{"id":"https://openalex.org/W4385823215","doi":"https://doi.org/10.21437/interspeech.2023-2207","title":"Improving RNN Transducer Acoustic Models for English Conversational Speech Recognition","display_name":"Improving RNN Transducer Acoustic Models for English Conversational Speech Recognition","publication_year":2023,"publication_date":"2023-08-14","ids":{"openalex":"https://openalex.org/W4385823215","doi":"https://doi.org/10.21437/interspeech.2023-2207"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2023-2207","is_oa":false,"landing_page_url":"http://dx.doi.org/10.21437/interspeech.2023-2207","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"INTERSPEECH 2023","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/A5102014291","display_name":"Xiaodong Cui","orcid":"https://orcid.org/0000-0003-4865-1307"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xiaodong Cui","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","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":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5003725957","display_name":"Brian Kingsbury","orcid":"https://orcid.org/0000-0002-1343-6837"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Brian Kingsbury","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"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":"1299","last_page":"1303"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9648000001907349,"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":0.9648000001907349,"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":0.7783365249633789},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6880671977996826},{"id":"https://openalex.org/keywords/transducer","display_name":"Transducer","score":0.6119473576545715},{"id":"https://openalex.org/keywords/recurrent-neural-network","display_name":"Recurrent neural network","score":0.5723918080329895},{"id":"https://openalex.org/keywords/acoustic-model","display_name":"Acoustic model","score":0.471415251493454},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.3640022873878479},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.343085914850235},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.2679286003112793},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.17432871460914612},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.053101688623428345}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7783365249633789},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6880671977996826},{"id":"https://openalex.org/C56318395","wikidata":"https://www.wikidata.org/wiki/Q215928","display_name":"Transducer","level":2,"score":0.6119473576545715},{"id":"https://openalex.org/C147168706","wikidata":"https://www.wikidata.org/wiki/Q1457734","display_name":"Recurrent neural network","level":3,"score":0.5723918080329895},{"id":"https://openalex.org/C155635449","wikidata":"https://www.wikidata.org/wiki/Q4674699","display_name":"Acoustic model","level":3,"score":0.471415251493454},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.3640022873878479},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.343085914850235},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.2679286003112793},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.17432871460914612},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.053101688623428345}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21437/interspeech.2023-2207","is_oa":false,"landing_page_url":"http://dx.doi.org/10.21437/interspeech.2023-2207","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"INTERSPEECH 2023","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W2963414781","https://openalex.org/W2963920996","https://openalex.org/W1489125746","https://openalex.org/W2782005958","https://openalex.org/W4297665160","https://openalex.org/W1499864241","https://openalex.org/W2147212219","https://openalex.org/W1533416326","https://openalex.org/W2160553647","https://openalex.org/W3103945224"],"abstract_inverted_index":null,"counts_by_year":[{"year":2024,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}