{"id":"https://openalex.org/W3129124668","doi":"https://doi.org/10.21437/interspeech.2021-1582","title":"PhonemeBERT: Joint Language Modelling of Phoneme Sequence and ASR Transcript","display_name":"PhonemeBERT: Joint Language Modelling of Phoneme Sequence and ASR Transcript","publication_year":2021,"publication_date":"2021-08-27","ids":{"openalex":"https://openalex.org/W3129124668","doi":"https://doi.org/10.21437/interspeech.2021-1582","mag":"3129124668"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2021-1582","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2021-1582","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2021","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2102.00804","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5018787065","display_name":"Mukuntha Narayanan Sundararaman","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Mukuntha Narayanan Sundararaman","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101963152","display_name":"Ayush Kumar","orcid":"https://orcid.org/0000-0002-5174-9906"},"institutions":[{"id":"https://openalex.org/I132153292","display_name":"Indian Institute of Technology Patna","ror":"https://ror.org/01ft5vz71","country_code":"IN","type":"education","lineage":["https://openalex.org/I132153292"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Ayush Kumar","raw_affiliation_strings":["Indian Institute of Technology Patna, Patna, India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Indian Institute of Technology Patna, Patna, India","institution_ids":["https://openalex.org/I132153292"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5106182403","display_name":"Jithendra Vepa","orcid":null},"institutions":[{"id":"https://openalex.org/I1329325741","display_name":"Philips (Finland)","ror":"https://ror.org/01g4jev56","country_code":"FI","type":"company","lineage":["https://openalex.org/I1329325741","https://openalex.org/I4210122849"]}],"countries":["FI"],"is_corresponding":false,"raw_author_name":"Jithendra Vepa","raw_affiliation_strings":["Philips (Finland), Vantaa, Finland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Philips (Finland), Vantaa, Finland","institution_ids":["https://openalex.org/I1329325741"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.01825554,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"3236","last_page":"3240"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9998999834060669,"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/T10028","display_name":"Topic Modeling","score":0.9998999834060669,"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":0.9997000098228455,"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/T10664","display_name":"Sentiment Analysis and Opinion Mining","score":0.9980999827384949,"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/treebank","display_name":"Treebank","score":0.8659666776657104},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8494085073471069},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.6435828804969788},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.6173555850982666},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.6042509078979492},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.593123733997345},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5468863248825073},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5240238308906555},{"id":"https://openalex.org/keywords/spoken-language","display_name":"Spoken language","score":0.5066119432449341},{"id":"https://openalex.org/keywords/joint","display_name":"Joint (building)","score":0.48929497599601746},{"id":"https://openalex.org/keywords/sequence-labeling","display_name":"Sequence labeling","score":0.4766840934753418},{"id":"https://openalex.org/keywords/sequence","display_name":"Sequence (biology)","score":0.44132310152053833},{"id":"https://openalex.org/keywords/annotation","display_name":"Annotation","score":0.15089601278305054}],"concepts":[{"id":"https://openalex.org/C206134035","wikidata":"https://www.wikidata.org/wiki/Q811525","display_name":"Treebank","level":3,"score":0.8659666776657104},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8494085073471069},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.6435828804969788},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.6173555850982666},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.6042509078979492},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.593123733997345},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5468863248825073},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5240238308906555},{"id":"https://openalex.org/C2776230583","wikidata":"https://www.wikidata.org/wiki/Q1322198","display_name":"Spoken language","level":2,"score":0.5066119432449341},{"id":"https://openalex.org/C18555067","wikidata":"https://www.wikidata.org/wiki/Q8375051","display_name":"Joint (building)","level":2,"score":0.48929497599601746},{"id":"https://openalex.org/C35639132","wikidata":"https://www.wikidata.org/wiki/Q7452468","display_name":"Sequence