Speech technologies.

Speech technologies enable machines to process speech; they include speech synthesis  and speech recognition. They have numerous applications: in virtual assistants, speech-to-speech machine translation, automatic dubbing or automatic subtitling, automatic transcription of video and audio material, dictation, etc.  They also provide much help in the area of accessibility and inclusiveness, such as reading a text for the sight-impaired or helping those with motor disabilities to operate a computer through speech.

Main lines of research

  • Speech synthesis (TTS or Text to Speech)
  • Speech recognition of commands and continuous speech (ASR-Automatic Speech Recognition).

Ongoing research projects

  • BIKOHITZ: Generación de voces expresivas para doblaje y producciones audiovisuales. Partially funded by the Hazitek program, Basque government (2020-2021).