{"id":"https://openalex.org/W4385823111","doi":"https://doi.org/10.21437/interspeech.2023-1233","title":"GigaST: A 10,000-hour Pseudo Speech Translation Corpus","display_name":"GigaST: A 10,000-hour Pseudo Speech Translation Corpus","publication_year":2023,"publication_date":"2023-08-14","ids":{"openalex":"https://openalex.org/W4385823111","doi":"https://doi.org/10.21437/interspeech.2023-1233"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2023-1233","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2023-1233","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":"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/A5100624648","display_name":"Rong Ye","orcid":"https://orcid.org/0000-0002-6693-3079"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Rong Ye","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5017907143","display_name":"Chengqi Zhao","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chengqi Zhao","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5038062913","display_name":"Tom Ko","orcid":"https://orcid.org/0000-0002-5324-8961"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Tom Ko","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5069433018","display_name":"Chutong Meng","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chutong Meng","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100453495","display_name":"Tao Wang","orcid":"https://orcid.org/0000-0002-2480-878X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Tao Wang","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101693712","display_name":"Mingxuan Wang","orcid":"https://orcid.org/0009-0000-9738-4263"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Mingxuan Wang","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5057370662","display_name":"Jun Cao","orcid":"https://orcid.org/0000-0002-5634-3008"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jun Cao","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5100624648"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.9117,"has_fulltext":false,"cited_by_count":11,"citation_normalized_percentile":{"value":0.88680212,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"2168","last_page":"2172"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9926000237464905,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9926000237464905,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.982699990272522,"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/T12031","display_name":"Speech and dialogue systems","score":0.933899998664856,"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/speech-translation","display_name":"Speech translation","score":0.7045551538467407},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6974272131919861},{"id":"https://openalex.org/keywords/translation","display_name":"Translation (biology)","score":0.6191261410713196},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5609492063522339},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.551215410232544},{"id":"https://openalex.org/keywords/speech-corpus","display_name":"Speech corpus","score":0.47458720207214355},{"id":"https://openalex.org/keywords/machine-translation","display_name":"Machine translation","score":0.449053555727005},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4370497465133667},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.29443132877349854}],"concepts":[{"id":"https://openalex.org/C2780366754","wikidata":"https://www.wikidata.org/wiki/Q7494857","display_name":"Speech translation","level":3,"score":0.7045551538467407},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6974272131919861},{"id":"https://openalex.org/C149364088","wikidata":"https://www.wikidata.org/wiki/Q185917","display_name":"Translation (biology)","level":4,"score":0.6191261410713196},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5609492063522339},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.551215410232544},{"id":"https://openalex.org/C91863865","wikidata":"https://www.wikidata.org/wiki/Q4349497","display_name":"Speech corpus","level":3,"score":0.47458720207214355},{"id":"https://openalex.org/C203005215","wikidata":"https://www.wikidata.org/wiki/Q79798","display_name":"Machine translation","level":2,"score":0.449053555727005},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4370497465133667},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.29443132877349854},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C105580179","wikidata":"https://www.wikidata.org/wiki/Q188928","display_name":"Messenger RNA","level":3,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21437/interspeech.2023-1233","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2023-1233","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/W2883671469","https://openalex.org/W2728761353","https://openalex.org/W2969905756","https://openalex.org/W4362498905","https://openalex.org/W2338806053","https://openalex.org/W1489621819","https://openalex.org/W2572044271","https://openalex.org/W3354101","https://openalex.org/W2760702566","https://openalex.org/W2909367404"],"abstract_inverted_index":null,"counts_by_year":[{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":6}],"updated_date":"2026-04-03T22:45:19.894376","created_date":"2025-10-10T00:00:00"}
