{"id":"https://openalex.org/W3160648428","doi":"https://doi.org/10.1109/icassp39728.2021.9414518","title":"Making Punctuation Restoration Robust and Fast with Multi-Task Learning and Knowledge Distillation","display_name":"Making Punctuation Restoration Robust and Fast with Multi-Task Learning and Knowledge Distillation","publication_year":2021,"publication_date":"2021-05-13","ids":{"openalex":"https://openalex.org/W3160648428","doi":"https://doi.org/10.1109/icassp39728.2021.9414518","mag":"3160648428"},"language":"en","primary_location":{"id":"doi:10.1109/icassp39728.2021.9414518","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp39728.2021.9414518","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2021 - 2021 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/A5010628266","display_name":"Michael Hentschel","orcid":"https://orcid.org/0000-0003-3986-5725"},"institutions":[{"id":"https://openalex.org/I2800278093","display_name":"Sony Corporation (United States)","ror":"https://ror.org/05k91zb11","country_code":"US","type":"company","lineage":["https://openalex.org/I2800278093"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Michael Hentschel","raw_affiliation_strings":["Sony Corporation, Tokyo"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Sony Corporation, Tokyo","institution_ids":["https://openalex.org/I2800278093"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5011937407","display_name":"Emiru Tsunoo","orcid":null},"institutions":[{"id":"https://openalex.org/I2800278093","display_name":"Sony Corporation (United States)","ror":"https://ror.org/05k91zb11","country_code":"US","type":"company","lineage":["https://openalex.org/I2800278093"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Emiru Tsunoo","raw_affiliation_strings":["Sony Corporation, Tokyo"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Sony Corporation, Tokyo","institution_ids":["https://openalex.org/I2800278093"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5102113456","display_name":"Takao Okuda","orcid":null},"institutions":[{"id":"https://openalex.org/I2800278093","display_name":"Sony Corporation (United States)","ror":"https://ror.org/05k91zb11","country_code":"US","type":"company","lineage":["https://openalex.org/I2800278093"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Takao Okuda","raw_affiliation_strings":["Sony Corporation, Tokyo"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Sony Corporation, Tokyo","institution_ids":["https://openalex.org/I2800278093"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I2800278093"],"apc_list":null,"apc_paid":null,"fwci":1.9049,"has_fulltext":false,"cited_by_count":15,"citation_normalized_percentile":{"value":0.88360803,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"7773","last_page":"7777"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9997000098228455,"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":0.9997000098228455,"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/T10860","display_name":"Speech and Audio Processing","score":0.9966999888420105,"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":0.9951000213623047,"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":0.8232967853546143},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.6728638410568237},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.6687012910842896},{"id":"https://openalex.org/keywords/discriminator","display_name":"Discriminator","score":0.6605541706085205},{"id":"https://openalex.org/keywords/punctuation","display_name":"Punctuation","score":0.6053566932678223},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5796804428100586},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.5733373761177063},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5140188932418823},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4840514063835144},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.4692862927913666},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.4615379273891449},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.44909366965293884},{"id":"https://openalex.org/keywords/pruning","display_name":"Pruning","score":0.42542457580566406},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3680476248264313}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8232967853546143},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.6728638410568237},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.6687012910842896},{"id":"https://openalex.org/C2779803651","wikidata":"https://www.wikidata.org/wiki/Q5282088","display_name":"Discriminator","level":3,"score":0.6605541706085205},{"id":"https://openalex.org/C540372491","wikidata":"https://www.wikidata.org/wiki/Q82622","display_name":"Punctuation","level":2,"score":0.6053566932678223},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5796804428100586},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.5733373761177063},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5140188932418823},