The Kore.ai Bots Platform includes an automatic speech recognition (ASR) engine to enable voice-driven interactions. It also lets your bot communicate outside of traditional text interfaces or messaging applications – including IP Phones, wearables, and other speech-enabled gadgets like Amazon’s Echo and more. The engine is trained using our robust speech recognition toolkit and a deep neural network implementation for a higher vocabulary ranking that drives better, more complete interactions. The Kore.ai ASR engine gives enterprises complete control over speech engine training, meaning they decide what is fed into the engine and how ongoing training is handled.
The engine is available for integration using mobile and web SDK. The SDK allows connectivity to the Speech API to send a stream of audio and receives a stream of converted text from the server. The ASR engine is trained using deep neural networks with thousands of hours of training corpus. TDNN and LSTM networks have been used to train the model which achieved an excellent word error rate (WER) of 8.5 against the NIST test corpus.
Alternatively, clients can also integrate third party ASR engines into the Kore.ai Platform using either the SDK or API integration approach.