Sampling-based speech parameter generation using moment-matching networks.
Shinnosuke TakamichiTomoki KoriyamaHiroshi SaruwatariPublished in: CoRR (2017)
Keyphrases
- network parameters
- matching algorithm
- pattern matching
- speech recognition
- matching process
- speech signal
- network structure
- input parameters
- automatic speech recognition
- audio visual
- computer vision
- scoring metrics
- recognition engine
- matching scheme
- motion planning
- affine invariant
- parameter settings
- affine transformation
- network design
- emotion recognition
- image matching
- keypoints
- speech synthesis
- feature points
- social networks