{"id":"https://openalex.org/W4372260231","doi":"https://doi.org/10.1109/icassp49357.2023.10096944","title":"Anchored Speech Recognition with Neural Transducers","display_name":"Anchored Speech Recognition with Neural Transducers","publication_year":2023,"publication_date":"2023-05-05","ids":{"openalex":"https://openalex.org/W4372260231","doi":"https://doi.org/10.1109/icassp49357.2023.10096944"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49357.2023.10096944","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49357.2023.10096944","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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/A5004777817","display_name":"Desh Raj","orcid":"https://orcid.org/0000-0002-5038-9400"},"institutions":[{"id":"https://openalex.org/I145311948","display_name":"Johns Hopkins University","ror":"https://ror.org/00za53h95","country_code":"US","type":"education","lineage":["https://openalex.org/I145311948"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Desh Raj","raw_affiliation_strings":["Johns Hopkins University,Center for Language and Speech Processing,USA","Center for Language and Speech Processing, Johns Hopkins University, USA"],"affiliations":[{"raw_affiliation_string":"Johns Hopkins University,Center for Language and Speech Processing,USA","institution_ids":["https://openalex.org/I145311948"]},{"raw_affiliation_string":"Center for Language and Speech Processing, Johns Hopkins University, USA","institution_ids":["https://openalex.org/I145311948"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5113970008","display_name":"Junteng Jia","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Junteng Jia","raw_affiliation_strings":["Meta AI,USA","Meta AI, USA"],"affiliations":[{"raw_affiliation_string":"Meta AI,USA","institution_ids":[]},{"raw_affiliation_string":"Meta AI, USA","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5074237839","display_name":"Jay Mahadeokar","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jay Mahadeokar","raw_affiliation_strings":["Meta AI,USA","Meta AI, USA"],"affiliations":[{"raw_affiliation_string":"Meta AI,USA","institution_ids":[]},{"raw_affiliation_string":"Meta AI, USA","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103012144","display_name":"Chunyang Wu","orcid":"https://orcid.org/0000-0002-5796-8288"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chunyang Wu","raw_affiliation_strings":["Meta AI,USA","Meta AI, USA"],"affiliations":[{"raw_affiliation_string":"Meta AI,USA","institution_ids":[]},{"raw_affiliation_string":"Meta AI, USA","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5013781881","display_name":"Niko Moritz","orcid":"https://orcid.org/0000-0003-4352-8115"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Niko Moritz","raw_affiliation_strings":["Meta AI,USA","Meta AI, USA"],"affiliations":[{"raw_affiliation_string":"Meta AI,USA","institution_ids":[]},{"raw_affiliation_string":"Meta AI, USA","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5062542406","display_name":"Xiaohui Zhang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xiaohui Zhang","raw_affiliation_strings":["Meta AI,USA","Meta AI, USA"],"affiliations":[{"raw_affiliation_string":"Meta AI,USA","institution_ids":[]},{"raw_affiliation_string":"Meta AI, USA","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5066166549","display_name":"Ozlem Kalinli","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ozlem Kalinli","raw_affiliation_strings":["Meta AI,USA","Meta AI, USA"],"affiliations":[{"raw_affiliation_string":"Meta AI,USA","institution_ids":[]},{"raw_affiliation_string":"Meta AI, USA","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5004777817"],"corresponding_institution_ids":["https://openalex.org/I145311948"],"apc_list":null,"apc_paid":null,"fwci":0.3497,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.63043543,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":95,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"5"},"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":0.9997000098228455,"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":0.9983999729156494,"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/speech-recognition","display_name":"Speech recognition","score":0.7948839068412781},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7717115879058838},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.6326820850372314},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.5267873406410217},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.4628322422504425},{"id":"https://openalex.org/keywords/voice-activity-detection","display_name":"Voice activity