{"id":"https://openalex.org/W4225297945","doi":"https://doi.org/10.1109/icassp43922.2022.9746366","title":"Punctuation Prediction for Streaming On-Device Speech Recognition","display_name":"Punctuation Prediction for Streaming On-Device Speech Recognition","publication_year":2022,"publication_date":"2022-04-27","ids":{"openalex":"https://openalex.org/W4225297945","doi":"https://doi.org/10.1109/icassp43922.2022.9746366"},"language":"en","primary_location":{"id":"doi:10.1109/icassp43922.2022.9746366","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp43922.2022.9746366","pdf_url":null,"source":{"id":"https://openalex.org/S4363607702","display_name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2022 - 2022 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/A5102974956","display_name":"Zhikai Zhou","orcid":"https://orcid.org/0000-0002-4626-2677"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhikai Zhou","raw_affiliation_strings":["Shanghai Jiao Tong University,MoE Key Lab of Artificial Intelligence, AI Institute X-LANCE Lab,Department of Computer Science and Engineering,Shanghai,China","Department of Computer Science and Engineering, MoE Key Lab of Artificial Intelligence, AI Institute X-LANCE Lab, Shanghai Jiao Tong University, Shanghai, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University,MoE Key Lab of Artificial Intelligence, AI Institute X-LANCE Lab,Department of Computer Science and Engineering,Shanghai,China","institution_ids":["https://openalex.org/I183067930"]},{"raw_affiliation_string":"Department of Computer Science and Engineering, MoE Key Lab of Artificial Intelligence, AI Institute X-LANCE Lab, Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101667381","display_name":"Tian Tan","orcid":"https://orcid.org/0000-0002-4723-0044"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Tian Tan","raw_affiliation_strings":["AISpeech Ltd,Suzhou,China","AISpeech Ltd, Suzhou, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"AISpeech Ltd,Suzhou,China","institution_ids":[]},{"raw_affiliation_string":"AISpeech Ltd, Suzhou, China","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100341993","display_name":"Yanmin Qian","orcid":"https://orcid.org/0000-0002-0314-3790"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yanmin Qian","raw_affiliation_strings":["Shanghai Jiao Tong University,MoE Key Lab of Artificial Intelligence, AI Institute X-LANCE Lab,Department of Computer Science and Engineering,Shanghai,China","Department of Computer Science and Engineering, MoE Key Lab of Artificial Intelligence, AI Institute X-LANCE Lab, Shanghai Jiao Tong University, Shanghai, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University,MoE Key Lab of Artificial Intelligence, AI Institute X-LANCE Lab,Department of Computer Science and Engineering,Shanghai,China","institution_ids":["https://openalex.org/I183067930"]},{"raw_affiliation_string":"Department of Computer Science and Engineering, MoE Key Lab of Artificial Intelligence, AI Institute X-LANCE Lab, Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"7277","last_page":"7281"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9980999827384949,"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/T12031","display_name":"Speech and dialogue systems","score":0.9980999827384949,"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/punctuation","display_name":"Punctuation","score":0.9815999269485474},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8426034450531006},{"id":"https://openalex.org/keywords/pipeline","display_name":"Pipeline (software)","score":0.7239543199539185},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.6441234350204468},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6397738456726074},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4640817642211914},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4572789669036865},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.43635886907577515},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.06863147020339966}],"concepts":[{"id":"https://openalex.org/C540372491","wikidata":"https://www.wikidata.org/wiki/Q82622","display_name":"Punctuation","level":2,"score":0.9815999269485474},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8426034450531006},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.7239543199539185},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.6441234350204468},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6397738456726074},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4640817642211914},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4572789669036865},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.43635886907577515},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.06863147020339966},{"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/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp43922.2022.9746366","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp43922.2022.9746366","pdf_url":null,"source":{"id":"https://openalex.org/S4363607702","display_name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2022 - 2022 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/4","display_name":"Quality Education","score":0.5199999809265137}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":32,"referenced_works":["https://openalex.org/W2062752744","https://openalex.org/W2293829681","https://openalex.org/W2403334028","https://openalex.org/W2513522215","https://openalex.org/W2526425061","https://openalex.org/W2627092829","https://openalex.org/W2705373224","https://openalex.org/W2936123380","https://openalex.org/W2936774411","https://openalex.org/W2962760690","https://openalex.org/W2965373594","https://openalex.org/W2972411269","https://openalex.org/W2972818416","https://openalex.org/W3007328579","https://openalex.org/W3007528493","https://openalex.org/W3010663975","https://openalex.org/W3011222885","https://openalex.org/W3016128928","https://openalex.org/W3037101098","https://openalex.org/W3039572191","https://openalex.org/W3045571807","https://openalex.org/W3095994005","https://openalex.org/W3096726003","https://openalex.org/W3160648428","https://openalex.org/W3163457913","https://openalex.org/W3185113268","https://openalex.org/W4287824654","https://openalex.org/W4385245566","https://openalex.org/W6728030952","https://openalex.org/W6739901393","https://openalex.org/W6766673545","https://openalex.org/W6771917389"],"related_works":["https://openalex.org/W2981428355","https://openalex.org/W1834994814","https://openalex.org/W2041273198","https://openalex.org/W1599055764","https://openalex.org/W2131711534","https://openalex.org/W2149163000","https://openalex.org/W2962858469","https://openalex.org/W2289873871","https://openalex.org/W2559040841","https://openalex.org/W114661351"],"abstract_inverted_index":{"Punctuation":[0],"prediction":[1,30,83],"is":[2,32,55,96],"essential":[3],"for":[4,15,68,78],"automatic":[5],"speech":[6],"recognition":[7,105],"(ASR).":[8],"Although":[9],"many":[10],"works":[11],"have":[12],"been":[13],"proposed":[14,97,117],"punctuation":[16,29,82,107],"prediction,":[17],"the":[18,42,86,92,104,109,116,123,139],"on-device":[19],"scenarios":[20],"are":[21,65],"rarely":[22],"discussed":[23],"with":[24,61,127,145],"an":[25],"end-to-end":[26],"ASR.":[27],"The":[28],"task":[31],"often":[33],"treated":[34],"as":[35],"a":[36],"post-processing":[37,89,125],"of":[38],"ASR":[39,51,80,110,141],"outputs,":[40],"but":[41,131],"mismatch":[43],"between":[44],"natural":[45],"language":[46,58],"in":[47,53,136],"training":[48],"input":[49],"and":[50,81,106],"hypotheses":[52],"testing":[54],"ignored.":[56],"Besides,":[57],"models":[59,77],"built":[60],"deep":[62],"neural":[63],"networks":[64],"too":[66],"large":[67],"edge":[69],"devices.":[70],"In":[71],"this":[72],"paper,":[73],"we":[74],"discuss":[75],"one-pass":[76],"both":[79],"to":[84,98,102,138],"replace":[85],"conventional":[87],"two-pass":[88],"pipeline.":[90],"Then":[91],"joint":[93,118],"ASR-punctuation":[94],"model":[95,119],"utilize":[99],"multi-task":[100],"learning":[101],"decouple":[103],"on":[108,143],"decoder.":[111],"Experimental":[112],"results":[113],"show":[114],"that":[115],"not":[120],"only":[121],"outperforms":[122],"traditional":[124],"method":[126],"limited":[128],"extra":[129],"parameters,":[130],"also":[132],"achieves":[133],"better":[134],"accuracy":[135],"comparison":[137],"direct":[140],"modeling":[142],"transcripts":[144],"punctuation.":[146]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}