{"id":"https://openalex.org/W3015440307","doi":"https://doi.org/10.1109/icassp40776.2020.9053406","title":"SkinAugment: Auto-Encoding Speaker Conversions for Automatic Speech Translation","display_name":"SkinAugment: Auto-Encoding Speaker Conversions for Automatic Speech Translation","publication_year":2020,"publication_date":"2020-04-09","ids":{"openalex":"https://openalex.org/W3015440307","doi":"https://doi.org/10.1109/icassp40776.2020.9053406","mag":"3015440307"},"language":"en","primary_location":{"id":"doi:10.1109/icassp40776.2020.9053406","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp40776.2020.9053406","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/A5046881440","display_name":"Arya D. McCarthy","orcid":"https://orcid.org/0000-0001-9440-8792"},"institutions":[{"id":"https://openalex.org/I145311948","display_name":"Johns Hopkins University","ror":"https://ror.org/00za53h95","country_code":"US","type":"education","lineage":["https://openalex.org/I145311948"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Arya D. McCarthy","raw_affiliation_strings":["Center for Language and Speech Processing, Johns Hopkins University"],"affiliations":[{"raw_affiliation_string":"Center for Language and Speech Processing, Johns Hopkins University","institution_ids":["https://openalex.org/I145311948"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5057594465","display_name":"Liezl Puzon","orcid":null},"institutions":[{"id":"https://openalex.org/I2252078561","display_name":"Meta (Israel)","ror":"https://ror.org/02388em19","country_code":"IL","type":"company","lineage":["https://openalex.org/I2252078561","https://openalex.org/I4210114444"]}],"countries":["IL"],"is_corresponding":false,"raw_author_name":"Liezl Puzon","raw_affiliation_strings":["Facebook"],"affiliations":[{"raw_affiliation_string":"Facebook","institution_ids":["https://openalex.org/I2252078561"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5058915697","display_name":"Juan Pino","orcid":null},"institutions":[{"id":"https://openalex.org/I2252078561","display_name":"Meta (Israel)","ror":"https://ror.org/02388em19","country_code":"IL","type":"company","lineage":["https://openalex.org/I2252078561","https://openalex.org/I4210114444"]}],"countries":["IL"],"is_corresponding":false,"raw_author_name":"Juan Pino","raw_affiliation_strings":["Facebook"],"affiliations":[{"raw_affiliation_string":"Facebook","institution_ids":["https://openalex.org/I2252078561"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5046881440"],"corresponding_institution_ids":["https://openalex.org/I145311948"],"apc_list":null,"apc_paid":null,"fwci":2.6512,"has_fulltext":false,"cited_by_count":22,"citation_normalized_percentile":{"value":0.91729557,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":95,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"7924","last_page":"7928"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","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/T10181","display_name":"Natural Language Processing Techniques","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/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/T10028","display_name":"Topic Modeling","score":0.9994000196456909,"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":0.8358573317527771},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7484585642814636},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.6585532426834106},{"id":"https://openalex.org/keywords/machine-translation","display_name":"Machine translation","score":0.5595716238021851},{"id":"https://openalex.org/keywords/encoding","display_name":"Encoding (memory)","score":0.5406034588813782},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5191113948822021},{"id":"https://openalex.org/keywords/speech-translation","display_name":"Speech translation","score":0.4672797918319702},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.44695693254470825},{"id":"https://openalex.org/keywords/translation","display_name":"Translation (biology)","score":0.416535884141922},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.41595029830932617},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.41063764691352844}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8358573317527771},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7484585642814636},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.6585532426834106},{"id":"https://openalex.org/C203005215","wikidata":"https://www.wikidata.org/wiki/Q79798","display_name":"Machine