{"id":"https://openalex.org/W2962825331","doi":"https://doi.org/10.21437/interspeech.2018-1544","title":"Gated Recurrent Unit Based Acoustic Modeling with Future Context","display_name":"Gated Recurrent Unit Based Acoustic Modeling with Future Context","publication_year":2018,"publication_date":"2018-08-28","ids":{"openalex":"https://openalex.org/W2962825331","doi":"https://doi.org/10.21437/interspeech.2018-1544","mag":"2962825331"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2018-1544","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2018-1544","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2018","raw_type":"proceedings-article"},"type":"article","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/A5040606548","display_name":"Jie Li","orcid":"https://orcid.org/0000-0001-7147-4746"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Jie Li","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5076259390","display_name":"Xiaorui Wang","orcid":"https://orcid.org/0000-0002-7795-0990"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xiaorui Wang","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101995701","display_name":"Yuanyuan Zhao","orcid":"https://orcid.org/0000-0002-6107-2185"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yuanyuan Zhao","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5100443879","display_name":"Yan Li","orcid":"https://orcid.org/0000-0002-4694-4926"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yan Li","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5040606548"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.3031,"has_fulltext":false,"cited_by_count":9,"citation_normalized_percentile":{"value":0.85896741,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"1788","last_page":"1792"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9980999827384949,"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":0.9980999827384949,"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":0.9980000257492065,"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":0.9950000047683716,"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":0.659094512462616},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.5944172143936157},{"id":"https://openalex.org/keywords/unit","display_name":"Unit (ring theory)","score":0.4860575497150421},{"id":"https://openalex.org/keywords/context-model","display_name":"Context model","score":0.4670364558696747},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.37630951404571533},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.20568698644638062},{"id":"https://openalex.org/keywords/geology","display_name":"Geology","score":0.11032888293266296},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.06409025192260742}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.659094512462616},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.5944172143936157},{"id":"https://openalex.org/C122637931","wikidata":"https://www.wikidata.org/wiki/Q118084","display_name":"Unit (ring theory)","level":2,"score":0.4860575497150421},{"id":"https://openalex.org/C183322885","wikidata":"https://www.wikidata.org/wiki/Q17007702","display_name":"Context model","level":3,"score":0.4670364558696747},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.37630951404571533},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.20568698644638062},{"id":"https://openalex.org/C127313418","wikidata":"https://www.wikidata.org/wiki/Q1069","display_name":"Geology","level":0,"score":0.11032888293266296},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.06409025192260742},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"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/C145420912","wikidata":"https://www.wikidata.org/wiki/Q853077","display_name":"Mathematics education","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21437/interspeech.2018-1544","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2018-1544","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2018","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W2349222429","https://openalex.org/W2116230991","https://openalex.org/W2590751808","https://openalex.org/W2132709506","https://openalex.org/W1972377868","https://openalex.org/W2186895195","https://openalex.org/W2551233873","https://openalex.org/W2388933862","https://openalex.org/W2493957742","https://openalex.org/W1588556181"],"abstract_inverted_index":{"The":[0,71],"use":[1],"of":[2,52,146],"future":[3,29,55,108],"contextual":[4],"information":[5],"is":[6,74],"typically":[7],"shown":[8],"to":[9,26,43,105],"be":[10],"helpful":[11],"for":[12,16,102],"acoustic":[13,47],"modeling.":[14],"However,":[15],"the":[17,28,54,61,77,107,113,124],"recurrent":[18,80],"neural":[19],"network":[20],"(RNN),":[21],"it's":[22],"not":[23],"so":[24],"easy":[25],"model":[27,36,48,62,73,106,126,150,160],"temporal":[30,94,97],"context":[31,56,92],"effectively,":[32],"meanwhile":[33],"keep":[34],"lower":[35],"latency.":[37],"In":[38],"this":[39,103],"paper,":[40],"we":[41],"attempt":[42],"design":[44],"a":[45,143,153],"RNN":[46],"that":[49],"being":[50],"capable":[51],"utilizing":[53],"effectively":[57],"and":[58,64,96,116,135,162],"directly,":[59],"with":[60,83,142,158],"latency":[63,145,161],"computation":[65],"cost":[66],"as":[67,69],"low":[68],"possible.":[70],"proposed":[72,125],"based":[75],"on":[76,112],"minimal":[78],"gated":[79],"unit":[81],"(mGRU)":[82],"an":[84,117],"input":[85],"projection":[86],"layer":[87],"inserted":[88],"in":[89],"it.":[90],"Two":[91],"modules,":[93],"encoding":[95],"convolution,":[98],"are":[99],"specifically":[100],"designed":[101],"architecture":[104],"context.":[109],"Experimental":[110],"results":[111],"Switchboard":[114],"task":[115,121],"internal":[118],"Mandarin":[119],"ASR":[120],"show":[122],"that,":[123],"performs":[127],"much":[128],"better":[129],"than":[130],"long":[131],"short-term":[132],"memory":[133],"(LSTM)":[134],"mGRU":[136],"models,":[137],"whereas":[138],"enables":[139],"online":[140],"decoding":[141],"maximum":[144],"170":[147],"ms.":[148],"This":[149],"even":[151],"outperforms":[152],"very":[154],"strong":[155],"baseline,":[156],"TDNN-LSTM,":[157],"smaller":[159],"almost":[163],"half":[164],"less":[165],"parameters.":[166]},"counts_by_year":[{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":2},{"year":2019,"cited_by_count":4},{"year":2018,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}