{"id":"https://openalex.org/W4224292837","doi":"https://doi.org/10.21437/interspeech.2022-933","title":"Blockwise Streaming Transformer for Spoken Language Understanding and Simultaneous Speech Translation","display_name":"Blockwise Streaming Transformer for Spoken Language Understanding and Simultaneous Speech Translation","publication_year":2022,"publication_date":"2022-09-16","ids":{"openalex":"https://openalex.org/W4224292837","doi":"https://doi.org/10.21437/interspeech.2022-933"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2022-933","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2022-933","pdf_url":null,"source":{"id":"https://openalex.org/S4363604309","display_name":"Interspeech 2022","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":"Interspeech 2022","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/A5068367173","display_name":"Keqi Deng","orcid":"https://orcid.org/0000-0003-1490-963X"},"institutions":[{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Keqi Deng","raw_affiliation_strings":["University of Chinese Academy of Sciences, China"],"affiliations":[{"raw_affiliation_string":"University of Chinese Academy of Sciences, China","institution_ids":["https://openalex.org/I4210165038"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5001291873","display_name":"Shinji Watanabe","orcid":"https://orcid.org/0000-0002-5970-8631"},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Shinji Watanabe","raw_affiliation_strings":["Carnegie Mellon University, USA"],"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University, USA","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101063912","display_name":"Jiatong Shi","orcid":null},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jiatong Shi","raw_affiliation_strings":["Carnegie Mellon University, USA"],"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University, USA","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5047892839","display_name":"Siddhant Arora","orcid":"https://orcid.org/0000-0003-0375-496X"},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Siddhant Arora","raw_affiliation_strings":["Carnegie Mellon University, USA"],"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University, USA","institution_ids":["https://openalex.org/I74973139"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5068367173"],"corresponding_institution_ids":["https://openalex.org/I4210165038"],"apc_list":null,"apc_paid":null,"fwci":0.9355,"has_fulltext":false,"cited_by_count":9,"citation_normalized_percentile":{"value":0.75463262,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9986000061035156,"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":0.9986000061035156,"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":0.9954000115394592,"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":0.9926999807357788,"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":0.7750981450080872},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.722103476524353},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5460950136184692},{"id":"https://openalex.org/keywords/speech-translation","display_name":"Speech translation","score":0.5055942535400391},{"id":"https://openalex.org/keywords/spoken-language","display_name":"Spoken language","score":0.41744866967201233},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.40013253688812256},{"id":"https://openalex.org/keywords/machine-translation","display_name":"Machine translation","score":0.3209383189678192},{"id":"https://openalex.org/keywords/voltage","display_name":"Voltage","score":0.15114155411720276},{"id":"https://openalex.org/keywords/electrical-engineering","display_name":"Electrical engineering","score":0.1350668966770172},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.10397759079933167}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7750981450080872},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.722103476524353},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5460950136184692},{"id":"https://openalex.org/C2780366754","wikidata":"https://www.wikidata.org/wiki/Q7494857","display_name":"Speech translation","level":3,"score":0.5055942535400391},{"id":"https://openalex.org/C2776230583","wikidata":"https://www.wikidata.org/wiki/Q1322198","display_name":"Spoken language","level":2,"score":0.41744866967201233},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.40013253688812256},{"id":"https://openalex.org/C203005215","wikidata":"https://www.wikidata.org/wiki/Q79798","display_name":"Machine