Bengali is the fifth most spoken of all native languages all over the world. But so far very little work has been done on Bengali Speech Transcription. Considering the large audience and far-reaching opportunities, there’s significant business and educational interest in developing AI that can be used in **𝐁𝐞𝐧𝐠𝐚𝐥𝐢 𝐀𝐒𝐑** (Automatic Speech Recognition). We, at the 𝐃𝐞𝐩𝐚𝐫𝐭𝐦𝐞𝐧𝐭 𝐨𝐟 𝐂𝐨𝐦𝐩𝐮𝐭𝐞𝐫 𝐒𝐜𝐢𝐞𝐧𝐜𝐞 𝐚𝐧𝐝 𝐄𝐧𝐠𝐢𝐧𝐞𝐞𝐫𝐢𝐧𝐠, 𝐁𝐔𝐄𝐓, in partnership with 𝐁𝐞𝐧𝐠𝐚𝐥𝐢.𝐀𝐈, are glad to present the very first Bengali ASR competition of its kind, 𝐃𝐋 𝐒𝐩𝐫𝐢𝐧𝐭, as a part of BUET CSE Fest 2022.

For training the model, we will be using a crowdsourced sentence-level automatic speech recognition corpus collected on the Mozilla Common Voice platform. The details of the dataset can be found here: [https://arxiv.org/abs/2206.14053](https://arxiv.org/abs/2206.14053). 

**This competition is open for all, not only for undergraduates. Anyone from any institution can participate.**

##Competition Website 

Important information and FAQ on the competition can be found here: [https://buetcsefest2022.com/dlsprint/](https://buetcsefest2022.com/dlsprint/). 
You can even join this facebook group for relevant updates: [https://www.facebook.com/groups/1185590455630397](https://www.facebook.com/groups/1185590455630397).
Registration link: [https://tiny.cc/dlsprint22](https://tiny.cc/dlsprint22). **Registration is mandatory to participate in Phase 1 Part 2 and Phase 2 rounds.**

##Competition Schedule 

**Phase 1 Part 1:** Will be held in Kaggle from July 1st to August 25th (12:00 AM GMT+6). Participants are expected to build and train their model during this phase.
**Phase 1 Part 2:** Will be held in Kaggle on August 25th. **Only registered teams will be allowed.** Participants will infer their model on a new dataset. The top 15 teams from this round will be selected for Phase 2.
**Phase 2:** Will be held onsite at the Department of CSE, BUET, on September 2nd. Only invited participants can participate. Participants will infer their model on a new dataset and present their methods live in front of the judges’ panel. 

##Important
**All teams will submit working Kaggle notebooks for Train and Test with appropriate instructions and documentations for reproducibility after Phase 1 Part 1.**

##Acknowledgements

EBLICT Project, BCC, ICT Division, Bangladesh and IEEE Computer Society BUET Student Branch Chapter are jointly hosting the event with the organizers. The event is also supported by [Incepta Solutions Limited](https://www2.inceptasolutions.com/).