Applications and Demonstrations

Applications

• homeService

 

Demonstration Systems

• Festival text-to-speech online demo
• HMM speech synthesis demonstrations
• WebASR - developed at Sheffield as pasrt of the AMIDA project, free automatic speech recognition on the web
• Podcastle - developed at AIST in Japan (and in collaboration with Edinburgh for the English language version).  PodCastle is a service that enables searching of speech data such as podcasts, individual audio or video files on the web, and video clips on video sharing services such as YouTube. Speech data are converted to text data by using automatic speech recognition. All users accessing the PodCastle service can correct speech recognition errors.

 

Demonstrations at Annual Meeting, April 2012

These are some initial demonstrations, presented at the NST Annual Meeting in Edinburgh on 24 April 2012:

• Voice banking and reconstruction
• Live voice cloning
• Examples of BBC data processing
• Podcastle
• Lecture Processing - Initial Work on Domain Independence 
• Transcription and navigation of conference talks and lectures
• homeService demonstrations
• Family Life Corpus - Initial Work on Domain Independence  and Structuring Diverse Data
• The Ambient Spotlight