{"id":"https://openalex.org/W3095373628","doi":"https://doi.org/10.21437/interspeech.2020-1881","title":"Neural Zero-Inflated Quality Estimation Model for Automatic Speech Recognition System","display_name":"Neural Zero-Inflated Quality Estimation Model for Automatic Speech Recognition System","publication_year":2020,"publication_date":"2020-10-25","ids":{"openalex":"https://openalex.org/W3095373628","doi":"https://doi.org/10.21437/interspeech.2020-1881","mag":"3095373628"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2020-1881","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2020-1881","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2020","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/A5055225377","display_name":"Kai Fan","orcid":"https://orcid.org/0000-0002-8256-0807"},"institutions":[{"id":"https://openalex.org/I4210095624","display_name":"Alibaba Group (United States)","ror":"https://ror.org/00rn0m335","country_code":"US","type":"company","lineage":["https://openalex.org/I4210095624","https://openalex.org/I45928872"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Kai Fan","raw_affiliation_strings":["Alibaba Group Inc"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Alibaba Group Inc","institution_ids":["https://openalex.org/I4210095624"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100374360","display_name":"Bo Li","orcid":"https://orcid.org/0000-0001-6709-0942"},"institutions":[{"id":"https://openalex.org/I4210095624","display_name":"Alibaba Group (United States)","ror":"https://ror.org/00rn0m335","country_code":"US","type":"company","lineage":["https://openalex.org/I4210095624","https://openalex.org/I45928872"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Bo Li","raw_affiliation_strings":["Alibaba Group Inc"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Alibaba Group Inc","institution_ids":["https://openalex.org/I4210095624"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100449263","display_name":"Jiayi Wang","orcid":"https://orcid.org/0000-0002-7785-3381"},"institutions":[{"id":"https://openalex.org/I4210095624","display_name":"Alibaba Group (United States)","ror":"https://ror.org/00rn0m335","country_code":"US","type":"company","lineage":["https://openalex.org/I4210095624","https://openalex.org/I45928872"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jiayi Wang","raw_affiliation_strings":["Alibaba Group Inc"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Alibaba Group Inc","institution_ids":["https://openalex.org/I4210095624"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101777591","display_name":"Shiliang Zhang","orcid":"https://orcid.org/0000-0002-9524-1602"},"institutions":[{"id":"https://openalex.org/I4210095624","display_name":"Alibaba Group (United States)","ror":"https://ror.org/00rn0m335","country_code":"US","type":"company","lineage":["https://openalex.org/I4210095624","https://openalex.org/I45928872"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Shiliang Zhang","raw_affiliation_strings":["Alibaba Group Inc"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Alibaba Group Inc","institution_ids":["https://openalex.org/I4210095624"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5019715118","display_name":"Boxing Chen","orcid":"https://orcid.org/0000-0002-3170-4858"},"institutions":[{"id":"https://openalex.org/I4210095624","display_name":"Alibaba Group (United States)","ror":"https://ror.org/00rn0m335","country_code":"US","type":"company","lineage":["https://openalex.org/I4210095624","https://openalex.org/I45928872"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Boxing Chen","raw_affiliation_strings":["Alibaba Group Inc"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Alibaba Group Inc","institution_ids":["https://openalex.org/I4210095624"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5016546383","display_name":"Niyu Ge","orcid":null},"institutions":[{"id":"https://openalex.org/I4210095624","display_name":"Alibaba Group (United States)","ror":"https://ror.org/00rn0m335","country_code":"US","type":"company","lineage":["https://openalex.org/I4210095624","https://openalex.org/I45928872"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Niyu Ge","raw_affiliation_strings":["Alibaba Group Inc"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Alibaba Group Inc","institution_ids":["https://openalex.org/I4210095624"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5061850214","display_name":"Zhijie Yan","orcid":"https://orcid.org/0000-0001-8065-0748"},"institutions":[{"id":"https://openalex.org/I4210095624","display_name":"Alibaba Group (United States)","ror":"https://ror.org/00rn0m335","country_code":"US","type":"company","lineage":["https://openalex.org/I4210095624","https://openalex.org/I45928872"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Zhijie Yan","raw_affiliation_strings":["Alibaba Group Inc"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Alibaba Group Inc","institution_ids":["https://openalex.org/I4210095624"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I4210095624"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"606","last_page":"610"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10320","display_name":"Neural Networks and Applications","score":0.8802000284194946,"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/T10320","display_name":"Neural Networks and Applications","score":0.8802000284194946,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.8180999755859375,"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/T13717","display_name":"Advanced