Herramientas de transcripción y traducción automáticas de audio/vídeo
The TTT software developed by the UPV is composed of advanced automatic speech recognition and translation systems. Among its advantages is its ability to adapt to the subject area of each video, surpassing the solutions that general speech recognition systems can provide. The system recognizes the context and automatically processes specific expressions from a given field, which facilitates transcription. Thus, in the field of educational videos, for example, it offers a more complete service than YouTube, thanks to an extensive corpus that, in Spanish alone, already includes more than sixty million phrases.
Automatic multilingual subtitling of audio or video recordings. Automatic transcription of video or audio for keyword detection and automatic cataloguing. Adaptation of automatic transcription and translation systems to the subject area of each audio/video.
Automatic Speech Recognition (ASR) Machine Translation (MT) Speech synthesis.