{"id":"https://openalex.org/W4224917388","doi":"https://doi.org/10.1109/icassp43922.2022.9747481","title":"Zero-Shot Cross-Lingual Transfer Using Multi-Stream Encoder and Efficient Speaker Representation","display_name":"Zero-Shot Cross-Lingual Transfer Using Multi-Stream Encoder and Efficient Speaker Representation","publication_year":2022,"publication_date":"2022-04-27","ids":{"openalex":"https://openalex.org/W4224917388","doi":"https://doi.org/10.1109/icassp43922.2022.9747481"},"language":"en","primary_location":{"id":"doi:10.1109/icassp43922.2022.9747481","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp43922.2022.9747481","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/A5101398585","display_name":"Yibin Zheng","orcid":"https://orcid.org/0000-0001-9158-1813"},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yibin Zheng","raw_affiliation_strings":["Tencent Inc,China","Tencent Inc, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tencent Inc,China","institution_ids":["https://openalex.org/I2250653659"]},{"raw_affiliation_string":"Tencent Inc, China","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5048848376","display_name":"Zewang Zhang","orcid":"https://orcid.org/0009-0001-3620-8706"},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zewang Zhang","raw_affiliation_strings":["Tencent Inc,China","Tencent Inc, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tencent Inc,China","institution_ids":["https://openalex.org/I2250653659"]},{"raw_affiliation_string":"Tencent Inc, China","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100701662","display_name":"Xinhui Li","orcid":"https://orcid.org/0000-0002-8398-8741"},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xinhui Li","raw_affiliation_strings":["Tencent Inc,China","Tencent Inc, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tencent Inc,China","institution_ids":["https://openalex.org/I2250653659"]},{"raw_affiliation_string":"Tencent Inc, China","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5041866046","display_name":"Wenchao Su","orcid":"https://orcid.org/0000-0002-9851-9753"},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wenchao Su","raw_affiliation_strings":["Tencent Inc,China","Tencent Inc, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tencent Inc,China","institution_ids":["https://openalex.org/I2250653659"]},{"raw_affiliation_string":"Tencent Inc, China","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100658678","display_name":"Li L\u00fc","orcid":"https://orcid.org/0000-0001-5230-3749"},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Li Lu","raw_affiliation_strings":["Tencent Inc,China","Tencent Inc, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tencent Inc,China","institution_ids":["https://openalex.org/I2250653659"]},{"raw_affiliation_string":"Tencent Inc, China","institution_ids":["https://openalex.org/I2250653659"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I2250653659"],"apc_list":null,"apc_paid":null,"fwci":0.5061,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.61295434,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":96,"max":97},"biblio":{"volume":"80","issue":null,"first_page":"8027","last_page":"8031"},"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":0.9970999956130981,"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/T11309","display_name":"Music and Audio Processing","score":0.9947999715805054,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7414027452468872},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.7319022417068481},{"id":"https://openalex.org/keywords/transfer","display_name":"Transfer (computing)","score":0.5350070595741272},{"id":"https://openalex.org/keywords/zero","display_name":"Zero (linguistics)","score":0.5291438698768616},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.5198822021484375},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4677838087081909},{"id":"https://openalex.org/keywords/shot","display_name":"Shot (pellet)","score":0.4667295217514038},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.07308623194694519}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7414027452468872},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.7319022417068481},{"id":"https://openalex.org/C2776175482","wikidata":"https://www.wikidata.org/wiki/Q1195816","display_name":"Transfer (computing)","level":2,"score":0.5350070595741272},{"id":"https://openalex.org/C2780813799","wikidata":"https://www.wikidata.org/wiki/Q3274237","display_name":"Zero (linguistics)","level":2,"score":0.5291438698768616},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.5198822021484375},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4677838087081909},{"id":"https://openalex.org/C2778344882","wikidata":"https://www.wikidata.org/wiki/Q278938","display_name":"Shot (pellet)","level":2,"score":0.4667295217514038},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.07308623194694519},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C178790620","wikidata":"https://www.wikidata.org/wiki/Q11351","display_name":"Organic chemistry","level":1,"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/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp43922.2022.9747481","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp43922.2022.9747481","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":[{"score":0.7799999713897705,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":36,"referenced_works":["https://openalex.org/W1522301498","https://openalex.org/W1731081199","https://openalex.org/W2025638820","https://openalex.org/W2494654097","https://openalex.org/W2619368999","https://openalex.org/W2766406951","https://openalex.org/W2789758093","https://openalex.org/W2794490148","https://openalex.org/W2795109282","https://openalex.org/W2892620417","https://openalex.org/W2903739847","https://openalex.org/W2936832667","https://openalex.org/W2963091184","https://openalex.org/W2963609956","https://openalex.org/W2963964591","https://openalex.org/W2964002616","https://openalex.org/W2964243274","https://openalex.org/W2969521066","https://openalex.org/W2972473628","https://openalex.org/W2972574864","https://openalex.org/W2973177731","https://openalex.org/W3096702751","https://openalex.org/W3097297926","https://openalex.org/W3163929126","https://openalex.org/W4287070893","https://openalex.org/W4295731579","https://openalex.org/W4298857617","https://openalex.org/W6631190155","https://openalex.org/W6637618735","https://openalex.org/W6723457072","https://openalex.org/W6745232783","https://openalex.org/W6745569068","https://openalex.org/W6750489868","https://openalex.org/W6755135894","https://openalex.org/W6765987481","https://openalex.org/W6798837988"],"related_works":["https://openalex.org/W2074502265","https://openalex.org/W4214877189","https://openalex.org/W2773965352","https://openalex.org/W2381179799","https://openalex.org/W2980279061","https://openalex.org/W2334685461","https://openalex.org/W2366718574","https://openalex.org/W2359774528","https://openalex.org/W4298312966","https://openalex.org/W2325697621"],"abstract_inverted_index":{"We":[0],"propose":[1,97],"a":[2,20,46,66,70,75,114],"novel":[3],"method":[4,124],"for":[5,147,154],"zero-shot":[6,100,148],"cross-lingual":[7,101,149,156],"TTS":[8],"task":[9],"by":[10,65],"using":[11],"multi-stream":[12,22,47],"text":[13,23],"encoder":[14,24,68],"and":[15,31,74,92,113,132,142],"efficient":[16,99],"speaker":[17,58,67,82,133],"representation.":[18],"Specifically,":[19],"unified":[21],"that":[25,85],"takes":[26],"both":[27,89],"advantages":[28],"of":[29,88,107,140],"Transformer":[30,43,48],"CBHG":[32],"is":[33,49],"proposed":[34,51,123],"to":[35,52,80],"retain":[36],"multiple":[37],"hypotheses":[38],"about":[39],"input":[40],"representations.":[41],"For":[42],"based":[44],"stream,":[45],"further":[50],"strengthen":[53],"these":[54],"hypotheses.":[55],"Then":[56],"the":[57,105,122],"representations":[59],"are":[60,86],"extracted":[61],"from":[62],"audio":[63],"signals":[64],"with":[69,104],"random":[71],"sampling":[72,116],"mechanism":[73],"language":[76,93],"adversarial":[77],"loss,":[78],"aiming":[79],"extract":[81],"embedding":[83],"features":[84],"independent":[87],"content":[90],"information":[91],"identity.":[94],"Meanwhile,":[95],"we":[96],"an":[98,136],"transfer":[102,157],"strategy":[103],"help":[106],"other":[108],"target":[109],"lingual":[110],"speakers\u2019":[111],"data":[112],"language-balanced":[115],"strategy.":[117],"The":[118],"Experimental":[119],"results":[120],"show":[121],"not":[125],"only":[126],"could":[127],"achieve":[128],"higher":[129],"speech":[130],"quality":[131],"similarity":[134],"(with":[135],"average":[137],"absolute":[138],"improvement":[139],"0.38":[141],"0.27":[143],"in":[144,158],"MOS":[145],"respectively)":[146],"transfer,":[150],"but":[151],"also":[152],"helpful":[153],"few-shot":[155],"which":[159],"has":[160],"multi-lingual":[161],"data.1":[162]},"counts_by_year":[{"year":2023,"cited_by_count":3}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}