Speech is an interdisciplinary subfield of computer science and computational linguistics that develops methodologies and technologies that enables cognitive auditory tasks in machines.


Following are the subfields of Speech supported by Theos.

  • Speech Recognition is the task of recognising speech within audio and converting it into text.

  • Voice Cloning is the task of creating speech that's indistinguishable from the original speaker.

  • Emotion Recognition is the task of detecting human emotions using speech signals.

  • Speaker Verification is the task of verifying a person's identity from the characteristics of his or her voice.

  • Speech Synthesis is the task of generating speech from text.

Last updated