{"id":"https://openalex.org/W2963048539","doi":"https://doi.org/10.1109/ccoms.2017.8075276","title":"An improved residual LSTM architecture for acoustic modeling","display_name":"An improved residual LSTM architecture for acoustic modeling","publication_year":2017,"publication_date":"2017-07-01","ids":{"openalex":"https://openalex.org/W2963048539","doi":"https://doi.org/10.1109/ccoms.2017.8075276","mag":"2963048539"},"language":"en","primary_location":{"id":"doi:10.1109/ccoms.2017.8075276","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ccoms.2017.8075276","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2017 2nd International Conference on Computer and Communication Systems (ICCCS)","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/A5101623835","display_name":"Lu Huang","orcid":"https://orcid.org/0000-0002-1588-8669"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Lu Huang","raw_affiliation_strings":["Department of Electronic Engineering, Tsinghua University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Department of Electronic Engineering, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5023545041","display_name":"Xu Ji","orcid":"https://orcid.org/0000-0002-3754-228X"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ji Xu","raw_affiliation_strings":["Department of Electronic Engineering, Tsinghua University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Department of Electronic Engineering, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100298903","display_name":"Jiasong Sun","orcid":null},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"funder","lineage":["https://openalex.org/I19820366"]},{"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":"Jiasong Sun","raw_affiliation_strings":["Key Lab of Speech Acoustics & Content Understanding, Chinese Academy of Sciences, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Key Lab of Speech Acoustics & Content Understanding, Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210099069","https://openalex.org/I19820366"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100733868","display_name":"Yi Yang","orcid":"https://orcid.org/0000-0002-4736-5491"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yi Yang","raw_affiliation_strings":["Department of Electronic Engineering, Tsinghua University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Department of Electronic Engineering, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5101623835"],"corresponding_institution_ids":["https://openalex.org/I99065089"],"apc_list":null,"apc_paid":null,"fwci":0.7801,"has_fulltext":false,"cited_by_count":8,"citation_normalized_percentile":{"value":0.80772825,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":"4","issue":null,"first_page":"101","last_page":"105"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":1.0,"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":1.0,"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":0.9994999766349792,"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":0.9993000030517578,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/residual","display_name":"Residual","score":0.813007116317749},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7751427292823792},{"id":"https://openalex.org/keywords/timit","display_name":"TIMIT","score":0.713398277759552},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.62962406873703},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5963569283485413},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.5962825417518616},{"id":"https://openalex.org/keywords/reduction","display_name":"Reduction (mathematics)","score":0.5670974850654602},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.5490649938583374},{"id":"https://openalex.org/keywords/recurrent-neural-network","display_name":"Recurrent neural network","score":0.5070481300354004},{"id":"https://openalex.org/keywords/architecture","display_name":"Architecture","score":0.49431514739990234},{"id":"https://openalex.org/keywords/approximation-error","display_name":"Approximation error","score":0.47141075134277344},{"id":"https://openalex.org/keywords/acoustic-model","display_name":"Acoustic model","score":0.45456770062446594},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.43863797187805176},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.33328598737716675},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.19468563795089722},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.14968788623809814},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.06703823804855347},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.0606749951839447}],"concepts":[{"id":"https://openalex.org/C155512373","wikidata":"https://www.wikidata.org/wiki/Q287450","display_name":"Residual","level":2,"score":0.813007116317749},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7751427292823792},{"id":"https://openalex.org/C2778724510","wikidata":"https://www.wikidata.org/wiki/Q7670405","display_name":"TIMIT","level":3,"score":0.713398277759552},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.62962406873703},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5963569283485413},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.5962825417518616},{"id":"https://openalex.org/C111335779","wikidata":"https://www.wikidata.org/wiki/Q3454686","display_name":"Reduction (mathematics)","level":2,"score":0.5670974850654602},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5490649938583374},{"id":"https://openalex.org/C147168706","wikidata":"https://www.wikidata.org/wiki/Q1457734","display_name":"Recurrent neural network","level":3,"score":0.5070481300354004},{"id":"https://openalex.org/C123657996","wikidata":"https://www.wikidata.org/wiki/Q12271","display_name":"Architecture","level":2,"score":0.49431514739990234},{"id":"https://openalex.org/C122383733","wikidata":"https://www.wikidata.org/wiki/Q865920","display_name":"Approximation error","level":2,"score":0.47141075134277344},{"id":"https://openalex.org/C155635449","wikidata":"https://www.wikidata.org/wiki/Q4674699","display_name":"Acoustic model","level":3,"score":0.45456770062446594},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.43863797187805176},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.33328598737716675},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.19468563795089722},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.14968788623809814},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.06703823804855347},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0606749951839447},{"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/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/ccoms.2017.8075276","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ccoms.2017.8075276","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2017 2nd International Conference on Computer and Communication Systems (ICCCS)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","score":0.7400000095367432,"id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":31,"referenced_works":["https://openalex.org/W97072897","https://openalex.org/W1494198834","https://openalex.org/W1524333225","https://openalex.org/W1608367484","https://openalex.org/W1762484328","https://openalex.org/W2005708641","https://openalex.org/W2064675550","https://openalex.org/W2079623482","https://openalex.org/W2107878631","https://openalex.org/W2132083787","https://openalex.org/W2144499799","https://openalex.org/W2194775991","https://openalex.org/W2284628133","https://openalex.org/W2293634267","https://openalex.org/W2394932179","https://openalex.org/W2396384435","https://openalex.org/W2407080277","https://openalex.org/W2519224033","https://openalex.org/W2529731305","https://openalex.org/W2530876040","https://openalex.org/W2533523411","https://openalex.org/W2963266252","https://openalex.org/W2963917928","https://openalex.org/W2985850616","https://openalex.org/W3127686677","https://openalex.org/W6603931906","https://openalex.org/W6631362777","https://openalex.org/W6637956674","https://openalex.org/W6696934422","https://openalex.org/W6713762819","https://openalex.org/W6789826613"],"related_works":["https://openalex.org/W2994894110","https://openalex.org/W4377862891","https://openalex.org/W2005708641","https://openalex.org/W80018097","https://openalex.org/W2100729928","https://openalex.org/W2964207879","https://openalex.org/W2080458333","https://openalex.org/W3181208372","https://openalex.org/W1995562189","https://openalex.org/W2050397613"],"abstract_inverted_index":{"Long":[0],"Short-Term":[1],"Memory":[2],"(LSTM)":[3],"is":[4,21],"the":[5,73,88],"primary":[6],"recurrent":[7],"neural":[8,27],"networks":[9,28],"architecture":[10,57,97],"for":[11,44],"acoustic":[12,46],"modeling":[13],"in":[14,64,85],"automatic":[15],"speech":[16],"recognition":[17],"systems.":[18],"Residual":[19],"learning":[20],"an":[22],"efficient":[23],"method":[24],"to":[25],"help":[26],"converge":[29],"easier":[30],"and":[31,105],"faster.":[32],"In":[33],"this":[34,96],"paper,":[35],"we":[36,92],"propose":[37],"several":[38],"types":[39],"of":[40],"residual":[41,77],"LSTM":[42,79],"methods":[43],"our":[45,56,76],"modeling.":[47],"Our":[48],"experiments":[49],"indicate":[50],"that,":[51],"compared":[52],"with":[53],"classic":[54],"LSTM,":[55],"shows":[58,81],"more":[59],"than":[60],"8%":[61],"relative":[62,83],"reduction":[63,84],"Phone":[65],"Error":[66],"Rate":[67],"(PER)":[68],"on":[69,87,102],"TIMIT":[70],"tasks.":[71],"At":[72],"same":[74,89],"time,":[75],"fast":[78],"approach":[80],"4%":[82],"PER":[86],"task.":[90],"Besides,":[91],"find":[93],"that":[94],"all":[95],"could":[98],"have":[99],"good":[100],"results":[101],"THCHS-30,":[103],"Librispeech":[104],"Switchboard":[106],"corpora.":[107]},"counts_by_year":[{"year":2023,"cited_by_count":1},{"year":2021,"cited_by_count":3},{"year":2020,"cited_by_count":2},{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}