{"id":"https://openalex.org/W2972847736","doi":"https://doi.org/10.21437/interspeech.2019-1880","title":"End-to-End Adaptation with Backpropagation Through WFST for On-Device Speech Recognition System","display_name":"End-to-End Adaptation with Backpropagation Through WFST for On-Device Speech Recognition System","publication_year":2019,"publication_date":"2019-09-13","ids":{"openalex":"https://openalex.org/W2972847736","doi":"https://doi.org/10.21437/interspeech.2019-1880","mag":"2972847736"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2019-1880","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2019-1880","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2019","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/A5011937407","display_name":"Emiru Tsunoo","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Emiru Tsunoo","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5109644502","display_name":"Yosuke Kashiwagi","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yosuke Kashiwagi","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103581782","display_name":"Satoshi Asakawa","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Satoshi Asakawa","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5084435555","display_name":"Toshiyuki Kumakura","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Toshiyuki Kumakura","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.4374,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.67155116,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"764","last_page":"768"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.998199999332428,"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":0.998199999332428,"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":0.9922000169754028,"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/T11447","display_name":"Blind Source Separation Techniques","score":0.932699978351593,"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":0.8207687735557556},{"id":"https://openalex.org/keywords/vocabulary","display_name":"Vocabulary","score":0.7196563482284546},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7066314816474915},{"id":"https://openalex.org/keywords/discriminative-model","display_name":"Discriminative model","score":0.6837740540504456},{"id":"https://openalex.org/keywords/adaptation","display_name":"Adaptation (eye)","score":0.6447458267211914},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.5623224973678589},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.5462441444396973},{"id":"https://openalex.org/keywords/backpropagation","display_name":"Backpropagation","score":0.5182021260261536},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5149500966072083},{"id":"https://openalex.org/keywords/recurrent-neural-network","display_name":"Recurrent neural network","score":0.4844694137573242},{"id":"https://openalex.org/keywords/decoding-methods","display_name":"Decoding methods","score":0.4503905475139618},{"id":"https://openalex.org/keywords/computation","display_name":"Computation","score":0.4367069602012634},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4027279019355774}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8207687735557556},{"id":"https://openalex.org/C2777601683","wikidata":"https://www.wikidata.org/wiki/Q6499736","display_name":"Vocabulary","level":2,"score":0.7196563482284546},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7066314816474915},{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.6837740540504456},{"id":"https://openalex.org/C139807058","wikidata":"https://www.wikidata.org/wiki/Q352374","display_name":"Adaptation (eye)","level":2,"score":0.6447458267211914},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.5623224973678589},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5462441444396973},{"id":"https://openalex.org/C155032097","wikidata":"https://www.wikidata.org/wiki/Q798503","display_name":"Backpropagation","level":3,"score":0.5182021260261536},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5149500966072083},{"id":"https://openalex.org/C147168706","wikidata":"https://www.wikidata.org/wiki/Q1457734","display_name":"Recurrent neural network","level":3,"score":0.4844694137573242},{"id":"https://openalex.org/C57273362","wikidata":"https://www.wikidata.org/wiki/Q576722","display_name":"Decoding methods","level":2,"score":0.4503905475139618},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.4367069602012634},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4027279019355774},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","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},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","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/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21437/interspeech.2019-1880","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2019-1880","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2019","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.699999988079071,"id":"https://metadata.un.org/sdg/10","display_name":"Reduced inequalities"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4389116644","https://openalex.org/W2153315159","https://openalex.org/W3103844505","https://openalex.org/W259157601","https://openalex.org/W4205463238","https://openalex.org/W2761785940","https://openalex.org/W1482209366","https://openalex.org/W4239286941","https://openalex.org/W2053269318","https://openalex.org/W2088845016"],"abstract_inverted_index":{"An":[0],"on-device":[1],"DNN-HMM":[2],"speech":[3],"recognition":[4,158],"system":[5,72,165],"efficiently":[6],"works":[7,183],"with":[8,80,87],"a":[9,16,23,37,54,61,65,105,143],"limited":[10],"vocabulary":[11,25,106],"in":[12],"the":[13,71,129,152,156,167,171,175,179],"presence":[14],"of":[15,18,40,123,131,136,151],"variety":[17],"predictable":[19],"noise.":[20],"In":[21,32],"such":[22],"case,":[24],"and":[26,69,113,134,147,174],"environment":[27],"adaptation":[28,125,145,172],"is":[29,93,111],"highly":[30],"effective.":[31],"this":[33],"paper,":[34],"we":[35],"propose":[36],"novel":[38],"method":[39,181],"end-to-end":[41],"(E2E)":[42],"adaptation,":[43],"which":[44,92],"adjusts":[45],"not":[46],"only":[47,132,137],"an":[48,81],"acoustic":[49],"model":[50],"(AM)":[51],"but":[52],"also":[53,161,182],"weighted":[55],"finite-state":[56],"transducer":[57],"(WFST).":[58],"We":[59,83,160],"convert":[60],"pretrained":[62],"WFST":[63],"to":[64,73,95,142,166],"trainable":[66],"neural":[67,89,97],"network":[68,90],"adapt":[70,162],"target":[74],"environments/vocabulary":[75],"by":[76],"E2E":[77,148],"joint":[78,149],"training":[79,150],"AM.":[82],"replicate":[84],"Viterbi":[85],"decoding":[86],"forward--backward":[88],"computation,":[91],"similar":[94],"recurrent":[96],"networks":[98],"(RNNs).":[99],"By":[100],"pooling":[101],"output":[102],"score":[103],"sequences,":[104],"posterior":[107],"for":[108,115,185],"each":[109,163],"utterance":[110],"obtained":[112],"used":[114],"discriminative":[116],"loss":[117],"computation.":[118],"Experiments":[119],"using":[120,170],"2--10":[121],"hours":[122],"English/Japanese":[124],"datasets":[126],"indicate":[127],"that":[128,135,178],"fine-tuning":[130],"WFSTs":[133],"AMs":[138],"are":[139],"both":[140],"comparable":[141],"state-of-the-art":[144],"method,":[146],"two":[153],"components":[154],"achieves":[155],"best":[157],"performance.":[159],"language":[164,169,186],"other":[168],"data,":[173],"results":[176],"show":[177],"proposed":[180],"well":[184],"adaptations.":[187]},"counts_by_year":[{"year":2023,"cited_by_count":1},{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":2}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}