detection","score":0.442289263010025},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.4128211736679077},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3446142375469208},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.32805079221725464},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.32087910175323486}],"concepts":[{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7948839068412781},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7717115879058838},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.6326820850372314},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.5267873406410217},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.4628322422504425},{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.442289263010025},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.4128211736679077},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3446142375469208},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.32805079221725464},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.32087910175323486},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49357.2023.10096944","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49357.2023.10096944","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":37,"referenced_works":["https://openalex.org/W1494198834","https://openalex.org/W1522301498","https://openalex.org/W1828163288","https://openalex.org/W2127141656","https://openalex.org/W2327501763","https://openalex.org/W2526425061","https://openalex.org/W2749659773","https://openalex.org/W2891833136","https://openalex.org/W2912512634","https://openalex.org/W2962760690","https://openalex.org/W2963596039","https://openalex.org/W2972705840","https://openalex.org/W2975044525","https://openalex.org/W3007227084","https://openalex.org/W3008525923","https://openalex.org/W3015927303","https://openalex.org/W3018441253","https://openalex.org/W3096090308","https://openalex.org/W3096888553","https://openalex.org/W3144557079","https://openalex.org/W3146505093","https://openalex.org/W3148386121","https://openalex.org/W3149509723","https://openalex.org/W3161354387","https://openalex.org/W3162665866","https://openalex.org/W3197381252","https://openalex.org/W3198413388","https://openalex.org/W4226428303","https://openalex.org/W4286695273","https://openalex.org/W4295312788","https://openalex.org/W6631190155","https://openalex.org/W6638749077","https://openalex.org/W6754734105","https://openalex.org/W6766978945","https://openalex.org/W6768205276","https://openalex.org/W6785769429","https://openalex.org/W6795754764"],"related_works":["https://openalex.org/W191108438","https://openalex.org/W3135230428","https://openalex.org/W2904739811","https://openalex.org/W249088392","https://openalex.org/W2152158029","https://openalex.org/W2012540220","https://openalex.org/W2559837139","https://openalex.org/W2131711534","https://openalex.org/W2559040841","https://openalex.org/W114661351"],"abstract_inverted_index":{"Neural":[0],"transducers":[1,70],"have":[2],"achieved":[3],"human":[4],"level":[5],"performance":[6,14],"on":[7,128],"standard":[8],"speech":[9,33,53,65],"recognition":[10,34,66],"benchmarks.":[11],"However,":[12],"their":[13],"significantly":[15],"degrades":[16],"in":[17],"the":[18,24,80,97,100,106],"presence":[19],"of":[20,39,108],"cross-talk,":[21],"especially":[22],"when":[23,150],"primary":[25],"speaker":[26],"has":[27],"a":[28,37,84,147],"low":[29],"signal-to-noise":[30],"ratio.":[31],"Anchored":[32],"refers":[35],"to":[36,50,67,72,95,104,117],"class":[38],"methods":[40,127],"that":[41],"use":[42,89],"information":[43,78],"from":[44,79,121],"an":[45],"anchor":[46,81],"segment":[47,82],"(e.g.,":[48],"wake-words)":[49],"recognize":[51],"device-directed":[52],"while":[54],"ignoring":[55],"interfering":[56],"background":[57,73],"speech.":[58,74,102],"In":[59],"this":[60],"paper,":[61],"we":[62,112],"investigate":[63],"anchored":[64],"make":[68],"neural":[69],"robust":[71],"We":[75,124],"extract":[76],"context":[77,109],"with":[83],"tiny":[85],"auxiliary":[86,114],"network,":[87],"and":[88,92,135],"encoder":[90],"biasing":[91],"joiner":[93],"gating":[94],"guide":[96],"transducer":[98],"towards":[99],"target":[101],"Moreover,":[103],"improve":[105,139],"robustness":[107],"embedding":[110],"extraction,":[111],"propose":[113],"training":[115],"objectives":[116],"disentangle":[118],"lexical":[119],"content":[120],"speaking":[122],"style.":[123],"evaluate":[125],"our":[126],"synthetic":[129],"LibriSpeech-based":[130],"mixtures":[131],"comprising":[132],"several":[133],"SNR":[134],"overlap":[136],"conditions;":[137],"they":[138],"relative":[140],"word":[141],"error":[142],"rates":[143],"by":[144],"19.6%":[145],"over":[146,152],"strong":[148],"baseline,":[149],"averaged":[151],"all":[153],"conditions.":[154]},"counts_by_year":[{"year":2025,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
