{"id":"https://openalex.org/W2955933182","doi":null,"title":"Contextual Phonetic Pre-training for End-to-end Utterance-level Language and Speaker Recognition","display_name":"Contextual Phonetic Pre-training for End-to-end Utterance-level Language and Speaker Recognition","publication_year":2019,"publication_date":"2019-06-30","ids":{"openalex":"https://openalex.org/W2955933182","mag":"2955933182"},"language":"en","primary_location":{"id":"mag:2955933182","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/pdf/1907.00457.pdf","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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},"volume":null,"type":"preprint","indexed_in":[],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/1907.00457.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5109397773","display_name":"Shaoshi Ling","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Shaoshi Ling","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5037283647","display_name":"Juli\u00e1n Salazar","orcid":"https://orcid.org/0000-0003-0943-7594","observed_orcids":["https://orcid.org/0000-0003-0943-7594"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Juli\u00e1n Salazar","raw_affiliation_strings":[],"raw_orcid":"https://orcid.org/0000-0003-0943-7594","affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5050325468","display_name":"Katrin Kirchhoff","orcid":"https://orcid.org/0000-0002-6645-6030","observed_orcids":["https://orcid.org/0000-0002-6645-6030"]},"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":false,"raw_author_name":"Katrin Kirchhoff","raw_affiliation_strings":["Amazon"],"raw_orcid":"https://orcid.org/0000-0002-6645-6030","affiliations":[{"raw_affiliation_string":"Amazon","institution_ids":["https://openalex.org/I1311688040"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"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":9.999999747378752e-05,"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":0.0,"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-speech-recognition","display_name":"end-to-end speech recognition","score":0.7329999804496765},{"id":"https://openalex.org/keywords/language-identification","display_name":"language identification","score":0.6620000004768372},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"speaker recognition","score":0.9350000023841858},{"id":"https://openalex.org/keywords/transfer-learning","display_name":"transfer learning","score":0.35199999809265137}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8059377074241638},{"id":"https://openalex.org/C2775852435","wikidata":"https://www.wikidata.org/wiki/Q258403","display_name":"Utterance","level":2,"score":0.7342542409896851},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7317932844161987},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.5846757888793945},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5476112365722656},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5465807318687439},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.5295066833496094},{"id":"https://openalex.org/C149838564","wikidata":"https://www.wikidata.org/wiki/Q7574248","display_name":"Speaker diarisation","level":3,"score":0.5293508172035217},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.5158359408378601},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4832321107387543},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.4822333753108978},{"id":"https://openalex.org/C126042441","wikidata":"https://www.wikidata.org/wiki/Q1324888","display_name":"Frame (networking)","level":2,"score":0.47486138343811035},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.4582054615020752},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.43474507331848145},{"id":"https://openalex.org/C111219384","wikidata":"https://www.wikidata.org/wiki/Q6954384","display_name":"NIST","level":2,"score":0.42333394289016724},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"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/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"mag:2955933182","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/pdf/1907.00457.pdf","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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}],"best_oa_location":{"id":"mag:2955933182","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/pdf/1907.00457.pdf","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":38,"referenced_works":["https://openalex.org/W97072897","https://openalex.org/W119864726","https://openalex.org/W123007118","https://openalex.org/W1524333225","https://openalex.org/W1909308924","https://openalex.org/W2039057510","https://openalex.org/W2056119007","https://openalex.org/W2093311764","https://openalex.org/W2114925438","https://openalex.org/W2150769028","https://openalex.org/W2186615578","https://openalex.org/W2189248916","https://openalex.org/W2406392101","https://openalex.org/W2408175559","https://openalex.org/W2470673105","https://openalex.org/W2509361310","https://openalex.org/W2515090196","https://openalex.org/W2519091744","https://openalex.org/W2584329820","https://openalex.org/W2612434969","https://openalex.org/W2626778328","https://openalex.org/W2749006664","https://openalex.org/W2787560479","https://openalex.org/W2794506738","https://openalex.org/W2808631503","https://openalex.org/W2889519245","https://openalex.org/W2890964092","https://openalex.org/W2900200882","https://openalex.org/W2901997113","https://openalex.org/W2911291251","https://openalex.org/W2916113431","https://openalex.org/W2962813140","https://openalex.org/W2963032538","https://openalex.org/W2963341956","https://openalex.org/W2963371159","https://openalex.org/W2963425185","https://openalex.org/W2963846733","https://openalex.org/W2964247977"],"related_works":["https://openalex.org/W3024182269","https://openalex.org/W4283694096","https://openalex.org/W3035676545","https://openalex.org/W3170266452","https://openalex.org/W7017203309","https://openalex.org/W4385822425","https://openalex.org/W4386502669","https://openalex.org/W3096485810","https://openalex.org/W3205715971","https://openalex.org/W3097370710"],"abstract_inverted_index":{"Pretrained":[0],"contextual":[1,18],"word":[2],"representations":[3,20,42,48,76],"in":[4,118],"NLP":[5],"have":[6],"greatly":[7],"improved":[8],"performance":[9],"on":[10,56,64,85,105,112],"various":[11],"downstream":[12],"tasks.":[13],"For":[14],"speech,":[15],"we":[16],"propose":[17],"frame":[19,28],"that":[21],"capture":[22],"phonetic":[23],"information":[24],"at":[25,77],"the":[26,45,62,65,86,103],"acoustic":[27],"level":[29],"and":[30,38,93],"can":[31],"be":[32],"used":[33],"for":[34,82,131],"utterance-level":[35],"language,":[36],"speaker,":[37],"speech":[39],"recognition.":[40],"These":[41],"come":[43],"from":[44],"frame-wise":[46],"intermediate":[47],"of":[49,110],"an":[50],"end-to-end,":[51],"self-attentive":[52],"ASR":[53,136],"model":[54,63,130],"(SAN-CTC)":[55],"spoken":[57],"utterances.":[58],"We":[59],"first":[60],"train":[61],"Fisher":[66,95],"English":[67],"corpus":[68],"with":[69,140],"context-independent":[70],"phoneme":[71],"labels,":[72],"then":[73],"use":[74],"its":[75],"inference":[78],"time":[79],"as":[80],"features":[81],"task-specific":[83],"models":[84],"NIST":[87],"LRE07":[88],"closed-set":[89],"language":[90,108,132],"recognition":[91,97],"task":[92],"a":[94,126],"speaker":[96,119],"task,":[98],"giving":[99],"significant":[100],"improvements":[101],"over":[102],"state-of-the-art":[104],"both":[106],"(e.g.,":[107],"EER":[109],"4.68%":[111],"3sec":[113],"utterances,":[114],"23%":[115],"relative":[116],"reduction":[117],"EER).":[120],"Results":[121],"remain":[122],"competitive":[123],"when":[124,135],"using":[125],"novel":[127],"dilated":[128],"convolutional":[129],"recognition,":[133],"or":[134],"pretraining":[137],"is":[138],"done":[139],"character":[141],"labels":[142],"only.":[143]},"counts_by_year":[{"year":2023,"cited_by_count":1}],"updated_date":"2026-09-26T08:19:03.415552","created_date":"2019-07-12T00:00:00"}