{"id":"https://openalex.org/W3016128928","doi":"https://doi.org/10.1109/icassp40776.2020.9053159","title":"Controllable Time-Delay Transformer for Real-Time Punctuation Prediction and Disfluency Detection","display_name":"Controllable Time-Delay Transformer for Real-Time Punctuation Prediction and Disfluency Detection","publication_year":2020,"publication_date":"2020-04-09","ids":{"openalex":"https://openalex.org/W3016128928","doi":"https://doi.org/10.1109/icassp40776.2020.9053159","mag":"3016128928"},"language":"en","primary_location":{"id":"doi:10.1109/icassp40776.2020.9053159","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp40776.2020.9053159","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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/A5100657544","display_name":"Chen Qian","orcid":"https://orcid.org/0000-0002-8761-5563"},"institutions":[{"id":"https://openalex.org/I4210086143","display_name":"Alibaba Group (Cayman Islands)","ror":"https://ror.org/00mnrxf72","country_code":"KY","type":"company","lineage":["https://openalex.org/I4210086143","https://openalex.org/I45928872"]}],"countries":["KY"],"is_corresponding":true,"raw_author_name":"Qian Chen","raw_affiliation_strings":["Alibaba Group, DAMO Academy"],"affiliations":[{"raw_affiliation_string":"Alibaba Group, DAMO Academy","institution_ids":["https://openalex.org/I4210086143"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5058945912","display_name":"Mengzhe Chen","orcid":null},"institutions":[{"id":"https://openalex.org/I4210086143","display_name":"Alibaba Group (Cayman Islands)","ror":"https://ror.org/00mnrxf72","country_code":"KY","type":"company","lineage":["https://openalex.org/I4210086143","https://openalex.org/I45928872"]}],"countries":["KY"],"is_corresponding":false,"raw_author_name":"Mengzhe Chen","raw_affiliation_strings":["Alibaba Group, DAMO Academy"],"affiliations":[{"raw_affiliation_string":"Alibaba Group, DAMO Academy","institution_ids":["https://openalex.org/I4210086143"]}]},{"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/I4210086143","display_name":"Alibaba Group (Cayman Islands)","ror":"https://ror.org/00mnrxf72","country_code":"KY","type":"company","lineage":["https://openalex.org/I4210086143","https://openalex.org/I45928872"]}],"countries":["KY"],"is_corresponding":false,"raw_author_name":"Bo Li","raw_affiliation_strings":["Alibaba Group, DAMO Academy"],"affiliations":[{"raw_affiliation_string":"Alibaba Group, DAMO Academy","institution_ids":["https://openalex.org/I4210086143"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100396375","display_name":"Wen Wang","orcid":"https://orcid.org/0000-0002-0356-1968"},"institutions":[{"id":"https://openalex.org/I4210086143","display_name":"Alibaba Group (Cayman Islands)","ror":"https://ror.org/00mnrxf72","country_code":"KY","type":"company","lineage":["https://openalex.org/I4210086143","https://openalex.org/I45928872"]}],"countries":["KY"],"is_corresponding":false,"raw_author_name":"Wen Wang","raw_affiliation_strings":["Alibaba Group, DAMO Academy"],"affiliations":[{"raw_affiliation_string":"Alibaba Group, DAMO Academy","institution_ids":["https://openalex.org/I4210086143"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5100657544"],"corresponding_institution_ids":["https://openalex.org/I4210086143"],"apc_list":null,"apc_paid":null,"fwci":2.7837,"has_fulltext":false,"cited_by_count":33,"citation_normalized_percentile":{"value":0.92127653,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"8069","last_page":"8073"},"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9987999796867371,"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/T12031","display_name":"Speech and dialogue systems","score":0.9970999956130981,"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":0.802842378616333},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.6969395875930786},{"id":"https://openalex.org/keywords/punctuation","display_name":"Punctuation","score":0.6734073162078857},{"id":"https://openalex.org/keywords/decoding-methods","display_name":"Decoding methods","score":0.6315845251083374},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.5790328979492188},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5587189793586731},{"id":"https://openalex.org/keywords/latency","display_name":"Latency (audio)","score":0.5556768178939819},{"id":"https://openalex.org/keywords/readability","display_name":"Readability","score":0.5219287872314453},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.46344566345214844},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.41944217681884766},{"id":"https://openalex.org/keywords/voltage","display_name":"Voltage","score":0.14751330018043518},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.1407674252986908},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.09040546417236328}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.802842378616333},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.6969395875930786},{"id":"https://openalex.org/C540372491","wikidata":"https://www.wikidata.org/wiki/Q82622","display_name":"Punctuation","level":2,"score":0.6734073162078857},{"id":"https://openalex.org/C57273362","wikidata":"https://www.wikidata.org/wiki/Q576722","display_name":"Decoding methods","level":2,"score":0.6315845251083374},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.5790328979492188},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5587189793586731},{"id":"https://openalex.org/C82876162","wikidata":"https://www.wikidata.org/wiki/Q17096504","display_name":"Latency (audio)","level":2,"score":0.5556768178939819},{"id":"https://openalex.org/C2778143727","wikidata":"https://www.wikidata.org/wiki/Q1820650","display_name":"Readability","level":2,"score":0.5219287872314453},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.46344566345214844},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.41944217681884766},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.14751330018043518},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.1407674252986908},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.09040546417236328},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"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/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/icassp40776.2020.9053159","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp40776.2020.9053159","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.6299999952316284,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":60,"referenced_works":["https://openalex.org/W1522301498","https://openalex.org/W1587490638","https://openalex.org/W1597349739","https://openalex.org/W1623072288","https://openalex.org/W1979702444","https://openalex.org/W2113851376","https://openalex.org/W2117682636","https://openalex.org/W2161274063","https://openalex.org/W2166116787","https://openalex.org/W2169058332","https://openalex.org/W2214962597","https://openalex.org/W2250330117","https://openalex.org/W2251145407","https://openalex.org/W2398104528","https://openalex.org/W2400986993","https://openalex.org/W2403334028","https://openalex.org/W2406343628","https://openalex.org/W2407834842","https://openalex.org/W2513522215","https://openalex.org/W2566299766","https://openalex.org/W2575282817","https://openalex.org/W2586117383","https://openalex.org/W2741045570","https://openalex.org/W2750292073","https://openalex.org/W2899280787","https://openalex.org/W2904571617","https://openalex.org/W2938722449","https://openalex.org/W2951456627","https://openalex.org/W2951562155","https://openalex.org/W2962989741","https://openalex.org/W2963403868","https://openalex.org/W2963560594","https://openalex.org/W2964121744","https://openalex.org/W2964189376","https://openalex.org/W2965885792","https://openalex.org/W2996888978","https://openalex.org/W3011222885","https://openalex.org/W3202802636","https://openalex.org/W4385245566","https://openalex.org/W6631190155","https://openalex.org/W6635223454","https://openalex.org/W6635795559","https://openalex.org/W6636392717","https://openalex.org/W6683637288","https://openalex.org/W6684662674","https://openalex.org/W6688371331","https://openalex.org/W6691168804","https://openalex.org/W6712411474","https://openalex.org/W6713196122","https://openalex.org/W6713441181","https://openalex.org/W6713490458","https://openalex.org/W6714054690","https://openalex.org/W6731992975","https://openalex.org/W6739901393","https://openalex.org/W6741936628","https://openalex.org/W6744649695","https://openalex.org/W6746565888","https://openalex.org/W6755898573","https://openalex.org/W6766717302","https://openalex.org/W6802354036"],"related_works":["https://openalex.org/W1964661231","https://openalex.org/W4254960163","https://openalex.org/W3110264473","https://openalex.org/W2936002343","https://openalex.org/W2032810564","https://openalex.org/W2370831213","https://openalex.org/W2188883480","https://openalex.org/W2972807713","https://openalex.org/W1592364192","https://openalex.org/W4315704968"],"abstract_inverted_index":{"With":[0],"the":[1,27,30,35,63,86,113,125,129],"increased":[2],"applications":[3],"of":[4,29,37],"automatic":[5],"speech":[6],"recognition":[7],"(ASR)":[8],"in":[9,23,70,89],"recent":[10],"years,":[11],"it":[12],"is":[13],"essential":[14],"to":[15,25,84,103],"automatically":[16],"insert":[17],"punctuation":[18,64],"marks":[19],"and":[20,46,66,117,135],"remove":[21],"disfluencies":[22],"transcripts,":[24],"improve":[26],"readability":[28],"transcripts":[31],"as":[32,34,41],"well":[33],"performance":[36],"subsequent":[38,94],"applications,":[39],"such":[40],"machine":[42],"translation,":[43],"dialogue":[44],"systems,":[45],"so":[47],"forth.":[48],"In":[49],"this":[50],"paper,":[51],"we":[52],"propose":[53,98],"a":[54,99,137],"Controllable":[55],"Time-delay":[56],"Transformer":[57],"(CT-Transformer)":[58],"model":[59,75],"that":[60,124],"jointly":[61],"completes":[62],"prediction":[65],"disfluency":[67],"detection":[68],"tasks":[69],"real":[71],"time.":[72],"The":[73],"CT-Transformer":[74],"facilitates":[76],"freezing":[77],"partial":[78,90],"outputs":[79],"with":[80],"controllable":[81],"time":[82],"delay":[83],"fulfill":[85],"real-time":[87],"constraints":[88],"decoding":[91,101],"required":[92],"by":[93],"applications.":[95],"We":[96],"further":[97],"fast":[100],"strategy":[102],"minimize":[104],"latency":[105],"while":[106],"maintaining":[107],"competitive":[108,138],"performance.":[109],"Experimental":[110],"results":[111],"on":[112,133],"IWSLT2011":[114],"benchmark":[115],"dataset":[116,122],"an":[118],"in-house":[119],"Chinese":[120],"annotated":[121],"demonstrate":[123],"proposed":[126],"approach":[127],"outperforms":[128],"previous":[130],"state-of-the-art":[131],"models":[132],"F-scores":[134],"achieves":[136],"inference":[139],"speed.":[140]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":9},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":7},{"year":2022,"cited_by_count":6},{"year":2021,"cited_by_count":6},{"year":2020,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}