A few days ago we organized an interesting event on AI focused on Speech-to-Text. We explored cutting-edge technologies applied to real scenarios that open the door to a multitude of possibilities and areas of application for this technology.
We used different technologies, both Open Source and cloud APIs to perform some exercises that allowed us to see how a speech recognition system can be implemented in different scenarios:
- Audio to text transcription.
- Speakers recognition.
- Sentiment analysis.
- Text translation.
- Summary generation.