DNN Speech Recognition
Our Automatic Speech Recognition engine leverages the most advanced forms of Deep Learning, achieving unprecedented accuracy in recognition that routinely reaches human-level performance.
Today, our engine excels in recognizing 10 languages including English (US, Canadian, UK, & South Africa), Spanish, Russian, Polish, Romanian, Kazakh, Ukrainian and Greek.
Thanks to Omilia’s proprietary method of training and tuning, deepASR® is able to achieve Word Error Rates of less than half of legacy incumbent providers.
For all primary languages Omilia offers adapted acoustic and language models that cover the accent and dialectic variations within the country.
Don’t see your language here? We will develop an adapted acoustic and language model for your language in less than 2 months.