translation","level":2,"score":0.5595716238021851},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.5406034588813782},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5191113948822021},{"id":"https://openalex.org/C2780366754","wikidata":"https://www.wikidata.org/wiki/Q7494857","display_name":"Speech translation","level":3,"score":0.4672797918319702},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.44695693254470825},{"id":"https://openalex.org/C149364088","wikidata":"https://www.wikidata.org/wiki/Q185917","display_name":"Translation (biology)","level":4,"score":0.416535884141922},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.41595029830932617},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.41063764691352844},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"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/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C105580179","wikidata":"https://www.wikidata.org/wiki/Q188928","display_name":"Messenger RNA","level":3,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp40776.2020.9053406","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp40776.2020.9053406","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":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.6399999856948853}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":28,"referenced_works":["https://openalex.org/W1522301498","https://openalex.org/W1970987322","https://openalex.org/W2101105183","https://openalex.org/W2124807415","https://openalex.org/W2605131327","https://openalex.org/W2785350307","https://openalex.org/W2936774411","https://openalex.org/W2945700568","https://openalex.org/W2947007461","https://openalex.org/W2963035245","https://openalex.org/W2963250244","https://openalex.org/W2964121744","https://openalex.org/W2964161387","https://openalex.org/W2964172053","https://openalex.org/W2972818416","https://openalex.org/W2972970915","https://openalex.org/W2982129078","https://openalex.org/W3007328579","https://openalex.org/W3012492057","https://openalex.org/W3096323553","https://openalex.org/W4300558631","https://openalex.org/W4394649814","https://openalex.org/W6631190155","https://openalex.org/W6748215858","https://openalex.org/W6761567302","https://openalex.org/W6763209921","https://openalex.org/W6769269733","https://openalex.org/W6898505805"],"related_works":["https://openalex.org/W3011059803","https://openalex.org/W4301342010","https://openalex.org/W158465921","https://openalex.org/W3151736118","https://openalex.org/W4362495644","https://openalex.org/W2261315194","https://openalex.org/W2338806053","https://openalex.org/W4385571610","https://openalex.org/W2293738010","https://openalex.org/W4360995948"],"abstract_inverted_index":{"We":[0],"propose":[1],"autoencoding":[2],"speaker":[3],"conversion":[4],"for":[5],"training":[6],"data":[7],"augmentation":[8,81],"in":[9,21,57,68],"automatic":[10,39,51],"speech":[11,40,52,116],"translation.":[12],"This":[13],"technique":[14],"directly":[15],"transforms":[16],"an":[17,100],"audio":[18,22],"sequence,":[19],"resulting":[20],"thesized":[23],"to":[24,33,85,114],"resemble":[25],"another":[26],"speaker's":[27],"voice.":[28],"Our":[29,104],"method":[30,105],"compares":[31],"favorably":[32],"SpecAugment":[34],"on":[35,47,99],"English-French":[36,101],"and":[37,66,118],"English-Romanian":[38],"translation":[41],"(AST)":[42],"tasks":[43],"as":[44,46],"well":[45],"a":[48,87,94],"low-resource":[49],"English":[50],"recognition":[53],"(ASR)":[54],"task.":[55,103],"Further,":[56],"ablations,":[58],"we":[59,72,75],"show":[60,73],"the":[61],"benefits":[62],"of":[63],"both":[64],"quantity":[65],"diversity":[67],"augmented":[69],"data.":[70],"Finally,":[71],"that":[74,92,109],"can":[76,111],"combine":[77],"our":[78],"approach":[79],"with":[80],"by":[82],"machine-translated":[83],"transcripts":[84],"obtain":[86],"competitive":[88],"end-to-end":[89],"AST":[90,102],"model":[91,98],"outperforms":[93],"very":[95],"strong":[96],"cascade":[97],"is":[106],"sufficiently":[107],"general":[108],"it":[110],"be":[112],"applied":[113],"other":[115],"generation":[117],"analysis":[119],"tasks.":[120]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2023,"cited_by_count":6},{"year":2022,"cited_by_count":4},{"year":2021,"cited_by_count":5},{"year":2020,"cited_by_count":5}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}