{"id":"https://openalex.org/W4391021762","doi":"https://doi.org/10.1109/asru57964.2023.10389716","title":"Improving Large-Scale Deep Biasing With Phoneme Features and Text-Only Data in Streaming Transducer","display_name":"Improving Large-Scale Deep Biasing With Phoneme Features and Text-Only Data in Streaming Transducer","publication_year":2023,"publication_date":"2023-12-16","ids":{"openalex":"https://openalex.org/W4391021762","doi":"https://doi.org/10.1109/asru57964.2023.10389716"},"language":"en","primary_location":{"id":"doi:10.1109/asru57964.2023.10389716","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/asru57964.2023.10389716","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","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/A5114110864","display_name":"Jin Qiu","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Jin Qiu","raw_affiliation_strings":["ByteDance"],"affiliations":[{"raw_affiliation_string":"ByteDance","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100651264","display_name":"Lu Huang","orcid":"https://orcid.org/0000-0002-1064-7399"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Lu Huang","raw_affiliation_strings":["ByteDance"],"affiliations":[{"raw_affiliation_string":"ByteDance","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5106552530","display_name":"Boyu Li","orcid":"https://orcid.org/0000-0003-2425-936X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Boyu Li","raw_affiliation_strings":["ByteDance"],"affiliations":[{"raw_affiliation_string":"ByteDance","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5092136641","display_name":"Jun Zhang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jun Zhang","raw_affiliation_strings":["ByteDance"],"affiliations":[{"raw_affiliation_string":"ByteDance","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5013657813","display_name":"Lu Lu","orcid":"https://orcid.org/0000-0002-8834-1947"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Lu Lu","raw_affiliation_strings":["ByteDance"],"affiliations":[{"raw_affiliation_string":"ByteDance","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101108160","display_name":"Zejun Ma","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zejun Ma","raw_affiliation_strings":["ByteDance"],"affiliations":[{"raw_affiliation_string":"ByteDance","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5114110864"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.3411,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.68150553,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"8"},"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/T10181","display_name":"Natural Language Processing Techniques","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"}},{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9991000294685364,"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":0.7764273285865784},{"id":"https://openalex.org/keywords/pronunciation","display_name":"Pronunciation","score":0.7361586093902588},{"id":"https://openalex.org/keywords/biasing","display_name":"Biasing","score":0.6585206389427185},{"id":"https://openalex.org/keywords/spelling","display_name":"Spelling","score":0.6375064849853516},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5863361954689026},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.5794482827186584},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.5314596891403198},{"id":"https://openalex.org/keywords/scale","display_name":"Scale (ratio)","score":0.46977323293685913},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4231290817260742},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4122960567474365},{"id":"https://openalex.org/keywords/voltage","display_name":"Voltage","score":0.11741456389427185},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.09687107801437378},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.07031494379043579}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7764273285865784},{"id":"https://openalex.org/C2780844864","wikidata":"https://www.wikidata.org/wiki/Q184377","display_name":"Pronunciation","level":2,"score":0.7361586093902588},{"id":"https://openalex.org/C20254490","wikidata":"https://www.wikidata.org/wiki/Q719550","display_name":"Biasing","level":3,"score":0.6585206389427185},{"id":"https://openalex.org/C2777801307","wikidata":"https://www.wikidata.org/wiki/Q2088390","display_name":"Spelling","level":2,"score":0.6375064849853516},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5863361954689026},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.5794482827186584},