labeling","level":3,"score":0.4766840934753418},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.44132310152053833},{"id":"https://openalex.org/C2776321320","wikidata":"https://www.wikidata.org/wiki/Q857525","display_name":"Annotation","level":2,"score":0.15089601278305054},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.0},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.0},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0},{"id":"https://openalex.org/C170154142","wikidata":"https://www.wikidata.org/wiki/Q150737","display_name":"Architectural engineering","level":1,"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/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.21437/interspeech.2021-1582","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2021-1582","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2021","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2102.00804","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2102.00804","pdf_url":"https://arxiv.org/pdf/2102.00804","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,"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"mag:3129124668","is_oa":true,"landing_page_url":"https://arxiv.org/pdf/2102.00804.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,"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.2102.00804","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2102.00804","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,"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2102.00804","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2102.00804","pdf_url":"https://arxiv.org/pdf/2102.00804","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,"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.8199999928474426,"display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3129124668.pdf","grobid_xml":"https://content.openalex.org/works/W3129124668.grobid-xml"},"referenced_works_count":17,"referenced_works":["https://openalex.org/W1494198834","https://openalex.org/W2070246124","https://openalex.org/W2097550833","https://openalex.org/W2251939518","https://openalex.org/W2511962886","https://openalex.org/W2889191349","https://openalex.org/W2914417638","https://openalex.org/W2963288440","https://openalex.org/W2963748441","https://openalex.org/W2965373594","https://openalex.org/W3005352739","https://openalex.org/W3015747801","https://openalex.org/W3026470569","https://openalex.org/W3034931686","https://openalex.org/W3046177490","https://openalex.org/W3095711142","https://openalex.org/W3098649723"],"related_works":["https://openalex.org/W3197744084","https://openalex.org/W3034931686","https://openalex.org/W3161127962","https://openalex.org/W2975237304","https://openalex.org/W2963230678","https://openalex.org/W2802390314","https://openalex.org/W3171851140","https://openalex.org/W2921339572","https://openalex.org/W2933022734","https://openalex.org/W3094180720","https://openalex.org/W2805937441","https://openalex.org/W3200895333","https://openalex.org/W2618015847","https://openalex.org/W3028178035","https://openalex.org/W2521604020","https://openalex.org/W3003335331","https://openalex.org/W3156762052","https://openalex.org/W2950658695","https://openalex.org/W3037190132","https://openalex.org/W2986963494"],"abstract_inverted_index":{"Recent":[0],"years":[1],"have":[2,104],"witnessed":[3],"significant":[4],"improvement":[5],"in":[6,32,98],"ASR":[7,68,78],"systems":[8],"to":[9,55,70,77],"recognize":[10],"spoken":[11],"utterances.":[12],"However,":[13],"it":[14],"is":[15],"still":[16],"a":[17,50,60],"challenging":[18],"task":[19],"for":[20,106,124,135],"noisy":[21,122],"and":[22,27,67,96,133,138],"out-of-domain":[23],"data,":[24],"where":[25,101],"substitution":[26],"deletion":[28],"errors":[29,37],"are":[30,75],"prevalent":[31],"the":[33,40,107,146,150],"transcribed":[34],"text.":[35],"These":[36],"significantly":[38],"degrade":[39],"performance":[41],"of":[42,145],"downstream":[43,88,108],"tasks.":[44],"In":[45],"this":[46],"work,":[47],"we":[48,102],"propose":[49],"BERT-style":[51],"language":[52,62],"model,":[53],"referred":[54],"as":[56,93],"PhonemeBERT,":[57],"that":[58,74,82],"learns":[59],"joint":[61],"model":[63],"with":[64,110],"phoneme":[65,91,112],"sequence":[66],"transcript":[69],"learn":[71],"phonetic-aware":[72],"representations":[73],"robust":[76],"errors.":[79],"We":[80,115],"show":[81],"PhonemeBERT":[83],"can":[84],"be":[85],"used":[86],"on":[87,154],"tasks":[89,109,141],"using":[90],"sequences":[92],"additional":[94],"features,":[95],"also":[97],"low-resource":[99],"setup":[100],"only":[103],"ASR-transcripts":[105],"no":[111],"information":[113],"available.":[114],"evaluate":[116],"our":[117],"approach":[118,148],"extensively":[119],"by":[120],"generating":[121],"data":[123],"three":[125],"benchmark":[126],"datasets":[127],"-":[128],"Stanford":[129],"Sentiment":[130],"Treebank,":[131],"TREC":[132],"ATIS":[134],"sentiment,":[136],"question":[137],"intent":[139],"classification":[140],"respectively.":[142],"The":[143],"results":[144],"proposed":[147],"beats":[149],"state-of-the-art":[151],"baselines":[152],"comprehensively":[153],"each":[155],"dataset.":[156]},"counts_by_year":[],"updated_date":"2026-08-05T07:39:15.569665","created_date":"2025-10-10T00:00:00"}