Algorithms and Applications","score":0.7644000053405762,"subfield":{"id":"https://openalex.org/subfields/2207","display_name":"Control and Systems Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7445337176322937},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7380276918411255},{"id":"https://openalex.org/keywords/zero","display_name":"Zero (linguistics)","score":0.565794825553894},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5013246536254883},{"id":"https://openalex.org/keywords/quality","display_name":"Quality (philosophy)","score":0.4310445487499237},{"id":"https://openalex.org/keywords/estimation","display_name":"Estimation","score":0.42519310116767883},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.4243625998497009},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.4211879372596741},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3932691812515259},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.08748286962509155}],"concepts":[{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7445337176322937},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7380276918411255},{"id":"https://openalex.org/C2780813799","wikidata":"https://www.wikidata.org/wiki/Q3274237","display_name":"Zero (linguistics)","level":2,"score":0.565794825553894},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5013246536254883},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.4310445487499237},{"id":"https://openalex.org/C96250715","wikidata":"https://www.wikidata.org/wiki/Q965330","display_name":"Estimation","level":2,"score":0.42519310116767883},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.4243625998497009},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.4211879372596741},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3932691812515259},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.08748286962509155},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","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/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21437/interspeech.2020-1881","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2020-1881","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2020","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":24,"referenced_works":["https://openalex.org/W179875071","https://openalex.org/W1485103818","https://openalex.org/W1524333225","https://openalex.org/W2005708641","https://openalex.org/W2097978681","https://openalex.org/W2136811424","https://openalex.org/W2184045248","https://openalex.org/W2289394825","https://openalex.org/W2517015344","https://openalex.org/W2573658159","https://openalex.org/W2613253298","https://openalex.org/W2798685342","https://openalex.org/W2892009249","https://openalex.org/W2896457183","https://openalex.org/W2897945220","https://openalex.org/W2902463012","https://openalex.org/W2914120296","https://openalex.org/W2951635603","https://openalex.org/W2963380677","https://openalex.org/W2963824830","https://openalex.org/W2970690146","https://openalex.org/W2972981900","https://openalex.org/W3103076024","https://openalex.org/W4385245566"],"related_works":["https://openalex.org/W2136763963","https://openalex.org/W2109705048","https://openalex.org/W2940588515","https://openalex.org/W1909151225","https://openalex.org/W3184123547","https://openalex.org/W2160030256","https://openalex.org/W1521297879","https://openalex.org/W4253235840","https://openalex.org/W3151937861","https://openalex.org/W2488941600"],"abstract_inverted_index":{"The":[0],"performances":[1],"of":[2,38,69,85,99,114,134],"automatic":[3],"speech":[4,107],"recognition":[5],"(ASR)":[6],"systems":[7,43],"are":[8,23],"usually":[9,44],"evaluated":[10],"by":[11],"the":[12,19,31,35,66,83,86,111,132],"metric":[13],"word":[14],"error":[15],"rate":[16],"(WER)":[17],"when":[18],"manually":[20],"transcribed":[21],"data":[22],"provided,":[24],"which":[25],"are,":[26],"however,":[27],"expensively":[28],"available":[29],"in":[30],"real":[32],"scenario.In":[33],"addition,":[34],"empirical":[36],"distribution":[37],"WER":[39,84,149],"for":[40,120,131],"most":[41],"ASR":[42,70,87],"tends":[45],"to":[46,56,64,81],"put":[47],"a":[48,59,76,92,100],"significant":[49],"mass":[50],"near":[51],"zero,":[52],"making":[53],"it":[54],"difficult":[55],"simulate":[57],"with":[58,127,152],"single":[60],"continuous":[61,137],"distribution.In":[62],"order":[63],"address":[65],"two":[67],"issues":[68],"quality":[71],"estimation":[72],"(QE),":[73],"we":[74],"propose":[75],"novel":[77],"neural":[78,93],"zero-inflated":[79,129],"model":[80,104],"predict":[82],"result":[88],"without":[89],"transcripts.We":[90],"design":[91],"zeroinflated":[94],"beta":[95],"regression":[96],"on":[97,106,148],"top":[98],"bidirectional":[101],"transformer":[102],"language":[103,118],"conditional":[105],"features":[108],"(speech-BERT).We":[109],"adopt":[110],"pre-training":[112],"strategy":[113],"token":[115],"level":[116],"masked":[117],"modeling":[119],"speech-BERT":[121],"as":[122],"well,":[123],"and":[124,136],"further":[125],"fine-tune":[126],"our":[128,143],"layer":[130],"mixture":[133],"discrete":[135],"outputs.The":[138],"experimental":[139],"results":[140],"show":[141],"that":[142],"approach":[144],"achieves":[145],"better":[146],"performance":[147],"prediction":[150],"compared":[151],"strong":[153],"baselines.":[154]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2023,"cited_by_count":4}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}