{"id":"https://openalex.org/W3196548933","doi":"https://doi.org/10.21437/interspeech.2021-690","title":"Residual Energy-Based Models for End-to-End Speech Recognition","display_name":"Residual Energy-Based Models for End-to-End Speech Recognition","publication_year":2021,"publication_date":"2021-08-27","ids":{"openalex":"https://openalex.org/W3196548933","doi":"https://doi.org/10.21437/interspeech.2021-690","mag":"3196548933"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2021-690","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2021-690","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2021","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/A5030757951","display_name":"Qiujia Li","orcid":"https://orcid.org/0000-0003-3074-3692"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Qiujia Li","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100433691","display_name":"Yu Zhang","orcid":"https://orcid.org/0000-0003-1100-4835"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yu Zhang","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101706071","display_name":"Bo Li","orcid":"https://orcid.org/0000-0003-3605-9437"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Bo Li","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103187717","display_name":"Liangliang Cao","orcid":"https://orcid.org/0000-0003-0900-1512"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Liangliang Cao","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5002191410","display_name":"Philip C. Woodland","orcid":"https://orcid.org/0000-0001-9069-0225"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Philip C. Woodland","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5030757951"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.2237,"has_fulltext":false,"cited_by_count":10,"citation_normalized_percentile":{"value":0.83386188,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"4069","last_page":"4073"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","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"}},"topics":[{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","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/T10181","display_name":"Natural Language Processing Techniques","score":0.9954000115394592,"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/T10028","display_name":"Topic Modeling","score":0.9876000285148621,"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/residual","display_name":"Residual","score":0.6954246759414673},{"id":"https://openalex.org/keywords/estimator","display_name":"Estimator","score":0.6761378645896912},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.560402512550354},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5159481167793274},{"id":"https://openalex.org/keywords/autoregressive-model","display_name":"Autoregressive model","score":0.4558897614479065},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3812461197376251},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.367426335811615},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.30573904514312744},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.25638917088508606}],"concepts":[{"id":"https://openalex.org/C155512373","wikidata":"https://www.wikidata.org/wiki/Q287450","display_name":"Residual","level":2,"score":0.6954246759414673},{"id":"https://openalex.org/C185429906","wikidata":"https://www.wikidata.org/wiki/Q1130160","display_name":"Estimator","level":2,"score":0.6761378645896912},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.560402512550354},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5159481167793274},{"id":"https://openalex.org/C159877910","wikidata":"https://www.wikidata.org/wiki/Q2202883","display_name":"Autoregressive model","level":2,"score":0.4558897614479065},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3812461197376251},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.367426335811615},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.30573904514312744},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.25638917088508606}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21437/interspeech.2021-690","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2021-690","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2021","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W2171218219","https://openalex.org/W1972271943","https://openalex.org/W4287880334","https://openalex.org/W2150410159","https://openalex.org/W2560215812","https://openalex.org/W4366700029","https://openalex.org/W4327525404","https://openalex.org/W4287185323","https://openalex.org/W3150905897","https://openalex.org/W4313645560"],"abstract_inverted_index":{"End-to-end":[0],"models":[1,15,40],"with":[2],"auto-regressive":[3,74],"decoders":[4],"have":[5],"shown":[6],"impressive":[7],"results":[8],"for":[9],"automatic":[10],"speech":[11],"recognition":[12],"(ASR).":[13],"These":[14],"formulate":[16],"the":[17,24,35,52,57,64,73,79,82,112,148],"sequence-level":[18],"probability":[19],"as":[20,48,91],"a":[21,103,135],"product":[22],"of":[23,27,37,45,125],"conditional":[25],"probabilities":[26],"all":[28],"individual":[29],"tokens":[30],"given":[31],"their":[32],"histories.":[33],"However,":[34],"performance":[36],"locally":[38],"normalised":[39],"can":[41,87,110],"be":[42,89],"sub-optimal":[43],"because":[44],"factors":[46],"such":[47],"exposure":[49],"bias.":[50],"Consequently,":[51],"model":[53,67,76,137],"distribution":[54],"differs":[55],"from":[56],"underlying":[58],"data":[59],"distribution.":[60],"In":[61],"this":[62],"paper,":[63],"residual":[65],"energy-based":[66],"(R-EBM)":[68],"is":[69],"proposed":[70],"to":[71,77],"complement":[72],"ASR":[75],"close":[78],"gap":[80],"between":[81],"two":[83],"distributions.":[84],"Meanwhile,":[85],"R-EBMs":[86,109,143],"also":[88],"regarded":[90],"utterance-level":[92],"confidence":[93,126,151],"estimators,":[94],"which":[95],"may":[96],"benefit":[97],"many":[98],"downstream":[99],"tasks.":[100],"Experiments":[101],"on":[102,130,134],"100hr":[104],"LibriSpeech":[105],"dataset":[106],"show":[107],"that":[108],"reduce":[111],"word":[113],"error":[114],"rates":[115],"(WERs)":[116],"by":[117,128],"8.2%/6.7%":[118],"while":[119],"improving":[120],"areas":[121],"under":[122],"precision-recall":[123],"curves":[124],"scores":[127],"12.6%/28.4%":[129],"test-clean/test-other":[131],"sets.":[132],"Furthermore,":[133],"state-of-the-art":[136],"using":[138],"self-supervised":[139],"learning":[140],"(wav2vec":[141],"2.0),":[142],"still":[144],"significantly":[145],"improves":[146],"both":[147],"WER":[149],"and":[150],"estimation":[152],"performance.":[153]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}