{"id":"https://openalex.org/W3011712140","doi":"https://doi.org/10.1109/apsipaasc47483.2019.9023040","title":"Semi-supervised Training of Acoustic Models Leveraging Knowledge Transferred from Out-of-Domain Data","display_name":"Semi-supervised Training of Acoustic Models Leveraging Knowledge Transferred from Out-of-Domain Data","publication_year":2019,"publication_date":"2019-11-01","ids":{"openalex":"https://openalex.org/W3011712140","doi":"https://doi.org/10.1109/apsipaasc47483.2019.9023040","mag":"3011712140"},"language":"en","primary_location":{"id":"doi:10.1109/apsipaasc47483.2019.9023040","is_oa":false,"landing_page_url":"https://doi.org/10.1109/apsipaasc47483.2019.9023040","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)","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/A5110596981","display_name":"Tien-Hong Lo","orcid":null},"institutions":[{"id":"https://openalex.org/I134161618","display_name":"National Taiwan Normal University","ror":"https://ror.org/059dkdx38","country_code":"TW","type":"education","lineage":["https://openalex.org/I134161618"]}],"countries":["TW"],"is_corresponding":true,"raw_author_name":"Tien-Hong Lo","raw_affiliation_strings":["National Taiwan Normal University, Taipei, Taiwan"],"affiliations":[{"raw_affiliation_string":"National Taiwan Normal University, Taipei, Taiwan","institution_ids":["https://openalex.org/I134161618"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5009731825","display_name":"Berlin Chen","orcid":null},"institutions":[{"id":"https://openalex.org/I4210149422","display_name":"Pervasive Artificial Intelligence Research Labs","ror":"https://ror.org/05qjw7v53","country_code":"TW","type":"facility","lineage":["https://openalex.org/I4210149422"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Berlin Chen","raw_affiliation_strings":["Pervasive Artificial Intelligence Research (PAIR) Labs, Taiwan"],"affiliations":[{"raw_affiliation_string":"Pervasive Artificial Intelligence Research (PAIR) Labs, Taiwan","institution_ids":["https://openalex.org/I4210149422"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5110596981"],"corresponding_institution_ids":["https://openalex.org/I134161618"],"apc_list":null,"apc_paid":null,"fwci":0.14,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.6059049,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":93},"biblio":{"volume":"27","issue":null,"first_page":"1400","last_page":"1404"},"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":0.9984999895095825,"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":0.9984999895095825,"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/discriminative-model","display_name":"Discriminative model","score":0.9109382629394531},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7824609279632568},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.6012247800827026},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5934829711914062},{"id":"https://openalex.org/keywords/correctness","display_name":"Correctness","score":0.5280562043190002},{"id":"https://openalex.org/keywords/labeled-data","display_name":"Labeled data","score":0.519365131855011},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.518550455570221},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.5156230330467224},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4917598068714142},{"id":"https://openalex.org/keywords/training","display_name":"Training (meteorology)","score":0.4551510810852051},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.41317838430404663},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.35386574268341064},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.0871959924697876}],"concepts":[{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.9109382629394531},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7824609279632568},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.6012247800827026},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5934829711914062},{"id":"https://openalex.org/C55439883","wikidata":"https://www.wikidata.org/wiki/Q360812","display_name":"Correctness","level":2,"score":0.5280562043190002},{"id":"https://openalex.org/C2776145971","wikidata":"https://www.wikidata.org/wiki/Q30673951","display_name":"Labeled data","level":2,"score":0.519365131855011},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.518550455570221},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.5156230330467224},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4917598068714142},{"id":"https://openalex.org/C2777211547","wikidata":"https://www.wikidata.org/wiki/Q17141490","display_name":"Training (meteorology)","level":2,"score":0.4551510810852051},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.41317838430404663},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.35386574268341064},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0871959924697876},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","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/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"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/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/apsipaasc47483.2019.9023040","is_oa":false,"landing_page_url":"https://doi.org/10.1109/apsipaasc47483.2019.9023040","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/10","score":0.6899999976158142,"display_name":"Reduced inequalities"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":43,"referenced_works":["https://openalex.org/W82886505","https://openalex.org/W176510440","https://openalex.org/W1494198834","https://openalex.org/W1513862252","https://openalex.org/W1524333225","https://openalex.org/W1569447338","https://openalex.org/W1588593315","https://openalex.org/W1965842648","https://openalex.org/W1975953721","https://openalex.org/W1978660892","https://openalex.org/W1986614398","https://openalex.org/W1993660824","https://openalex.org/W2025198378","https://openalex.org/W2058552721","https://openalex.org/W2080005694","https://openalex.org/W2085598899","https://openalex.org/W2087006792","https://openalex.org/W2124558353","https://openalex.org/W2139453310","https://openalex.org/W2145494108","https://openalex.org/W2150769028","https://openalex.org/W2165698076","https://openalex.org/W2170461116","https://openalex.org/W2293363371","https://openalex.org/W2295582178","https://openalex.org/W2345393872","https://openalex.org/W2346660049","https://openalex.org/W2407793339","https://openalex.org/W2514741789","https://openalex.org/W2616180702","https://openalex.org/W2617565145","https://openalex.org/W2786459654","https://openalex.org/W2802248956","https://openalex.org/W2963522845","https://openalex.org/W6603381559","https://openalex.org/W6607081860","https://openalex.org/W6630673164","https://openalex.org/W6631362777","https://openalex.org/W6633847657","https://openalex.org/W6648822320","https://openalex.org/W6681588610","https://openalex.org/W6697274609","https://openalex.org/W6713823255"],"related_works":["https://openalex.org/W3172695526","https://openalex.org/W1757117718","https://openalex.org/W2889166412","https://openalex.org/W2130553454","https://openalex.org/W3022007134","https://openalex.org/W4317548404","https://openalex.org/W2087783760","https://openalex.org/W1509924131","https://openalex.org/W3104108945","https://openalex.org/W2033364610"],"abstract_inverted_index":{"More":[0],"recently,":[1],"a":[2,34,46,82,87,142],"novel":[3,127],"objective":[4],"function":[5],"of":[6,37,48,57,69,90,105,112,120,145,167,178],"discriminative":[7,106],"acoustic":[8,70],"model":[9,71,84],"training,":[10],"namely":[11],"lattice-free":[12],"MMI":[13],"(LF-MMI),":[14],"has":[15],"been":[16],"proposed":[17],"and":[18,195,202],"achieved":[19],"the":[20,55,63,74,103,121,151,168,182,187],"new":[21],"state-of-the-art":[22],"in":[23,33,54,156],"automatic":[24],"speech":[25,113],"recognition":[26],"(ASR).":[27],"Although":[28],"LF-MMI":[29],"shows":[30],"excellent":[31],"performance":[32,104],"wide":[35],"array":[36],"ASR":[38],"tasks":[39],"with":[40],"supervised":[41],"training":[42,107,139],"settings,":[43],"there":[44],"is":[45,78,94,98,108,134,162],"dearth":[47],"work":[49],"on":[50,181],"investigating":[51],"its":[52],"effectiveness":[53,201],"scenario":[56],"unsupervised":[58],"or":[59],"semi-supervised":[60,66,157,174],"training.":[61,117,158,175],"On":[62],"other":[64],"hand,":[65],"(or":[67],"self-training)":[68],"suffers":[72],"from":[73,141,189],"problem":[75],"that":[76,102],"it":[77],"hard":[79],"to":[80,110,129,135,148,163],"estimate":[81,150],"good":[83],"when":[85],"only":[86],"limited":[88],"amount":[89,144],"correctly":[91],"transcribed":[92],"data":[93,147,172],"made":[95],"available.":[96],"It":[97],"also":[99,198],"generally":[100],"acknowledged":[101],"vulnerable":[109],"correctness":[111],"transcripts":[114],"employed":[115],"for":[116,154,173],"In":[118],"view":[119],"above,":[122],"this":[123],"paper":[124],"explores":[125],"two":[126,191],"extensions":[128,192],"LF-MMI.":[130],"The":[131,159],"first":[132],"one":[133,161],"distill":[136],"knowledge":[137],"(acoustic":[138],"statistics)":[140],"large":[143],"out-of-domain":[146],"better":[149],"seed":[152],"models":[153],"use":[155],"second":[160],"make":[164],"effective":[165],"selection":[166],"untranscribed":[169],"target":[170],"domain":[171],"A":[176],"series":[177],"experiments":[179],"conducted":[180],"AMI":[183],"benchmark":[184],"corpus":[185],"demonstrate":[186],"gains":[188],"these":[190],"are":[193],"pronounced":[194],"additive,":[196],"which":[197],"reveals":[199],"their":[200],"viability.":[203]},"counts_by_year":[{"year":2021,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}