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.5314596891403198},{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.46977323293685913},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4231290817260742},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4122960567474365},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.11741456389427185},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.09687107801437378},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.07031494379043579},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","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/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/asru57964.2023.10389716","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/asru57964.2023.10389716","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.75}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":49,"referenced_works":["https://openalex.org/W854541894","https://openalex.org/W1494198834","https://openalex.org/W1828163288","https://openalex.org/W2062227835","https://openalex.org/W2127141656","https://openalex.org/W2156387975","https://openalex.org/W2407080277","https://openalex.org/W2886319145","https://openalex.org/W2925513271","https://openalex.org/W2936774411","https://openalex.org/W2937402758","https://openalex.org/W2962784628","https://openalex.org/W2963747784","https://openalex.org/W2963970535","https://openalex.org/W2972625221","https://openalex.org/W2972818416","https://openalex.org/W2973172693","https://openalex.org/W3007328579","https://openalex.org/W3015194534","https://openalex.org/W3035207248","https://openalex.org/W3094667432","https://openalex.org/W3095311338","https://openalex.org/W3096815019","https://openalex.org/W3097777922","https://openalex.org/W3097794466","https://openalex.org/W3140235797","https://openalex.org/W3160413945","https://openalex.org/W3197438100","https://openalex.org/W3198004110","https://openalex.org/W3198602963","https://openalex.org/W3211278025","https://openalex.org/W4223954171","https://openalex.org/W4224918838","https://openalex.org/W4225308107","https://openalex.org/W4225985539","https://openalex.org/W4226120743","https://openalex.org/W4226462878","https://openalex.org/W4296069324","https://openalex.org/W4297841248","https://openalex.org/W4319862261","https://openalex.org/W4319862474","https://openalex.org/W4372259757","https://openalex.org/W4372266720","https://openalex.org/W4375869024","https://openalex.org/W4385822246","https://openalex.org/W4385822500","https://openalex.org/W6623517193","https://openalex.org/W6638749077","https://openalex.org/W6682889407"],"related_works":["https://openalex.org/W2100947578","https://openalex.org/W2161008081","https://openalex.org/W1555832326","https://openalex.org/W4298186509","https://openalex.org/W2556702969","https://openalex.org/W217221262","https://openalex.org/W611030372","https://openalex.org/W1974418053","https://openalex.org/W2081317458","https://openalex.org/W2944691285"],"abstract_inverted_index":{"Deep":[0],"biasing":[1,31],"for":[2,23,117],"the":[3,7,39,56,64,83,101,106],"Transducer":[4],"can":[5],"improve":[6],"recognition":[8],"performance":[9,40,111],"of":[10,69,85,122],"rare":[11,34,70,92,113],"words":[12,35,50,71,76,93],"or":[13,80],"contextual":[14],"entities,":[15],"which":[16],"is":[17],"essential":[18],"in":[19,55,72],"practical":[20],"applications,":[21],"especially":[22],"streaming":[24],"Automatic":[25],"Speech":[26],"Recognition":[27],"(ASR).":[28],"However,":[29],"deep":[30,96],"with":[32,51,77,87],"large-scale":[33,95],"remains":[36],"challenging,":[37],"as":[38],"drops":[41],"significantly":[42],"when":[43],"more":[44,91],"distractors":[45],"exist":[46],"and":[47,66,120],"there":[48],"are":[49],"similar":[52,78],"grapheme":[53],"sequences":[54],"bias":[57,123],"list.":[58],"In":[59],"this":[60],"paper,":[61],"we":[62],"combine":[63],"phoneme":[65],"textual":[67],"information":[68],"Transducers":[73],"to":[74],"distinguish":[75],"pronunciation":[79],"spelling.":[81],"Moreover,":[82],"introduction":[84],"training":[86],"text-only":[88],"data":[89],"containing":[90],"benefits":[94],"biasing.":[97],"The":[98],"experiments":[99],"on":[100,112],"Librispeech":[102],"corpus":[103],"demonstrate":[104],"that":[105],"proposed":[107],"method":[108],"achieves":[109],"state-of-the-art":[110],"word":[114],"error":[115],"rate":[116],"different":[118],"scales":[119],"levels":[121],"lists.":[124]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2024,"cited_by_count":1}],"updated_date":"2026-04-23T09:07:50.710637","created_date":"2025-10-10T00:00:00"}