However, this solution is also restricted to a particular (or specific) domain (public services) and the time needed for translating speech into LSE (speech recognition, translation and signing) is around 8 s per sentence, which makes the solution unfeasible for real time domains (e.g., television).
Nuance's voice-recognition technology is used for things like translating speech to text and delivering turn-by-turn directions for drivers.
For listening and language, we're focusing on translating speech to text, text between any languages, and also being able to answer any natural language question you ask".
This article describes an architecture for translating speech into Spanish Sign Language (SSL).
It handles voice input really well, too, translating speech to text accurately and also picking up the sound even in a relatively loud room.
San-Segundo et al. [17, 34, 35] proposed an architecture for translating speech into Spanish sign language (LSE) focused on helping deaf people when they want to renew their identity card or driver's license.
Furthermore, this average delay time is smaller than the time used in other related works, such as the solution proposed by San-Segundo et al. [17, 34, 35] which reported an average delay for translating speech into LSE of around 8 s per sentence.
Both Apple and Google use artificial intelligence to do a reasonably good job of translating speech to text, even in noisy environments.
(He would later translate speeches by Soviet officials like Anastas I. Mikoyan and Andrei A. Gromyko).
With the architecture proposed, we are not trying to build a domain independent translator but a system able to translate speech utterances into gesture sequences in a restricted domain: railway, flights or weather information.
