Attributing modelling errors in HMM synthesis by stepping gradually from natural to modelled speech.
Thomas MerrittJavier LatorreSimon KingPublished in: ICASSP (2015)
Keyphrases
- speech recognition
- hidden markov models
- speech signal
- multi stream
- automatic speech recognition systems
- speech recognition errors
- automatic speech recognition
- speech synthesis
- recognition errors
- recognition engine
- speech recognizer
- neural network
- keyword spotting
- audio visual
- real world
- program synthesis
- speaker independent
- facial animation
- phoneme recognition
- pattern recognition
- finite state transducers
- speech processing
- speaker adaptation
- spoken language