{"id":"https://openalex.org/W2913554070","doi":"https://doi.org/10.1109/icdsp.2018.8631855","title":"Information Distance Based Self-Attention-BGRU Layer for End-to-End Speech Recognition","display_name":"Information Distance Based Self-Attention-BGRU Layer for End-to-End Speech Recognition","publication_year":2018,"publication_date":"2018-11-01","ids":{"openalex":"https://openalex.org/W2913554070","doi":"https://doi.org/10.1109/icdsp.2018.8631855","mag":"2913554070"},"language":"en","primary_location":{"id":"doi:10.1109/icdsp.2018.8631855","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icdsp.2018.8631855","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 IEEE 23rd International Conference on Digital Signal Processing (DSP)","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/A5100303520","display_name":"Yunhao Yan","orcid":null},"institutions":[{"id":"https://openalex.org/I37461747","display_name":"Wuhan University","ror":"https://ror.org/033vjfk17","country_code":"CN","type":"education","lineage":["https://openalex.org/I37461747"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yunhao Yan","raw_affiliation_strings":["Signal Processing Lab. School of Electronic Information, Wuhan University, Wuhan, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Signal Processing Lab. School of Electronic Information, Wuhan University, Wuhan, China","institution_ids":["https://openalex.org/I37461747"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101049939","display_name":"Qinmengying Yan","orcid":null},"institutions":[{"id":"https://openalex.org/I37461747","display_name":"Wuhan University","ror":"https://ror.org/033vjfk17","country_code":"CN","type":"education","lineage":["https://openalex.org/I37461747"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qinmengying Yan","raw_affiliation_strings":["Signal Processing Lab. School of Electronic Information, Wuhan University, Wuhan, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Signal Processing Lab. School of Electronic Information, Wuhan University, Wuhan, China","institution_ids":["https://openalex.org/I37461747"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5068604294","display_name":"Guang Hua","orcid":"https://orcid.org/0000-0001-5184-4359"},"institutions":[{"id":"https://openalex.org/I37461747","display_name":"Wuhan University","ror":"https://ror.org/033vjfk17","country_code":"CN","type":"education","lineage":["https://openalex.org/I37461747"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Guang Hua","raw_affiliation_strings":["Signal Processing Lab. School of Electronic Information, Wuhan University, Wuhan, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Signal Processing Lab. School of Electronic Information, Wuhan University, Wuhan, China","institution_ids":["https://openalex.org/I37461747"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5003692319","display_name":"Haijian Zhang","orcid":"https://orcid.org/0000-0001-8314-6563"},"institutions":[{"id":"https://openalex.org/I37461747","display_name":"Wuhan University","ror":"https://ror.org/033vjfk17","country_code":"CN","type":"education","lineage":["https://openalex.org/I37461747"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Haijian Zhang","raw_affiliation_strings":["Signal Processing Lab. School of Electronic Information, Wuhan University, Wuhan, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Signal Processing Lab. School of Electronic Information, Wuhan University, Wuhan, China","institution_ids":["https://openalex.org/I37461747"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I37461747"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.18901154,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"2018","issue":null,"first_page":"1","last_page":"5"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","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/T10201","display_name":"Speech Recognition and Synthesis","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/T12031","display_name":"Speech and dialogue systems","score":0.9944000244140625,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.992900013923645,"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":0.76717209815979},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.732286274433136},{"id":"https://openalex.org/keywords/redundancy","display_name":"Redundancy (engineering)","score":0.6909681558609009},{"id":"https://openalex.org/keywords/end-to-end-principle","display_name":"End-to-end principle","score":0.6776690483093262},{"id":"https://openalex.org/keywords/architecture","display_name":"Architecture","score":0.44426172971725464},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.43427595496177673},{"id":"https://openalex.org/keywords/layer","display_name":"Layer (electronics)","score":0.41607865691185},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.41527581214904785},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3678901791572571}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.76717209815979},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.732286274433136},{"id":"https://openalex.org/C152124472","wikidata":"https://www.wikidata.org/wiki/Q1204361","display_name":"Redundancy (engineering)","level":2,"score":0.6909681558609009},{"id":"https://openalex.org/C74296488","wikidata":"https://www.wikidata.org/wiki/Q2527392","display_name":"End-to-end principle","level":2,"score":0.6776690483093262},{"id":"https://openalex.org/C123657996","wikidata":"https://www.wikidata.org/wiki/Q12271","display_name":"Architecture","level":2,"score":0.44426172971725464},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.43427595496177673},{"id":"https://openalex.org/C2779227376","wikidata":"https://www.wikidata.org/wiki/Q6505497","display_name":"Layer (electronics)","level":2,"score":0.41607865691185},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.41527581214904785},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3678901791572571},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"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/C153349607","wikidata":"https://www.wikidata.org/wiki/Q36649","display_name":"Visual arts","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/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/icdsp.2018.8631855","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icdsp.2018.8631855","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 IEEE 23rd International Conference on Digital Signal Processing (DSP)","raw_type":"proceedings-article"},{"id":"mag:3083784533","is_oa":false,"landing_page_url":"https://jglobal.jst.go.jp/en/detail?JGLOBAL_ID=201902222735637403","pdf_url":null,"source":{"id":"https://openalex.org/S4306512817","display_name":"IEEE Conference Proceedings","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":null,"is_accepted":false,"is_published":null,"raw_source_name":"IEEE Conference Proceedings","raw_type":null}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":21,"referenced_works":["https://openalex.org/W581956982","https://openalex.org/W854541894","https://openalex.org/W1494198834","https://openalex.org/W1554982972","https://openalex.org/W1586532344","https://openalex.org/W1855892484","https://openalex.org/W1922655562","https://openalex.org/W1993882792","https://openalex.org/W2127141656","https://openalex.org/W2143612262","https://openalex.org/W2157331557","https://openalex.org/W2193413348","https://openalex.org/W2267186426","https://openalex.org/W2413794162","https://openalex.org/W2515753980","https://openalex.org/W2597655663","https://openalex.org/W2612675303","https://openalex.org/W2627092829","https://openalex.org/W2962826786","https://openalex.org/W2963403868","https://openalex.org/W2963909185"],"related_works":["https://openalex.org/W3179968364","https://openalex.org/W1999612375","https://openalex.org/W2938107654","https://openalex.org/W2151749779","https://openalex.org/W3008587939","https://openalex.org/W3196421258","https://openalex.org/W1495042958","https://openalex.org/W2494338568","https://openalex.org/W4387301579","https://openalex.org/W2122678784"],"abstract_inverted_index":{"The":[0,21],"common":[1],"utilization":[2],"of":[3,58,94],"bidirectional":[4,103],"gated":[5,104],"recurrent":[6,105],"unit":[7,106],"(BGRU)":[8],"architectures":[9,28],"for":[10],"end-to-end":[11],"speech":[12,30,40,53,73,117],"recognition":[13,118],"suffers":[14],"from":[15],"long-term":[16],"dependence":[17],"and":[18,62],"information":[19,77,86],"redundancy.":[20],"reason":[22],"lies":[23],"in":[24],"that":[25,39,111],"the":[26,56,92,97],"BGRU":[27],"model":[29,72],"data":[31,41,54,74],"according":[32,75],"to":[33,71,76],"time":[34],"distance,":[35],"which":[36],"implicitly":[37],"assumes":[38],"is":[42,100],"continuous.":[43],"In":[44],"this":[45,67,81],"paper,":[46],"we":[47,69,83],"propose":[48,70],"a":[49],"new":[50],"hypothesis,":[51,68,82],"i.e.,":[52],"possess":[55],"feature":[57],"being":[59],"locally":[60],"continuous":[61],"globally":[63],"discrete.":[64],"Based":[65],"on":[66],"distance.":[78],"To":[79],"support":[80],"design":[84],"an":[85],"distance":[87],"based":[88],"modeling":[89],"architecture.":[90],"Via":[91],"incorporation":[93],"self-attention":[95,102],"mechanism,":[96],"proposed":[98],"architecture":[99],"termed":[101],"(SABGRU).":[107],"Experiment":[108],"results":[109],"show":[110],"SABGRU":[112],"increases":[113],"more":[114],"than":[115],"10%":[116],"accuracy":[119],"over":[120],"conventional":[121],"BGRU.":[122]},"counts_by_year":[],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}