translation","level":2,"score":0.3209383189678192},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.15114155411720276},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.1350668966770172},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.10397759079933167}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21437/interspeech.2022-933","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2022-933","pdf_url":null,"source":{"id":"https://openalex.org/S4363604309","display_name":"Interspeech 2022","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":"Interspeech 2022","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.6499999761581421}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":40,"referenced_works":["https://openalex.org/W46679369","https://openalex.org/W2102113734","https://openalex.org/W2739883972","https://openalex.org/W2742061524","https://openalex.org/W2766219058","https://openalex.org/W2894164357","https://openalex.org/W2936774411","https://openalex.org/W2951456627","https://openalex.org/W2962780374","https://openalex.org/W2972584841","https://openalex.org/W2975711469","https://openalex.org/W2989399107","https://openalex.org/W2998386507","https://openalex.org/W3007433671","https://openalex.org/W3008549139","https://openalex.org/W3012492057","https://openalex.org/W3015583403","https://openalex.org/W3015974384","https://openalex.org/W3037217258","https://openalex.org/W3097964672","https://openalex.org/W3100460087","https://openalex.org/W3115075512","https://openalex.org/W3148654612","https://openalex.org/W3155427814","https://openalex.org/W3162000275","https://openalex.org/W3162249256","https://openalex.org/W3162665866","https://openalex.org/W3173171878","https://openalex.org/W3174032041","https://openalex.org/W3176711365","https://openalex.org/W3177132412","https://openalex.org/W3188372498","https://openalex.org/W3209828067","https://openalex.org/W3217767527","https://openalex.org/W4226054021","https://openalex.org/W4287122800","https://openalex.org/W4287989347","https://openalex.org/W4288817190","https://openalex.org/W4294619417","https://openalex.org/W4385245566"],"related_works":["https://openalex.org/W1592339875","https://openalex.org/W2435130738","https://openalex.org/W2186089609","https://openalex.org/W4206534379","https://openalex.org/W970670907","https://openalex.org/W30494850","https://openalex.org/W2066913438","https://openalex.org/W2251328660","https://openalex.org/W2406273306","https://openalex.org/W3102471799"],"abstract_inverted_index":{"Although":[0],"Transformers":[1],"have":[2],"gained":[3],"success":[4],"in":[5],"several":[6],"speech":[7,16,66],"processing":[8,21,56],"tasks":[9],"like":[10],"spoken":[11],"language":[12,102],"understanding":[13],"(SLU)":[14],"and":[15,42,57,136,148,182],"translation":[17,107,125],"(ST),":[18],"achieving":[19,121],"online":[20],"while":[22,139],"keeping":[23],"competitive":[24,160],"performance":[25,81],"is":[26,51,109,143],"still":[27],"essential":[28],"for":[29,72,83,126,130],"real-world":[30],"interaction.In":[31],"this":[32],"paper,":[33],"we":[34,62,88],"take":[35],"the":[36,73,79,84,105,114,127,140,155,179,188],"first":[37,128],"step":[38],"on":[39,53,134,145,178,187],"streaming":[40,48,74,157,192],"SLU":[41,75,131,180],"simultaneous":[43,85,124],"ST":[44,86,141,189],"using":[45],"a":[46,90,96,174,183],"blockwise":[47,58,156],"Transformer,":[49],"which":[50,94],"based":[52],"contextual":[54],"block":[55],"synchronous":[59],"beam":[60],"search.Furthermore,":[61],"design":[63],"an":[64],"automatic":[65],"recognition":[67],"(ASR)-based":[68],"intermediate":[69],"loss":[70],"regularization":[71],"task":[76,142,181,190],"to":[77,112,163],"improve":[78],"classification":[80],"further.As":[82],"task,":[87],"propose":[89],"cross-lingual":[91],"encoding":[92],"method,":[93],"employs":[95],"CTC":[97,106,118],"branch":[98],"optimized":[99],"with":[100,117,167],"target":[101],"translations.In":[103],"addition,":[104],"output":[108],"also":[110],"used":[111],"refine":[113],"search":[115],"space":[116],"prefix":[119],"score,":[120],"joint":[122],"CTC/attention":[123],"time.Experiments":[129],"are":[132],"conducted":[133],"FSC":[135],"SLURP":[137],"corpora,":[138],"evaluated":[144],"Fisher-CallHome":[146],"Spanish":[147],"MuST-C":[149],"En-De":[150],"corpora.Experimental":[151],"results":[152,161],"show":[153],"that":[154,171],"Transformer":[158],"achieves":[159],"compared":[162],"offline":[164],"models,":[165],"especially":[166],"our":[168],"proposed":[169],"methods":[170],"further":[172],"yield":[173],"2.4%":[175],"accuracy":[176],"gain":[177,186],"4.3":[184],"BLEU":[185],"over":[191],"baselines.":[193]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":5},{"year":2022,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}