{"id":"https://openalex.org/W2750545698","doi":"https://doi.org/10.21437/interspeech.2017-111","title":"Multilingual Recurrent Neural Networks with Residual Learning for Low-Resource Speech Recognition","display_name":"Multilingual Recurrent Neural Networks with Residual Learning for Low-Resource Speech Recognition","publication_year":2017,"publication_date":"2017-08-16","ids":{"openalex":"https://openalex.org/W2750545698","doi":"https://doi.org/10.21437/interspeech.2017-111","mag":"2750545698"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2017-111","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2017-111","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2017","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/A5101400153","display_name":"Shiyu Zhou","orcid":"https://orcid.org/0000-0002-6889-0316"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Shiyu Zhou","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":"middle","author":{"id":"https://openalex.org/A5004363895","display_name":"Shuang Xu","orcid":"https://orcid.org/0000-0003-3576-6914"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Shuang Xu","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5108642431","display_name":"Bo Xu","orcid":"https://orcid.org/0000-0002-1111-1529"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Bo Xu","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5101400153"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":2.1452,"has_fulltext":false,"cited_by_count":22,"citation_normalized_percentile":{"value":0.90451625,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"704","last_page":"708"},"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":0.9993000030517578,"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"}},{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9977999925613403,"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":0.835946261882782},{"id":"https://openalex.org/keywords/residual","display_name":"Residual","score":0.7499396204948425},{"id":"https://openalex.org/keywords/softmax-function","display_name":"Softmax function","score":0.6815868616104126},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6534169912338257},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6483378410339355},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.5733492374420166},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.5268734097480774},{"id":"https://openalex.org/keywords/recurrent-neural-network","display_name":"Recurrent neural network","score":0.5018482208251953},{"id":"https://openalex.org/keywords/layer","display_name":"Layer (electronics)","score":0.4911198318004608},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.46277129650115967},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.41012099385261536}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.835946261882782},{"id":"https://openalex.org/C155512373","wikidata":"https://www.wikidata.org/wiki/Q287450","display_name":"Residual","level":2,"score":0.7499396204948425},{"id":"https://openalex.org/C188441871","wikidata":"https://www.wikidata.org/wiki/Q7554146","display_name":"Softmax function","level":3,"score":0.6815868616104126},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6534169912338257},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6483378410339355},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5733492374420166},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.5268734097480774},{"id":"https://openalex.org/C147168706","wikidata":"https://www.wikidata.org/wiki/Q1457734","display_name":"Recurrent neural network","level":3,"score":0.5018482208251953},{"id":"https://openalex.org/C2779227376","wikidata":"https://www.wikidata.org/wiki/Q6505497","display_name":"Layer (electronics)","level":2,"score":0.4911198318004608},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.46277129650115967},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.41012099385261536},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","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/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21437/interspeech.2017-111","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2017-111","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2017","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","score":0.6000000238418579,"id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":12,"referenced_works":["https://openalex.org/W1499864241","https://openalex.org/W1525636403","https://openalex.org/W1565000507","https://openalex.org/W2005708641","https://openalex.org/W2106440210","https://openalex.org/W2123798005","https://openalex.org/W2160306971","https://openalex.org/W2194775991","https://openalex.org/W2400564850","https://openalex.org/W2408183654","https://openalex.org/W2513938599","https://openalex.org/W2963410064"],"related_works":["https://openalex.org/W3107204728","https://openalex.org/W4287591324","https://openalex.org/W3108503355","https://openalex.org/W4226420367","https://openalex.org/W2962876041","https://openalex.org/W3090555870","https://openalex.org/W3022820045","https://openalex.org/W4323060069","https://openalex.org/W2790400419","https://openalex.org/W3008584592"],"abstract_inverted_index":{"The":[0],"shared-hidden-layer":[1,51,83],"multilingual":[2,40,84,98,174],"deep":[3,14,112],"neural":[4,15,58],"network":[5,16],"(SHL-MDNN),":[6],"in":[7],"which":[8,165],"the":[9,24,50,71,101,108,141],"hidden":[10],"layers":[11,26],"of":[12,39,74,111],"feed-forward":[13],"(DNN)":[17],"are":[18,27],"shared":[19],"across":[20],"multiple":[21],"languages":[22,133],"while":[23],"softmax":[25],"language":[28,142],"dependent,":[29],"has":[30,67],"been":[31],"shown":[32],"to":[33],"be":[34,157],"effective":[35],"on":[36,145,162,173],"acoustic":[37,72],"modeling":[38],"low-resource":[41,175],"speech":[42,76],"recognition.":[43],"In":[44],"this":[45],"paper,":[46],"we":[47,80],"propose":[48],"that":[49,82,103,117],"with":[52,87],"Long":[53],"Short-Term":[54],"Memory":[55],"(LSTM)":[56],"recurrent":[57],"networks":[59],"can":[60,90,106,119,156],"achieve":[61],"further":[62],"performance":[63],"improvement":[64],"considering":[65],"LSTM":[66,85,138],"outperformed":[68],"DNN":[69],"as":[70],"model":[73],"automatic":[75],"recognition":[77],"(ASR).":[78],"Moreover,":[79],"reveal":[81],"(SHL-MLSTM)":[86],"residual":[88,104,160,167],"learning":[89,105,161,168],"yield":[91],"additional":[92],"moderate":[93],"but":[94],"consistent":[95],"gain":[96],"from":[97],"tasks":[99],"given":[100],"fact":[102],"allievate":[107],"degradation":[109],"problem":[110],"LSTMs.":[113],"Experimental":[114],"results":[115],"demonstrate":[116],"SHL-MLSTM":[118,172],"relatively":[120,152],"reduce":[121],"word":[122],"error":[123],"rate":[124],"(WER)":[125],"by":[126],"2.1-6.8\\%":[127],"over":[128,136,154],"SHL-MDNN":[129],"trained":[130,139],"using":[131,140],"six":[132],"and":[134],"2.6-7.3\\%":[135],"monolingual":[137],"specific":[143],"data":[144],"CALLHOME":[146,163],"datasets.":[147],"Additional":[148],"WER":[149],"reduction,":[150],"about":[151],"2\\%":[153],"SHL-MLSTM,":[155],"obtained":[158],"through":[159],"datasets,":[164],"demonstrates":[166],"is":[169],"useful":[170],"for":[171],"ASR.":[176]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":5},{"year":2020,"cited_by_count":4},{"year":2019,"cited_by_count":3},{"year":2018,"cited_by_count":4}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}