{"id":"https://openalex.org/W3161365423","doi":"https://doi.org/10.1109/icassp39728.2021.9414477","title":"Transformer Language Models with LSTM-Based Cross-Utterance Information Representation","display_name":"Transformer Language Models with LSTM-Based Cross-Utterance Information Representation","publication_year":2021,"publication_date":"2021-05-13","ids":{"openalex":"https://openalex.org/W3161365423","doi":"https://doi.org/10.1109/icassp39728.2021.9414477","mag":"3161365423"},"language":"en","primary_location":{"id":"doi:10.1109/icassp39728.2021.9414477","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp39728.2021.9414477","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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/A5077772423","display_name":"Guangzhi Sun","orcid":"https://orcid.org/0000-0002-5886-056X"},"institutions":[{"id":"https://openalex.org/I241749","display_name":"University of Cambridge","ror":"https://ror.org/013meh722","country_code":"GB","type":"education","lineage":["https://openalex.org/I241749"]}],"countries":["GB"],"is_corresponding":true,"raw_author_name":"G. Sun","raw_affiliation_strings":["Cambridge University, Cambridge, U.K"],"affiliations":[{"raw_affiliation_string":"Cambridge University, Cambridge, U.K","institution_ids":["https://openalex.org/I241749"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5007989522","display_name":"C. Zhang","orcid":"https://orcid.org/0000-0002-2173-6872"},"institutions":[{"id":"https://openalex.org/I241749","display_name":"University of Cambridge","ror":"https://ror.org/013meh722","country_code":"GB","type":"education","lineage":["https://openalex.org/I241749"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"C. Zhang","raw_affiliation_strings":["Cambridge University, Cambridge, U.K"],"affiliations":[{"raw_affiliation_string":"Cambridge University, Cambridge, U.K","institution_ids":["https://openalex.org/I241749"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5002191410","display_name":"Philip C. Woodland","orcid":"https://orcid.org/0000-0001-9069-0225"},"institutions":[{"id":"https://openalex.org/I241749","display_name":"University of Cambridge","ror":"https://ror.org/013meh722","country_code":"GB","type":"education","lineage":["https://openalex.org/I241749"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"P. C. Woodland","raw_affiliation_strings":["Cambridge University, Cambridge, U.K"],"affiliations":[{"raw_affiliation_string":"Cambridge University, Cambridge, U.K","institution_ids":["https://openalex.org/I241749"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5077772423"],"corresponding_institution_ids":["https://openalex.org/I241749"],"apc_list":null,"apc_paid":null,"fwci":3.3992,"has_fulltext":false,"cited_by_count":29,"citation_normalized_percentile":{"value":0.93508985,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"7363","last_page":"7367"},"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9948999881744385,"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":0.9933000206947327,"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/utterance","display_name":"Utterance","score":0.8786513805389404},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.7736718654632568},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7227107286453247},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5893042087554932},{"id":"https://openalex.org/keywords/encode","display_name":"ENCODE","score":0.4863477349281311},{"id":"https://openalex.org/keywords/conversation","display_name":"Conversation","score":0.4825241267681122},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.46129903197288513},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.39710864424705505},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.333614319562912}],"concepts":[{"id":"https://openalex.org/C2775852435","wikidata":"https://www.wikidata.org/wiki/Q258403","display_name":"Utterance","level":2,"score":0.8786513805389404},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.7736718654632568},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7227107286453247},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5893042087554932},{"id":"https://openalex.org/C66746571","wikidata":"https://www.wikidata.org/wiki/Q1134833","display_name":"ENCODE","level":3,"score":0.4863477349281311},{"id":"https://openalex.org/C2777200299","wikidata":"https://www.wikidata.org/wiki/Q52943","display_name":"Conversation","level":2,"score":0.4825241267681122},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.46129903197288513},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.39710864424705505},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.333614319562912},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