{"id":"https://openalex.org/W2944006668","doi":"https://doi.org/10.1109/iscslp.2018.8706565","title":"Space-Time Residual LSTM Architechture for Distant Speech Recognition","display_name":"Space-Time Residual LSTM Architechture for Distant Speech Recognition","publication_year":2018,"publication_date":"2018-11-01","ids":{"openalex":"https://openalex.org/W2944006668","doi":"https://doi.org/10.1109/iscslp.2018.8706565","mag":"2944006668"},"language":"en","primary_location":{"id":"doi:10.1109/iscslp.2018.8706565","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iscslp.2018.8706565","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 11th International Symposium on Chinese Spoken Language Processing (ISCSLP)","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/A5102979204","display_name":"Long Wu","orcid":"https://orcid.org/0000-0003-3055-6600"},"institutions":[{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Long Wu","raw_affiliation_strings":["University of Chinese Academy of Sciences, China"],"affiliations":[{"raw_affiliation_string":"University of Chinese Academy of Sciences, China","institution_ids":["https://openalex.org/I4210165038"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100336197","display_name":"Li Wang","orcid":"https://orcid.org/0000-0003-2165-0080"},"institutions":[{"id":"https://openalex.org/I4210099069","display_name":"Institute of Acoustics","ror":"https://ror.org/00v8rqv75","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210099069"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Li Wang","raw_affiliation_strings":["Key Laboratory of Speech Acoustics and Content Understanding, Institute of Acoustics, China"],"affiliations":[{"raw_affiliation_string":"Key Laboratory of Speech Acoustics and Content Understanding, Institute of Acoustics, China","institution_ids":["https://openalex.org/I4210099069"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5036446253","display_name":"Pengyuan Zhang","orcid":"https://orcid.org/0000-0001-6838-5160"},"institutions":[{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Pengyuan Zhang","raw_affiliation_strings":["University of Chinese Academy of Sciences, China"],"affiliations":[{"raw_affiliation_string":"University of Chinese Academy of Sciences, China","institution_ids":["https://openalex.org/I4210165038"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5052454197","display_name":"Li Ta","orcid":"https://orcid.org/0000-0001-5431-9787"},"institutions":[{"id":"https://openalex.org/I4210099069","display_name":"Institute of Acoustics","ror":"https://ror.org/00v8rqv75","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210099069"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ta Li","raw_affiliation_strings":["Key Laboratory of Speech Acoustics and Content Understanding, Institute of Acoustics, China"],"affiliations":[{"raw_affiliation_string":"Key Laboratory of Speech Acoustics and Content Understanding, Institute of Acoustics, China","institution_ids":["https://openalex.org/I4210099069"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100425112","display_name":"Yonghong Yan","orcid":"https://orcid.org/0000-0001-6907-5770"},"institutions":[{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yonghong Yan","raw_affiliation_strings":["University of Chinese Academy of Sciences, China"],"affiliations":[{"raw_affiliation_string":"University of Chinese Academy of Sciences, China","institution_ids":["https://openalex.org/I4210165038"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5102979204"],"corresponding_institution_ids":["https://openalex.org/I4210165038"],"apc_list":null,"apc_paid":null,"fwci":0.1629,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.62639876,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":"9","issue":null,"first_page":"379","last_page":"383"},"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":0.9987999796867371,"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":0.9979000091552734,"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/residual","display_name":"Residual","score":0.81562340259552},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6656886339187622},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6558725833892822},{"id":"https://openalex.org/keywords/projection","display_name":"Projection (relational algebra)","score":0.6037541031837463},{"id":"https://openalex.org/keywords/layer","display_name":"Layer (electronics)","score":0.5526144504547119},{"id":"https://openalex.org/keywords/reduction","display_name":"Reduction (mathematics)","score":0.5509037375450134},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5134474039077759},{"id":"https://openalex.org/keywords/dimension","display_name":"Dimension (graph theory)","score":0.4289613962173462},{"id":"https://openalex.org/keywords/space","display_name":"Space (punctuation)","score":0.4105236530303955},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.23721924424171448},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.14731493592262268}],"concepts":[{"id":"https://openalex.org/C155512373","wikidata":"https://www.wikidata.org/wiki/Q287450","display_name":"Residual","level":2,"score":0.81562340259552},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6656886339187622},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6558725833892822},{"id":"https://openalex.org/C57493831","wikidata":"https://www.wikidata.org/wiki/Q3134666","display_name":"Projection (relational algebra)","level":2,"score":0.6037541031837463},{"id":"https://openalex.org/C2779227376","wikidata":"https://www.wikidata.org/wiki/Q6505497","display_name":"Layer (electronics)","level":2,"score":0.5526144504547119},{"id":"https://openalex.org/C111335779","wikidata":"https://www.wikidata.org/wiki/Q3454686","display_name":"Reduction (mathematics)","level":2,"score":0.5509037375450134},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5134474039077759},{"id":"https://openalex.org/C33676613","wikidata":"https://www.wikidata.org/wiki/Q13415176","display_name":"Dimension (graph theory)","level":2,"score":0.4289613962173462},{"id":"https://openalex.org/C2778572836","wikidata":"https://www.wikidata.org/wiki/Q380933","display_name":"Space (punctuation)","level":2,"score":0.4105236530303955},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.23721924424171448},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.14731493592262268},{"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/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","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/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C202444582","wikidata":"https://www.wikidata.org/wiki/Q837863","display_name":"Pure mathematics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/iscslp.2018.8706565","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iscslp.2018.8706565","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 11th International Symposium on Chinese Spoken Language Processing (ISCSLP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":35,"referenced_works":["https://openalex.org/W1489125746","https://openalex.org/W1524333225","https://openalex.org/W1533861849","https://openalex.org/W1686810756","https://openalex.org/W1692173902","https://openalex.org/W1815076433","https://openalex.org/W2097117768","https://openalex.org/W2110798204","https://openalex.org/W2125336414","https://openalex.org/W2125930537","https://openalex.org/W2144792281","https://openalex.org/W2147768505","https://openalex.org/W2194775991","https://openalex.org/W2255466643","https://openalex.org/W2293634267","https://openalex.org/W2394932179","https://openalex.org/W2473934411","https://openalex.org/W2513938599","https://openalex.org/W2533523411","https://openalex.org/W2540556213","https://openalex.org/W2572403989","https://openalex.org/W2963266252","https://openalex.org/W2963917928","https://openalex.org/W2963920996","https://openalex.org/W2964084166","https://openalex.org/W4294555862","https://openalex.org/W6629052376","https://openalex.org/W6631362777","https://openalex.org/W6631943919","https://openalex.org/W6637373629","https://openalex.org/W6637396859","https://openalex.org/W6638545294","https://openalex.org/W6640608466","https://openalex.org/W6678818196","https://openalex.org/W6696934422"],"related_works":["https://openalex.org/W2560215812","https://openalex.org/W2949601986","https://openalex.org/W2788972299","https://openalex.org/W2498789492","https://openalex.org/W2521347458","https://openalex.org/W2729981612","https://openalex.org/W4233449973","https://openalex.org/W2925692864","https://openalex.org/W2768526084","https://openalex.org/W151988857"],"abstract_inverted_index":{"Long":[0],"Short-Term":[1],"Memory":[2],"(Plain-LSTM)":[3],"is":[4,17,117],"efficient":[5],"for":[6,60,108],"acoustic":[7],"modeling":[8],"in":[9,85,88,100,125,152,154],"automatic":[10],"speech":[11,62],"recognition":[12,63],"systems,":[13],"but":[14],"their":[15],"training":[16],"obstructed":[18],"by":[19],"the":[20,28,30,41,46,56,65,83,98,105,110,126,135,138],"vanishing":[21],"and":[22,76,112,137,146],"exploding":[23],"gradient":[24],"issues.":[25],"To":[26,102],"alleviate":[27],"problem,":[29],"paper":[31],"introduces":[32],"an":[33,121],"improved":[34],"space":[35,111],"residual":[36,114,123],"LSTM":[37,47,115],"(S-RES-LSTM),":[38],"which":[39,119],"uses":[40],"output":[42],"before":[43],"not":[44],"after":[45],"projection":[48],"layer":[49,87],"as":[50],"spatial":[51],"shortcut":[52],"connection":[53,124],"compared":[54,133],"to":[55],"previous":[57],"RES-LSTM.":[58],"Experiments":[59],"distant":[61],"on":[64],"AMI":[66],"SDM":[67],"show":[68,131],"that":[69,132],"S-RES-LSTM":[70],"can":[71],"reach":[72],"5%":[73],"absolute":[74,78,94,143,148],"WER(over)":[75,144,149],"5.9%":[77],"WER":[79,95],"(non-over)":[80],"reduction":[81,96,150],"than":[82,97],"Plain-LSTM":[84,136],"9-":[86],"eval.":[89,155],"It":[90],"also":[91],"has":[92],"0.6%":[93],"RES-LSTM":[99],"9-layer.":[101],"further":[103],"enhance":[104],"information":[106],"flow":[107],"S-RES-LSTM,":[109],"time":[113],"(ST-RES-LSTM)":[116],"proposed,":[118],"adds":[120],"innovational":[122],"temporal":[127],"dimension.":[128],"The":[129],"experiments":[130],"with":[134],"RES-LSTM,":[139],"ST-RES-LSTM":[140],"achieves":[141],"5.5%":[142],"degradation":[145],"1%":[147],"respectively":[151],"9-layer":[153]},"counts_by_year":[{"year":2023,"cited_by_count":1},{"year":2019,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}