Speech synthesis using HMMs with dynamic features.
Takashi MasukoKeiichi TokudaTakao KobayashiSatoshi ImaiPublished in: ICASSP (1996)
Keyphrases
- speech synthesis
- speech recognition
- hidden markov models
- text to speech
- prosodic features
- vocal tract
- language model
- speech signal
- automatic speech recognition
- handwriting recognition
- speech corpus
- pattern recognition
- real time
- gesture recognition
- hidden state
- computer vision
- hidden states
- noisy images
- viterbi algorithm
- dynamical systems
- anomaly detection
- artificial intelligence
- genetic algorithm
- information retrieval
- databases
- data sets