"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/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp39728.2021.9414477","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp39728.2021.9414477","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.800000011920929}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":49,"referenced_works":["https://openalex.org/W179875071","https://openalex.org/W1508165687","https://openalex.org/W1524333225","https://openalex.org/W1999965501","https://openalex.org/W2005708641","https://openalex.org/W2026149468","https://openalex.org/W2064675550","https://openalex.org/W2125336414","https://openalex.org/W2399550240","https://openalex.org/W2514741789","https://openalex.org/W2519224033","https://openalex.org/W2533523411","https://openalex.org/W2545177271","https://openalex.org/W2748679025","https://openalex.org/W2886180730","https://openalex.org/W2888779557","https://openalex.org/W2888867175","https://openalex.org/W2889152503","https://openalex.org/W2896457183","https://openalex.org/W2901265786","https://openalex.org/W2937649809","https://openalex.org/W2940744433","https://openalex.org/W2943845043","https://openalex.org/W2946567085","https://openalex.org/W2949640357","https://openalex.org/W2956480774","https://openalex.org/W2962739339","https://openalex.org/W2962745521","https://openalex.org/W2963362078","https://openalex.org/W2963925437","https://openalex.org/W2964110616","https://openalex.org/W2998704965","https://openalex.org/W3007776460","https://openalex.org/W3015586278","https://openalex.org/W3082335021","https://openalex.org/W3096471021","https://openalex.org/W4323654151","https://openalex.org/W4385245566","https://openalex.org/W6631362777","https://openalex.org/W6678809451","https://openalex.org/W6680532216","https://openalex.org/W6712868603","https://openalex.org/W6726720044","https://openalex.org/W6728841359","https://openalex.org/W6739901393","https://openalex.org/W6743477263","https://openalex.org/W6755207826","https://openalex.org/W6765571568","https://openalex.org/W6782476408"],"related_works":["https://openalex.org/W2899084033","https://openalex.org/W1968552888","https://openalex.org/W2468279273","https://openalex.org/W2374116601","https://openalex.org/W3093134843","https://openalex.org/W1511346092","https://openalex.org/W1527532029","https://openalex.org/W3133700904","https://openalex.org/W3016124757","https://openalex.org/W3034520363"],"abstract_inverted_index":{"The":[0,92,111,178],"effective":[1],"incorporation":[2],"of":[3,66],"cross-utterance":[4,25,51,137],"information":[5],"has":[6],"the":[7,28,35,50,53,67,73,86,98,102,105,123,141],"potential":[8],"to":[9,72,163,176],"improve":[10],"language":[11],"models":[12],"(LMs)":[13],"for":[14,27],"automatic":[15],"speech":[16],"recognition":[17,171],"(ASR).":[18],"To":[19,48],"extract":[20],"more":[21,174],"powerful":[22],"and":[23,104,117,127,146,152],"robust":[24],"representations":[26],"Transformer":[29,68],"LM":[30,166],"(TLM),":[31],"this":[32],"paper":[33],"proposes":[34],"R-TLM":[36,54,113,179],"which":[37,84],"uses":[38],"hidden":[39],"states":[40],"in":[41,64],"a":[42,61,77,81,135],"long":[43],"short-term":[44],"memory":[45],"(LSTM)":[46],"LM.":[47],"encode":[49],"information,":[52],"incorporates":[55],"an":[56,188],"LSTM":[57,74,87],"module":[58,75,88],"together":[59],"with":[60,187],"segment-wise":[62],"recurrence":[63],"some":[65],"blocks.":[69],"In":[70],"addition":[71],"output,":[76],"shortcut":[78],"connection":[79],"using":[80],"fusion":[82],"layer":[83],"bypasses":[85],"is":[89],"also":[90],"investigated.":[91],"proposed":[93],"system":[94],"was":[95],"evaluated":[96],"on":[97,140,150,168],"AMI":[99,142],"meeting":[100],"corpus,":[101],"Eval2000":[103,145,151],"RT03":[106,147,153],"telephone":[107],"conversation":[108],"evaluation":[109,143],"sets.":[110],"best":[112],"achieved":[114],"0.9%,":[115],"0.6%":[116],"0.8%":[118],"absolute":[119,131],"WER":[120,132,180],"reductions":[121,133],"over":[122,134],"single-utterance":[124],"TLM":[125,138],"baseline,":[126],"0.5%,":[128],"0.3%,":[129],"0.2%":[130],"strong":[136],"baseline":[139],"set,":[144],"respectively.":[148],"Improvements":[149],"were":[154,161],"further":[155,183],"supported":[156],"by":[157,185],"significance":[158],"tests.":[159],"R-TLMs":[160],"found":[162],"have":[164],"better":[165],"scores":[167],"words":[169],"where":[170],"errors":[172],"are":[173],"likely":[175],"occur.":[177],"can":[181],"be":[182],"reduced":[184],"interpolation":[186],"LSTM-LM.":[189]},"counts_by_year":[{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":6},{"year":2023,"cited_by_count":7},{"year":2022,"cited_by_count":11},{"year":2021,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}