Bridging the Segment-Prosody Divide in Speech Production and Perception.
Klaus J. KohlerPublished in: Phonetica (2012)
Keyphrases
- text to speech
- speech synthesis
- speech recognition
- prosodic features
- multi stream
- synthesized speech
- audio visual
- vocal tract
- text to speech synthesis
- production system
- spoken language
- visual perception
- spontaneous speech
- machine intelligence
- human perception
- hidden markov models
- production process
- fully unsupervised
- data sets
- information retrieval
- manufacturing process
- speaker identification
- manufacturing processes
- language acquisition
- production planning
- speech signal
- gaussian mixture model
- natural gas
- recognition engine
- pattern recognition
- reinforcement learning