With more than 20 years experience on the field we do speech recognition research and development and give training courses.
We research and develop speech-to-text engines for multiple languages (with an emphasis on Hungarian) and for various tasks: real-time, low latency applications, dictation systems or off-line mass transcription. Automatic speech recognition (ASR) – as a hot topic in Artificial Intelligence – is rooted profoundly in “deep learning” applying its entire arsenal, including GPU/TPU-based gradient calculations, supervised, semi-supervised and unsupervised learning and more.
Project laboratory topics
- Conversational AI applications
- End-to-end ASR
- Semi-supervised acoustic modeling by the Fairseq toolkit
- Unsupervised acoustic modeling using GAN (Generative Adversarial Network) technology
- Low latency ASR inference for streaming using GPU’s
- Neural Language modeling for ASR
- Open-source ASR engine comparison
Description of the lectures