{"id":"https://openalex.org/W2289121263","doi":"https://doi.org/10.1109/apsipa.2015.7415462","title":"Integrating prosodic information into recurrent neural network language model for speech recognition","display_name":"Integrating prosodic information into recurrent neural network language model for speech recognition","publication_year":2015,"publication_date":"2015-12-01","ids":{"openalex":"https://openalex.org/W2289121263","doi":"https://doi.org/10.1109/apsipa.2015.7415462","mag":"2289121263"},"language":"en","primary_location":{"id":"doi:10.1109/apsipa.2015.7415462","is_oa":false,"landing_page_url":"https://doi.org/10.1109/apsipa.2015.7415462","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2015 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA)","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/A5050157606","display_name":"Tong Fu","orcid":null},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Tong Fu","raw_affiliation_strings":["Speech and Hearing Research Center, Peking University, Beijing"],"affiliations":[{"raw_affiliation_string":"Speech and Hearing Research Center, Peking University, Beijing","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5055058218","display_name":"Han Yang","orcid":"https://orcid.org/0000-0003-4469-6743"},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yang Han","raw_affiliation_strings":["Speech and Hearing Research Center, Peking University, Beijing"],"affiliations":[{"raw_affiliation_string":"Speech and Hearing Research Center, Peking University, Beijing","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5081173423","display_name":"Xiangang Li","orcid":"https://orcid.org/0000-0002-7810-1077"},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiangang Li","raw_affiliation_strings":["Speech and Hearing Research Center, Peking University, Beijing"],"affiliations":[{"raw_affiliation_string":"Speech and Hearing Research Center, Peking University, Beijing","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100330618","display_name":"Yi Liu","orcid":"https://orcid.org/0000-0003-1399-7420"},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yi Liu","raw_affiliation_strings":["Speech and Hearing Research Center, Peking University, Beijing"],"affiliations":[{"raw_affiliation_string":"Speech and Hearing Research Center, Peking University, Beijing","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5084685506","display_name":"Xihong Wu","orcid":"https://orcid.org/0009-0004-5236-7469"},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xihong Wu","raw_affiliation_strings":["Speech and Hearing Research Center, Peking University, Beijing"],"affiliations":[{"raw_affiliation_string":"Speech and Hearing Research Center, Peking University, Beijing","institution_ids":["https://openalex.org/I20231570"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5050157606"],"corresponding_institution_ids":["https://openalex.org/I20231570"],"apc_list":null,"apc_paid":null,"fwci":1.7258,"has_fulltext":false,"cited_by_count":9,"citation_normalized_percentile":{"value":0.88938897,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":97},"biblio":{"volume":"3","issue":null,"first_page":"1194","last_page":"1197"},"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":0.9987000226974487,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.996399998664856,"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":0.8073993921279907},{"id":"https://openalex.org/keywords/prosody","display_name":"Prosody","score":0.7854436039924622},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7426082491874695},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.7386825084686279},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.6310857534408569},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.5671697854995728},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5103999972343445},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5090968012809753},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.48274725675582886},{"id":"https://openalex.org/keywords/acoustic-model","display_name":"Acoustic model","score":0.47323712706565857},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.4731646180152893},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.32451796531677246},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.13450846076011658}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8073993921279907},{"id":"https://openalex.org/C542774811","wikidata":"https://www.wikidata.org/wiki/Q10880526","display_name":"Prosody","level":2,"score":0.7854436039924622},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7426082491874695},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.7386825084686279},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.6310857534408569},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.5671697854995728},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5103999972343445},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5090968012809753},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.48274725675582886},{"id":"https://openalex.org/C155635449","wikidata":"https://www.wikidata.org/wiki/Q4674699","display_name":"Acoustic model","level":3,"score":0.47323712706565857},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.4731646180152893},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.32451796531677246},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.13450846076011658},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/apsipa.2015.7415462","is_oa":false,"landing_page_url":"https://doi.org/10.1109/apsipa.2015.7415462","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2015 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.5799999833106995,"display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":28,"referenced_works":["https://openalex.org/W62658503","https://openalex.org/W179875071","https://openalex.org/W1493946344","https://openalex.org/W1494198834","https://openalex.org/W1494802605","https://openalex.org/W1524333225","https://openalex.org/W1528486167","https://openalex.org/W1597422500","https://openalex.org/W1600591519","https://openalex.org/W1970689298","https://openalex.org/W1999965501","https://openalex.org/W2085628288","https://openalex.org/W2110485445","https://openalex.org/W2116324305","https://openalex.org/W2141885148","https://openalex.org/W2147794814","https://openalex.org/W2160815625","https://openalex.org/W2265370285","https://openalex.org/W2998704965","https://openalex.org/W4254816979","https://openalex.org/W4285719527","https://openalex.org/W6602519137","https://openalex.org/W6631362777","https://openalex.org/W6631440866","https://openalex.org/W6635774499","https://openalex.org/W6636111528","https://openalex.org/W6680532216","https://openalex.org/W6996569244"],"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/W4290708361","https://openalex.org/W2126322296","https://openalex.org/W2129812225","https://openalex.org/W2523799048","https://openalex.org/W2244609359"],"abstract_inverted_index":{"Prosody":[0],"is":[1,17,36,124],"a":[2,29],"kind":[3],"of":[4,31],"cues":[5],"that":[6,111],"are":[7,82],"critical":[8],"to":[9,19,38,50,62,89,119],"human":[10],"speech":[11,25,70,85],"perception":[12],"and":[13,86,102,128,133],"comprehension,":[14],"so":[15],"it":[16,35],"plausible":[18],"integrate":[20,39,63],"prosodic":[21,40,64,80,100,122],"information":[22,41,65,123],"into":[23,66],"machine":[24],"recognition.":[26],"However,":[27],"as":[28],"result":[30],"the":[32,52,95,112],"supra-segmental":[33],"nature,":[34],"hard":[37],"with":[42],"conventional":[43],"acoustic":[44],"features.":[45],"Recently,":[46],"RNNLMs":[47,67,90,93],"have":[48],"shown":[49],"be":[51],"state-of-the-art":[53],"language":[54],"model":[55],"in":[56],"many":[57],"tasks.":[58],"We":[59],"thus":[60],"attempt":[61],"for":[68,130],"improving":[69],"recognition":[71],"performance":[72],"based":[73,98],"on":[74,99,107,126],"rescoring":[75],"strategy.":[76],"Firstly,":[77],"three":[78],"word-level":[79],"features":[81,101],"extracted":[83],"from":[84,117],"then":[87],"passed":[88],"separately.":[91],"Therefore":[92],"predict":[94],"next":[96],"word":[97,103,113,134],"history.":[104],"Experiments":[105],"conducted":[106],"LibriSpeech":[108],"Corpus":[109],"show":[110],"error":[114,135],"rate":[115,136],"decreases":[116,137],"8.07%":[118],"7.96%.":[120],"Secondly,":[121],"combined":[125],"feature-level":[127],"model-level":[129],"further":[131],"improvements":[132],"4.71%":[138],"relatively.":[139]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":2},{"year":2018,"cited_by_count":1},{"year":2017,"cited_by_count":3}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}