{"id":"https://openalex.org/W4402115989","doi":"https://doi.org/10.21437/interspeech.2024-442","title":"Boosting Hybrid Autoregressive Transducer-based ASR with Internal Acoustic Model Training and Dual Blank Thresholding","display_name":"Boosting Hybrid Autoregressive Transducer-based ASR with Internal Acoustic Model Training and Dual Blank Thresholding","publication_year":2024,"publication_date":"2024-09-01","ids":{"openalex":"https://openalex.org/W4402115989","doi":"https://doi.org/10.21437/interspeech.2024-442"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2024-442","is_oa":false,"landing_page_url":"http://dx.doi.org/10.21437/interspeech.2024-442","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2024","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/A5087290011","display_name":"Takafumi Moriya","orcid":"https://orcid.org/0000-0003-1942-7250"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Takafumi Moriya","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5033975068","display_name":"Takanori Ashihara","orcid":"https://orcid.org/0009-0003-4322-4127"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Takanori Ashihara","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102851028","display_name":"Masato Mimura","orcid":"https://orcid.org/0000-0002-2403-0680"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Masato Mimura","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101739550","display_name":"Hiroshi Sato","orcid":"https://orcid.org/0000-0001-6575-0396"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hiroshi Sato","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5000803465","display_name":"Kohei Matsuura","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Kohei Matsuura","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5060644399","display_name":"Ryo Masumura","orcid":"https://orcid.org/0000-0002-2415-4149"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ryo Masumura","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5112536171","display_name":"Taichi Asami","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Taichi Asami","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":"3465","last_page":"3469"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9757999777793884,"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":0.9757999777793884,"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":0.9736999869346619,"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/T10662","display_name":"Ultrasonics and Acoustic Wave Propagation","score":0.95660001039505,"subfield":{"id":"https://openalex.org/subfields/2211","display_name":"Mechanics of Materials"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/boosting","display_name":"Boosting (machine learning)","score":0.8414102792739868},{"id":"https://openalex.org/keywords/blank","display_name":"Blank","score":0.7795810699462891},{"id":"https://openalex.org/keywords/thresholding","display_name":"Thresholding","score":0.7469558715820312},{"id":"https://openalex.org/keywords/autoregressive-model","display_name":"Autoregressive model","score":0.6707456111907959},{"id":"https://openalex.org/keywords/dual","display_name":"Dual (grammatical number)","score":0.6318004131317139},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6309618949890137},{"id":"https://openalex.org/keywords/transducer","display_name":"Transducer","score":0.5041972398757935},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.46996399760246277},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4578797221183777},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4414166808128357},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.317913293838501},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.1450115144252777},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.14118236303329468},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.06420943140983582}],"concepts":[{"id":"https://openalex.org/C46686674","wikidata":"https://www.wikidata.org/wiki/Q466303","display_name":"Boosting (machine learning)","level":2,"score":0.8414102792739868},{"id":"https://openalex.org/C2778089247","wikidata":"https://www.wikidata.org/wiki/Q368951","display_name":"Blank","level":2,"score":0.7795810699462891},{"id":"https://openalex.org/C191178318","wikidata":"https://www.wikidata.org/wiki/Q2256906","display_name":"Thresholding","level":3,"score":0.7469558715820312},{"id":"https://openalex.org/C159877910","wikidata":"https://www.wikidata.org/wiki/Q2202883","display_name":"Autoregressive model","level":2,"score":0.6707456111907959},{"id":"https://openalex.org/C2780980858","wikidata":"https://www.wikidata.org/wiki/Q110022","display_name":"Dual (grammatical number)","level":2,"score":0.6318004131317139},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6309618949890137},{"id":"https://openalex.org/C56318395","wikidata":"https://www.wikidata.org/wiki/Q215928","display_name":"Transducer","level":2,"score":0.5041972398757935},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.46996399760246277},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4578797221183777},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4414166808128357},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.317913293838501},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.1450115144252777},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.14118236303329468},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.06420943140983582},{"id":"https://openalex.org/C124952713","wikidata":"https://www.wikidata.org/wiki/Q8242","display_name":"Literature","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0},{"id":"https://openalex.org/C78519656","wikidata":"https://www.wikidata.org/wiki/Q101333","display_name":"Mechanical engineering","level":1,"score":0.0},{"id":"https://openalex.org/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21437/interspeech.2024-442","is_oa":false,"landing_page_url":"http://dx.doi.org/10.21437/interspeech.2024-442","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2024","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W2361638505","https://openalex.org/W1993662208","https://openalex.org/W2370352440","https://openalex.org/W2009954581","https://openalex.org/W4296141694","https://openalex.org/W2379220204","https://openalex.org/W3160305016","https://openalex.org/W2005071119","https://openalex.org/W3158546193","https://openalex.org/W4249926107"],"abstract_inverted_index":null,"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}
