{"id":"https://openalex.org/W4296069165","doi":"https://doi.org/10.21437/interspeech.2022-10480","title":"Extending RNN-T-based speech recognition systems with emotion and language classification","display_name":"Extending RNN-T-based speech recognition systems with emotion and language classification","publication_year":2022,"publication_date":"2022-09-16","ids":{"openalex":"https://openalex.org/W4296069165","doi":"https://doi.org/10.21437/interspeech.2022-10480"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2022-10480","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2022-10480","pdf_url":null,"source":{"id":"https://openalex.org/S4363604309","display_name":"Interspeech 2022","issn_l":null,"issn":null,"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":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2022","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/A5054462082","display_name":"Zvi Kons","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Zvi Kons","raw_affiliation_strings":["IBM Research AI"],"affiliations":[{"raw_affiliation_string":"IBM Research AI","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5021900623","display_name":"Hagai Aronowitz","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hagai Aronowitz","raw_affiliation_strings":["IBM Research AI"],"affiliations":[{"raw_affiliation_string":"IBM Research AI","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5079262240","display_name":"Edmilson Morais","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Edmilson Morais","raw_affiliation_strings":["IBM Research AI"],"affiliations":[{"raw_affiliation_string":"IBM Research AI","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5041968045","display_name":"Matheus Damasceno","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Matheus Damasceno","raw_affiliation_strings":["IBM Research AI"],"affiliations":[{"raw_affiliation_string":"IBM Research AI","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5110252428","display_name":"Hong-Kwang Jeff Kuo","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hong-Kwang Kuo","raw_affiliation_strings":["IBM Research AI"],"affiliations":[{"raw_affiliation_string":"IBM Research AI","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101787514","display_name":"Samuel Thomas","orcid":"https://orcid.org/0000-0001-7573-0620"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Samuel Thomas","raw_affiliation_strings":["IBM Research AI"],"affiliations":[{"raw_affiliation_string":"IBM Research AI","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5079994647","display_name":"George Saon","orcid":"https://orcid.org/0009-0004-6837-5009"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"George Saon","raw_affiliation_strings":["IBM Research AI"],"affiliations":[{"raw_affiliation_string":"IBM Research AI","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5054462082"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.3118,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.50646412,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"546","last_page":"549"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9526000022888184,"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":0.9526000022888184,"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/computer-science","display_name":"Computer science","score":0.7649775743484497},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.653442919254303},{"id":"https://openalex.org/keywords/recurrent-neural-network","display_name":"Recurrent neural network","score":0.5802084803581238},{"id":"https://openalex.org/keywords/emotion-recognition","display_name":"Emotion recognition","score":0.5508659482002258},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4296955466270447},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4061979651451111},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.1411641538143158}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7649775743484497},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.653442919254303},{"id":"https://openalex.org/C147168706","wikidata":"https://www.wikidata.org/wiki/Q1457734","display_name":"Recurrent neural network","level":3,"score":0.5802084803581238},{"id":"https://openalex.org/C2777438025","wikidata":"https://www.wikidata.org/wiki/Q1339090","display_name":"Emotion recognition","level":2,"score":0.5508659482002258},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4296955466270447},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4061979651451111},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.1411641538143158}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21437/interspeech.2022-10480","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2022-10480","pdf_url":null,"source":{"id":"https://openalex.org/S4363604309","display_name":"Interspeech 2022","issn_l":null,"issn":null,"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":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2022","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.4399999976158142,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":15,"referenced_works":["https://openalex.org/W1828163288","https://openalex.org/W2146334809","https://openalex.org/W2584561145","https://openalex.org/W2963686995","https://openalex.org/W2973127116","https://openalex.org/W3008434450","https://openalex.org/W3036601975","https://openalex.org/W3148338017","https://openalex.org/W3163300396","https://openalex.org/W3169320628","https://openalex.org/W3195874849","https://openalex.org/W3197580070","https://openalex.org/W4225297336","https://openalex.org/W4225635674","https://openalex.org/W4287726212"],"related_works":["https://openalex.org/W4225394202","https://openalex.org/W4298287631","https://openalex.org/W2953061907","https://openalex.org/W3032952384","https://openalex.org/W3034302643","https://openalex.org/W1847088711","https://openalex.org/W3036642985","https://openalex.org/W2578422401","https://openalex.org/W3192589309","https://openalex.org/W3126677997"],"abstract_inverted_index":{"Speech":[0],"transcription,":[1],"emotion":[2,47,64],"recognition,":[3],"and":[4,24,49,69,76],"language":[5,50,98],"identification":[6,51],"are":[7],"usually":[8],"considered":[9],"to":[10,88],"be":[11,44,95],"three":[12],"different":[13,18,22],"tasks.Each":[14],"one":[15],"requires":[16],"a":[17,21,29,39,85],"model":[19],"with":[20],"architecture":[23],"training":[25],"process.We":[26],"propose":[27],"using":[28],"recurrent":[30],"neural":[31],"network":[32],"transducer":[33],"(RNN-T)-based":[34],"speech-to-text":[35],"(STT)":[36],"system":[37,62],"as":[38,52,54],"common":[40],"component":[41,87],"that":[42,82],"can":[43,93],"used":[45,96],"for":[46,55,63,97,108],"recognition":[48],"well":[53],"speech":[56],"recognition.Our":[57],"work":[58],"extends":[59],"the":[60,74,89,109],"STT":[61],"classification":[65],"through":[66],"minimal":[67],"changes,":[68],"shows":[70],"successful":[71],"results":[72],"on":[73],"IEMOCAP":[75],"MELD":[77],"datasets.In":[78],"addition,":[79],"we":[80],"demonstrate":[81],"by":[83],"adding":[84],"lightweight":[86],"RNN-T":[90],"module,":[91],"it":[92],"also":[94],"identification.In":[99],"our":[100],"evaluations,":[101],"this":[102],"new":[103],"classifier":[104],"demonstrates":[105],"state-of-the-art":[106],"accuracy":[107],"NIST-LRE-07":[110],"dataset.":[111]},"counts_by_year":[{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}