{"id":"https://openalex.org/W3095738461","doi":"https://doi.org/10.21437/interspeech.2020-2757","title":"All-in-One Transformer: Unifying Speech Recognition, Audio Tagging, and Event Detection","display_name":"All-in-One Transformer: Unifying Speech Recognition, Audio Tagging, and Event Detection","publication_year":2020,"publication_date":"2020-10-25","ids":{"openalex":"https://openalex.org/W3095738461","doi":"https://doi.org/10.21437/interspeech.2020-2757","mag":"3095738461"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2020-2757","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2020-2757","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2020","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/A5071286568","display_name":"Niko Moritz","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Niko Moritz","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5086940921","display_name":"Gordon Wichern","orcid":"https://orcid.org/0000-0002-8597-6795"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Gordon Wichern","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5087554069","display_name":"Takaaki Hori","orcid":"https://orcid.org/0000-0003-4560-8039"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Takaaki Hori","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5076453358","display_name":"Jonathan Le Roux","orcid":"https://orcid.org/0000-0002-3451-171X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jonathan Le Roux","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":22,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"3112","last_page":"3116"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":1.0,"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"}},"topics":[{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":1.0,"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"}},{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9995999932289124,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9994000196456909,"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":0.7140278220176697},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6759060621261597},{"id":"https://openalex.org/keywords/voice-activity-detection","display_name":"Voice activity detection","score":0.5949093699455261},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.5650414228439331},{"id":"https://openalex.org/keywords/event","display_name":"Event (particle physics)","score":0.4815552532672882},{"id":"https://openalex.org/keywords/audio-mining","display_name":"Audio mining","score":0.4481382668018341},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.41610413789749146},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.3988410532474518},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3313354253768921},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.12441548705101013},{"id":"https://openalex.org/keywords/voltage","display_name":"Voltage","score":0.07692188024520874},{"id":"https://openalex.org/keywords/electrical-engineering","display_name":"Electrical engineering","score":0.07552975416183472}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7140278220176697},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6759060621261597},{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.5949093699455261},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.5650414228439331},{"id":"https://openalex.org/C2779662365","wikidata":"https://www.wikidata.org/wiki/Q5416694","display_name":"Event (particle physics)","level":2,"score":0.4815552532672882},{"id":"https://openalex.org/C157968479","wikidata":"https://www.wikidata.org/wiki/Q3079876","display_name":"Audio mining","level":4,"score":0.4481382668018341},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.41610413789749146},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.3988410532474518},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3313354253768921},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.12441548705101013},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.07692188024520874},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.07552975416183472},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21437/interspeech.2020-2757","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2020-2757","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2020","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":21,"referenced_works":["https://openalex.org/W1974387177","https://openalex.org/W1983108229","https://openalex.org/W2127141656","https://openalex.org/W2408239454","https://openalex.org/W2533523411","https://openalex.org/W2627092829","https://openalex.org/W2766219058","https://openalex.org/W2801659857","https://openalex.org/W2803193013","https://openalex.org/W2886180730","https://openalex.org/W2912056372","https://openalex.org/W2936123380","https://openalex.org/W2948982921","https://openalex.org/W2959539607","https://openalex.org/W2963266252","https://openalex.org/W2963403868","https://openalex.org/W2972389417","https://openalex.org/W2972780808","https://openalex.org/W2972818416","https://openalex.org/W2981822321","https://openalex.org/W3007073761"],"related_works":["https://openalex.org/W2401827384","https://openalex.org/W2355290951","https://openalex.org/W4304187160","https://openalex.org/W642007152","https://openalex.org/W2131711534","https://openalex.org/W2184127972","https://openalex.org/W2343205865","https://openalex.org/W2341426843","https://openalex.org/W2550171623","https://openalex.org/W2009814707"],"abstract_inverted_index":null,"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":5},{"year":2022,"cited_by_count":4},{"year":2021,"cited_by_count":6}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}
