{"id":"https://openalex.org/W3133595249","doi":"https://doi.org/10.1109/iscslp49672.2021.9362109","title":"Context-aware RNNLM Rescoring for Conversational Speech Recognition","display_name":"Context-aware RNNLM Rescoring for Conversational Speech Recognition","publication_year":2021,"publication_date":"2021-01-24","ids":{"openalex":"https://openalex.org/W3133595249","doi":"https://doi.org/10.1109/iscslp49672.2021.9362109","mag":"3133595249"},"language":"en","primary_location":{"id":"doi:10.1109/iscslp49672.2021.9362109","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iscslp49672.2021.9362109","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 12th International Symposium on Chinese Spoken Language Processing (ISCSLP)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5100649112","display_name":"Kun Wei","orcid":null},"institutions":[{"id":"https://openalex.org/I17145004","display_name":"Northwestern Polytechnical University","ror":"https://ror.org/01y0j0j86","country_code":"CN","type":"education","lineage":["https://openalex.org/I17145004"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Kun Wei","raw_affiliation_strings":["Northwestern Polytechnical University,Audio, Speech and Language Processing Group (ASLP@NPU), School of Computer Science,Xian,China","Audio, Speech and Language Processing Group (ASLP@NPU), School of Computer Science, Northwestern Polytechnical University, Xian, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Northwestern Polytechnical University,Audio, Speech and Language Processing Group (ASLP@NPU), School of Computer Science,Xian,China","institution_ids":["https://openalex.org/I17145004"]},{"raw_affiliation_string":"Audio, Speech and Language Processing Group (ASLP@NPU), School of Computer Science, Northwestern Polytechnical University, Xian, China","institution_ids":["https://openalex.org/I17145004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101783173","display_name":"Pengcheng Guo","orcid":"https://orcid.org/0009-0001-2388-5935"},"institutions":[{"id":"https://openalex.org/I17145004","display_name":"Northwestern Polytechnical University","ror":"https://ror.org/01y0j0j86","country_code":"CN","type":"education","lineage":["https://openalex.org/I17145004"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Pengcheng Guo","raw_affiliation_strings":["Northwestern Polytechnical University,Audio, Speech and Language Processing Group (ASLP@NPU), School of Computer Science,Xian,China","Audio, Speech and Language Processing Group (ASLP@NPU), School of Computer Science, Northwestern Polytechnical University, Xian, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Northwestern Polytechnical University,Audio, Speech and Language Processing Group (ASLP@NPU), School of Computer Science,Xian,China","institution_ids":["https://openalex.org/I17145004"]},{"raw_affiliation_string":"Audio, Speech and Language Processing Group (ASLP@NPU), School of Computer Science, Northwestern Polytechnical University, Xian, China","institution_ids":["https://openalex.org/I17145004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100751610","display_name":"Hang Lv","orcid":"https://orcid.org/0000-0003-3761-1684"},"institutions":[{"id":"https://openalex.org/I17145004","display_name":"Northwestern Polytechnical University","ror":"https://ror.org/01y0j0j86","country_code":"CN","type":"education","lineage":["https://openalex.org/I17145004"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hang Lv","raw_affiliation_strings":["Northwestern Polytechnical University,Audio, Speech and Language Processing Group (ASLP@NPU), School of Computer Science,Xian,China","Audio, Speech and Language Processing Group (ASLP@NPU), School of Computer Science, Northwestern Polytechnical University, Xian, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Northwestern Polytechnical University,Audio, Speech and Language Processing Group (ASLP@NPU), School of Computer Science,Xian,China","institution_ids":["https://openalex.org/I17145004"]},{"raw_affiliation_string":"Audio, Speech and Language Processing Group (ASLP@NPU), School of Computer Science, Northwestern Polytechnical University, Xian, China","institution_ids":["https://openalex.org/I17145004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5013394195","display_name":"Zhen Tu","orcid":"https://orcid.org/0000-0001-5431-6842"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhen Tu","raw_affiliation_strings":["Zhuiyi Technology,Shenzhen,China","Zhuiyi Technology, Shenzhen, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Zhuiyi Technology,Shenzhen,China","institution_ids":[]},{"raw_affiliation_string":"Zhuiyi Technology, Shenzhen, China","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100668966","display_name":"Lei Xie","orcid":"https://orcid.org/0000-0001-8234-0823"},"institutions":[{"id":"https://openalex.org/I17145004","display_name":"Northwestern Polytechnical University","ror":"https://ror.org/01y0j0j86","country_code":"CN","type":"education","lineage":["https://openalex.org/I17145004"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lei Xie","raw_affiliation_strings":["Northwestern Polytechnical University,Audio, Speech and Language Processing Group (ASLP@NPU), School of Computer Science,Xian,China","Audio, Speech and Language Processing Group (ASLP@NPU), School of Computer Science, Northwestern Polytechnical University, Xian, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Northwestern Polytechnical University,Audio, Speech and Language Processing Group (ASLP@NPU), School of Computer Science,Xian,China","institution_ids":["https://openalex.org/I17145004"]},{"raw_affiliation_string":"Audio, Speech and Language Processing Group (ASLP@NPU), School of Computer Science, Northwestern Polytechnical University, Xian, China","institution_ids":["https://openalex.org/I17145004"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.5861,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.66205174,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"5"},"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/T10860","display_name":"Speech and Audio Processing","score":0.9987000226974487,"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/T12031","display_name":"Speech and dialogue systems","score":0.9962999820709229,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8757020235061646},{"id":"https://openalex.org/keywords/conversation","display_name":"Conversation","score":0.7552030086517334},{"id":"https://openalex.org/keywords/concatenation","display_name":"Concatenation (mathematics)","score":0.6855159997940063},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6196576356887817},{"id":"https://openalex.org/keywords/decoding-methods","display_name":"Decoding methods","score":0.6031208038330078},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.5693128108978271},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.43946048617362976},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4380636513233185},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.4374101758003235},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.4310864210128784},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4071522355079651},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.1275109052658081},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.11245927214622498},{"id":"https://openalex.org/keywords/arithmetic","display_name":"Arithmetic","score":0.06693363189697266}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8757020235061646},{"id":"https://openalex.org/C2777200299","wikidata":"https://www.wikidata.org/wiki/Q52943","display_name":"Conversation","level":2,"score":0.7552030086517334},{"id":"https://openalex.org/C87619178","wikidata":"https://www.wikidata.org/wiki/Q126002","display_name":"Concatenation (mathematics)","level":2,"score":0.6855159997940063},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6196576356887817},{"id":"https://openalex.org/C57273362","wikidata":"https://www.wikidata.org/wiki/Q576722","display_name":"Decoding methods","level":2,"score":0.6031208038330078},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.5693128108978271},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.43946048617362976},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4380636513233185},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.4374101758003235},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.4310864210128784},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4071522355079651},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.1275109052658081},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.11245927214622498},{"id":"https://openalex.org/C94375191","wikidata":"https://www.wikidata.org/wiki/Q11205","display_name":"Arithmetic","level":1,"score":0.06693363189697266},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"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/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/iscslp49672.2021.9362109","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iscslp49672.2021.9362109","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 12th International Symposium on Chinese Spoken Language Processing (ISCSLP)","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":39,"referenced_works":["https://openalex.org/W82457882","https://openalex.org/W1524333225","https://openalex.org/W1526236009","https://openalex.org/W1665921526","https://openalex.org/W2127836646","https://openalex.org/W2166637769","https://openalex.org/W2275115695","https://openalex.org/W2345190899","https://openalex.org/W2402268235","https://openalex.org/W2403440562","https://openalex.org/W2404974730","https://openalex.org/W2474824677","https://openalex.org/W2514741789","https://openalex.org/W2747917286","https://openalex.org/W2775767017","https://openalex.org/W2782451907","https://openalex.org/W2802201485","https://openalex.org/W2802422770","https://openalex.org/W2888975141","https://openalex.org/W2889152503","https://openalex.org/W2916979304","https://openalex.org/W2936202865","https://openalex.org/W2936652946","https://openalex.org/W2951672049","https://openalex.org/W2963451498","https://openalex.org/W2964286182","https://openalex.org/W2972545188","https://openalex.org/W3007776460","https://openalex.org/W3095962459","https://openalex.org/W6603321172","https://openalex.org/W6631362777","https://openalex.org/W6713098461","https://openalex.org/W6713561562","https://openalex.org/W6720877245","https://openalex.org/W6731780175","https://openalex.org/W6747418505","https://openalex.org/W6747836893","https://openalex.org/W6751267225","https://openalex.org/W6761380950"],"related_works":["https://openalex.org/W1566315437","https://openalex.org/W2594897229","https://openalex.org/W4221142855","https://openalex.org/W2151348424","https://openalex.org/W2050138804","https://openalex.org/W767271433","https://openalex.org/W4290708361","https://openalex.org/W2129812225","https://openalex.org/W2523799048","https://openalex.org/W2155620340"],"abstract_inverted_index":{"Conversational":[0],"speech":[1],"recognition":[2],"is":[3],"regarded":[4],"as":[5,45,77],"a":[6,42,56,105],"challenging":[7],"task":[8],"due":[9],"to":[10,55,119,136],"its":[11],"free-style":[12],"speaking":[13],"and":[14,138,148],"long-term":[15],"contextual":[16,66,117],"dependencies.":[17],"Prior":[18],"work":[19],"has":[20],"explored":[21],"the":[22,38,52,65,85,94,113],"modeling":[23],"of":[24,37,87,116],"long-range":[25],"context":[26],"through":[27],"RNNLM":[28,61],"rescoring":[29,53],"with":[30,72,93,145],"improved":[31],"performance.":[32,122],"To":[33],"further":[34],"take":[35],"advantage":[36],"persisted":[39],"nature":[40],"during":[41],"conversation,":[43],"such":[44,76],"topics":[46],"or":[47,79],"speaker":[48,78],"turn,":[49],"we":[50,63,102],"extend":[51],"procedure":[54],"new":[57],"context-aware":[58],"manner.":[59],"For":[60,82],"training,":[62],"capture":[64],"dependencies":[67],"by":[68,98],"concatenating":[69],"adjacent":[70,88],"sentences":[71,89],"various":[73],"tag":[74,99],"words,":[75],"intention":[80],"information.":[81],"lattice":[83,86],"rescoring,":[84],"are":[90],"also":[91,103],"connected":[92],"first-pass":[95],"decoded":[96],"result":[97],"words.":[100],"Besides,":[101],"adopt":[104],"selective":[106],"concatenation":[107],"strategy":[108],"based":[109],"on":[110,124],"tf-idf,":[111],"making":[112],"best":[114],"use":[115],"similarity":[118],"improve":[120],"transcription":[121],"Results":[123],"four":[125],"different":[126],"conversation":[127],"test":[128],"sets":[129],"show":[130],"that":[131],"our":[132],"approach":[133],"yields":[134],"up":[135],"13.1%":[137],"6%":[139],"relative":[140],"char-error-rate":[141],"(CER)":[142],"reduction":[143],"compared":[144],"1st-pass":[146],"decoding":[147],"common":[149],"lattice-rescoring,":[150],"respectively.":[151]},"counts_by_year":[{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":3}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}