org/W6635078382","https://openalex.org/W6638749077","https://openalex.org/W6685711979","https://openalex.org/W6696116229","https://openalex.org/W6729544866","https://openalex.org/W6735706088","https://openalex.org/W6745543685","https://openalex.org/W6747158283","https://openalex.org/W6757717501","https://openalex.org/W6775566006","https://openalex.org/W6778184438","https://openalex.org/W6793472422","https://openalex.org/W6803996941"],"related_works":["https://openalex.org/W4380682190","https://openalex.org/W4315701745","https://openalex.org/W1990290471","https://openalex.org/W2945307361","https://openalex.org/W2005710836","https://openalex.org/W2102386043","https://openalex.org/W2003813852","https://openalex.org/W2116636209","https://openalex.org/W2803711932","https://openalex.org/W4366779185"],"abstract_inverted_index":{"We":[0,10,33,42],"introduce":[1],"a":[2,70,81],"novel":[3,68],"segmental-attention":[4,39,92],"model":[5,83,93,117],"for":[6,64],"automatic":[7],"speech":[8],"recognition.":[9],"restrict":[11],"the":[12,53,78,86,109,115],"decoder":[13],"attention":[14,106],"to":[15,17,26,84,103,121,126],"segments":[16],"avoid":[18],"quadratic":[19],"runtime":[20],"of":[21,80,124],"global":[22],"attention,":[23],"better":[24,98,120],"generalize":[25],"long":[27,122],"sequences,":[28],"and":[29,37,44,69],"eventually":[30],"enable":[31],"streaming.":[32],"directly":[34],"compare":[35,45],"global-attention":[36],"different":[38],"modeling":[40],"variants.":[41],"develop":[43],"two":[46],"separate":[47],"time-synchronous":[48,62],"decoders,":[49],"one":[50],"specifically":[51],"taking":[52],"segmental":[54,65,95,116],"nature":[55],"into":[56],"account,":[57],"yielding":[58],"further":[59],"improvements.":[60],"Using":[61],"decoding":[63,96],"models":[66],"is":[67],"step":[71],"towards":[72],"streaming":[73],"applications.":[74],"Our":[75],"experiments":[76],"show":[77],"importance":[79],"length":[82],"predict":[85],"segment":[87],"boundaries.":[88],"The":[89],"final":[90],"best":[91],"using":[94],"performs":[97],"than":[99],"global-attention,":[100],"in":[101,108],"contrast":[102],"other":[104],"monotonic":[105],"approaches":[107],"literature.":[110],"Further,":[111],"we":[112],"observe":[113],"that":[114],"generalizes":[118],"much":[119],"sequences":[123],"up":[125],"several":[127],"minutes.":[128]},"counts_by_year":[{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":4},{"year":2023,"cited_by_count":2}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}