Perceptual Foundations for Naturalistic Variability in the Prosody of Synthetic Speech.
Nanette VeilleuxJonathan BarnesAlejna BrugosStefanie Shattuck-HufnagelPublished in: INTERSPEECH (2012)
Keyphrases
- text to speech
- speech synthesis
- prosodic features
- speech recognition
- audio visual
- multi stream
- synthesized speech
- vocal tract
- speech signal
- human visual system
- real scenes
- real images are presented
- visual perception
- low level
- perceptual grouping
- perceptual organization
- human perception
- artificial intelligence
- text to speech synthesis
- speaker verification
- pattern recognition
- multiscale
- english text
- software product line
- perceptual quality
- human vision
- automatic speech recognition
- endpoint detection