{"id":"https://openalex.org/W2972721952","doi":"https://doi.org/10.21437/interspeech.2019-3137","title":"Performance Monitoring for End-to-End Speech Recognition","display_name":"Performance Monitoring for End-to-End Speech Recognition","publication_year":2019,"publication_date":"2019-09-13","ids":{"openalex":"https://openalex.org/W2972721952","doi":"https://doi.org/10.21437/interspeech.2019-3137","mag":"2972721952"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2019-3137","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2019-3137","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/A5100760516","display_name":"Ruizhi Li","orcid":"https://orcid.org/0000-0002-2496-5224"},"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":false,"raw_author_name":"Ruizhi Li","raw_affiliation_strings":["Center for Language and Speech Processing, The Johns Hopkins University, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Center for Language and Speech Processing, The Johns Hopkins University, USA","institution_ids":["https://openalex.org/I145311948"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5046596198","display_name":"Gregory Sell","orcid":null},"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":false,"raw_author_name":"Gregory Sell","raw_affiliation_strings":["Center for Language and Speech Processing, The Johns Hopkins University, USA","Human Language Technology Center of Excellence, The Johns Hopkins University, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Center for Language and Speech Processing, The Johns Hopkins University, USA","institution_ids":["https://openalex.org/I145311948"]},{"raw_affiliation_string":"Human Language Technology Center of Excellence, The Johns Hopkins University, USA","institution_ids":["https://openalex.org/I145311948"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5042260050","display_name":"Hynek He\u0159mansk\u00fd","orcid":"https://orcid.org/0000-0001-8032-4811"},"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":false,"raw_author_name":"Hynek Hermansky","raw_affiliation_strings":["Center for Language and Speech Processing, The Johns Hopkins University, USA","Human Language Technology Center of Excellence, The Johns Hopkins University, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Center for Language and Speech Processing, The Johns Hopkins University, USA","institution_ids":["https://openalex.org/I145311948"]},{"raw_affiliation_string":"Human Language Technology Center of Excellence, The Johns Hopkins University, USA","institution_ids":["https://openalex.org/I145311948"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I145311948"],"apc_list":null,"apc_paid":null,"fwci":0.2187,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.524837,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":93,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"2245","last_page":"2249"},"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":0.9984999895095825,"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":0.9955999851226807,"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/end-to-end-principle","display_name":"End-to-end principle","score":0.8677020072937012},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6003643274307251},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4556470513343811},{"id":"https://openalex.org/keywords/end-of-history","display_name":"End of history","score":0.4515763819217682},{"id":"https://openalex.org/keywords/end-user","display_name":"End user","score":0.4326394200325012},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.183001309633255},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.10155713558197021}],"concepts":[{"id":"https://openalex.org/C74296488","wikidata":"https://www.wikidata.org/wiki/Q2527392","display_name":"End-to-end principle","level":2,"score":0.8677020072937012},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6003643274307251},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4556470513343811},{"id":"https://openalex.org/C2778935963","wikidata":"https://www.wikidata.org/wiki/Q13218530","display_name":"End of history","level":3,"score":0.4515763819217682},{"id":"https://openalex.org/C91262260","wikidata":"https://www.wikidata.org/wiki/Q528074","display_name":"End user","level":2,"score":0.4326394200325012},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.183001309633255},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.10155713558197021},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21437/interspeech.2019-3137","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2019-3137","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":[{"display_name":"Peace, Justice and strong institutions","score":0.6600000262260437,"id":"https://metadata.un.org/sdg/16"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":25,"referenced_works":["https://openalex.org/W854541894","https://openalex.org/W1736701665","https://openalex.org/W1989314204","https://openalex.org/W2039420750","https://openalex.org/W2048741136","https://openalex.org/W2102113734","https://openalex.org/W2103621378","https://openalex.org/W2144121180","https://openalex.org/W2153723410","https://openalex.org/W2289690552","https://openalex.org/W2327501763","https://openalex.org/W2399383297","https://openalex.org/W2403021744","https://openalex.org/W2514966966","https://openalex.org/W2526425061","https://openalex.org/W2587464121","https://openalex.org/W2627092829","https://openalex.org/W2766219058","https://openalex.org/W2889508099","https://openalex.org/W2899640612","https://openalex.org/W2900092534","https://openalex.org/W2903253899","https://openalex.org/W2962780374","https://openalex.org/W2963064586","https://openalex.org/W4250727028"],"related_works":["https://openalex.org/W3016188207","https://openalex.org/W4299590256","https://openalex.org/W4286908490","https://openalex.org/W4307058106","https://openalex.org/W3163634122","https://openalex.org/W3179968364","https://openalex.org/W4393212338","https://openalex.org/W4367860523","https://openalex.org/W2417674618","https://openalex.org/W1538841260"],"abstract_inverted_index":{"Measuring":[0],"performance":[1,24,33,42,145],"of":[2,76],"an":[3,147],"automatic":[4],"speech":[5],"recognition":[6],"(ASR)":[7],"system":[8],"without":[9],"ground-truth":[10],"could":[11],"be":[12,26],"beneficial":[13],"in":[14,93],"many":[15],"scenarios,":[16],"especially":[17,160],"with":[18,113,146],"data":[19],"from":[20,51],"unseen":[21,162],"domains,":[22],"where":[23],"can":[25],"highly":[27],"inconsistent.In":[28],"conventional":[29],"ASR":[30,63],"systems,":[31],"several":[32],"monitoring":[34,58],"(PM)":[35],"techniques":[36],"have":[37,65],"been":[38,68],"well-developed":[39],"to":[40],"monitor":[41],"by":[43],"looking":[44],"at":[45],"triphone":[46],"posteriors":[47,139],"or":[48],"pre-softmax":[49],"activations":[50],"neural":[52],"network":[53],"acoustic":[54],"modeling.However,":[55],"strategies":[56],"for":[57,130,161],"more":[59,123],"recently":[60],"developed":[61],"end-to-end":[62],"systems":[64],"not":[66],"yet":[67],"explored,":[69],"and":[70,85,87,103,107,125,133,153],"so":[71],"that":[72,119,134],"is":[73,111],"the":[74,94,99,137,141],"focus":[75],"this":[77],"paper.We":[78],"adapt":[79],"previous":[80],"PM":[81,131],"measures":[82,97,152],"(Entropy,":[83],"M-measure":[84],"Autoencoder)":[86],"apply":[88],"our":[89],"proposed":[90],"RNN":[91],"predictor":[92],"end-toend":[95],"setting.These":[96],"utilize":[98],"decoder":[100,138],"output":[101],"layer":[102],"attention":[104],"probability":[105],"vectors,":[106],"their":[108],"predictive":[109,144],"power":[110],"measured":[112],"simple":[114],"linear":[115],"models.Our":[116],"findings":[117],"suggest":[118],"decoder-level":[120],"features":[121],"are":[122],"feasible":[124],"informative":[126],"than":[127],"attention-level":[128],"probabilities":[129],"measures,":[132],"Mmeasure":[135],"on":[136],"achieves":[140],"best":[142],"overall":[143],"average":[148],"prediction":[149,155],"error":[150],"8.8%.Entropy":[151],"RNN-based":[154],"also":[156],"show":[157],"competitive":[158],"predictability,":[159],"conditions.":[163]},"counts_by_year":[{"year":2021,"cited_by_count":2}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}