The current projects of the speech group

In accordance with the main research topics of the speech processing group, which are text-to-speech synthesis and speech recognition, most of the research projects have a strong relation to one of these two topics.

 
• POSPER: Polyglot Speech Recognizer
• VSHMI: Vision-Supported Speech-Based Human Machine Interaction
• VoiceTools: Methods and Tools for Improved Concatenative Text-to-Speech Synthesis
• PROSO: Prosody Control for Polyglot Speech Synthesis
• RULAMO: Rule-Based Language Model for Speech Recognition