{"id":"https://openalex.org/W2802023636","doi":"https://doi.org/10.1109/icassp.2018.8462497","title":"A Time-Restricted Self-Attention Layer for ASR","display_name":"A Time-Restricted Self-Attention Layer for ASR","publication_year":2018,"publication_date":"2018-04-01","ids":{"openalex":"https://openalex.org/W2802023636","doi":"https://doi.org/10.1109/icassp.2018.8462497","mag":"2802023636"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2018.8462497","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2018.8462497","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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/A5084286453","display_name":"Daniel Povey","orcid":"https://orcid.org/0000-0002-0611-3634"},"institutions":[{"id":"https://openalex.org/I145311948","display_name":"Johns Hopkins University","ror":"https://ror.org/00za53h95","country_code":"US","type":"education","lineage":["https://openalex.org/I145311948"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Daniel Povey","raw_affiliation_strings":["Human Language Technology Center of Excellence, Johns Hopkins University, Baltimore, MD, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Human Language Technology Center of Excellence, Johns Hopkins University, Baltimore, MD, USA","institution_ids":["https://openalex.org/I145311948"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5041855151","display_name":"Hossein Hadian","orcid":"https://orcid.org/0000-0002-1083-6026"},"institutions":[{"id":"https://openalex.org/I145311948","display_name":"Johns Hopkins University","ror":"https://ror.org/00za53h95","country_code":"US","type":"education","lineage":["https://openalex.org/I145311948"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Hossein Hadian","raw_affiliation_strings":["Center for Language and Speech Processing, Johns Hopkins University, Baltimore, MD, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Center for Language and Speech Processing, Johns Hopkins University, Baltimore, MD, USA","institution_ids":["https://openalex.org/I145311948"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5029777844","display_name":"Pegah Ghahremani","orcid":null},"institutions":[{"id":"https://openalex.org/I145311948","display_name":"Johns Hopkins University","ror":"https://ror.org/00za53h95","country_code":"US","type":"education","lineage":["https://openalex.org/I145311948"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Pegah Ghahremani","raw_affiliation_strings":["Center for Language and Speech Processing, Johns Hopkins University, Baltimore, MD, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Center for Language and Speech Processing, Johns Hopkins University, Baltimore, MD, USA","institution_ids":["https://openalex.org/I145311948"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100725160","display_name":"Ke Li","orcid":"https://orcid.org/0000-0001-7998-0731"},"institutions":[{"id":"https://openalex.org/I145311948","display_name":"Johns Hopkins University","ror":"https://ror.org/00za53h95","country_code":"US","type":"education","lineage":["https://openalex.org/I145311948"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ke Li","raw_affiliation_strings":["Center for Language and Speech Processing, Johns Hopkins University, Baltimore, MD, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Center for Language and Speech Processing, Johns Hopkins University, Baltimore, MD, USA","institution_ids":["https://openalex.org/I145311948"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5014580424","display_name":"Sanjeev Khudanpur","orcid":"https://orcid.org/0000-0001-5976-0897"},"institutions":[{"id":"https://openalex.org/I145311948","display_name":"Johns Hopkins University","ror":"https://ror.org/00za53h95","country_code":"US","type":"education","lineage":["https://openalex.org/I145311948"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Sanjeev Khudanpur","raw_affiliation_strings":["Human Language Technology Center of Excellence, Johns Hopkins University, Baltimore, MD, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Human Language Technology Center of Excellence, Johns Hopkins University, Baltimore, MD, USA","institution_ids":["https://openalex.org/I145311948"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I145311948"],"apc_list":null,"apc_paid":null,"fwci":12.2236,"has_fulltext":false,"cited_by_count":168,"citation_normalized_percentile":{"value":0.98838435,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"5874","last_page":"5878"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9998000264167786,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9998000264167786,"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/T10028","display_name":"Topic Modeling","score":0.9997000098228455,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9970999956130981,"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":0.8575684428215027},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7052260637283325},{"id":"https://openalex.org/keywords/offset","display_name":"Offset (computer science)","score":0.6201286315917969},{"id":"https://openalex.org/keywords/frame","display_name":"Frame (networking)","score":0.6141336560249329},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.540135383605957},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.5368236899375916},{"id":"https://openalex.org/keywords/layer","display_name":"Layer (electronics)","score":0.530367374420166},{"id":"https://openalex.org/keywords/encoding","display_name":"Encoding (memory)","score":0.5078602433204651},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5066867470741272},{"id":"https://openalex.org/keywords/encode","display_name":"ENCODE","score":0.4304730296134949},{"id":"https://openalex.org/keywords/time-delay-neural-network","display_name":"Time