{"id":"https://openalex.org/W2890817076","doi":"https://doi.org/10.1109/icassp.2018.8461405","title":"Rescoring N-Best Speech Recognition List Based on One-on-One Hypothesis Comparison Using Encoder-Classifier Model","display_name":"Rescoring N-Best Speech Recognition List Based on One-on-One Hypothesis Comparison Using Encoder-Classifier Model","publication_year":2018,"publication_date":"2018-04-01","ids":{"openalex":"https://openalex.org/W2890817076","doi":"https://doi.org/10.1109/icassp.2018.8461405","mag":"2890817076"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2018.8461405","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2018.8461405","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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/A5101949937","display_name":"Atsunori Ogawa","orcid":"https://orcid.org/0000-0002-2888-101X"},"institutions":[{"id":"https://openalex.org/I2251713219","display_name":"NTT (Japan)","ror":"https://ror.org/00berct97","country_code":"JP","type":"company","lineage":["https://openalex.org/I2251713219"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Atsunori Ogawa","raw_affiliation_strings":["NTT Communication Science Laboratories, NTT Corporation, Kyoto, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NTT Communication Science Laboratories, NTT Corporation, Kyoto, Japan","institution_ids":["https://openalex.org/I2251713219"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5023868166","display_name":"Marc Delcroix","orcid":"https://orcid.org/0000-0002-5175-7834"},"institutions":[{"id":"https://openalex.org/I2251713219","display_name":"NTT (Japan)","ror":"https://ror.org/00berct97","country_code":"JP","type":"company","lineage":["https://openalex.org/I2251713219"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Marc Delcroix","raw_affiliation_strings":["NTT Communication Science Laboratories, NTT Corporation, Kyoto, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NTT Communication Science Laboratories, NTT Corporation, Kyoto, Japan","institution_ids":["https://openalex.org/I2251713219"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5036532214","display_name":"Shigeki Karita","orcid":null},"institutions":[{"id":"https://openalex.org/I2251713219","display_name":"NTT (Japan)","ror":"https://ror.org/00berct97","country_code":"JP","type":"company","lineage":["https://openalex.org/I2251713219"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Shigeki Karita","raw_affiliation_strings":["NTT Communication Science Laboratories, NTT Corporation, Kyoto, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NTT Communication Science Laboratories, NTT Corporation, Kyoto, Japan","institution_ids":["https://openalex.org/I2251713219"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5021240106","display_name":"Tomohiro Nakatani","orcid":"https://orcid.org/0000-0002-7487-7150"},"institutions":[{"id":"https://openalex.org/I2251713219","display_name":"NTT (Japan)","ror":"https://ror.org/00berct97","country_code":"JP","type":"company","lineage":["https://openalex.org/I2251713219"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Tomohiro Nakatani","raw_affiliation_strings":["NTT Communication Science Laboratories, NTT Corporation, Kyoto, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NTT Communication Science Laboratories, NTT Corporation, Kyoto, Japan","institution_ids":["https://openalex.org/I2251713219"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I2251713219"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":23,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"6099","last_page":"6103"},"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9993000030517578,"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":0.9983000159263611,"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/computer-science","display_name":"Computer science","score":0.7958484292030334},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.6945115327835083},{"id":"https://openalex.org/keywords/classifier","display_name":"Classifier (UML)","score":0.6600626111030579},{"id":"https://openalex.org/keywords/binary-number","display_name":"Binary number","score":0.615878701210022},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5483343601226807},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.547883152961731},{"id":"https://openalex.org/keywords/binary-classification","display_name":"Binary classification","score":0.5469233989715576},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.5160683989524841},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.5128908157348633},{"id":"https://openalex.org/keywords/feature-vector","display_name":"Feature vector","score":0.49540746212005615},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.48314613103866577},{"id":"https://openalex.org/keywords/feed-forward","display_name":"Feed forward","score":0.4400934875011444},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.4360806941986084},{"id":"https://openalex.org/keywords/support-vector-machine","display_name":"Support vector machine","score":0.2191375494003296},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.0788547694683075},{"id":"https://openalex.org/keywords/arithmetic","display_name":"Arithmetic","score":0.06625938415527344}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7958484292030334},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.6945115327835083},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.6600626111030579},{"id":"https://openalex.org/C48372109","wikidata":"https://www.wikidata.org/wiki/Q3913","display_name":"Binary number","level":2,"score":0.615878701210022},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5483343601226807},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.547883152961731},{"id":"https://openalex.org/C66905080","wikidata":"https://www.wikidata.org/wiki/Q17005494","display_name":"Binary