National Repository of Grey Literature 2 records found  Search took 0.01 seconds. 
GLOTTAL SIGNAL MODIFICATION FOR EMOTIONAL SPEECH SYNTHESIS
Vondra, Martin ; Vích, Robert
In the contribution speech decomposition into the source and vocal tract components is described. It is based on separation of the signal into the minimum- and maximum-phase speech components. Further the modification of the source speech component by changing the glottal model parameters is applied in order to achieve emotional speech by change of the neutral speech style
IMPROVING UNIT CONCATENATIONS IN EXPERIMENTAL SPEECH SYNTHESIS BASED UPON COMPLEX CEPSTRUM IN THE CONCATENATION-BASED TTS SYSTEM EPOS
Staněk, Jan
During testing phase of a new speech analysis and synthesis methods based upon complex cepstrum and implemented in a TTS system Epos, we have discovered disturbing speech artifacts on the borders of the concatenated units. To eliminate these artifacts, we have chosen to practically implement and test usage of smoothing algorithms in the cepstral domain and observe its impact on the resulting synthesized speech. The results of our tests are presented in this paper.

Interested in being notified about new results for this query?
Subscribe to the RSS feed.