delay neural network","score":0.4302677512168884},{"id":"https://openalex.org/keywords/mechanism","display_name":"Mechanism (biology)","score":0.4211367964744568},{"id":"https://openalex.org/keywords/machine-translation","display_name":"Machine translation","score":0.4106556475162506},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4036198854446411},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.06654950976371765}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8575684428215027},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7052260637283325},{"id":"https://openalex.org/C175291020","wikidata":"https://www.wikidata.org/wiki/Q1156822","display_name":"Offset (computer science)","level":2,"score":0.6201286315917969},{"id":"https://openalex.org/C126042441","wikidata":"https://www.wikidata.org/wiki/Q1324888","display_name":"Frame (networking)","level":2,"score":0.6141336560249329},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.540135383605957},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5368236899375916},{"id":"https://openalex.org/C2779227376","wikidata":"https://www.wikidata.org/wiki/Q6505497","display_name":"Layer (electronics)","level":2,"score":0.530367374420166},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.5078602433204651},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5066867470741272},{"id":"https://openalex.org/C66746571","wikidata":"https://www.wikidata.org/wiki/Q1134833","display_name":"ENCODE","level":3,"score":0.4304730296134949},{"id":"https://openalex.org/C175202392","wikidata":"https://www.wikidata.org/wiki/Q2434543","display_name":"Time delay neural network","level":3,"score":0.4302677512168884},{"id":"https://openalex.org/C89611455","wikidata":"https://www.wikidata.org/wiki/Q6804646","display_name":"Mechanism (biology)","level":2,"score":0.4211367964744568},{"id":"https://openalex.org/C203005215","wikidata":"https://www.wikidata.org/wiki/Q79798","display_name":"Machine translation","level":2,"score":0.4106556475162506},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4036198854446411},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.06654950976371765},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0},{"id":"https://openalex.org/C178790620","wikidata":"https://www.wikidata.org/wiki/Q11351","display_name":"Organic chemistry","level":1,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","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":1,"locations":[{"id":"doi:10.1109/icassp.2018.8462497","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2018.8462497","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","score":0.5,"id":"https://metadata.un.org/sdg/16"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":22,"referenced_works":["https://openalex.org/W854541894","https://openalex.org/W1514535095","https://openalex.org/W1524333225","https://openalex.org/W1586532344","https://openalex.org/W1836465849","https://openalex.org/W1902237438","https://openalex.org/W2024490156","https://openalex.org/W2133564696","https://openalex.org/W2166637769","https://openalex.org/W2251321385","https://openalex.org/W2293634267","https://openalex.org/W2514741789","https://openalex.org/W2949117887","https://openalex.org/W2962826786","https://openalex.org/W2964308564","https://openalex.org/W4385245566","https://openalex.org/W6623517193","https://openalex.org/W6630875275","https://openalex.org/W6631362777","https://openalex.org/W6638667902","https://openalex.org/W6691770337","https://openalex.org/W6696934422"],"related_works":["https://openalex.org/W2389073067","https://openalex.org/W2386387936","https://openalex.org/W2905846897","https://openalex.org/W2624764041","https://openalex.org/W2367618470","https://openalex.org/W2794558692","https://openalex.org/W2182112479","https://openalex.org/W1998051514","https://openalex.org/W2121214821","https://openalex.org/W1575012072"],"abstract_inverted_index":{"Self-attention":[0],"-":[1,15,82],"an":[2],"attention":[3,95,105],"mechanism":[4,37,50],"where":[5],"the":[6,13,49,65,70,77,80,89,124],"input":[7,57,81],"and":[8,26,67,100,126],"output":[9],"sequence":[10],"lengths":[11],"are":[12,131],"same":[14],"has":[16],"recently":[17],"been":[18],"successfully":[19],"applied":[20],"to":[21,41,64,75,123],"machine":[22],"translation,":[23],"caption":[24],"generation,":[25],"phoneme":[27],"recognition.":[28,43],"In":[29],"this":[30],"paper":[31],"we":[32,46,83],"apply":[33],"a":[34,52,59,85,114],"restricted":[35],"self-attention":[36],"(with":[38],"multiple":[39],"heads)":[40],"speech":[42],"By":[44],"\u201crestricted\u201d":[45],"mean":[47],"that":[48],"at":[51],"particular":[53],"frame":[54,90],"only":[55],"sees":[56],"from":[58],"limited":[60],"number":[61,115],"of":[62,79,88,116],"frames":[63],"left":[66],"right.":[68],"Restricting":[69],"context":[71],"makes":[72],"it":[73],"easier":[74],"encode":[76],"position":[78],"use":[84],"I-hot":[86],"encoding":[87],"offset.":[91],"We":[92,110,119],"try":[93],"introducing":[94],"layers":[96,103,106,130,136],"into":[97],"TDNN":[98,125],"architectures,":[99],"replacing":[101],"LSTM":[102,135],"with":[104],"in":[107,137],"TDNN+LSTM":[108,127],"architectures.":[109],"show":[111],"experiments":[112],"on":[113],"ASR":[117],"setups.":[118],"observe":[120],"improvements":[121],"compared":[122],"baselines.":[128],"Attention":[129],"also":[132],"faster":[133],"than":[134],"test":[138],"time,":[139],"since":[140],"they":[141],"lack":[142],"recurrence.":[143]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":6},{"year":2024,"cited_by_count":8},{"year":2023,"cited_by_count":22},{"year":2022,"cited_by_count":23},{"year":2021,"cited_by_count":43},{"year":2020,"cited_by_count":36},{"year":2019,"cited_by_count":22},{"year":2018,"cited_by_count":7}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}