{"id":"https://openalex.org/W2936401635","doi":"https://doi.org/10.1109/icassp.2019.8683088","title":"Learning Discriminative Features in Sequence Training without Requiring Framewise Labelled Data","display_name":"Learning Discriminative Features in Sequence Training without Requiring Framewise Labelled Data","publication_year":2019,"publication_date":"2019-04-17","ids":{"openalex":"https://openalex.org/W2936401635","doi":"https://doi.org/10.1109/icassp.2019.8683088","mag":"2936401635"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2019.8683088","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2019.8683088","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2019 - 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"type":"preprint","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/A5100384686","display_name":"Jun Wang","orcid":"https://orcid.org/0000-0002-1305-5735"},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Jun Wang","raw_affiliation_strings":["Tencent AI Lab, Shenzhen, China"],"affiliations":[{"raw_affiliation_string":"Tencent AI Lab, Shenzhen, China","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101913303","display_name":"Dan Su","orcid":"https://orcid.org/0000-0003-0072-0967"},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Dan Su","raw_affiliation_strings":["Tencent AI Lab, Shenzhen, China"],"affiliations":[{"raw_affiliation_string":"Tencent AI Lab, Shenzhen, China","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100332817","display_name":"Jie Chen","orcid":"https://orcid.org/0000-0001-5351-1136"},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jie Chen","raw_affiliation_strings":["Tencent AI Lab, Shenzhen, China"],"affiliations":[{"raw_affiliation_string":"Tencent AI Lab, Shenzhen, China","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5018718403","display_name":"Shulin Feng","orcid":"https://orcid.org/0000-0002-2437-6227"},"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":"Shulin Feng","raw_affiliation_strings":["Key Laboratory on Machine Perception, Peking University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Key Laboratory on Machine Perception, Peking University, Beijing, China","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5082253092","display_name":"Dongpeng Ma","orcid":null},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Dongpeng Ma","raw_affiliation_strings":["Tencent AI Lab, Shenzhen, China"],"affiliations":[{"raw_affiliation_string":"Tencent AI Lab, Shenzhen, China","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5114488748","display_name":"Na Li","orcid":"https://orcid.org/0000-0003-4538-1663"},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Na Li","raw_affiliation_strings":["Tencent AI Lab, Shenzhen, China"],"affiliations":[{"raw_affiliation_string":"Tencent AI Lab, Shenzhen, China","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5034476404","display_name":"Dong Yu","orcid":"https://orcid.org/0000-0003-0520-6844"},"institutions":[{"id":"https://openalex.org/I4210108985","display_name":"Bellevue Hospital Center","ror":"https://ror.org/01ky34z31","country_code":"US","type":"healthcare","lineage":["https://openalex.org/I1283621791","https://openalex.org/I4210086933","https://openalex.org/I4210108985"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Dong Yu","raw_affiliation_strings":["Tencent AI Lab, Bellevue, WA, USA"],"affiliations":[{"raw_affiliation_string":"Tencent AI Lab, Bellevue, WA, USA","institution_ids":["https://openalex.org/I4210108985"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5100384686"],"corresponding_institution_ids":["https://openalex.org/I2250653659"],"apc_list":null,"apc_paid":null,"fwci":0.21377151,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.51603117,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"5696","last_page":"5700"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10601","display_name":"Handwritten Text Recognition Techniques","score":0.9994000196456909,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/T10601","display_name":"Handwritten Text Recognition Techniques","score":0.9994000196456909,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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":0.996399998664856,"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"}},{"id":"https://openalex.org/T10057","display_name":"Face and Expression Recognition","score":0.9890999794006348,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/discriminative-model","display_name":"Discriminative model","score":0.8784275054931641},{"id":"https://openalex.org/keywords/sequence","display_name":"Sequence (biology)","score":0.6763932108879089},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6713441014289856},{"id":"https://openalex.org/keywords/training","display_name":"Training (meteorology)","score":0.6315077543258667},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5856657028198242},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.48398447036743164},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.423796147108078},{"id":"https://openalex.org/keywords/geography","display_name":"Geography","score":0.08364927768707275}],"concepts":[{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.8784275054931641},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.6763932108879089},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6713441014289856},{"id":"https://openalex.org/C2777211547","wikidata":"https://www.wikidata.org/wiki/Q17141490","display_name":"Training (meteorology)","level":2,"score":0.6315077543258667},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5856657028198242},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.48398447036743164},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.423796147108078},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.08364927768707275},{"id":"https://openalex.org/C153294291","wikidata":"https://www.wikidata.org/wiki/Q25261","display_name":"Meteorology","level":1,"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/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp.2019.8683088","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2019.8683088","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2019 - 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Reduced inequalities","id":"https://metadata.un.org/sdg/10","score":0.7599999904632568}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":31,"referenced_works":["https://openalex.org/W1976637928","https://openalex.org/W2010023285","https://openalex.org/W2062164080","https://openalex.org/W2079623482","https://openalex.org/W2096733369","https://openalex.org/W2114016253","https://openalex.org/W2117678320","https://openalex.org/W2118497033","https://openalex.org/W2125234026","https://openalex.org/W2127141656","https://openalex.org/W2131342762","https://openalex.org/W2138621090","https://openalex.org/W2144172034","https://openalex.org/W2213952365","https://openalex.org/W2293009711","https://openalex.org/W2294245963","https://openalex.org/W2514741789","https://openalex.org/W2888897023","https://openalex.org/W2889385246","https://openalex.org/W2892034016","https://openalex.org/W2962898354","https://openalex.org/W2963466847","https://openalex.org/W2964138484","https://openalex.org/W3099206234","https://openalex.org/W6678457041","https://openalex.org/W6679429981","https://openalex.org/W6681239517","https://openalex.org/W6688428952","https://openalex.org/W6696829052","https://openalex.org/W6696982659","https://openalex.org/W6748257384"],"related_works":["https://openalex.org/W2965546495","https://openalex.org/W4389116644","https://openalex.org/W2153315159","https://openalex.org/W3103844505","https://openalex.org/W2404514746","https://openalex.org/W1652783584","https://openalex.org/W2082783427","https://openalex.org/W4394050964","https://openalex.org/W3172695526","https://openalex.org/W2551249631"],"abstract_inverted_index":{"In":[0],"this":[1],"work,":[2],"we":[3],"try":[4],"to":[5,21,26,56,163],"answer":[6],"two":[7],"questions:":[8],"Can":[9],"deeply":[10],"learned":[11],"features":[12,92],"with":[13,143],"discriminative":[14,73,78,90],"power":[15],"benefit":[16],"an":[17],"ASR":[18,110],"system's":[19],"robustness":[20],"acoustic":[22,164],"variability?":[23],"And":[24],"how":[25],"learn":[27,89],"them":[28],"without":[29,114],"requiring":[30,115],"framewise":[31],"labelled":[32],"sequence":[33,59,72,94],"training":[34,74,95,102],"data?":[35],"As":[36],"existing":[37],"methods":[38],"usually":[39],"require":[40],"knowing":[41],"where":[42],"the":[43,47,71,76,98],"labels":[44],"occur":[45],"in":[46,93,106],"input":[48],"sequence,":[49],"they":[50],"have":[51,125],"so":[52,85],"far":[53],"been":[54],"limited":[55],"many":[57],"real-world":[58],"learning":[60,79],"tasks.":[61],"We":[62],"propose":[63],"a":[64,81,107],"novel":[65],"method":[66],"which":[67],"simultaneously":[68],"models":[69,124,129,159],"both":[70],"and":[75,130,141,154],"feature":[77],"within":[80],"single":[82],"network":[83],"architecture,":[84],"that":[86,96],"it":[87],"can":[88,160],"deep":[91],"obviates":[97],"need":[99],"for":[100],"presegmented":[101],"data.":[103],"Our":[104],"experiment":[105],"realistic":[108],"industrial":[109],"task":[111],"shows":[112],"that,":[113],"any":[116],"specific":[117],"fine-tuning":[118],"or":[119],"additional":[120],"complexity,":[121],"our":[122,157],"proposed":[123,158],"consistently":[126],"outperformed":[127],"state-of-the-art":[128],"significantly":[131],"reduced":[132],"Word":[133],"Error":[134],"Rate":[135],"(WER)":[136],"under":[137,146],"all":[138],"test":[139],"conditions,":[140,149],"especially":[142],"highest":[144],"improvements":[145],"unseen":[147],"noise":[148],"by":[150],"relative":[151],"12.94%,":[152],"8.66%":[153],"5.80%,":[155],"showing":[156],"generalize":[161],"better":[162],"variability.":[165]},"counts_by_year":[{"year":2019,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}