Introduction of OLR 2020
The OLR challenge series organized by Speechocean and Tsinghua University aim at boosting language recognition technology for oriental languages. Following the success of the past four OLR challenges, the new challenge in 2020 is coming now and is more challenging and more interesting.
188 hours of speech recognition corpus covering 18 languages are totally free for each participant. Besides, in addition to the conventional "Cross-channel LID" task, “Dialect Identification” and “Noisy LID" will be added for the first time in OLR 2020.
Come and join this challenge right now!
Tasks and Data Details
Languages of Training Set and
|Languages of Test Set|
|Task 1||Cross-channel LID|
Mandarin / Cantonese / Japanese / Korean /
Indonesian / Vietnamese / Russian / Catalan /
Greek / Telugu / Kazak / Tibetan / Uyghur /
Sichuanese / Shanghainese / Hokkien
Cantonese / Japanese / Korean / Indonesian /
Vietnamese / Russian
|Task 2||Dialect Identification|
Sichuanese / Shanghainese / Hokkien /
Three nontarget languages (Mandarin /
Malay / Thai）
Mandarin / Cantonese / Japanese /
Korean / Russian
Training and development data release
|October 1||Registration close|
|October 20||Test data release|
|November 1||Test result submission deadline|
|November 27||Convening of seminar|
|December 10||Results announcement|
* Due to the COVID-19, the seminar and award ceremony will be adjusted according to the actual situation.
Northwestern Polytechnical University
Please send email to the email@example.com
-- Team name
-- Duty person
-- If any, homepage or published papers in speech field of person / organization / company.
Please check this website to get more details: