In this assignment students need to predict a phoneme sound, `g`, based on its spectral representation. For a complete example see [p.148 in *The Elements of Statistical Learning (ESL)*](https://hastie.su.domains/ElemStatLearn/printings/ESLII_print12.pdf#page=167) by Hastie, Tibshirani and Friedman. Also see [*Penalized Discriminant Analysis*](https://scholar.google.com/scholar?hl=en&as_sdt=0%2C48&q=Penalized+Discriminant+Analysis&btnG=) by Hastie, Buja and Tibshirani (1995)

* HSE students model in R 
* JHU students model in Python. 

See **Rules** tab for more details.

## Acknowledgements
1. Data set is from TIMIT database (TIMIT Acoustic-Phonetic Continuous Speech Corpus, NTIS, US Dept of Commerce). It has been augmented for this competition.
1. The image is from https://milehighhearing.com/blog/types-of-hearing-loss
1. **Competition Authors**. [HSE](https://hse.ru/) [ML Teaching Team](https://www.hse.ru/edu/courses/?filial=22723&lecturer=409923484&year=2021): [Oleg Melnikov](https://www.linkedin.com/in/olegmelnikov/), [Alexey Boldyrev](https://www.hse.ru/org/persons/223985242), [Vladimir Kirillin](https://www.hse.ru/org/persons/499313273), [Sergey Chervontsev](https://www.hse.ru/org/persons/305134539), Margarita Lazareva, Tatyana Yazykova, Mike Ovyan, Lika Lomidze, Vladimir Novikov, Valeriya Rogovchenko