Synthesis of Child Speech With HMM Adaptation and Voice Conversion.
Oliver WattsJunichi YamagishiSimon KingKay BerklingPublished in: IEEE Trans. Speech Audio Process. (2010)
Keyphrases
- visual information
- audio visual
- speaker adaptation
- speech recognition
- multi stream
- speech signal
- emotion recognition
- hidden markov models
- automatic speech recognition
- text to speech
- speech synthesis
- speech quality
- speech sounds
- fundamental frequency
- automatic speech recognition systems
- speech recognition errors
- maximum likelihood
- voice activity detection
- speech recognizer
- speaker independent
- young children
- noisy environments
- speaker identification
- speaker dependent
- keyword spotting
- prosodic features
- speech processing
- mel frequency cepstral coefficients
- facial animation
- recognition engine
- text to speech synthesis
- phoneme recognition
- non stationary
- multi modal
- vocal tract
- program synthesis
- word recognition
- neural network
- speech enhancement
- handwritten word recognition
- linear prediction
- synthesized speech
- acoustic features
- spoken language