Interactive speech conversion system cloning speaker intonation automatically.
Yoshihiro AdachiShigeo MorishimaPublished in: SIGGRAPH Posters (2005)
Keyphrases
- prosodic features
- synthesized speech
- speech recognition
- speech synthesis
- speaker verification
- audio visual
- speaker recognition
- text to speech
- automatic speech recognition
- speaker identification
- speaker dependent
- speech signal
- vocal tract
- automatically generated
- audio stream
- user defined
- noisy environments
- multi modal
- hidden markov models
- spontaneous speech
- acoustic features
- automatic speech recognition systems
- speaker adaptation
- speech recognition systems
- probabilistic neural network
- speaker diarization
- audio signals
- data sets
- virtual reality
- computer graphics
- vector quantization
- user interaction
- maximum likelihood
- computer vision