{"id":"https://openalex.org/W4225827662","doi":"https://doi.org/10.21437/interspeech.2022-10422","title":"PM-MMUT: Boosted Phone-mask Data Augmentation using Multi-Modeling Unit Training for Phonetic-Reduction-Robust E2E Speech Recognition","display_name":"PM-MMUT: Boosted Phone-mask Data Augmentation using Multi-Modeling Unit Training for Phonetic-Reduction-Robust E2E Speech Recognition","publication_year":2022,"publication_date":"2022-09-16","ids":{"openalex":"https://openalex.org/W4225827662","doi":"https://doi.org/10.21437/interspeech.2022-10422"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2022-10422","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2022-10422","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/A5052807371","display_name":"Guodong Ma","orcid":"https://orcid.org/0009-0005-1910-7494"},"institutions":[{"id":"https://openalex.org/I96908189","display_name":"Xinjiang University","ror":"https://ror.org/059gw8r13","country_code":"CN","type":"education","lineage":["https://openalex.org/I96908189"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Guodong Ma","raw_affiliation_strings":["School of Information Science and Engineering, Xinjiang University, Urumqi, China"],"affiliations":[{"raw_affiliation_string":"School of Information Science and Engineering, Xinjiang University, Urumqi, China","institution_ids":["https://openalex.org/I96908189"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100703624","display_name":"Pengfei Hu","orcid":"https://orcid.org/0009-0000-4537-6288"},"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":"Pengfei Hu","raw_affiliation_strings":["Tencent Minority-Mandarin Translation, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Tencent Minority-Mandarin Translation, Beijing, China","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5076021252","display_name":"Nurmemet Yolwas","orcid":null},"institutions":[{"id":"https://openalex.org/I96908189","display_name":"Xinjiang University","ror":"https://ror.org/059gw8r13","country_code":"CN","type":"education","lineage":["https://openalex.org/I96908189"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Nurmemet Yolwas","raw_affiliation_strings":["School of Information Science and Engineering, Xinjiang University, Urumqi, China","Xinjiang Key Laboratory of Multi-lingual Information Technology, Urumqi, China"],"affiliations":[{"raw_affiliation_string":"School of Information Science and Engineering, Xinjiang University, Urumqi, China","institution_ids":["https://openalex.org/I96908189"]},{"raw_affiliation_string":"Xinjiang Key Laboratory of Multi-lingual Information Technology, Urumqi, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5108615106","display_name":"Shen Huang","orcid":null},"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":"Shen Huang","raw_affiliation_strings":["Tencent Minority-Mandarin Translation, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Tencent Minority-Mandarin Translation, Beijing, China","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101667364","display_name":"Hao Huang","orcid":"https://orcid.org/0000-0002-9131-5854"},"institutions":[{"id":"https://openalex.org/I96908189","display_name":"Xinjiang University","ror":"https://ror.org/059gw8r13","country_code":"CN","type":"education","lineage":["https://openalex.org/I96908189"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Hao Huang","raw_affiliation_strings":["School of Information Science and Engineering, Xinjiang University, Urumqi, China","Xinjiang Key Laboratory of Multi-lingual Information Technology, Urumqi, China"],"affiliations":[{"raw_affiliation_string":"School of Information Science and Engineering, Xinjiang University, Urumqi, China","institution_ids":["https://openalex.org/I96908189"]},{"raw_affiliation_string":"Xinjiang Key Laboratory of Multi-lingual Information Technology, Urumqi, China","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5101667364"],"corresponding_institution_ids":["https://openalex.org/I96908189"],"apc_list":null,"apc_paid":null,"fwci":0.313,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.48505564,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"1021","last_page":"1025"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":1.0,"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":1.0,"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":0.9990000128746033,"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/T10403","display_name":"Phonetics and Phonology Research","score":0.996399998664856,"subfield":{"id":"https://openalex.org/subfields/3205","display_name":"Experimental and Cognitive Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7676025629043579},{"id":"https://openalex.org/keywords/phone","display_name":"Phone","score":0.7483968138694763},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7481724619865417},{"id":"https://openalex.org/keywords/reduction","display_name":"Reduction (mathematics)","score":0.6441389322280884},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.5368090271949768},{"id":"https://openalex.org/keywords/training","display_name":"Training (meteorology)","score":0.4577864408493042},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.35607048869132996},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3291946053504944}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7676025629043579},{"id":"https://openalex.org/C2778707766","wikidata":"https://www.wikidata.org/wiki/Q202064","display_name":"Phone","level":2,"score":0.7483968138694763},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7481724619865417},{"id":"https://openalex.org/C111335779","wikidata":"https://www.wikidata.org/wiki/Q3454686","display_name":"Reduction (mathematics)","level":2,"score":0.6441389322280884},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.5368090271949768},{"id":"https://openalex.org/C2777211547","wikidata":"https://www.wikidata.org/wiki/Q17141490","display_name":"Training (meteorology)","level":2,"score":0.4577864408493042},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.35607048869132996},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3291946053504944},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","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/C153294291","wikidata":"https://www.wikidata.org/wiki/Q25261","display_name":"Meteorology","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21437/interspeech.2022-10422","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2022-10422","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":0.5}],"awards":[{"id":"https://openalex.org/G3100194551","display_name":null,"funder_award_id":"61761041","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G6861194883","display_name":null,"funder_award_id":"61663044","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":32,"referenced_works":["https://openalex.org/W1494198834","https://openalex.org/W1524333225","https://openalex.org/W1828163288","https://openalex.org/W2127141656","https://openalex.org/W2327501763","https://openalex.org/W2407080277","https://openalex.org/W2884254529","https://openalex.org/W2892009249","https://openalex.org/W2895417874","https://openalex.org/W2936774411","https://openalex.org/W2962780374","https://openalex.org/W2963250244","https://openalex.org/W2963303028","https://openalex.org/W3010788072","https://openalex.org/W3015995734","https://openalex.org/W3081794953","https://openalex.org/W3095189764","https://openalex.org/W3095229326","https://openalex.org/W3097777922","https://openalex.org/W3162249256","https://openalex.org/W3163487528","https://openalex.org/W3163702140","https://openalex.org/W3163793923","https://openalex.org/W3163839574","https://openalex.org/W3196843354","https://openalex.org/W3197507772","https://openalex.org/W3197849864","https://openalex.org/W3197898596","https://openalex.org/W4286908913","https://openalex.org/W4287029597","https://openalex.org/W4287118787","https://openalex.org/W4287630531"],"related_works":["https://openalex.org/W230091440","https://openalex.org/W2233261550","https://openalex.org/W2810751659","https://openalex.org/W258997015","https://openalex.org/W2997094352","https://openalex.org/W3216976533","https://openalex.org/W100620283","https://openalex.org/W2061937230","https://openalex.org/W4394050964","https://openalex.org/W2551249631"],"abstract_inverted_index":{"Consonant":[0],"and":[1,62,103],"vowel":[2],"reduction":[3,161],"are":[4],"often":[5],"encountered":[6],"in":[7,14,36],"speech,":[8],"which":[9,155],"might":[10],"cause":[11],"performance":[12,69],"degradation":[13],"automatic":[15],"speech":[16],"recognition":[17],"(ASR).Our":[18],"recently":[19],"proposed":[20,138],"learning":[21],"strategy":[22],"based":[23],"on":[24,132,148,162],"masking,":[25],"Phone":[26],"Masking":[27],"Training":[28],"(PMT),":[29],"alleviates":[30],"the":[31,52,56,63,68,90,123,137,142,149,164,172],"impact":[32],"of":[33,59,70,84],"such":[34],"phenomenon":[35],"Uyghur":[37,133],"ASR.Although":[38],"PMT":[39,60,81],"achieves":[40,156],"remarkably":[41],"improvements,":[42],"there":[43],"still":[44],"exists":[45],"room":[46],"for":[47],"further":[48],"gains":[49],"due":[50],"to":[51,88,99,106,112,121],"granularity":[53],"mismatch":[54],"between":[55],"masking":[57],"unit":[58,65,75],"(phoneme)":[61],"modeling":[64],"(word-piece).To":[66],"boost":[67],"PMT,":[71],"we":[72],"propose":[73],"multi-modeling":[74],"training":[76],"(MMUT)":[77],"architecture":[78],"fusion":[79,169],"with":[80,171],"(PM-MMUT).The":[82],"idea":[83],"MMUT":[85],"framework":[86],"is":[87],"split":[89],"Encoder":[91],"into":[92],"two":[93],"parts":[94],"including":[95],"acoustic":[96],"feature":[97],"sequences":[98],"phoneme-level":[100,104,125],"representation":[101,105,108],"(AF-to-PLR)":[102],"word-piece-level":[107],"(PLR-to-WPLR).It":[109],"allows":[110],"AF-to-PLR":[111],"be":[113],"optimized":[114],"by":[115,129],"an":[116],"intermediate":[117],"phoneme-based":[118],"CTC":[119],"loss":[120],"learn":[122],"rich":[124],"context":[126],"information":[127],"brought":[128],"PMT.Experimental":[130],"results":[131],"ASR":[134],"show":[135],"that":[136],"approaches":[139],"outperform":[140],"obviously":[141],"pure":[143],"PMT.We":[144],"also":[145],"conduct":[146],"experiments":[147],"960-hour":[150],"Librispeech":[151],"benchmark":[152],"using":[153],"ES-Pnet1,":[154],"about":[157],"10%":[158],"relative":[159],"WER":[160],"all":[163],"test":[165],"set":[166],"without":[167],"LM":[168],"comparing":[170],"latest":[173],"official":[174],"ESPnet1":[175],"pre-trained":[176],"model.":[177]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":1}],"updated_date":"2026-04-21T08:09:41.155169","created_date":"2025-10-10T00:00:00"}