classification","level":3,"score":0.5469233989715576},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5160683989524841},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.5128908157348633},{"id":"https://openalex.org/C83665646","wikidata":"https://www.wikidata.org/wiki/Q42139305","display_name":"Feature vector","level":2,"score":0.49540746212005615},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.48314613103866577},{"id":"https://openalex.org/C38858127","wikidata":"https://www.wikidata.org/wiki/Q5441228","display_name":"Feed forward","level":2,"score":0.4400934875011444},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.4360806941986084},{"id":"https://openalex.org/C12267149","wikidata":"https://www.wikidata.org/wiki/Q282453","display_name":"Support vector machine","level":2,"score":0.2191375494003296},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0788547694683075},{"id":"https://openalex.org/C94375191","wikidata":"https://www.wikidata.org/wiki/Q11205","display_name":"Arithmetic","level":1,"score":0.06625938415527344},{"id":"https://openalex.org/C133731056","wikidata":"https://www.wikidata.org/wiki/Q4917288","display_name":"Control engineering","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/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp.2018.8461405","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2018.8461405","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions","score":0.5099999904632568}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":44,"referenced_works":["https://openalex.org/W169474520","https://openalex.org/W179875071","https://openalex.org/W330298975","https://openalex.org/W1522301498","https://openalex.org/W1566877644","https://openalex.org/W1586532344","https://openalex.org/W1975244201","https://openalex.org/W1986767396","https://openalex.org/W1992475611","https://openalex.org/W2005733316","https://openalex.org/W2114912785","https://openalex.org/W2121127625","https://openalex.org/W2130942839","https://openalex.org/W2138889249","https://openalex.org/W2146574666","https://openalex.org/W2158025800","https://openalex.org/W2160815625","https://openalex.org/W2171928131","https://openalex.org/W2327501763","https://openalex.org/W2396464458","https://openalex.org/W2402268235","https://openalex.org/W2408583661","https://openalex.org/W2559260703","https://openalex.org/W2594395650","https://openalex.org/W2594610113","https://openalex.org/W2741823585","https://openalex.org/W2752061190","https://openalex.org/W2963399332","https://openalex.org/W3034729383","https://openalex.org/W3112742522","https://openalex.org/W6606997094","https://openalex.org/W6607333740","https://openalex.org/W6631190155","https://openalex.org/W6633879194","https://openalex.org/W6635078382","https://openalex.org/W6676903530","https://openalex.org/W6679436768","https://openalex.org/W6681671106","https://openalex.org/W6713098461","https://openalex.org/W6714233413","https://openalex.org/W6744529318","https://openalex.org/W6766224279","https://openalex.org/W6779469704","https://openalex.org/W6787533431"],"related_works":["https://openalex.org/W2594897229","https://openalex.org/W2151348424","https://openalex.org/W4221142855","https://openalex.org/W2050138804","https://openalex.org/W4290708361","https://openalex.org/W2129812225","https://openalex.org/W26527944","https://openalex.org/W2523799048","https://openalex.org/W2155620340","https://openalex.org/W2944691285"],"abstract_inverted_index":{"This":[0],"paper":[1],"proposes":[2],"a":[3,39,55,64,120,132,150,184],"new":[4],"model":[5,16,51,85,140,146,175,182],"for":[6],"accurately":[7],"rescoring":[8,129,170],"(reranking)":[9],"N-best":[10,32,41,122,128,169],"speech":[11,135],"recognition":[12],"hypothesis":[13,36,96,118],"lists.":[14],"The":[15,50,179],"is":[17,52,149,176],"based":[18],"on":[19,38,103],"state-of-the-art":[20],"neural":[21],"networks":[22],"(NNs)":[23],"and":[24,89,152],"provides":[25],"the":[26,72,98,104,106,137,159,168,173,190],"minimum":[27],"necessary":[28],"functionality":[29],"to":[30,79],"perform":[31],"rescoring,":[33],"i.e.":[34],"one-on-one":[35,117],"comparison":[37],"given":[40],"list":[42,123],"in":[43],"terms":[44],"of":[45,54,76,108,172],"word":[46],"error":[47],"rates":[48],"(WERs).":[49],"composed":[53],"long":[56],"short-term":[57],"memory":[58],"(LSTM)-based":[59],"encoder":[60],"network":[61],"followed":[62],"by":[63,157],"fully-connected":[65],"feedforward":[66],"NN-based":[67],"binary-class":[68,91],"classifier":[69],"network.":[70],"Given":[71],"feature":[73,165],"vector":[74,166],"sequences":[75],"two":[77],"hypotheses":[78,110],"be":[80,112,125],"compared,":[81],"this":[82,116],"encoder-classifier":[83],"(EC)":[84],"encodes":[86],"these":[87,109],"features":[88],"outputs":[90],"probabilities":[92],"that":[93],"indicate":[94],"which":[95,148],"has":[97],"lower":[99],"WER.":[100],"Then,":[101],"depending":[102],"output,":[105],"ranks":[107],"can":[111,124],"swapped.":[113],"By":[114],"repeating":[115],"comparison,":[119],"reranked":[121],"obtained.":[126],"In":[127,155],"experiments":[130],"using":[131],"large":[133],"scale":[134],"corpus,":[136],"proposed":[138],"EC":[139,174,181],"steadily":[141],"outperforms":[142],"an":[143,163],"LSTM-based":[144],"language":[145],"(LSTMLM),":[147],"strong":[151],"widely-used":[153],"competitor.":[154],"addition,":[156],"incorporating":[158],"LSTMLM":[160,191],"scores":[161],"as":[162],"additional":[164],"dimension,":[167],"performance":[171],"further":[177],"improved.":[178],"improved":[180],"achieves":[183],"10%":[185],"relative":[186],"WER":[187],"reduction":[188],"from":[189],"baseline.":[192]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":4},{"year":2021,"cited_by_count":8},{"year":2020,"cited_by_count":5},{"year":2019,"cited_by_count":3}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}