Topic


Speech-to-Speech Translation

Speech-to-Speech Translation (S2ST) technologies are an effective means to break through language barriers between people who do not speak the same language.

Speech-to-Speech Translation
Communication between two or more different languages is enabled when using the S2ST technology by connecting to the distributed S2ST servers, (i.e., ASR, MT, TTS) across the globe. The following have currently taken place; (see details on the Standardization page):

  1. Protocols to be used between S2ST modules as ITU-T Recommendations F.745 (Published ) and H.625 (Pre-published ) in October 2010 .
  2. The establishment of the Universal Speech Translation Advanced Research (U-STAR) Consortium was established as an international research collaboration entity to develop a universal network-based speech-to-speech translation system.

Architecture

- Automatic Speech Recognition (ASR)
- Machine Translation (MT)
- Text-to-Speech (TTS)

Speech translation integrates three components

U-STAR Members
   

   
               

   
                                       

Home
| About Us | Membership | Standardization | Research | U-STAR App | News & Events | Links