{"id":"https://openalex.org/W2992448548","doi":"https://doi.org/10.1109/icassp40776.2020.9054335","title":"Audio-Attention Discriminative Language Model for ASR Rescoring","display_name":"Audio-Attention Discriminative Language Model for ASR Rescoring","publication_year":2020,"publication_date":"2020-04-09","ids":{"openalex":"https://openalex.org/W2992448548","doi":"https://doi.org/10.1109/icassp40776.2020.9054335","mag":"2992448548"},"language":"en","primary_location":{"id":"doi:10.1109/icassp40776.2020.9054335","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp40776.2020.9054335","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"type":"preprint","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/1912.03363","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5014054572","display_name":"Ankur Gandhe","orcid":null},"institutions":[{"id":"https://openalex.org/I1311688040","display_name":"Amazon (United States)","ror":"https://ror.org/04mv4n011","country_code":"US","type":"company","lineage":["https://openalex.org/I1311688040"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Ankur Gandhe","raw_affiliation_strings":["Amazon (United States), Seattle, United States"],"affiliations":[{"raw_affiliation_string":"Amazon (United States), Seattle, United States","institution_ids":["https://openalex.org/I1311688040"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5110230355","display_name":"Ariya Rastrow","orcid":null},"institutions":[{"id":"https://openalex.org/I4210089985","display_name":"Amazon (Germany)","ror":"https://ror.org/00b9ktm87","country_code":"DE","type":"company","lineage":["https://openalex.org/I1311688040","https://openalex.org/I4210089985"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Ariya Rastrow","raw_affiliation_strings":["Amazon"],"affiliations":[{"raw_affiliation_string":"Amazon","institution_ids":["https://openalex.org/I4210089985"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5014054572"],"corresponding_institution_ids":["https://openalex.org/I1311688040"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.00861222,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"7944","last_page":"7948"},"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/T11309","display_name":"Music and Audio Processing","score":0.9995999932289124,"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/T10860","display_name":"Speech and Audio Processing","score":0.9977999925613403,"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":0.8529291152954102},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8309597969055176},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6364759802818298},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.6283888816833496},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.5790059566497803},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.5785123705863953},{"id":"https://openalex.org/keywords/adaptation","display_name":"Adaptation (eye)","score":0.5421190857887268},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.5188380479812622},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.49994516372680664},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4852859675884247},{"id":"https://openalex.org/keywords/end-to-end-principle","display_name":"End-to-end principle","score":0.4700661599636078},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.39546999335289}],"concepts":[{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.8529291152954102},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8309597969055176},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6364759802818298},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.6283888816833496},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.5790059566497803},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.5785123705863953},{"id":"https://openalex.org/C139807058","wikidata":"https://www.wikidata.org/wiki/Q352374","display_name":"Adaptation (eye)","level":2,"score":0.5421190857887268},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.5188380479812622},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.49994516372680664},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4852859675884247},{"id":"https://openalex.org/C74296488","wikidata":"https://www.wikidata.org/wiki/Q2527392","display_name":"End-to-end principle","level":2,"score":0.4700661599636078},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.39546999335289},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"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/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}],"mesh":[],"locations_count":5,"locations":[{"id":"doi:10.1109/icassp40776.2020.9054335","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp40776.2020.9054335","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:1912.03363","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1912.03363","pdf_url":"https://arxiv.org/pdf/1912.03363","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":null},{"id":"mag:2992448548","is_oa":true,"landing_page_url":"https://arxiv.org/abs/1912.03363","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"arXiv (Cornell University)","raw_type":null},{"id":"doi:10.48550/arxiv.1912.03363","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.1912.03363","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article"},{"id":"doi:10.17023/3xsf-w482","is_oa":true,"landing_page_url":"https://doi.org/10.17023/3xsf-w482","pdf_url":null,"source":{"id":"https://openalex.org/S7407051697","display_name":"IEEE RESOURCE CENTERS","issn_l":null,"issn":[],"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:1912.03363","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1912.03363","pdf_url":"https://arxiv.org/pdf/1912.03363","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":null},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/10","score":0.7400000095367432,"display_name":"Reduced inequalities"}],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":false},"content_urls":{"pdf":"https://content.openalex.org/works/W2992448548.pdf"},"referenced_works_count":31,"referenced_works":["https://openalex.org/W179875071","https://openalex.org/W1600744878","https://openalex.org/W1855892484","https://openalex.org/W1934041838","https://openalex.org/W2026149468","https://openalex.org/W2064675550","https://openalex.org/W2131342762","https://openalex.org/W2143612262","https://openalex.org/W2160815625","https://openalex.org/W2184045248","https://openalex.org/W2396464458","https://openalex.org/W2402146185","https://openalex.org/W2402268235","https://openalex.org/W2622203030","https://openalex.org/W2750499125","https://openalex.org/W2886319145","https://openalex.org/W2888779557","https://openalex.org/W2916997151","https://openalex.org/W2937402758","https://openalex.org/W2962824709","https://openalex.org/W2963240019","https://openalex.org/W2963660642","https://openalex.org/W2972320704","https://openalex.org/W2972625221","https://openalex.org/W2973122799","https://openalex.org/W6607333740","https://openalex.org/W6639156005","https://openalex.org/W6712930963","https://openalex.org/W6713098461","https://openalex.org/W6743477263","https://openalex.org/W6746574493"],"related_works":["https://openalex.org/W3105804405","https://openalex.org/W2913566369","https://openalex.org/W3168872064","https://openalex.org/W3137489363","https://openalex.org/W3163339532","https://openalex.org/W2804884650","https://openalex.org/W3095773170","https://openalex.org/W3155168732","https://openalex.org/W2952010730","https://openalex.org/W3198413388","https://openalex.org/W3211655143","https://openalex.org/W2572023240","https://openalex.org/W1974455634","https://openalex.org/W2766058732","https://openalex.org/W3155343771","https://openalex.org/W2900312178","https://openalex.org/W3131305672","https://openalex.org/W3108266107","https://openalex.org/W3182939642","https://openalex.org/W2548256801"],"abstract_inverted_index":{"End-to-end":[0],"approaches":[1,89],"for":[2,49,71,156],"automatic":[3],"speech":[4],"recognition":[5],"(ASR)":[6],"benefit":[7],"from":[8],"directly":[9],"modeling":[10],"the":[11,14,18,65,85,104,130,145,158],"probability":[12],"of":[13,87,106,119,147,153],"word":[15,140],"sequence":[16],"given":[17],"input":[19],"audio":[20],"stream":[21],"in":[22,136,139],"a":[23,91,107,117,151],"single":[24],"neural":[25],"network.":[26],"However,":[27],"compared":[28],"to":[29,39,47,58,83,102,115,128],"conventional":[30,92],"ASR":[31,109,121],"systems,":[32,63],"these":[33],"models":[34],"typically":[35],"require":[36],"more":[37],"data":[38,149,154],"achieve":[40],"comparable":[41],"results.":[42],"Well-known":[43],"model":[44,99,134],"adaptation":[45],"techniques,":[46],"account":[48],"domain":[50],"and":[51,75],"style":[52],"adaptation,":[53],"are":[54],"not":[55],"easily":[56],"applicable":[57],"end-to-end":[59,88],"systems.":[60],"Conventional":[61],"HMM-based":[62],"on":[64],"other":[66],"hand,":[67],"have":[68],"been":[69],"optimized":[70],"various":[72],"production":[73],"environments":[74],"use":[76],"cases.":[77],"In":[78],"this":[79],"work,":[80],"we":[81],"propose":[82],"combine":[84],"benefits":[86],"with":[90],"system":[93],"using":[94],"an":[95],"attention-based":[96],"discriminative":[97],"language":[98],"that":[100,113],"learns":[101],"rescore":[103,116],"output":[105],"first-pass":[108,159],"system.":[110,160],"We":[111],"show":[112],"learning":[114,127],"list":[118],"potential":[120],"outputs":[122],"is":[123,150],"much":[124],"simpler":[125],"than":[126],"generate":[129],"hypothesis.":[131],"The":[132],"proposed":[133],"results":[135],"8%":[137],"improvement":[138],"error":[141],"rate":[142],"even":[143],"when":[144],"amount":[146],"training":[148,157],"fraction":[152],"used":[155]},"counts_by_year":[],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}