{"id":"https://openalex.org/W4385807434","doi":"https://doi.org/10.21437/interspeech.2023-1497","title":"ZeroPrompt: Streaming Acoustic Encoders are Zero-Shot Masked LMs","display_name":"ZeroPrompt: Streaming Acoustic Encoders are Zero-Shot Masked LMs","publication_year":2023,"publication_date":"2023-08-14","ids":{"openalex":"https://openalex.org/W4385807434","doi":"https://doi.org/10.21437/interspeech.2023-1497"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2023-1497","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2023-1497","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"INTERSPEECH 2023","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/A5074833963","display_name":"Xingchen Song","orcid":"https://orcid.org/0009-0009-9516-5361"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Xingchen Song","raw_affiliation_strings":["Tsinghua Univ., Beijing, China","WeNet Open Source Community","Horizon Inc., Beijing, China"],"affiliations":[{"raw_affiliation_string":"Tsinghua Univ., Beijing, China","institution_ids":["https://openalex.org/I99065089"]},{"raw_affiliation_string":"WeNet Open Source Community","institution_ids":[]},{"raw_affiliation_string":"Horizon Inc., Beijing, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100599890","display_name":"Di Wu","orcid":"https://orcid.org/0000-0002-4753-8161"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Di Wu","raw_affiliation_strings":["WeNet Open Source Community","Horizon Inc., Beijing, China"],"affiliations":[{"raw_affiliation_string":"WeNet Open Source Community","institution_ids":[]},{"raw_affiliation_string":"Horizon Inc., Beijing, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100449716","display_name":"Binbin Zhang","orcid":"https://orcid.org/0000-0002-7164-5127"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Binbin Zhang","raw_affiliation_strings":["Horizon Inc., Beijing, China","WeNet Open Source Community"],"affiliations":[{"raw_affiliation_string":"Horizon Inc., Beijing, China","institution_ids":[]},{"raw_affiliation_string":"WeNet Open Source Community","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5041630666","display_name":"Zhendong Peng","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhendong Peng","raw_affiliation_strings":["Horizon Inc., Beijing, China","WeNet Open Source Community"],"affiliations":[{"raw_affiliation_string":"Horizon Inc., Beijing, China","institution_ids":[]},{"raw_affiliation_string":"WeNet Open Source Community","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5110978167","display_name":"Bo Dang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Bo Dang","raw_affiliation_strings":["WeNet Open Source Community"],"affiliations":[{"raw_affiliation_string":"WeNet Open Source Community","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5031150833","display_name":"Fuping Pan","orcid":"https://orcid.org/0000-0001-9171-0726"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Fuping Pan","raw_affiliation_strings":["WeNet Open Source Community"],"affiliations":[{"raw_affiliation_string":"WeNet Open Source Community","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5102869280","display_name":"Zhiyong Wu","orcid":"https://orcid.org/0000-0001-8533-0524"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhiyong Wu","raw_affiliation_strings":["Tsinghua Univ., Beijing, China"],"affiliations":[{"raw_affiliation_string":"Tsinghua Univ., Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5074833963"],"corresponding_institution_ids":["https://openalex.org/I99065089"],"apc_list":null,"apc_paid":null,"fwci":2.6185,"has_fulltext":false,"cited_by_count":15,"citation_normalized_percentile":{"value":0.91775974,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":91,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"1648","last_page":"1652"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9998000264167786,"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":0.9998000264167786,"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/T11309","display_name":"Music and Audio Processing","score":0.9991999864578247,"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/T10028","display_name":"Topic Modeling","score":0.9987000226974487,"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/security-token","display_name":"Security token","score":0.9070186018943787},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.7701160907745361},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7569980621337891},{"id":"https://openalex.org/keywords/reduction","display_name":"Reduction (mathematics)","score":0.5440260171890259},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5295703411102295},{"id":"https://openalex.org/keywords/real-time-computing","display_name":"Real-time computing","score":0.3572181761264801},{"id":"https://openalex.org/keywords/computer-network","display_name":"Computer network","score":0.16200876235961914},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.09264999628067017}],"concepts":[{"id":"https://openalex.org/C48145219","wikidata":"https://www.wikidata.org/wiki/Q1335365","display_name":"Security token","level":2,"score":0.9070186018943787},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.7701160907745361},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7569980621337891},{"id":"https://openalex.org/C111335779","wikidata":"https://www.wikidata.org/wiki/Q3454686","display_name":"Reduction (mathematics)","level":2,"score":0.5440260171890259},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5295703411102295},{"id":"https://openalex.org/C79403827","wikidata":"https://www.wikidata.org/wiki/Q3988","display_name":"Real-time computing","level":1,"score":0.3572181761264801},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.16200876235961914},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.09264999628067017},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21437/interspeech.2023-1497","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2023-1497","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"INTERSPEECH 2023","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":22,"referenced_works":["https://openalex.org/W1494198834","https://openalex.org/W1828163288","https://openalex.org/W2127141656","https://openalex.org/W2131774270","https://openalex.org/W2802023636","https://openalex.org/W2892009249","https://openalex.org/W2913718171","https://openalex.org/W2963242190","https://openalex.org/W2963341956","https://openalex.org/W3016011332","https://openalex.org/W3096888553","https://openalex.org/W3111562797","https://openalex.org/W3125815078","https://openalex.org/W3163907627","https://openalex.org/W3196784225","https://openalex.org/W4221167707","https://openalex.org/W4284974905","https://openalex.org/W4296070361","https://openalex.org/W4308022738","https://openalex.org/W4308614381","https://openalex.org/W4321392390","https://openalex.org/W4385245566"],"related_works":["https://openalex.org/W4388335561","https://openalex.org/W2970530566","https://openalex.org/W4288261899","https://openalex.org/W4307309205","https://openalex.org/W2967478618","https://openalex.org/W4385009901","https://openalex.org/W4385572700","https://openalex.org/W2997152889","https://openalex.org/W4387768015","https://openalex.org/W4285141722"],"abstract_inverted_index":{"In":[0],"this":[1],"paper,":[2],"we":[3,111],"present":[4],"ZeroPrompt":[5,39,87],"(Figure":[6,13],"1-(a))":[7],"and":[8,82,91,123,136,143],"the":[9,23,57,75],"corresponding":[10],"Prompt-and-Refine":[11],"strategy":[12],"3),":[14],"two":[15],"simple":[16],"but":[17],"effective":[18],"training-free":[19],"methods":[20],"to":[21,41,45,55,59,95],"decrease":[22],"Token":[24,119,130],"Display":[25,120,131],"Time":[26,121,132],"(TDT)":[27],"of":[28,38,78],"streaming":[29,70,96],"ASR":[30],"models":[31],"without":[32,102],"any":[33,100,103],"accuracy":[34,104],"loss.The":[35],"core":[36],"idea":[37],"is":[40,88],"append":[42],"zeroed":[43],"content":[44],"each":[46],"chunk":[47],"during":[48],"inference,":[49],"which":[50],"acts":[51],"like":[52],"a":[53],"prompt":[54],"encourage":[56],"model":[58],"predict":[60],"future":[61],"tokens":[62],"even":[63],"before":[64],"they":[65],"were":[66],"spoken.We":[67],"argue":[68],"that":[69,86],"acoustic":[71,97],"encoders":[72,98],"naturally":[73],"have":[74],"modeling":[76],"ability":[77],"Masked":[79],"Language":[80],"Models":[81],"our":[83,108],"experiments":[84],"demonstrate":[85],"engineering":[89],"cheap":[90],"can":[92],"be":[93],"applied":[94],"on":[99,117,128,140],"dataset":[101],"loss.Specifically,":[105],"compared":[106],"with":[107,134],"baseline":[109],"models,":[110],"achieve":[112],"350":[113],"\u223c":[114,125],"700ms":[115],"reduction":[116,127],"First":[118],"(TDT-F)":[122],"100":[124],"400ms":[126],"Last":[129],"(TDT-L),":[133],"theoretically":[135],"experimentally":[137],"equal":[138],"WER":[139],"both":[141],"Aishell-1":[142],"Librispeech":[144],"datasets.":[145]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":13}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}