{"id":"https://openalex.org/W4285192675","doi":"https://doi.org/10.1109/jstsp.2022.3186162","title":"Ask2Mask: Guided Data Selection for Masked Speech Modeling","display_name":"Ask2Mask: Guided Data Selection for Masked Speech Modeling","publication_year":2022,"publication_date":"2022-06-24","ids":{"openalex":"https://openalex.org/W4285192675","doi":"https://doi.org/10.1109/jstsp.2022.3186162"},"language":"en","primary_location":{"id":"doi:10.1109/jstsp.2022.3186162","is_oa":false,"landing_page_url":"https://doi.org/10.1109/jstsp.2022.3186162","pdf_url":null,"source":{"id":"https://openalex.org/S42167783","display_name":"IEEE Journal of Selected Topics in Signal Processing","issn_l":"1932-4553","issn":["1932-4553","1941-0484"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Journal of Selected Topics in Signal Processing","raw_type":"journal-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/A5064113992","display_name":"Murali Karthick Baskar","orcid":"https://orcid.org/0000-0002-9396-6319"},"institutions":[{"id":"https://openalex.org/I60587646","display_name":"Brno University of Technology","ror":"https://ror.org/03613d656","country_code":"CZ","type":"education","lineage":["https://openalex.org/I60587646"]}],"countries":["CZ"],"is_corresponding":true,"raw_author_name":"Murali Karthick Baskar","raw_affiliation_strings":["Faculty of Information Technology, Brno University of Technology, Brno-stred, Czechia"],"affiliations":[{"raw_affiliation_string":"Faculty of Information Technology, Brno University of Technology, Brno-stred, Czechia","institution_ids":["https://openalex.org/I60587646"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5024773539","display_name":"Andrew Rosenberg","orcid":null},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Andrew Rosenberg","raw_affiliation_strings":["Google. Inc., Mountain View, CA, USA"],"affiliations":[{"raw_affiliation_string":"Google. Inc., Mountain View, CA, USA","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5071715737","display_name":"Bhuvana Ramabhadran","orcid":null},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Bhuvana Ramabhadran","raw_affiliation_strings":["Google. Inc., Mountain View, CA, USA"],"affiliations":[{"raw_affiliation_string":"Google. Inc., Mountain View, CA, USA","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100433648","display_name":"Yu Zhang","orcid":"https://orcid.org/0000-0002-9505-1833"},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yu Zhang","raw_affiliation_strings":["Google. Inc., Mountain View, CA, USA"],"affiliations":[{"raw_affiliation_string":"Google. Inc., Mountain View, CA, USA","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5103874391","display_name":"Pedro J. Moreno","orcid":null},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Pedro Moreno","raw_affiliation_strings":["Google. Inc., Mountain View, CA, USA"],"affiliations":[{"raw_affiliation_string":"Google. Inc., Mountain View, CA, USA","institution_ids":["https://openalex.org/I1291425158"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5064113992"],"corresponding_institution_ids":["https://openalex.org/I60587646"],"apc_list":null,"apc_paid":null,"fwci":1.3262,"has_fulltext":false,"cited_by_count":10,"citation_normalized_percentile":{"value":0.83394679,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":"16","issue":"6","first_page":"1357","last_page":"1366"},"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":0.9940999746322632,"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/T10860","display_name":"Speech and Audio Processing","score":0.992900013923645,"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/utterance","display_name":"Utterance","score":0.8400416374206543},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7995293140411377},{"id":"https://openalex.org/keywords/weighting","display_name":"Weighting","score":0.7295826077461243},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.6655296087265015},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6444652676582336},{"id":"https://openalex.org/keywords/masking","display_name":"Masking (illustration)","score":0.6003796458244324},{"id":"https://openalex.org/keywords/selection","display_name":"Selection (genetic algorithm)","score":0.5982599258422852},{"id":"https://openalex.org/keywords/matching","display_name":"Matching (statistics)","score":0.5360216498374939},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5141685009002686},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4346611797809601},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.4330526292324066},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.11436823010444641},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.07542049884796143}],"concepts":[{"id":"https://openalex.org/C2775852435","wikidata":"https://www.wikidata.org/wiki/Q258403","display_name":"Utterance","level":2,"score":0.8400416374206543},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7995293140411377},{"id":"https://openalex.org/C183115368","wikidata":"https://www.wikidata.org/wiki/Q856577","display_name":"Weighting","level":2,"score":0.7295826077461243},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.6655296087265015},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6444652676582336},{"id":"https://openalex.org/C2777402240","wikidata":"https://www.wikidata.org/wiki/Q6783436","display_name":"Masking (illustration)","level":2,"score":0.6003796458244324},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.5982599258422852},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.5360216498374939},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5141685009002686},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4346611797809601},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.4330526292324066},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.11436823010444641},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.07542049884796143},{"id":"https://openalex.org/C126838900","wikidata":"https://www.wikidata.org/wiki/Q77604","display_name":"Radiology","level":1,"score":0.0},{"id":"https://openalex.org/C71924100","wikidata":"https://www.wikidata.org/wiki/Q11190","display_name":"Medicine","level":0,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C153349607","wikidata":"https://www.wikidata.org/wiki/Q36649","display_name":"Visual arts","level":1,"score":0.0},{"id":"https://openalex.org/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","level":1,"score":0.0},{"id":"https://openalex.org/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/jstsp.2022.3186162","is_oa":false,"landing_page_url":"https://doi.org/10.1109/jstsp.2022.3186162","pdf_url":null,"source":{"id":"https://openalex.org/S42167783","display_name":"IEEE Journal of Selected Topics in Signal Processing","issn_l":"1932-4553","issn":["1932-4553","1941-0484"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Journal of Selected Topics in Signal Processing","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.5799999833106995,"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":35,"referenced_works":["https://openalex.org/W1494198834","https://openalex.org/W2111316763","https://openalex.org/W2127141656","https://openalex.org/W2134659216","https://openalex.org/W2748795451","https://openalex.org/W2896457183","https://openalex.org/W2953356739","https://openalex.org/W2954732411","https://openalex.org/W3011411500","https://openalex.org/W3015522062","https://openalex.org/W3016010032","https://openalex.org/W3020336359","https://openalex.org/W3026041220","https://openalex.org/W3093579165","https://openalex.org/W3095189764","https://openalex.org/W3099664505","https://openalex.org/W3139918052","https://openalex.org/W3160525311","https://openalex.org/W3163464943","https://openalex.org/W3196219156","https://openalex.org/W3196919915","https://openalex.org/W3198270883","https://openalex.org/W3198771897","https://openalex.org/W4226033575","https://openalex.org/W4287646293","https://openalex.org/W6675401909","https://openalex.org/W6739901393","https://openalex.org/W6765715182","https://openalex.org/W6771915120","https://openalex.org/W6779857854","https://openalex.org/W6780218876","https://openalex.org/W6780236752","https://openalex.org/W6783754597","https://openalex.org/W6784614252","https://openalex.org/W6791904447"],"related_works":["https://openalex.org/W2529301793","https://openalex.org/W2384121599","https://openalex.org/W2038083449","https://openalex.org/W2562096895","https://openalex.org/W2180954594","https://openalex.org/W2333799855","https://openalex.org/W3177678247","https://openalex.org/W1999617572","https://openalex.org/W2052835778","https://openalex.org/W2944572343"],"abstract_inverted_index":{"Masked":[0],"speech":[1,13,42],"modeling":[2],"(MSM)":[3],"methods":[4,24],"such":[5],"as":[6,50,117],"wav2vec2":[7],"or":[8,89],"w2v-BERT":[9],"learn":[10,58,127],"representations":[11],"over":[12,111,194,201],"frames":[14,116],"which":[15,47],"are":[16],"randomly":[17],"masked":[18],"within":[19],"an":[20,85],"utterance.":[21],"While":[22],"these":[23],"improve":[25],"performance":[26,186],"of":[27,179],"Automatic":[28],"Speech":[29],"Recognition":[30],"(ASR)":[31],"systems,":[32],"they":[33],"have":[34,54],"one":[35],"major":[36],"limitation.":[37,67],"They":[38],"treat":[39],"all":[40,52],"unsupervised":[41,95],"samples":[43,53,79,97],"with":[44,145],"equal":[45],"weight,":[46],"hinders":[48],"learning":[49],"not":[51],"relevant":[55],"information":[56],"to":[57,75,93,126,135,191],"meaningful":[59,128],"representations.":[60,129],"In":[61],"this":[62,66],"work,":[63],"we":[64],"address":[65],"We":[68,150],"propose":[69],"ask2mask":[70],"(ATM),":[71],"a":[72],"novel":[73],"approach":[74],"focus":[76,136],"on":[77,154,181],"specific":[78],"during":[80],"MSM":[81,143],"pre-training.":[82],"ATM":[83,131,180],"employs":[84],"external":[86],"ASR":[87],"model":[88,125],"<italic":[90],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[91],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">scorer</i>":[92],"weight":[94],"input":[96,115],"in":[98],"two":[99,155],"different":[100],"ways:":[101],"1)":[102],"A":[103],"fine-grained":[104],"data":[105],"selection":[106],"is":[107,132],"performed":[108],"by":[109,119,139],"masking":[110],"the":[112,120,124,141,146,160,171,177,184],"highly":[113],"confident":[114],"chosen":[118],"scorer.":[121],"This":[122],"allows":[123],"2)":[130],"further":[133],"extended":[134],"at":[137],"utterance-level":[138,147],"weighting":[140],"final":[142],"loss":[144],"confidence":[148],"score.":[149],"conduct":[151],"fine-tuning":[152],"experiments":[153],"well-benchmarked":[156],"corpora:":[157],"LibriSpeech":[158],"(matching":[159],"pre-training":[161,172],"data)":[162],"and":[163,167,197],"Commonvoice,":[164],"TED-LIUM,":[165],"AMI":[166],"CHiME-6":[168],"(not":[169],"matching":[170],"data).":[173],"The":[174],"results":[175,196],"substantiate":[176],"efficacy":[178],"significantly":[182],"improving":[183],"recognition":[185],"under":[187,210],"mismatched":[188],"conditions":[189],"(up":[190],"11.6%":[192],"relative":[193,200],"published":[195],"upto":[198],"4.46%":[199],"our":[202],"internal":[203],"baseline)":[204],"while":[205],"still":[206],"yielding":[207],"modest":[208],"improvements":[209],"matched":[211],"conditions.":[212]},"counts_by_year":[{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":4}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}