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4840514063835144},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.4692862927913666},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.4615379273891449},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.44909366965293884},{"id":"https://openalex.org/C108010975","wikidata":"https://www.wikidata.org/wiki/Q500094","display_name":"Pruning","level":2,"score":0.42542457580566406},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3680476248264313},{"id":"https://openalex.org/C94915269","wikidata":"https://www.wikidata.org/wiki/Q1834857","display_name":"Detector","level":2,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","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/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.0},{"id":"https://openalex.org/C6557445","wikidata":"https://www.wikidata.org/wiki/Q173113","display_name":"Agronomy","level":1,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp39728.2021.9414518","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp39728.2021.9414518","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2021 - 2021 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/10","score":0.6000000238418579,"display_name":"Reduced inequalities"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":39,"referenced_works":["https://openalex.org/W1522301498","https://openalex.org/W2121879602","https://openalex.org/W2250357346","https://openalex.org/W2513522215","https://openalex.org/W2575282817","https://openalex.org/W2759132769","https://openalex.org/W2888942278","https://openalex.org/W2896457183","https://openalex.org/W2917668649","https://openalex.org/W2937326859","https://openalex.org/W2938722449","https://openalex.org/W2946794439","https://openalex.org/W2962989741","https://openalex.org/W2963341956","https://openalex.org/W2964121744","https://openalex.org/W2978017171","https://openalex.org/W2980282514","https://openalex.org/W2996035354","https://openalex.org/W3010663975","https://openalex.org/W3011866533","https://openalex.org/W3015179046","https://openalex.org/W3015233032","https://openalex.org/W3030163527","https://openalex.org/W3037101098","https://openalex.org/W3045571807","https://openalex.org/W3094965760","https://openalex.org/W3105966348","https://openalex.org/W4287824654","https://openalex.org/W4292779060","https://openalex.org/W6631190155","https://openalex.org/W6691509046","https://openalex.org/W6731992975","https://openalex.org/W6755207826","https://openalex.org/W6759815381","https://openalex.org/W6768086466","https://openalex.org/W6768851824","https://openalex.org/W6771917389","https://openalex.org/W6775528981","https://openalex.org/W6778883912"],"related_works":["https://openalex.org/W3049463507","https://openalex.org/W2936497627","https://openalex.org/W4288365749","https://openalex.org/W3013624417","https://openalex.org/W4287826556","https://openalex.org/W4287598411","https://openalex.org/W3098382480","https://openalex.org/W3198458223","https://openalex.org/W4288267738","https://openalex.org/W3126642501"],"abstract_inverted_index":{"In":[0,127],"punctuation":[1,9],"restoration,":[2],"we":[3,70,118],"try":[4],"to":[5,15,37,93],"recover":[6],"the":[7,26,41,47,57,68,97,116,131,142],"missing":[8],"from":[10,50],"automatic":[11],"speech":[12,51,109],"recognition":[13,52,110],"output":[14,48],"improve":[16],"understandability.":[17],"Currently,":[18],"large":[19,58],"pre-trained":[20],"transformers":[21],"such":[22],"as":[23,101],"BERT":[24,145],"set":[25],"benchmark":[27,134],"on":[28,82,130],"this":[29,105],"task":[30],"but":[31],"there":[32],"are":[33],"two":[34],"main":[35],"drawbacks":[36],"these":[38],"models.":[39],"First,":[40],"pre-training":[42],"data":[43,49,99],"does":[44],"not":[45],"match":[46],"that":[53,84],"contains":[54],"errors.":[55],"Second,":[56],"number":[59],"of":[60,125,144],"model":[61,137],"parameters":[62],"increases":[63],"inference":[64,154],"time.":[65,155],"To":[66,114],"address":[67,115],"former,":[69],"use":[71],"a":[72,78,86,136],"multi-task":[73],"learning":[74],"framework":[75],"with":[76,138],"ELECTRA,":[77],"recently":[79],"proposed":[80],"improvement":[81],"BERT,":[83],"has":[85],"generator-discriminator":[87],"structure.":[88],"The":[89],"generator":[90],"allows":[91],"us":[92],"inject":[94],"errors":[95,111],"into":[96],"training":[98],"and,":[100],"our":[102,128],"experiments":[103,129],"show,":[104],"improves":[106],"robustness":[107],"against":[108],"during":[112],"inference.":[113],"latter,":[117],"investigate":[119],"knowledge":[120],"distillation":[121],"and":[122],"parameter":[123],"pruning":[124],"ELECTRA.":[126],"IWSLT":[132],"2012":[133],"data,":[135],"less":[139],"than":[140],"11%":[141],"size":[143],"achieved":[146],"better":[147],"performance":[148],"while":[149],"having":[150],"an":[151],"82%":[152],"faster":[153]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":5},{"year":2022,"cited_by_count":3},{"year":2021,"cited_by_count":4}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}