{"id":"https://openalex.org/W4402112016","doi":"https://doi.org/10.21437/interspeech.2024-890","title":"MSR-86K: An Evolving, Multilingual Corpus with 86,300 Hours of Transcribed Audio for Speech Recognition Research","display_name":"MSR-86K: An Evolving, Multilingual Corpus with 86,300 Hours of Transcribed Audio for Speech Recognition Research","publication_year":2024,"publication_date":"2024-09-01","ids":{"openalex":"https://openalex.org/W4402112016","doi":"https://doi.org/10.21437/interspeech.2024-890"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2024-890","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2024-890","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":"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/A5069018185","display_name":"Li Song","orcid":"https://orcid.org/0000-0002-4781-4023"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Song Li","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5029259399","display_name":"Yongbin You","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yongbin You","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5040824554","display_name":"Xuezhi Wang","orcid":"https://orcid.org/0000-0001-5222-248X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xuezhi Wang","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101817056","display_name":"Zhengkun Tian","orcid":"https://orcid.org/0000-0002-0469-3049"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhengkun Tian","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5086348845","display_name":"Ke Ding","orcid":"https://orcid.org/0000-0003-0653-8816"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ke Ding","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5072537055","display_name":"Guanglu Wan","orcid":"https://orcid.org/0009-0003-1061-3724"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Guanglu Wan","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5069018185"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.7274,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.75791766,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"1245","last_page":"1249"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9702000021934509,"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":0.9702000021934509,"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/T11309","display_name":"Music and Audio Processing","score":0.9476000070571899,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7466344833374023},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7237356305122375},{"id":"https://openalex.org/keywords/audio-mining","display_name":"Audio mining","score":0.4536074101924896},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.44161492586135864},{"id":"https://openalex.org/keywords/speech-corpus","display_name":"Speech corpus","score":0.4207855463027954},{"id":"https://openalex.org/keywords/acoustic-model","display_name":"Acoustic model","score":0.4092666804790497},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.34747636318206787},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3364456295967102},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.2668950855731964}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7466344833374023},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7237356305122375},{"id":"https://openalex.org/C157968479","wikidata":"https://www.wikidata.org/wiki/Q3079876","display_name":"Audio mining","level":4,"score":0.4536074101924896},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.44161492586135864},{"id":"https://openalex.org/C91863865","wikidata":"https://www.wikidata.org/wiki/Q4349497","display_name":"Speech corpus","level":3,"score":0.4207855463027954},{"id":"https://openalex.org/C155635449","wikidata":"https://www.wikidata.org/wiki/Q4674699","display_name":"Acoustic model","level":3,"score":0.4092666804790497},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.34747636318206787},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3364456295967102},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.2668950855731964}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21437/interspeech.2024-890","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2024-890","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":[{"score":0.5699999928474426,"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":0,"referenced_works":[],"related_works":["https://openalex.org/W22517275","https://openalex.org/W4383605217","https://openalex.org/W4281389974","https://openalex.org/W2064347532","https://openalex.org/W1911859126","https://openalex.org/W2131711534","https://openalex.org/W2537070497","https://openalex.org/W1560013842","https://openalex.org/W1987021544","https://openalex.org/W3151376046"],"abstract_inverted_index":null,"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}