Utterance Copy in Formant-Based Speech Synthesizers Using LSTM Neural Networks.
Cassio T. BatistaRenan F. CunhaPedro BatistaAldebaro KlautauNelson NetoPublished in: BRACIS (2019)
Keyphrases
- speech recognition
- neural network
- speech signal
- pattern recognition
- recurrent neural networks
- automatic speech recognition
- speech synthesis
- hidden markov models
- speech recognizer
- language model
- spoken language
- vocal tract
- speech recognition systems
- speaker identification
- fuzzy logic
- artificial neural networks
- speaker recognition
- noisy environments
- speaker independent
- genetic algorithm
- speaker adaptation
- information retrieval
- self organizing maps
- back propagation
- automatic speech recognition systems
- linear prediction
- fuzzy systems
- fault diagnosis
- multi modal
- recognition engine
- probabilistic model
- artificial intelligence
- learning algorithm